aboutsummaryrefslogtreecommitdiffstats
path: root/tools/lib/bpf/btf.c
blob: 4324eb47d214bcd43c10cebc08f3010bb65ad6d3 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/* Copyright (c) 2018 Facebook */

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <strings.h>
#include <unistd.h>
#include <errno.h>
#include <linux/err.h>
#include <linux/btf.h>
#include "btf.h"
#include "bpf.h"
#include "libbpf.h"
#include "libbpf_util.h"

#define max(a, b) ((a) > (b) ? (a) : (b))
#define min(a, b) ((a) < (b) ? (a) : (b))

#define BTF_MAX_NR_TYPES 65535

#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \
		((k) == BTF_KIND_VOLATILE) || \
		((k) == BTF_KIND_CONST) || \
		((k) == BTF_KIND_RESTRICT))

static struct btf_type btf_void;

struct btf {
	union {
		struct btf_header *hdr;
		void *data;
	};
	struct btf_type **types;
	const char *strings;
	void *nohdr_data;
	__u32 nr_types;
	__u32 types_size;
	__u32 data_size;
	int fd;
};

struct btf_ext_info {
	/*
	 * info points to a deep copy of the individual info section
	 * (e.g. func_info and line_info) from the .BTF.ext.
	 * It does not include the __u32 rec_size.
	 */
	void *info;
	__u32 rec_size;
	__u32 len;
};

struct btf_ext {
	struct btf_ext_info func_info;
	struct btf_ext_info line_info;
};

struct btf_ext_info_sec {
	__u32	sec_name_off;
	__u32	num_info;
	/* Followed by num_info * record_size number of bytes */
	__u8	data[0];
};

/* The minimum bpf_func_info checked by the loader */
struct bpf_func_info_min {
	__u32   insn_off;
	__u32   type_id;
};

/* The minimum bpf_line_info checked by the loader */
struct bpf_line_info_min {
	__u32	insn_off;
	__u32	file_name_off;
	__u32	line_off;
	__u32	line_col;
};

static inline __u64 ptr_to_u64(const void *ptr)
{
	return (__u64) (unsigned long) ptr;
}

static int btf_add_type(struct btf *btf, struct btf_type *t)
{
	if (btf->types_size - btf->nr_types < 2) {
		struct btf_type **new_types;
		__u32 expand_by, new_size;

		if (btf->types_size == BTF_MAX_NR_TYPES)
			return -E2BIG;

		expand_by = max(btf->types_size >> 2, 16);
		new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);

		new_types = realloc(btf->types, sizeof(*new_types) * new_size);
		if (!new_types)
			return -ENOMEM;

		if (btf->nr_types == 0)
			new_types[0] = &btf_void;

		btf->types = new_types;
		btf->types_size = new_size;
	}

	btf->types[++(btf->nr_types)] = t;

	return 0;
}

static int btf_parse_hdr(struct btf *btf)
{
	const struct btf_header *hdr = btf->hdr;
	__u32 meta_left;

	if (btf->data_size < sizeof(struct btf_header)) {
		pr_debug("BTF header not found\n");
		return -EINVAL;
	}

	if (hdr->magic != BTF_MAGIC) {
		pr_debug("Invalid BTF magic:%x\n", hdr->magic);
		return -EINVAL;
	}

	if (hdr->version != BTF_VERSION) {
		pr_debug("Unsupported BTF version:%u\n", hdr->version);
		return -ENOTSUP;
	}

	if (hdr->flags) {
		pr_debug("Unsupported BTF flags:%x\n", hdr->flags);
		return -ENOTSUP;
	}

	meta_left = btf->data_size - sizeof(*hdr);
	if (!meta_left) {
		pr_debug("BTF has no data\n");
		return -EINVAL;
	}

	if (meta_left < hdr->type_off) {
		pr_debug("Invalid BTF type section offset:%u\n", hdr->type_off);
		return -EINVAL;
	}

	if (meta_left < hdr->str_off) {
		pr_debug("Invalid BTF string section offset:%u\n", hdr->str_off);
		return -EINVAL;
	}

	if (hdr->type_off >= hdr->str_off) {
		pr_debug("BTF type section offset >= string section offset. No type?\n");
		return -EINVAL;
	}

	if (hdr->type_off & 0x02) {
		pr_debug("BTF type section is not aligned to 4 bytes\n");
		return -EINVAL;
	}

	btf->nohdr_data = btf->hdr + 1;

	return 0;
}

static int btf_parse_str_sec(struct btf *btf)
{
	const struct btf_header *hdr = btf->hdr;
	const char *start = btf->nohdr_data + hdr->str_off;
	const char *end = start + btf->hdr->str_len;

	if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
	    start[0] || end[-1]) {
		pr_debug("Invalid BTF string section\n");
		return -EINVAL;
	}

	btf->strings = start;

	return 0;
}

static int btf_type_size(struct btf_type *t)
{
	int base_size = sizeof(struct btf_type);
	__u16 vlen = BTF_INFO_VLEN(t->info);

	switch (BTF_INFO_KIND(t->info)) {
	case BTF_KIND_FWD:
	case BTF_KIND_CONST:
	case BTF_KIND_VOLATILE:
	case BTF_KIND_RESTRICT:
	case BTF_KIND_PTR:
	case BTF_KIND_TYPEDEF:
	case BTF_KIND_FUNC:
		return base_size;
	case BTF_KIND_INT:
		return base_size + sizeof(__u32);
	case BTF_KIND_ENUM:
		return base_size + vlen * sizeof(struct btf_enum);
	case BTF_KIND_ARRAY:
		return base_size + sizeof(struct btf_array);
	case BTF_KIND_STRUCT:
	case BTF_KIND_UNION:
		return base_size + vlen * sizeof(struct btf_member);
	case BTF_KIND_FUNC_PROTO:
		return base_size + vlen * sizeof(struct btf_param);
	default:
		pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info));
		return -EINVAL;
	}
}

static int btf_parse_type_sec(struct btf *btf)
{
	struct btf_header *hdr = btf->hdr;
	void *nohdr_data = btf->nohdr_data;
	void *next_type = nohdr_data + hdr->type_off;
	void *end_type = nohdr_data + hdr->str_off;

	while (next_type < end_type) {
		struct btf_type *t = next_type;
		int type_size;
		int err;

		type_size = btf_type_size(t);
		if (type_size < 0)
			return type_size;
		next_type += type_size;
		err = btf_add_type(btf, t);
		if (err)
			return err;
	}

	return 0;
}

__u32 btf__get_nr_types(const struct btf *btf)
{
	return btf->nr_types;
}

const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
{
	if (type_id > btf->nr_types)
		return NULL;

	return btf->types[type_id];
}

static bool btf_type_is_void(const struct btf_type *t)
{
	return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
}

static bool btf_type_is_void_or_null(const struct btf_type *t)
{
	return !t || btf_type_is_void(t);
}

#define MAX_RESOLVE_DEPTH 32

__s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
{
	const struct btf_array *array;
	const struct btf_type *t;
	__u32 nelems = 1;
	__s64 size = -1;
	int i;

	t = btf__type_by_id(btf, type_id);
	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
	     i++) {
		switch (BTF_INFO_KIND(t->info)) {
		case BTF_KIND_INT:
		case BTF_KIND_STRUCT:
		case BTF_KIND_UNION:
		case BTF_KIND_ENUM:
			size = t->size;
			goto done;
		case BTF_KIND_PTR:
			size = sizeof(void *);
			goto done;
		case BTF_KIND_TYPEDEF:
		case BTF_KIND_VOLATILE:
		case BTF_KIND_CONST:
		case BTF_KIND_RESTRICT:
			type_id = t->type;
			break;
		case BTF_KIND_ARRAY:
			array = (const struct btf_array *)(t + 1);
			if (nelems && array->nelems > UINT32_MAX / nelems)
				return -E2BIG;
			nelems *= array->nelems;
			type_id = array->type;
			break;
		default:
			return -EINVAL;
		}

		t = btf__type_by_id(btf, type_id);
	}

	if (size < 0)
		return -EINVAL;

done:
	if (nelems && size > UINT32_MAX / nelems)
		return -E2BIG;

	return nelems * size;
}

int btf__resolve_type(const struct btf *btf, __u32 type_id)
{
	const struct btf_type *t;
	int depth = 0;

	t = btf__type_by_id(btf, type_id);
	while (depth < MAX_RESOLVE_DEPTH &&
	       !btf_type_is_void_or_null(t) &&
	       IS_MODIFIER(BTF_INFO_KIND(t->info))) {
		type_id = t->type;
		t = btf__type_by_id(btf, type_id);
		depth++;
	}

	if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t))
		return -EINVAL;

	return type_id;
}

__s32 btf__find_by_name(const struct btf *btf, const char *type_name)
{
	__u32 i;

	if (!strcmp(type_name, "void"))
		return 0;

	for (i = 1; i <= btf->nr_types; i++) {
		const struct btf_type *t = btf->types[i];
		const char *name = btf__name_by_offset(btf, t->name_off);

		if (name && !strcmp(type_name, name))
			return i;
	}

	return -ENOENT;
}

void btf__free(struct btf *btf)
{
	if (!btf)
		return;

	if (btf->fd != -1)
		close(btf->fd);

	free(btf->data);
	free(btf->types);
	free(btf);
}

struct btf *btf__new(__u8 *data, __u32 size)
{
	__u32 log_buf_size = 0;
	char *log_buf = NULL;
	struct btf *btf;
	int err;

	btf = calloc(1, sizeof(struct btf));
	if (!btf)
		return ERR_PTR(-ENOMEM);

	btf->fd = -1;

	log_buf = malloc(BPF_LOG_BUF_SIZE);
	if (!log_buf) {
		err = -ENOMEM;
		goto done;
	}

	*log_buf = 0;
	log_buf_size = BPF_LOG_BUF_SIZE;

	btf->data = malloc(size);
	if (!btf->data) {
		err = -ENOMEM;
		goto done;
	}

	memcpy(btf->data, data, size);
	btf->data_size = size;

	btf->fd = bpf_load_btf(btf->data, btf->data_size,
			       log_buf, log_buf_size, false);

	if (btf->fd == -1) {
		err = -errno;
		pr_warning("Error loading BTF: %s(%d)\n", strerror(errno), errno);
		if (log_buf && *log_buf)
			pr_warning("%s\n", log_buf);
		goto done;
	}

	err = btf_parse_hdr(btf);
	if (err)
		goto done;

	err = btf_parse_str_sec(btf);
	if (err)
		goto done;

	err = btf_parse_type_sec(btf);

done:
	free(log_buf);

	if (err) {
		btf__free(btf);
		return ERR_PTR(err);
	}

	return btf;
}

int btf__fd(const struct btf *btf)
{
	return btf->fd;
}

void btf__get_strings(const struct btf *btf, const char **strings,
		      __u32 *str_len)
{
	*strings = btf->strings;
	*str_len = btf->hdr->str_len;
}

const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
{
	if (offset < btf->hdr->str_len)
		return &btf->strings[offset];
	else
		return NULL;
}

int btf__get_from_id(__u32 id, struct btf **btf)
{
	struct bpf_btf_info btf_info = { 0 };
	__u32 len = sizeof(btf_info);
	__u32 last_size;
	int btf_fd;
	void *ptr;
	int err;

	err = 0;
	*btf = NULL;
	btf_fd = bpf_btf_get_fd_by_id(id);
	if (btf_fd < 0)
		return 0;

	/* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
	 * let's start with a sane default - 4KiB here - and resize it only if
	 * bpf_obj_get_info_by_fd() needs a bigger buffer.
	 */
	btf_info.btf_size = 4096;
	last_size = btf_info.btf_size;
	ptr = malloc(last_size);
	if (!ptr) {
		err = -ENOMEM;
		goto exit_free;
	}

	bzero(ptr, last_size);
	btf_info.btf = ptr_to_u64(ptr);
	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);

	if (!err && btf_info.btf_size > last_size) {
		void *temp_ptr;

		last_size = btf_info.btf_size;
		temp_ptr = realloc(ptr, last_size);
		if (!temp_ptr) {
			err = -ENOMEM;
			goto exit_free;
		}
		ptr = temp_ptr;
		bzero(ptr, last_size);
		btf_info.btf = ptr_to_u64(ptr);
		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
	}

	if (err || btf_info.btf_size > last_size) {
		err = errno;
		goto exit_free;
	}

	*btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size);
	if (IS_ERR(*btf)) {
		err = PTR_ERR(*btf);
		*btf = NULL;
	}

exit_free:
	close(btf_fd);
	free(ptr);

	return err;
}

int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
			 __u32 expected_key_size, __u32 expected_value_size,
			 __u32 *key_type_id, __u32 *value_type_id)
{
	const struct btf_type *container_type;
	const struct btf_member *key, *value;
	const size_t max_name = 256;
	char container_name[max_name];
	__s64 key_size, value_size;
	__s32 container_id;

	if (snprintf(container_name, max_name, "____btf_map_%s", map_name) ==
	    max_name) {
		pr_warning("map:%s length of '____btf_map_%s' is too long\n",
			   map_name, map_name);
		return -EINVAL;
	}

	container_id = btf__find_by_name(btf, container_name);
	if (container_id < 0) {
		pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
			 map_name, container_name);
		return container_id;
	}

	container_type = btf__type_by_id(btf, container_id);
	if (!container_type) {
		pr_warning("map:%s cannot find BTF type for container_id:%u\n",
			   map_name, container_id);
		return -EINVAL;
	}

	if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
	    BTF_INFO_VLEN(container_type->info) < 2) {
		pr_warning("map:%s container_name:%s is an invalid container struct\n",
			   map_name, container_name);
		return -EINVAL;
	}

	key = (struct btf_member *)(container_type + 1);
	value = key + 1;

	key_size = btf__resolve_size(btf, key->type);
	if (key_size < 0) {
		pr_warning("map:%s invalid BTF key_type_size\n", map_name);
		return key_size;
	}

	if (expected_key_size != key_size) {
		pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
			   map_name, (__u32)key_size, expected_key_size);
		return -EINVAL;
	}

	value_size = btf__resolve_size(btf, value->type);
	if (value_size < 0) {
		pr_warning("map:%s invalid BTF value_type_size\n", map_name);
		return value_size;
	}

	if (expected_value_size != value_size) {
		pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
			   map_name, (__u32)value_size, expected_value_size);
		return -EINVAL;
	}

	*key_type_id = key->type;
	*value_type_id = value->type;

	return 0;
}

struct btf_ext_sec_copy_param {
	__u32 off;
	__u32 len;
	__u32 min_rec_size;
	struct btf_ext_info *ext_info;
	const char *desc;
};

static int btf_ext_copy_info(struct btf_ext *btf_ext,
			     __u8 *data, __u32 data_size,
			     struct btf_ext_sec_copy_param *ext_sec)
{
	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
	const struct btf_ext_info_sec *sinfo;
	struct btf_ext_info *ext_info;
	__u32 info_left, record_size;
	/* The start of the info sec (including the __u32 record_size). */
	const void *info;

	/* data and data_size do not include btf_ext_header from now on */
	data = data + hdr->hdr_len;
	data_size -= hdr->hdr_len;

	if (ext_sec->off & 0x03) {
		pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n",
		     ext_sec->desc);
		return -EINVAL;
	}

	if (data_size < ext_sec->off ||
	    ext_sec->len > data_size - ext_sec->off) {
		pr_debug("%s section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n",
		     ext_sec->desc, ext_sec->off, ext_sec->len);
		return -EINVAL;
	}

	info = data + ext_sec->off;
	info_left = ext_sec->len;

	/* At least a record size */
	if (info_left < sizeof(__u32)) {
		pr_debug(".BTF.ext %s record size not found\n", ext_sec->desc);
		return -EINVAL;
	}

	/* The record size needs to meet the minimum standard */
	record_size = *(__u32 *)info;
	if (record_size < ext_sec->min_rec_size ||
	    record_size & 0x03) {
		pr_debug("%s section in .BTF.ext has invalid record size %u\n",
		     ext_sec->desc, record_size);
		return -EINVAL;
	}

	sinfo = info + sizeof(__u32);
	info_left -= sizeof(__u32);

	/* If no records, return failure now so .BTF.ext won't be used. */
	if (!info_left) {
		pr_debug("%s section in .BTF.ext has no records", ext_sec->desc);
		return -EINVAL;
	}

	while (info_left) {
		unsigned int sec_hdrlen = sizeof(struct btf_ext_info_sec);
		__u64 total_record_size;
		__u32 num_records;

		if (info_left < sec_hdrlen) {
			pr_debug("%s section header is not found in .BTF.ext\n",
			     ext_sec->desc);
			return -EINVAL;
		}

		num_records = sinfo->num_info;
		if (num_records == 0) {
			pr_debug("%s section has incorrect num_records in .BTF.ext\n",
			     ext_sec->desc);
			return -EINVAL;
		}

		total_record_size = sec_hdrlen +
				    (__u64)num_records * record_size;
		if (info_left < total_record_size) {
			pr_debug("%s section has incorrect num_records in .BTF.ext\n",
			     ext_sec->desc);
			return -EINVAL;
		}

		info_left -= total_record_size;
		sinfo = (void *)sinfo + total_record_size;
	}

	ext_info = ext_sec->ext_info;
	ext_info->len = ext_sec->len - sizeof(__u32);
	ext_info->rec_size = record_size;
	ext_info->info = malloc(ext_info->len);
	if (!ext_info->info)
		return -ENOMEM;
	memcpy(ext_info->info, info + sizeof(__u32), ext_info->len);

	return 0;
}

static int btf_ext_copy_func_info(struct btf_ext *btf_ext,
				  __u8 *data, __u32 data_size)
{
	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
	struct btf_ext_sec_copy_param param = {
		.off = hdr->func_info_off,
		.len = hdr->func_info_len,
		.min_rec_size = sizeof(struct bpf_func_info_min),
		.ext_info = &btf_ext->func_info,
		.desc = "func_info"
	};

	return btf_ext_copy_info(btf_ext, data, data_size, &param);
}

static int btf_ext_copy_line_info(struct btf_ext *btf_ext,
				  __u8 *data, __u32 data_size)
{
	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
	struct btf_ext_sec_copy_param param = {
		.off = hdr->line_info_off,
		.len = hdr->line_info_len,
		.min_rec_size = sizeof(struct bpf_line_info_min),
		.ext_info = &btf_ext->line_info,
		.desc = "line_info",
	};

	return btf_ext_copy_info(btf_ext, data, data_size, &param);
}

static int btf_ext_parse_hdr(__u8 *data, __u32 data_size)
{
	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;

	if (data_size < offsetof(struct btf_ext_header, func_info_off) ||
	    data_size < hdr->hdr_len) {
		pr_debug("BTF.ext header not found");
		return -EINVAL;
	}

	if (hdr->magic != BTF_MAGIC) {
		pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic);
		return -EINVAL;
	}

	if (hdr->version != BTF_VERSION) {
		pr_debug("Unsupported BTF.ext version:%u\n", hdr->version);
		return -ENOTSUP;
	}

	if (hdr->flags) {
		pr_debug("Unsupported BTF.ext flags:%x\n", hdr->flags);
		return -ENOTSUP;
	}

	if (data_size == hdr->hdr_len) {
		pr_debug("BTF.ext has no data\n");
		return -EINVAL;
	}

	return 0;
}

void btf_ext__free(struct btf_ext *btf_ext)
{
	if (!btf_ext)
		return;

	free(btf_ext->func_info.info);
	free(btf_ext->line_info.info);
	free(btf_ext);
}

struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
{
	struct btf_ext *btf_ext;
	int err;

	err = btf_ext_parse_hdr(data, size);
	if (err)
		return ERR_PTR(err);

	btf_ext = calloc(1, sizeof(struct btf_ext));
	if (!btf_ext)
		return ERR_PTR(-ENOMEM);

	err = btf_ext_copy_func_info(btf_ext, data, size);
	if (err) {
		btf_ext__free(btf_ext);
		return ERR_PTR(err);
	}

	err = btf_ext_copy_line_info(btf_ext, data, size);
	if (err) {
		btf_ext__free(btf_ext);
		return ERR_PTR(err);
	}

	return btf_ext;
}

static int btf_ext_reloc_info(const struct btf *btf,
			      const struct btf_ext_info *ext_info,
			      const char *sec_name, __u32 insns_cnt,
			      void **info, __u32 *cnt)
{
	__u32 sec_hdrlen = sizeof(struct btf_ext_info_sec);
	__u32 i, record_size, existing_len, records_len;
	struct btf_ext_info_sec *sinfo;
	const char *info_sec_name;
	__u64 remain_len;
	void *data;

	record_size = ext_info->rec_size;
	sinfo = ext_info->info;
	remain_len = ext_info->len;
	while (remain_len > 0) {
		records_len = sinfo->num_info * record_size;
		info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
		if (strcmp(info_sec_name, sec_name)) {
			remain_len -= sec_hdrlen + records_len;
			sinfo = (void *)sinfo + sec_hdrlen + records_len;
			continue;
		}

		existing_len = (*cnt) * record_size;
		data = realloc(*info, existing_len + records_len);
		if (!data)
			return -ENOMEM;

		memcpy(data + existing_len, sinfo->data, records_len);
		/* adjust insn_off only, the rest data will be passed
		 * to the kernel.
		 */
		for (i = 0; i < sinfo->num_info; i++) {
			__u32 *insn_off;

			insn_off = data + existing_len + (i * record_size);
			*insn_off = *insn_off / sizeof(struct bpf_insn) +
				insns_cnt;
		}
		*info = data;
		*cnt += sinfo->num_info;
		return 0;
	}

	return -ENOENT;
}

int btf_ext__reloc_func_info(const struct btf *btf, const struct btf_ext *btf_ext,
			     const char *sec_name, __u32 insns_cnt,
			     void **func_info, __u32 *cnt)
{
	return btf_ext_reloc_info(btf, &btf_ext->func_info, sec_name,
				  insns_cnt, func_info, cnt);
}

int btf_ext__reloc_line_info(const struct btf *btf, const struct btf_ext *btf_ext,
			     const char *sec_name, __u32 insns_cnt,
			     void **line_info, __u32 *cnt)
{
	return btf_ext_reloc_info(btf, &btf_ext->line_info, sec_name,
				  insns_cnt, line_info, cnt);
}

__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext)
{
	return btf_ext->func_info.rec_size;
}

__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext)
{
	return btf_ext->line_info.rec_size;
}

struct btf_dedup;

static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
				       const struct btf_dedup_opts *opts);
static void btf_dedup_free(struct btf_dedup *d);
static int btf_dedup_strings(struct btf_dedup *d);
static int btf_dedup_prim_types(struct btf_dedup *d);
static int btf_dedup_struct_types(struct btf_dedup *d);
static int btf_dedup_ref_types(struct btf_dedup *d);
static int btf_dedup_compact_types(struct btf_dedup *d);
static int btf_dedup_remap_types(struct btf_dedup *d);

/*
 * Deduplicate BTF types and strings.
 *
 * BTF dedup algorithm takes as an input `struct btf` representing `.BTF` ELF
 * section with all BTF type descriptors and string data. It overwrites that
 * memory in-place with deduplicated types and strings without any loss of
 * information. If optional `struct btf_ext` representing '.BTF.ext' ELF section
 * is provided, all the strings referenced from .BTF.ext section are honored
 * and updated to point to the right offsets after deduplication.
 *
 * If function returns with error, type/string data might be garbled and should
 * be discarded.
 *
 * More verbose and detailed description of both problem btf_dedup is solving,
 * as well as solution could be found at:
 * https://facebookmicrosites.github.io/bpf/blog/2018/11/14/btf-enhancement.html
 *
 * Problem description and justification
 * =====================================
 *
 * BTF type information is typically emitted either as a result of conversion
 * from DWARF to BTF or directly by compiler. In both cases, each compilation
 * unit contains information about a subset of all the types that are used
 * in an application. These subsets are frequently overlapping and contain a lot
 * of duplicated information when later concatenated together into a single
 * binary. This algorithm ensures that each unique type is represented by single
 * BTF type descriptor, greatly reducing resulting size of BTF data.
 *
 * Compilation unit isolation and subsequent duplication of data is not the only
 * problem. The same type hierarchy (e.g., struct and all the type that struct
 * references) in different compilation units can be represented in BTF to
 * various degrees of completeness (or, rather, incompleteness) due to
 * struct/union forward declarations.
 *
 * Let's take a look at an example, that we'll use to better understand the
 * problem (and solution). Suppose we have two compilation units, each using
 * same `struct S`, but each of them having incomplete type information about
 * struct's fields:
 *
 * // CU #1:
 * struct S;
 * struct A {
 *	int a;
 *	struct A* self;
 *	struct S* parent;
 * };
 * struct B;
 * struct S {
 *	struct A* a_ptr;
 *	struct B* b_ptr;
 * };
 *
 * // CU #2:
 * struct S;
 * struct A;
 * struct B {
 *	int b;
 *	struct B* self;
 *	struct S* parent;
 * };
 * struct S {
 *	struct A* a_ptr;
 *	struct B* b_ptr;
 * };
 *
 * In case of CU #1, BTF data will know only that `struct B` exist (but no
 * more), but will know the complete type information about `struct A`. While
 * for CU #2, it will know full type information about `struct B`, but will
 * only know about forward declaration of `struct A` (in BTF terms, it will
 * have `BTF_KIND_FWD` type descriptor with name `B`).
 *
 * This compilation unit isolation means that it's possible that there is no
 * single CU with complete type information describing structs `S`, `A`, and
 * `B`. Also, we might get tons of duplicated and redundant type information.
 *
 * Additional complication we need to keep in mind comes from the fact that
 * types, in general, can form graphs containing cycles, not just DAGs.
 *
 * While algorithm does deduplication, it also merges and resolves type
 * information (unless disabled throught `struct btf_opts`), whenever possible.
 * E.g., in the example above with two compilation units having partial type
 * information for structs `A` and `B`, the output of algorithm will emit
 * a single copy of each BTF type that describes structs `A`, `B`, and `S`
 * (as well as type information for `int` and pointers), as if they were defined
 * in a single compilation unit as:
 *
 * struct A {
 *	int a;
 *	struct A* self;
 *	struct S* parent;
 * };
 * struct B {
 *	int b;
 *	struct B* self;
 *	struct S* parent;
 * };
 * struct S {
 *	struct A* a_ptr;
 *	struct B* b_ptr;
 * };
 *
 * Algorithm summary
 * =================
 *
 * Algorithm completes its work in 6 separate passes:
 *
 * 1. Strings deduplication.
 * 2. Primitive types deduplication (int, enum, fwd).
 * 3. Struct/union types deduplication.
 * 4. Reference types deduplication (pointers, typedefs, arrays, funcs, func
 *    protos, and const/volatile/restrict modifiers).
 * 5. Types compaction.
 * 6. Types remapping.
 *
 * Algorithm determines canonical type descriptor, which is a single
 * representative type for each truly unique type. This canonical type is the
 * one that will go into final deduplicated BTF type information. For
 * struct/unions, it is also the type that algorithm will merge additional type
 * information into (while resolving FWDs), as it discovers it from data in
 * other CUs. Each input BTF type eventually gets either mapped to itself, if
 * that type is canonical, or to some other type, if that type is equivalent
 * and was chosen as canonical representative. This mapping is stored in
 * `btf_dedup->map` array. This map is also used to record STRUCT/UNION that
 * FWD type got resolved to.
 *
 * To facilitate fast discovery of canonical types, we also maintain canonical
 * index (`btf_dedup->dedup_table`), which maps type descriptor's signature hash
 * (i.e., hashed kind, name, size, fields, etc) into a list of canonical types
 * that match that signature. With sufficiently good choice of type signature
 * hashing function, we can limit number of canonical types for each unique type
 * signature to a very small number, allowing to find canonical type for any
 * duplicated type very quickly.
 *
 * Struct/union deduplication is the most critical part and algorithm for
 * deduplicating structs/unions is described in greater details in comments for
 * `btf_dedup_is_equiv` function.
 */
int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
	       const struct btf_dedup_opts *opts)
{
	struct btf_dedup *d = btf_dedup_new(btf, btf_ext, opts);
	int err;

	if (IS_ERR(d)) {
		pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d));
		return -EINVAL;
	}

	err = btf_dedup_strings(d);
	if (err < 0) {
		pr_debug("btf_dedup_strings failed:%d\n", err);
		goto done;
	}
	err = btf_dedup_prim_types(d);
	if (err < 0) {
		pr_debug("btf_dedup_prim_types failed:%d\n", err);
		goto done;
	}
	err = btf_dedup_struct_types(d);
	if (err < 0) {
		pr_debug("btf_dedup_struct_types failed:%d\n", err);
		goto done;
	}
	err = btf_dedup_ref_types(d);
	if (err < 0) {
		pr_debug("btf_dedup_ref_types failed:%d\n", err);
		goto done;
	}
	err = btf_dedup_compact_types(d);
	if (err < 0) {
		pr_debug("btf_dedup_compact_types failed:%d\n", err);
		goto done;
	}
	err = btf_dedup_remap_types(d);
	if (err < 0) {
		pr_debug("btf_dedup_remap_types failed:%d\n", err);
		goto done;
	}

done:
	btf_dedup_free(d);
	return err;
}

#define BTF_DEDUP_TABLE_SIZE_LOG 14
#define BTF_DEDUP_TABLE_MOD ((1 << BTF_DEDUP_TABLE_SIZE_LOG) - 1)
#define BTF_UNPROCESSED_ID ((__u32)-1)
#define BTF_IN_PROGRESS_ID ((__u32)-2)

struct btf_dedup_node {
	struct btf_dedup_node *next;
	__u32 type_id;
};

struct btf_dedup {
	/* .BTF section to be deduped in-place */
	struct btf *btf;
	/*
	 * Optional .BTF.ext section. When provided, any strings referenced
	 * from it will be taken into account when deduping strings
	 */
	struct btf_ext *btf_ext;
	/*
	 * This is a map from any type's signature hash to a list of possible
	 * canonical representative type candidates. Hash collisions are
	 * ignored, so even types of various kinds can share same list of
	 * candidates, which is fine because we rely on subsequent
	 * btf_xxx_equal() checks to authoritatively verify type equality.
	 */
	struct btf_dedup_node **dedup_table;
	/* Canonical types map */
	__u32 *map;
	/* Hypothetical mapping, used during type graph equivalence checks */
	__u32 *hypot_map;
	__u32 *hypot_list;
	size_t hypot_cnt;
	size_t hypot_cap;
	/* Various option modifying behavior of algorithm */
	struct btf_dedup_opts opts;
};

struct btf_str_ptr {
	const char *str;
	__u32 new_off;
	bool used;
};

struct btf_str_ptrs {
	struct btf_str_ptr *ptrs;
	const char *data;
	__u32 cnt;
	__u32 cap;
};

static inline __u32 hash_combine(__u32 h, __u32 value)
{
/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
#define GOLDEN_RATIO_PRIME 0x9e370001UL
	return h * 37 + value * GOLDEN_RATIO_PRIME;
#undef GOLDEN_RATIO_PRIME
}

#define for_each_hash_node(table, hash, node) \
	for (node = table[hash & BTF_DEDUP_TABLE_MOD]; node; node = node->next)

static int btf_dedup_table_add(struct btf_dedup *d, __u32 hash, __u32 type_id)
{
	struct btf_dedup_node *node = malloc(sizeof(struct btf_dedup_node));

	if (!node)
		return -ENOMEM;
	node->type_id = type_id;
	node->next = d->dedup_table[hash & BTF_DEDUP_TABLE_MOD];
	d->dedup_table[hash & BTF_DEDUP_TABLE_MOD] = node;
	return 0;
}

static int btf_dedup_hypot_map_add(struct btf_dedup *d,
				   __u32 from_id, __u32 to_id)
{
	if (d->hypot_cnt == d->hypot_cap) {
		__u32 *new_list;

		d->hypot_cap += max(16, d->hypot_cap / 2);
		new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap);
		if (!new_list)
			return -ENOMEM;
		d->hypot_list = new_list;
	}
	d->hypot_list[d->hypot_cnt++] = from_id;
	d->hypot_map[from_id] = to_id;
	return 0;
}

static void btf_dedup_clear_hypot_map(struct btf_dedup *d)
{
	int i;

	for (i = 0; i < d->hypot_cnt; i++)
		d->hypot_map[d->hypot_list[i]] = BTF_UNPROCESSED_ID;
	d->hypot_cnt = 0;
}

static void btf_dedup_table_free(struct btf_dedup *d)
{
	struct btf_dedup_node *head, *tmp;
	int i;

	if (!d->dedup_table)
		return;

	for (i = 0; i < (1 << BTF_DEDUP_TABLE_SIZE_LOG); i++) {
		while (d->dedup_table[i]) {
			tmp = d->dedup_table[i];
			d->dedup_table[i] = tmp->next;
			free(tmp);
		}

		head = d->dedup_table[i];
		while (head) {
			tmp = head;
			head = head->next;
			free(tmp);
		}
	}

	free(d->dedup_table);
	d->dedup_table = NULL;
}

static void btf_dedup_free(struct btf_dedup *d)
{
	btf_dedup_table_free(d);

	free(d->map);
	d->map = NULL;

	free(d->hypot_map);
	d->hypot_map = NULL;

	free(d->hypot_list);
	d->hypot_list = NULL;

	free(d);
}

static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
				       const struct btf_dedup_opts *opts)
{
	struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup));
	int i, err = 0;

	if (!d)
		return ERR_PTR(-ENOMEM);

	d->btf = btf;
	d->btf_ext = btf_ext;

	d->dedup_table = calloc(1 << BTF_DEDUP_TABLE_SIZE_LOG,
				sizeof(struct btf_dedup_node *));
	if (!d->dedup_table) {
		err = -ENOMEM;
		goto done;
	}

	d->map = malloc(sizeof(__u32) * (1 + btf->nr_types));
	if (!d->map) {
		err = -ENOMEM;
		goto done;
	}
	/* special BTF "void" type is made canonical immediately */
	d->map[0] = 0;
	for (i = 1; i <= btf->nr_types; i++)
		d->map[i] = BTF_UNPROCESSED_ID;

	d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types));
	if (!d->hypot_map) {
		err = -ENOMEM;
		goto done;
	}
	for (i = 0; i <= btf->nr_types; i++)
		d->hypot_map[i] = BTF_UNPROCESSED_ID;

	d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds;

done:
	if (err) {
		btf_dedup_free(d);
		return ERR_PTR(err);
	}

	return d;
}

typedef int (*str_off_fn_t)(__u32 *str_off_ptr, void *ctx);

/*
 * Iterate over all possible places in .BTF and .BTF.ext that can reference
 * string and pass pointer to it to a provided callback `fn`.
 */
static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
{
	void *line_data_cur, *line_data_end;
	int i, j, r, rec_size;
	struct btf_type *t;

	for (i = 1; i <= d->btf->nr_types; i++) {
		t = d->btf->types[i];
		r = fn(&t->name_off, ctx);
		if (r)
			return r;

		switch (BTF_INFO_KIND(t->info)) {
		case BTF_KIND_STRUCT:
		case BTF_KIND_UNION: {
			struct btf_member *m = (struct btf_member *)(t + 1);
			__u16 vlen = BTF_INFO_VLEN(t->info);

			for (j = 0; j < vlen; j++) {
				r = fn(&m->name_off, ctx);
				if (r)
					return r;
				m++;
			}
			break;
		}
		case BTF_KIND_ENUM: {
			struct btf_enum *m = (struct btf_enum *)(t + 1);
			__u16 vlen = BTF_INFO_VLEN(t->info);

			for (j = 0; j < vlen; j++) {
				r = fn(&m->name_off, ctx);
				if (r)
					return r;
				m++;
			}
			break;
		}
		case BTF_KIND_FUNC_PROTO: {
			struct btf_param *m = (struct btf_param *)(t + 1);
			__u16 vlen = BTF_INFO_VLEN(t->info);

			for (j = 0; j < vlen; j++) {
				r = fn(&m->name_off, ctx);
				if (r)
					return r;
				m++;
			}
			break;
		}
		default:
			break;
		}
	}

	if (!d->btf_ext)
		return 0;

	line_data_cur = d->btf_ext->line_info.info;
	line_data_end = d->btf_ext->line_info.info + d->btf_ext->line_info.len;
	rec_size = d->btf_ext->line_info.rec_size;

	while (line_data_cur < line_data_end) {
		struct btf_ext_info_sec *sec = line_data_cur;
		struct bpf_line_info_min *line_info;
		__u32 num_info = sec->num_info;

		r = fn(&sec->sec_name_off, ctx);
		if (r)
			return r;

		line_data_cur += sizeof(struct btf_ext_info_sec);
		for (i = 0; i < num_info; i++) {
			line_info = line_data_cur;
			r = fn(&line_info->file_name_off, ctx);
			if (r)
				return r;
			r = fn(&line_info->line_off, ctx);
			if (r)
				return r;
			line_data_cur += rec_size;
		}
	}

	return 0;
}

static int str_sort_by_content(const void *a1, const void *a2)
{
	const struct btf_str_ptr *p1 = a1;
	const struct btf_str_ptr *p2 = a2;

	return strcmp(p1->str, p2->str);
}

static int str_sort_by_offset(const void *a1, const void *a2)
{
	const struct btf_str_ptr *p1 = a1;
	const struct btf_str_ptr *p2 = a2;

	if (p1->str != p2->str)
		return p1->str < p2->str ? -1 : 1;
	return 0;
}

static int btf_dedup_str_ptr_cmp(const void *str_ptr, const void *pelem)
{
	const struct btf_str_ptr *p = pelem;

	if (str_ptr != p->str)
		return (const char *)str_ptr < p->str ? -1 : 1;
	return 0;
}

static int btf_str_mark_as_used(__u32 *str_off_ptr, void *ctx)
{
	struct btf_str_ptrs *strs;
	struct btf_str_ptr *s;

	if (*str_off_ptr == 0)
		return 0;

	strs = ctx;
	s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
		    sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
	if (!s)
		return -EINVAL;
	s->used = true;
	return 0;
}

static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx)
{
	struct btf_str_ptrs *strs;
	struct btf_str_ptr *s;

	if (*str_off_ptr == 0)
		return 0;

	strs = ctx;
	s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
		    sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
	if (!s)
		return -EINVAL;
	*str_off_ptr = s->new_off;
	return 0;
}

/*
 * Dedup string and filter out those that are not referenced from either .BTF
 * or .BTF.ext (if provided) sections.
 *
 * This is done by building index of all strings in BTF's string section,
 * then iterating over all entities that can reference strings (e.g., type
 * names, struct field names, .BTF.ext line info, etc) and marking corresponding
 * strings as used. After that all used strings are deduped and compacted into
 * sequential blob of memory and new offsets are calculated. Then all the string
 * references are iterated again and rewritten using new offsets.
 */
static int btf_dedup_strings(struct btf_dedup *d)
{
	const struct btf_header *hdr = d->btf->hdr;
	char *start = (char *)d->btf->nohdr_data + hdr->str_off;
	char *end = start + d->btf->hdr->str_len;
	char *p = start, *tmp_strs = NULL;
	struct btf_str_ptrs strs = {
		.cnt = 0,
		.cap = 0,
		.ptrs = NULL,
		.data = start,
	};
	int i, j, err = 0, grp_idx;
	bool grp_used;

	/* build index of all strings */
	while (p < end) {
		if (strs.cnt + 1 > strs.cap) {
			struct btf_str_ptr *new_ptrs;

			strs.cap += max(strs.cnt / 2, 16);
			new_ptrs = realloc(strs.ptrs,
					   sizeof(strs.ptrs[0]) * strs.cap);
			if (!new_ptrs) {
				err = -ENOMEM;
				goto done;
			}
			strs.ptrs = new_ptrs;
		}

		strs.ptrs[strs.cnt].str = p;
		strs.ptrs[strs.cnt].used = false;

		p += strlen(p) + 1;
		strs.cnt++;
	}

	/* temporary storage for deduplicated strings */
	tmp_strs = malloc(d->btf->hdr->str_len);
	if (!tmp_strs) {
		err = -ENOMEM;
		goto done;
	}

	/* mark all used strings */
	strs.ptrs[0].used = true;
	err = btf_for_each_str_off(d, btf_str_mark_as_used, &strs);
	if (err)
		goto done;

	/* sort strings by context, so that we can identify duplicates */
	qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_content);

	/*
	 * iterate groups of equal strings and if any instance in a group was
	 * referenced, emit single instance and remember new offset
	 */
	p = tmp_strs;
	grp_idx = 0;
	grp_used = strs.ptrs[0].used;
	/* iterate past end to avoid code duplication after loop */
	for (i = 1; i <= strs.cnt; i++) {
		/*
		 * when i == strs.cnt, we want to skip string comparison and go
		 * straight to handling last group of strings (otherwise we'd
		 * need to handle last group after the loop w/ duplicated code)
		 */
		if (i < strs.cnt &&
		    !strcmp(strs.ptrs[i].str, strs.ptrs[grp_idx].str)) {
			grp_used = grp_used || strs.ptrs[i].used;
			continue;
		}

		/*
		 * this check would have been required after the loop to handle
		 * last group of strings, but due to <= condition in a loop
		 * we avoid that duplication
		 */
		if (grp_used) {
			int new_off = p - tmp_strs;
			__u32 len = strlen(strs.ptrs[grp_idx].str);

			memmove(p, strs.ptrs[grp_idx].str, len + 1);
			for (j = grp_idx; j < i; j++)
				strs.ptrs[j].new_off = new_off;
			p += len + 1;
		}

		if (i < strs.cnt) {
			grp_idx = i;
			grp_used = strs.ptrs[i].used;
		}
	}

	/* replace original strings with deduped ones */
	d->btf->hdr->str_len = p - tmp_strs;
	memmove(start, tmp_strs, d->btf->hdr->str_len);
	end = start + d->btf->hdr->str_len;

	/* restore original order for further binary search lookups */
	qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_offset);

	/* remap string offsets */
	err = btf_for_each_str_off(d, btf_str_remap_offset, &strs);
	if (err)
		goto done;

	d->btf->hdr->str_len = end - start;

done:
	free(tmp_strs);
	free(strs.ptrs);
	return err;
}

static __u32 btf_hash_common(struct btf_type *t)
{
	__u32 h;

	h = hash_combine(0, t->name_off);
	h = hash_combine(h, t->info);
	h = hash_combine(h, t->size);
	return h;
}

static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
{
	return t1->name_off == t2->name_off &&
	       t1->info == t2->info &&
	       t1->size == t2->size;
}

/* Calculate type signature hash of INT. */
static __u32 btf_hash_int(struct btf_type *t)
{
	__u32 info = *(__u32 *)(t + 1);
	__u32 h;

	h = btf_hash_common(t);
	h = hash_combine(h, info);
	return h;
}

/* Check structural equality of two INTs. */
static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
{
	__u32 info1, info2;

	if (!btf_equal_common(t1, t2))
		return false;
	info1 = *(__u32 *)(t1 + 1);
	info2 = *(__u32 *)(t2 + 1);
	return info1 == info2;
}

/* Calculate type signature hash of ENUM. */
static __u32 btf_hash_enum(struct btf_type *t)
{
	struct btf_enum *member = (struct btf_enum *)(t + 1);
	__u32 vlen = BTF_INFO_VLEN(t->info);
	__u32 h = btf_hash_common(t);
	int i;

	for (i = 0; i < vlen; i++) {
		h = hash_combine(h, member->name_off);
		h = hash_combine(h, member->val);
		member++;
	}
	return h;
}

/* Check structural equality of two ENUMs. */
static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
{
	struct btf_enum *m1, *m2;
	__u16 vlen;
	int i;

	if (!btf_equal_common(t1, t2))
		return false;

	vlen = BTF_INFO_VLEN(t1->info);
	m1 = (struct btf_enum *)(t1 + 1);
	m2 = (struct btf_enum *)(t2 + 1);
	for (i = 0; i < vlen; i++) {
		if (m1->name_off != m2->name_off || m1->val != m2->val)
			return false;
		m1++;
		m2++;
	}
	return true;
}

/*
 * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs,
 * as referenced type IDs equivalence is established separately during type
 * graph equivalence check algorithm.
 */
static __u32 btf_hash_struct(struct btf_type *t)
{
	struct btf_member *member = (struct btf_member *)(t + 1);
	__u32 vlen = BTF_INFO_VLEN(t->info);
	__u32 h = btf_hash_common(t);
	int i;

	for (i = 0; i < vlen; i++) {
		h = hash_combine(h, member->name_off);
		h = hash_combine(h, member->offset);
		/* no hashing of referenced type ID, it can be unresolved yet */
		member++;
	}
	return h;
}

/*
 * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type
 * IDs. This check is performed during type graph equivalence check and
 * referenced types equivalence is checked separately.
 */
static bool btf_equal_struct(struct btf_type *t1, struct btf_type *t2)
{
	struct btf_member *m1, *m2;
	__u16 vlen;
	int i;

	if (!btf_equal_common(t1, t2))
		return false;

	vlen = BTF_INFO_VLEN(t1->info);
	m1 = (struct btf_member *)(t1 + 1);
	m2 = (struct btf_member *)(t2 + 1);
	for (i = 0; i < vlen; i++) {
		if (m1->name_off != m2->name_off || m1->offset != m2->offset)
			return false;
		m1++;
		m2++;
	}
	return true;
}

/*
 * Calculate type signature hash of ARRAY, including referenced type IDs,
 * under assumption that they were already resolved to canonical type IDs and
 * are not going to change.
 */
static __u32 btf_hash_array(struct btf_type *t)
{
	struct btf_array *info = (struct btf_array *)(t + 1);
	__u32 h = btf_hash_common(t);

	h = hash_combine(h, info->type);
	h = hash_combine(h, info->index_type);
	h = hash_combine(h, info->nelems);
	return h;
}

/*
 * Check exact equality of two ARRAYs, taking into account referenced
 * type IDs, under assumption that they were already resolved to canonical
 * type IDs and are not going to change.
 * This function is called during reference types deduplication to compare
 * ARRAY to potential canonical representative.
 */
static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2)
{
	struct btf_array *info1, *info2;

	if (!btf_equal_common(t1, t2))
		return false;

	info1 = (struct btf_array *)(t1 + 1);
	info2 = (struct btf_array *)(t2 + 1);
	return info1->type == info2->type &&
	       info1->index_type == info2->index_type &&
	       info1->nelems == info2->nelems;
}

/*
 * Check structural compatibility of two ARRAYs, ignoring referenced type
 * IDs. This check is performed during type graph equivalence check and
 * referenced types equivalence is checked separately.
 */
static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2)
{
	struct btf_array *info1, *info2;

	if (!btf_equal_common(t1, t2))
		return false;

	info1 = (struct btf_array *)(t1 + 1);
	info2 = (struct btf_array *)(t2 + 1);
	return info1->nelems == info2->nelems;
}

/*
 * Calculate type signature hash of FUNC_PROTO, including referenced type IDs,
 * under assumption that they were already resolved to canonical type IDs and
 * are not going to change.
 */
static inline __u32 btf_hash_fnproto(struct btf_type *t)
{
	struct btf_param *member = (struct btf_param *)(t + 1);
	__u16 vlen = BTF_INFO_VLEN(t->info);
	__u32 h = btf_hash_common(t);
	int i;

	for (i = 0; i < vlen; i++) {
		h = hash_combine(h, member->name_off);
		h = hash_combine(h, member->type);
		member++;
	}
	return h;
}

/*
 * Check exact equality of two FUNC_PROTOs, taking into account referenced
 * type IDs, under assumption that they were already resolved to canonical
 * type IDs and are not going to change.
 * This function is called during reference types deduplication to compare
 * FUNC_PROTO to potential canonical representative.
 */
static inline bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
{
	struct btf_param *m1, *m2;
	__u16 vlen;
	int i;

	if (!btf_equal_common(t1, t2))
		return false;

	vlen = BTF_INFO_VLEN(t1->info);
	m1 = (struct btf_param *)(t1 + 1);
	m2 = (struct btf_param *)(t2 + 1);
	for (i = 0; i < vlen; i++) {
		if (m1->name_off != m2->name_off || m1->type != m2->type)
			return false;
		m1++;
		m2++;
	}
	return true;
}

/*
 * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type
 * IDs. This check is performed during type graph equivalence check and
 * referenced types equivalence is checked separately.
 */
static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
{
	struct btf_param *m1, *m2;
	__u16 vlen;
	int i;

	/* skip return type ID */
	if (t1->name_off != t2->name_off || t1->info != t2->info)
		return false;

	vlen = BTF_INFO_VLEN(t1->info);
	m1 = (struct btf_param *)(t1 + 1);
	m2 = (struct btf_param *)(t2 + 1);
	for (i = 0; i < vlen; i++) {
		if (m1->name_off != m2->name_off)
			return false;
		m1++;
		m2++;
	}
	return true;
}

/*
 * Deduplicate primitive types, that can't reference other types, by calculating
 * their type signature hash and comparing them with any possible canonical
 * candidate. If no canonical candidate matches, type itself is marked as
 * canonical and is added into `btf_dedup->dedup_table` as another candidate.
 */
static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
{
	struct btf_type *t = d->btf->types[type_id];
	struct btf_type *cand;
	struct btf_dedup_node *cand_node;
	/* if we don't find equivalent type, then we are canonical */
	__u32 new_id = type_id;
	__u32 h;

	switch (BTF_INFO_KIND(t->info)) {
	case BTF_KIND_CONST:
	case BTF_KIND_VOLATILE:
	case BTF_KIND_RESTRICT:
	case BTF_KIND_PTR:
	case BTF_KIND_TYPEDEF:
	case BTF_KIND_ARRAY:
	case BTF_KIND_STRUCT:
	case BTF_KIND_UNION:
	case BTF_KIND_FUNC:
	case BTF_KIND_FUNC_PROTO:
		return 0;

	case BTF_KIND_INT:
		h = btf_hash_int(t);
		for_each_hash_node(d->dedup_table, h, cand_node) {
			cand = d->btf->types[cand_node->type_id];
			if (btf_equal_int(t, cand)) {
				new_id = cand_node->type_id;
				break;
			}
		}
		break;

	case BTF_KIND_ENUM:
		h = btf_hash_enum(t);
		for_each_hash_node(d->dedup_table, h, cand_node) {
			cand = d->btf->types[cand_node->type_id];
			if (btf_equal_enum(t, cand)) {
				new_id = cand_node->type_id;
				break;
			}
		}
		break;

	case BTF_KIND_FWD:
		h = btf_hash_common(t);
		for_each_hash_node(d->dedup_table, h, cand_node) {
			cand = d->btf->types[cand_node->type_id];
			if (btf_equal_common(t, cand)) {
				new_id = cand_node->type_id;
				break;
			}
		}
		break;

	default:
		return -EINVAL;
	}

	d->map[type_id] = new_id;
	if (type_id == new_id && btf_dedup_table_add(d, h, type_id))
		return -ENOMEM;

	return 0;
}

static int btf_dedup_prim_types(struct btf_dedup *d)
{
	int i, err;

	for (i = 1; i <= d->btf->nr_types; i++) {
		err = btf_dedup_prim_type(d, i);
		if (err)
			return err;
	}
	return 0;
}

/*
 * Check whether type is already mapped into canonical one (could be to itself).
 */
static inline bool is_type_mapped(struct btf_dedup *d, uint32_t type_id)
{
	return d->map[type_id] <= BTF_MAX_TYPE;
}

/*
 * Resolve type ID into its canonical type ID, if any; otherwise return original
 * type ID. If type is FWD and is resolved into STRUCT/UNION already, follow
 * STRUCT/UNION link and resolve it into canonical type ID as well.
 */
static inline __u32 resolve_type_id(struct btf_dedup *d, __u32 type_id)
{
	while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
		type_id = d->map[type_id];
	return type_id;
}

/*
 * Resolve FWD to underlying STRUCT/UNION, if any; otherwise return original
 * type ID.
 */
static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id)
{
	__u32 orig_type_id = type_id;

	if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD)
		return type_id;

	while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
		type_id = d->map[type_id];

	if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD)
		return type_id;

	return orig_type_id;
}


static inline __u16 btf_fwd_kind(struct btf_type *t)
{
	return BTF_INFO_KFLAG(t->info) ? BTF_KIND_UNION : BTF_KIND_STRUCT;
}

/*
 * Check equivalence of BTF type graph formed by candidate struct/union (we'll
 * call it "candidate graph" in this description for brevity) to a type graph
 * formed by (potential) canonical struct/union ("canonical graph" for brevity
 * here, though keep in mind that not all types in canonical graph are
 * necessarily canonical representatives themselves, some of them might be
 * duplicates or its uniqueness might not have been established yet).
 * Returns:
 *  - >0, if type graphs are equivalent;
 *  -  0, if not equivalent;
 *  - <0, on error.
 *
 * Algorithm performs side-by-side DFS traversal of both type graphs and checks
 * equivalence of BTF types at each step. If at any point BTF types in candidate
 * and canonical graphs are not compatible structurally, whole graphs are
 * incompatible. If types are structurally equivalent (i.e., all information
 * except referenced type IDs is exactly the same), a mapping from `canon_id` to
 * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`).
 * If a type references other types, then those referenced types are checked
 * for equivalence recursively.
 *
 * During DFS traversal, if we find that for current `canon_id` type we
 * already have some mapping in hypothetical map, we check for two possible
 * situations:
 *   - `canon_id` is mapped to exactly the same type as `cand_id`. This will
 *     happen when type graphs have cycles. In this case we assume those two
 *     types are equivalent.
 *   - `canon_id` is mapped to different type. This is contradiction in our
 *     hypothetical mapping, because same graph in canonical graph corresponds
 *     to two different types in candidate graph, which for equivalent type
 *     graphs shouldn't happen. This condition terminates equivalence check
 *     with negative result.
 *
 * If type graphs traversal exhausts types to check and find no contradiction,
 * then type graphs are equivalent.
 *
 * When checking types for equivalence, there is one special case: FWD types.
 * If FWD type resolution is allowed and one of the types (either from canonical
 * or candidate graph) is FWD and other is STRUCT/UNION (depending on FWD's kind
 * flag) and their names match, hypothetical mapping is updated to point from
 * FWD to STRUCT/UNION. If graphs will be determined as equivalent successfully,
 * this mapping will be used to record FWD -> STRUCT/UNION mapping permanently.
 *
 * Technically, this could lead to incorrect FWD to STRUCT/UNION resolution,
 * if there are two exactly named (or anonymous) structs/unions that are
 * compatible structurally, one of which has FWD field, while other is concrete
 * STRUCT/UNION, but according to C sources they are different structs/unions
 * that are referencing different types with the same name. This is extremely
 * unlikely to happen, but btf_dedup API allows to disable FWD resolution if
 * this logic is causing problems.
 *
 * Doing FWD resolution means that both candidate and/or canonical graphs can
 * consists of portions of the graph that come from multiple compilation units.
 * This is due to the fact that types within single compilation unit are always
 * deduplicated and FWDs are already resolved, if referenced struct/union
 * definiton is available. So, if we had unresolved FWD and found corresponding
 * STRUCT/UNION, they will be from different compilation units. This
 * consequently means that when we "link" FWD to corresponding STRUCT/UNION,
 * type graph will likely have at least two different BTF types that describe
 * same type (e.g., most probably there will be two different BTF types for the
 * same 'int' primitive type) and could even have "overlapping" parts of type
 * graph that describe same subset of types.
 *
 * This in turn means that our assumption that each type in canonical graph
 * must correspond to exactly one type in candidate graph might not hold
 * anymore and will make it harder to detect contradictions using hypothetical
 * map. To handle this problem, we allow to follow FWD -> STRUCT/UNION
 * resolution only in canonical graph. FWDs in candidate graphs are never
 * resolved. To see why it's OK, let's check all possible situations w.r.t. FWDs
 * that can occur:
 *   - Both types in canonical and candidate graphs are FWDs. If they are
 *     structurally equivalent, then they can either be both resolved to the
 *     same STRUCT/UNION or not resolved at all. In both cases they are
 *     equivalent and there is no need to resolve FWD on candidate side.
 *   - Both types in canonical and candidate graphs are concrete STRUCT/UNION,
 *     so nothing to resolve as well, algorithm will check equivalence anyway.
 *   - Type in canonical graph is FWD, while type in candidate is concrete
 *     STRUCT/UNION. In this case candidate graph comes from single compilation
 *     unit, so there is exactly one BTF type for each unique C type. After
 *     resolving FWD into STRUCT/UNION, there might be more than one BTF type
 *     in canonical graph mapping to single BTF type in candidate graph, but
 *     because hypothetical mapping maps from canonical to candidate types, it's
 *     alright, and we still maintain the property of having single `canon_id`
 *     mapping to single `cand_id` (there could be two different `canon_id`
 *     mapped to the same `cand_id`, but it's not contradictory).
 *   - Type in canonical graph is concrete STRUCT/UNION, while type in candidate
 *     graph is FWD. In this case we are just going to check compatibility of
 *     STRUCT/UNION and corresponding FWD, and if they are compatible, we'll
 *     assume that whatever STRUCT/UNION FWD resolves to must be equivalent to
 *     a concrete STRUCT/UNION from canonical graph. If the rest of type graphs
 *     turn out equivalent, we'll re-resolve FWD to concrete STRUCT/UNION from
 *     canonical graph.
 */
static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
			      __u32 canon_id)
{
	struct btf_type *cand_type;
	struct btf_type *canon_type;
	__u32 hypot_type_id;
	__u16 cand_kind;
	__u16 canon_kind;
	int i, eq;

	/* if both resolve to the same canonical, they must be equivalent */
	if (resolve_type_id(d, cand_id) == resolve_type_id(d, canon_id))
		return 1;

	canon_id = resolve_fwd_id(d, canon_id);

	hypot_type_id = d->hypot_map[canon_id];
	if (hypot_type_id <= BTF_MAX_TYPE)
		return hypot_type_id == cand_id;

	if (btf_dedup_hypot_map_add(d, canon_id, cand_id))
		return -ENOMEM;

	cand_type = d->btf->types[cand_id];
	canon_type = d->btf->types[canon_id];
	cand_kind = BTF_INFO_KIND(cand_type->info);
	canon_kind = BTF_INFO_KIND(canon_type->info);

	if (cand_type->name_off != canon_type->name_off)
		return 0;

	/* FWD <--> STRUCT/UNION equivalence check, if enabled */
	if (!d->opts.dont_resolve_fwds
	    && (cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD)
	    && cand_kind != canon_kind) {
		__u16 real_kind;
		__u16 fwd_kind;

		if (cand_kind == BTF_KIND_FWD) {
			real_kind = canon_kind;
			fwd_kind = btf_fwd_kind(cand_type);
		} else {
			real_kind = cand_kind;
			fwd_kind = btf_fwd_kind(canon_type);
		}
		return fwd_kind == real_kind;
	}

	if (cand_type->info != canon_type->info)
		return 0;

	switch (cand_kind) {
	case BTF_KIND_INT:
		return btf_equal_int(cand_type, canon_type);

	case BTF_KIND_ENUM:
		return btf_equal_enum(cand_type, canon_type);

	case BTF_KIND_FWD:
		return btf_equal_common(cand_type, canon_type);

	case BTF_KIND_CONST:
	case BTF_KIND_VOLATILE:
	case BTF_KIND_RESTRICT:
	case BTF_KIND_PTR:
	case BTF_KIND_TYPEDEF:
	case BTF_KIND_FUNC:
		return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);

	case BTF_KIND_ARRAY: {
		struct btf_array *cand_arr, *canon_arr;

		if (!btf_compat_array(cand_type, canon_type))
			return 0;
		cand_arr = (struct btf_array *)(cand_type + 1);
		canon_arr = (struct btf_array *)(canon_type + 1);
		eq = btf_dedup_is_equiv(d,
			cand_arr->index_type, canon_arr->index_type);
		if (eq <= 0)
			return eq;
		return btf_dedup_is_equiv(d, cand_arr->type, canon_arr->type);
	}

	case BTF_KIND_STRUCT:
	case BTF_KIND_UNION: {
		struct btf_member *cand_m, *canon_m;
		__u16 vlen;

		if (!btf_equal_struct(cand_type, canon_type))
			return 0;
		vlen = BTF_INFO_VLEN(cand_type->info);
		cand_m = (struct btf_member *)(cand_type + 1);
		canon_m = (struct btf_member *)(canon_type + 1);
		for (i = 0; i < vlen; i++) {
			eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type);
			if (eq <= 0)
				return eq;
			cand_m++;
			canon_m++;
		}

		return 1;
	}

	case BTF_KIND_FUNC_PROTO: {
		struct btf_param *cand_p, *canon_p;
		__u16 vlen;

		if (!btf_compat_fnproto(cand_type, canon_type))
			return 0;
		eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
		if (eq <= 0)
			return eq;
		vlen = BTF_INFO_VLEN(cand_type->info);
		cand_p = (struct btf_param *)(cand_type + 1);
		canon_p = (struct btf_param *)(canon_type + 1);
		for (i = 0; i < vlen; i++) {
			eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type);
			if (eq <= 0)
				return eq;
			cand_p++;
			canon_p++;
		}
		return 1;
	}

	default:
		return -EINVAL;
	}
	return 0;
}

/*
 * Use hypothetical mapping, produced by successful type graph equivalence
 * check, to augment existing struct/union canonical mapping, where possible.
 *
 * If BTF_KIND_FWD resolution is allowed, this mapping is also used to record
 * FWD -> STRUCT/UNION correspondence as well. FWD resolution is bidirectional:
 * it doesn't matter if FWD type was part of canonical graph or candidate one,
 * we are recording the mapping anyway. As opposed to carefulness required
 * for struct/union correspondence mapping (described below), for FWD resolution
 * it's not important, as by the time that FWD type (reference type) will be
 * deduplicated all structs/unions will be deduped already anyway.
 *
 * Recording STRUCT/UNION mapping is purely a performance optimization and is
 * not required for correctness. It needs to be done carefully to ensure that
 * struct/union from candidate's type graph is not mapped into corresponding
 * struct/union from canonical type graph that itself hasn't been resolved into
 * canonical representative. The only guarantee we have is that canonical
 * struct/union was determined as canonical and that won't change. But any
 * types referenced through that struct/union fields could have been not yet
 * resolved, so in case like that it's too early to establish any kind of
 * correspondence between structs/unions.
 *
 * No canonical correspondence is derived for primitive types (they are already
 * deduplicated completely already anyway) or reference types (they rely on
 * stability of struct/union canonical relationship for equivalence checks).
 */
static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
{
	__u32 cand_type_id, targ_type_id;
	__u16 t_kind, c_kind;
	__u32 t_id, c_id;
	int i;

	for (i = 0; i < d->hypot_cnt; i++) {
		cand_type_id = d->hypot_list[i];
		targ_type_id = d->hypot_map[cand_type_id];
		t_id = resolve_type_id(d, targ_type_id);
		c_id = resolve_type_id(d, cand_type_id);
		t_kind = BTF_INFO_KIND(d->btf->types[t_id]->info);
		c_kind = BTF_INFO_KIND(d->btf->types[c_id]->info);
		/*
		 * Resolve FWD into STRUCT/UNION.
		 * It's ok to resolve FWD into STRUCT/UNION that's not yet
		 * mapped to canonical representative (as opposed to
		 * STRUCT/UNION <--> STRUCT/UNION mapping logic below), because
		 * eventually that struct is going to be mapped and all resolved
		 * FWDs will automatically resolve to correct canonical
		 * representative. This will happen before ref type deduping,
		 * which critically depends on stability of these mapping. This
		 * stability is not a requirement for STRUCT/UNION equivalence
		 * checks, though.
		 */
		if (t_kind != BTF_KIND_FWD && c_kind == BTF_KIND_FWD)
			d->map[c_id] = t_id;
		else if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD)
			d->map[t_id] = c_id;

		if ((t_kind == BTF_KIND_STRUCT || t_kind == BTF_KIND_UNION) &&
		    c_kind != BTF_KIND_FWD &&
		    is_type_mapped(d, c_id) &&
		    !is_type_mapped(d, t_id)) {
			/*
			 * as a perf optimization, we can map struct/union
			 * that's part of type graph we just verified for
			 * equivalence. We can do that for struct/union that has
			 * canonical representative only, though.
			 */
			d->map[t_id] = c_id;
		}
	}
}

/*
 * Deduplicate struct/union types.
 *
 * For each struct/union type its type signature hash is calculated, taking
 * into account type's name, size, number, order and names of fields, but
 * ignoring type ID's referenced from fields, because they might not be deduped
 * completely until after reference types deduplication phase. This type hash
 * is used to iterate over all potential canonical types, sharing same hash.
 * For each canonical candidate we check whether type graphs that they form
 * (through referenced types in fields and so on) are equivalent using algorithm
 * implemented in `btf_dedup_is_equiv`. If such equivalence is found and
 * BTF_KIND_FWD resolution is allowed, then hypothetical mapping
 * (btf_dedup->hypot_map) produced by aforementioned type graph equivalence
 * algorithm is used to record FWD -> STRUCT/UNION mapping. It's also used to
 * potentially map other structs/unions to their canonical representatives,
 * if such relationship hasn't yet been established. This speeds up algorithm
 * by eliminating some of the duplicate work.
 *
 * If no matching canonical representative was found, struct/union is marked
 * as canonical for itself and is added into btf_dedup->dedup_table hash map
 * for further look ups.
 */
static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
{
	struct btf_dedup_node *cand_node;
	struct btf_type *t;
	/* if we don't find equivalent type, then we are canonical */
	__u32 new_id = type_id;
	__u16 kind;
	__u32 h;

	/* already deduped or is in process of deduping (loop detected) */
	if (d->map[type_id] <= BTF_MAX_TYPE)
		return 0;

	t = d->btf->types[type_id];
	kind = BTF_INFO_KIND(t->info);

	if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
		return 0;

	h = btf_hash_struct(t);
	for_each_hash_node(d->dedup_table, h, cand_node) {
		int eq;

		btf_dedup_clear_hypot_map(d);
		eq = btf_dedup_is_equiv(d, type_id, cand_node->type_id);
		if (eq < 0)
			return eq;
		if (!eq)
			continue;
		new_id = cand_node->type_id;
		btf_dedup_merge_hypot_map(d);
		break;
	}

	d->map[type_id] = new_id;
	if (type_id == new_id && btf_dedup_table_add(d, h, type_id))
		return -ENOMEM;

	return 0;
}

static int btf_dedup_struct_types(struct btf_dedup *d)
{
	int i, err;

	for (i = 1; i <= d->btf->nr_types; i++) {
		err = btf_dedup_struct_type(d, i);
		if (err)
			return err;
	}
	return 0;
}

/*
 * Deduplicate reference type.
 *
 * Once all primitive and struct/union types got deduplicated, we can easily
 * deduplicate all other (reference) BTF types. This is done in two steps:
 *
 * 1. Resolve all referenced type IDs into their canonical type IDs. This
 * resolution can be done either immediately for primitive or struct/union types
 * (because they were deduped in previous two phases) or recursively for
 * reference types. Recursion will always terminate at either primitive or
 * struct/union type, at which point we can "unwind" chain of reference types
 * one by one. There is no danger of encountering cycles because in C type
 * system the only way to form type cycle is through struct/union, so any chain
 * of reference types, even those taking part in a type cycle, will inevitably
 * reach struct/union at some point.
 *
 * 2. Once all referenced type IDs are resolved into canonical ones, BTF type
 * becomes "stable", in the sense that no further deduplication will cause
 * any changes to it. With that, it's now possible to calculate type's signature
 * hash (this time taking into account referenced type IDs) and loop over all
 * potential canonical representatives. If no match was found, current type
 * will become canonical representative of itself and will be added into
 * btf_dedup->dedup_table as another possible canonical representative.
 */
static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
{
	struct btf_dedup_node *cand_node;
	struct btf_type *t, *cand;
	/* if we don't find equivalent type, then we are representative type */
	__u32 new_id = type_id;
	__u32 h, ref_type_id;

	if (d->map[type_id] == BTF_IN_PROGRESS_ID)
		return -ELOOP;
	if (d->map[type_id] <= BTF_MAX_TYPE)
		return resolve_type_id(d, type_id);

	t = d->btf->types[type_id];
	d->map[type_id] = BTF_IN_PROGRESS_ID;

	switch (BTF_INFO_KIND(t->info)) {
	case BTF_KIND_CONST:
	case BTF_KIND_VOLATILE:
	case BTF_KIND_RESTRICT:
	case BTF_KIND_PTR:
	case BTF_KIND_TYPEDEF:
	case BTF_KIND_FUNC:
		ref_type_id = btf_dedup_ref_type(d, t->type);
		if (ref_type_id < 0)
			return ref_type_id;
		t->type = ref_type_id;

		h = btf_hash_common(t);
		for_each_hash_node(d->dedup_table, h, cand_node) {
			cand = d->btf->types[cand_node->type_id];
			if (btf_equal_common(t, cand)) {
				new_id = cand_node->type_id;
				break;
			}
		}
		break;

	case BTF_KIND_ARRAY: {
		struct btf_array *info = (struct btf_array *)(t + 1);

		ref_type_id = btf_dedup_ref_type(d, info->type);
		if (ref_type_id < 0)
			return ref_type_id;
		info->type = ref_type_id;

		ref_type_id = btf_dedup_ref_type(d, info->index_type);
		if (ref_type_id < 0)
			return ref_type_id;
		info->index_type = ref_type_id;

		h = btf_hash_array(t);
		for_each_hash_node(d->dedup_table, h, cand_node) {
			cand = d->btf->types[cand_node->type_id];
			if (btf_equal_array(t, cand)) {
				new_id = cand_node->type_id;
				break;
			}
		}
		break;
	}

	case BTF_KIND_FUNC_PROTO: {
		struct btf_param *param;
		__u16 vlen;
		int i;

		ref_type_id = btf_dedup_ref_type(d, t->type);
		if (ref_type_id < 0)
			return ref_type_id;
		t->type = ref_type_id;

		vlen = BTF_INFO_VLEN(t->info);
		param = (struct btf_param *)(t + 1);
		for (i = 0; i < vlen; i++) {
			ref_type_id = btf_dedup_ref_type(d, param->type);
			if (ref_type_id < 0)
				return ref_type_id;
			param->type = ref_type_id;
			param++;
		}

		h = btf_hash_fnproto(t);
		for_each_hash_node(d->dedup_table, h, cand_node) {
			cand = d->btf->types[cand_node->type_id];
			if (btf_equal_fnproto(t, cand)) {
				new_id = cand_node->type_id;
				break;
			}
		}
		break;
	}

	default:
		return -EINVAL;
	}

	d->map[type_id] = new_id;
	if (type_id == new_id && btf_dedup_table_add(d, h, type_id))
		return -ENOMEM;

	return new_id;
}

static int btf_dedup_ref_types(struct btf_dedup *d)
{
	int i, err;

	for (i = 1; i <= d->btf->nr_types; i++) {
		err = btf_dedup_ref_type(d, i);
		if (err < 0)
			return err;
	}
	btf_dedup_table_free(d);
	return 0;
}

/*
 * Compact types.
 *
 * After we established for each type its corresponding canonical representative
 * type, we now can eliminate types that are not canonical and leave only
 * canonical ones layed out sequentially in memory by copying them over
 * duplicates. During compaction btf_dedup->hypot_map array is reused to store
 * a map from original type ID to a new compacted type ID, which will be used
 * during next phase to "fix up" type IDs, referenced from struct/union and
 * reference types.
 */
static int btf_dedup_compact_types(struct btf_dedup *d)
{
	struct btf_type **new_types;
	__u32 next_type_id = 1;
	char *types_start, *p;
	int i, len;

	/* we are going to reuse hypot_map to store compaction remapping */
	d->hypot_map[0] = 0;
	for (i = 1; i <= d->btf->nr_types; i++)
		d->hypot_map[i] = BTF_UNPROCESSED_ID;

	types_start = d->btf->nohdr_data + d->btf->hdr->type_off;
	p = types_start;

	for (i = 1; i <= d->btf->nr_types; i++) {
		if (d->map[i] != i)
			continue;

		len = btf_type_size(d->btf->types[i]);
		if (len < 0)
			return len;

		memmove(p, d->btf->types[i], len);
		d->hypot_map[i] = next_type_id;
		d->btf->types[next_type_id] = (struct btf_type *)p;
		p += len;
		next_type_id++;
	}

	/* shrink struct btf's internal types index and update btf_header */
	d->btf->nr_types = next_type_id - 1;
	d->btf->types_size = d->btf->nr_types;
	d->btf->hdr->type_len = p - types_start;
	new_types = realloc(d->btf->types,
			    (1 + d->btf->nr_types) * sizeof(struct btf_type *));
	if (!new_types)
		return -ENOMEM;
	d->btf->types = new_types;

	/* make sure string section follows type information without gaps */
	d->btf->hdr->str_off = p - (char *)d->btf->nohdr_data;
	memmove(p, d->btf->strings, d->btf->hdr->str_len);
	d->btf->strings = p;
	p += d->btf->hdr->str_len;

	d->btf->data_size = p - (char *)d->btf->data;
	return 0;
}

/*
 * Figure out final (deduplicated and compacted) type ID for provided original
 * `type_id` by first resolving it into corresponding canonical type ID and
 * then mapping it to a deduplicated type ID, stored in btf_dedup->hypot_map,
 * which is populated during compaction phase.
 */
static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id)
{
	__u32 resolved_type_id, new_type_id;

	resolved_type_id = resolve_type_id(d, type_id);
	new_type_id = d->hypot_map[resolved_type_id];
	if (new_type_id > BTF_MAX_TYPE)
		return -EINVAL;
	return new_type_id;
}

/*
 * Remap referenced type IDs into deduped type IDs.
 *
 * After BTF types are deduplicated and compacted, their final type IDs may
 * differ from original ones. The map from original to a corresponding
 * deduped type ID is stored in btf_dedup->hypot_map and is populated during
 * compaction phase. During remapping phase we are rewriting all type IDs
 * referenced from any BTF type (e.g., struct fields, func proto args, etc) to
 * their final deduped type IDs.
 */
static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
{
	struct btf_type *t = d->btf->types[type_id];
	int i, r;

	switch (BTF_INFO_KIND(t->info)) {
	case BTF_KIND_INT:
	case BTF_KIND_ENUM:
		break;

	case BTF_KIND_FWD:
	case BTF_KIND_CONST:
	case BTF_KIND_VOLATILE:
	case BTF_KIND_RESTRICT:
	case BTF_KIND_PTR:
	case BTF_KIND_TYPEDEF:
	case BTF_KIND_FUNC:
		r = btf_dedup_remap_type_id(d, t->type);
		if (r < 0)
			return r;
		t->type = r;
		break;

	case BTF_KIND_ARRAY: {
		struct btf_array *arr_info = (struct btf_array *)(t + 1);

		r = btf_dedup_remap_type_id(d, arr_info->type);
		if (r < 0)
			return r;
		arr_info->type = r;
		r = btf_dedup_remap_type_id(d, arr_info->index_type);
		if (r < 0)
			return r;
		arr_info->index_type = r;
		break;
	}

	case BTF_KIND_STRUCT:
	case BTF_KIND_UNION: {
		struct btf_member *member = (struct btf_member *)(t + 1);
		__u16 vlen = BTF_INFO_VLEN(t->info);

		for (i = 0; i < vlen; i++) {
			r = btf_dedup_remap_type_id(d, member->type);
			if (r < 0)
				return r;
			member->type = r;
			member++;
		}
		break;
	}

	case BTF_KIND_FUNC_PROTO: {
		struct btf_param *param = (struct btf_param *)(t + 1);
		__u16 vlen = BTF_INFO_VLEN(t->info);

		r = btf_dedup_remap_type_id(d, t->type);
		if (r < 0)
			return r;
		t->type = r;

		for (i = 0; i < vlen; i++) {
			r = btf_dedup_remap_type_id(d, param->type);
			if (r < 0)
				return r;
			param->type = r;
			param++;
		}
		break;
	}

	default:
		return -EINVAL;
	}

	return 0;
}

static int btf_dedup_remap_types(struct btf_dedup *d)
{
	int i, r;

	for (i = 1; i <= d->btf->nr_types; i++) {
		r = btf_dedup_remap_type(d, i);
		if (r < 0)
			return r;
	}
	return 0;
}