summaryrefslogtreecommitdiff
path: root/tools/lib/bpf/usdt.c
blob: f1c9339cfbbc2eae37bcbf2444f1bfdf3f17f7a0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
#include <ctype.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <libelf.h>
#include <gelf.h>
#include <unistd.h>
#include <linux/ptrace.h>
#include <linux/kernel.h>

/* s8 will be marked as poison while it's a reg of riscv */
#if defined(__riscv)
#define rv_s8 s8
#endif

#include "bpf.h"
#include "libbpf.h"
#include "libbpf_common.h"
#include "libbpf_internal.h"
#include "hashmap.h"

/* libbpf's USDT support consists of BPF-side state/code and user-space
 * state/code working together in concert. BPF-side parts are defined in
 * usdt.bpf.h header library. User-space state is encapsulated by struct
 * usdt_manager and all the supporting code centered around usdt_manager.
 *
 * usdt.bpf.h defines two BPF maps that usdt_manager expects: USDT spec map
 * and IP-to-spec-ID map, which is auxiliary map necessary for kernels that
 * don't support BPF cookie (see below). These two maps are implicitly
 * embedded into user's end BPF object file when user's code included
 * usdt.bpf.h. This means that libbpf doesn't do anything special to create
 * these USDT support maps. They are created by normal libbpf logic of
 * instantiating BPF maps when opening and loading BPF object.
 *
 * As such, libbpf is basically unaware of the need to do anything
 * USDT-related until the very first call to bpf_program__attach_usdt(), which
 * can be called by user explicitly or happen automatically during skeleton
 * attach (or, equivalently, through generic bpf_program__attach() call). At
 * this point, libbpf will instantiate and initialize struct usdt_manager and
 * store it in bpf_object. USDT manager is per-BPF object construct, as each
 * independent BPF object might or might not have USDT programs, and thus all
 * the expected USDT-related state. There is no coordination between two
 * bpf_object in parts of USDT attachment, they are oblivious of each other's
 * existence and libbpf is just oblivious, dealing with bpf_object-specific
 * USDT state.
 *
 * Quick crash course on USDTs.
 *
 * From user-space application's point of view, USDT is essentially just
 * a slightly special function call that normally has zero overhead, unless it
 * is being traced by some external entity (e.g, BPF-based tool). Here's how
 * a typical application can trigger USDT probe:
 *
 * #include <sys/sdt.h>  // provided by systemtap-sdt-devel package
 * // folly also provide similar functionality in folly/tracing/StaticTracepoint.h
 *
 * STAP_PROBE3(my_usdt_provider, my_usdt_probe_name, 123, x, &y);
 *
 * USDT is identified by it's <provider-name>:<probe-name> pair of names. Each
 * individual USDT has a fixed number of arguments (3 in the above example)
 * and specifies values of each argument as if it was a function call.
 *
 * USDT call is actually not a function call, but is instead replaced by
 * a single NOP instruction (thus zero overhead, effectively). But in addition
 * to that, those USDT macros generate special SHT_NOTE ELF records in
 * .note.stapsdt ELF section. Here's an example USDT definition as emitted by
 * `readelf -n <binary>`:
 *
 *   stapsdt              0x00000089       NT_STAPSDT (SystemTap probe descriptors)
 *   Provider: test
 *   Name: usdt12
 *   Location: 0x0000000000549df3, Base: 0x00000000008effa4, Semaphore: 0x0000000000a4606e
 *   Arguments: -4@-1204(%rbp) -4@%edi -8@-1216(%rbp) -8@%r8 -4@$5 -8@%r9 8@%rdx 8@%r10 -4@$-9 -2@%cx -2@%ax -1@%sil
 *
 * In this case we have USDT test:usdt12 with 12 arguments.
 *
 * Location and base are offsets used to calculate absolute IP address of that
 * NOP instruction that kernel can replace with an interrupt instruction to
 * trigger instrumentation code (BPF program for all that we care about).
 *
 * Semaphore above is and optional feature. It records an address of a 2-byte
 * refcount variable (normally in '.probes' ELF section) used for signaling if
 * there is anything that is attached to USDT. This is useful for user
 * applications if, for example, they need to prepare some arguments that are
 * passed only to USDTs and preparation is expensive. By checking if USDT is
 * "activated", an application can avoid paying those costs unnecessarily.
 * Recent enough kernel has built-in support for automatically managing this
 * refcount, which libbpf expects and relies on. If USDT is defined without
 * associated semaphore, this value will be zero. See selftests for semaphore
 * examples.
 *
 * Arguments is the most interesting part. This USDT specification string is
 * providing information about all the USDT arguments and their locations. The
 * part before @ sign defined byte size of the argument (1, 2, 4, or 8) and
 * whether the argument is signed or unsigned (negative size means signed).
 * The part after @ sign is assembly-like definition of argument location
 * (see [0] for more details). Technically, assembler can provide some pretty
 * advanced definitions, but libbpf is currently supporting three most common
 * cases:
 *   1) immediate constant, see 5th and 9th args above (-4@$5 and -4@-9);
 *   2) register value, e.g., 8@%rdx, which means "unsigned 8-byte integer
 *      whose value is in register %rdx";
 *   3) memory dereference addressed by register, e.g., -4@-1204(%rbp), which
 *      specifies signed 32-bit integer stored at offset -1204 bytes from
 *      memory address stored in %rbp.
 *
 *   [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation
 *
 * During attachment, libbpf parses all the relevant USDT specifications and
 * prepares `struct usdt_spec` (USDT spec), which is then provided to BPF-side
 * code through spec map. This allows BPF applications to quickly fetch the
 * actual value at runtime using a simple BPF-side code.
 *
 * With basics out of the way, let's go over less immediately obvious aspects
 * of supporting USDTs.
 *
 * First, there is no special USDT BPF program type. It is actually just
 * a uprobe BPF program (which for kernel, at least currently, is just a kprobe
 * program, so BPF_PROG_TYPE_KPROBE program type). With the only difference
 * that uprobe is usually attached at the function entry, while USDT will
 * normally will be somewhere inside the function. But it should always be
 * pointing to NOP instruction, which makes such uprobes the fastest uprobe
 * kind.
 *
 * Second, it's important to realize that such STAP_PROBEn(provider, name, ...)
 * macro invocations can end up being inlined many-many times, depending on
 * specifics of each individual user application. So single conceptual USDT
 * (identified by provider:name pair of identifiers) is, generally speaking,
 * multiple uprobe locations (USDT call sites) in different places in user
 * application. Further, again due to inlining, each USDT call site might end
 * up having the same argument #N be located in a different place. In one call
 * site it could be a constant, in another will end up in a register, and in
 * yet another could be some other register or even somewhere on the stack.
 *
 * As such, "attaching to USDT" means (in general case) attaching the same
 * uprobe BPF program to multiple target locations in user application, each
 * potentially having a completely different USDT spec associated with it.
 * To wire all this up together libbpf allocates a unique integer spec ID for
 * each unique USDT spec. Spec IDs are allocated as sequential small integers
 * so that they can be used as keys in array BPF map (for performance reasons).
 * Spec ID allocation and accounting is big part of what usdt_manager is
 * about. This state has to be maintained per-BPF object and coordinate
 * between different USDT attachments within the same BPF object.
 *
 * Spec ID is the key in spec BPF map, value is the actual USDT spec layed out
 * as struct usdt_spec. Each invocation of BPF program at runtime needs to
 * know its associated spec ID. It gets it either through BPF cookie, which
 * libbpf sets to spec ID during attach time, or, if kernel is too old to
 * support BPF cookie, through IP-to-spec-ID map that libbpf maintains in such
 * case. The latter means that some modes of operation can't be supported
 * without BPF cookie. Such mode is attaching to shared library "generically",
 * without specifying target process. In such case, it's impossible to
 * calculate absolute IP addresses for IP-to-spec-ID map, and thus such mode
 * is not supported without BPF cookie support.
 *
 * Note that libbpf is using BPF cookie functionality for its own internal
 * needs, so user itself can't rely on BPF cookie feature. To that end, libbpf
 * provides conceptually equivalent USDT cookie support. It's still u64
 * user-provided value that can be associated with USDT attachment. Note that
 * this will be the same value for all USDT call sites within the same single
 * *logical* USDT attachment. This makes sense because to user attaching to
 * USDT is a single BPF program triggered for singular USDT probe. The fact
 * that this is done at multiple actual locations is a mostly hidden
 * implementation details. This USDT cookie value can be fetched with
 * bpf_usdt_cookie(ctx) API provided by usdt.bpf.h
 *
 * Lastly, while single USDT can have tons of USDT call sites, it doesn't
 * necessarily have that many different USDT specs. It very well might be
 * that 1000 USDT call sites only need 5 different USDT specs, because all the
 * arguments are typically contained in a small set of registers or stack
 * locations. As such, it's wasteful to allocate as many USDT spec IDs as
 * there are USDT call sites. So libbpf tries to be frugal and performs
 * on-the-fly deduplication during a single USDT attachment to only allocate
 * the minimal required amount of unique USDT specs (and thus spec IDs). This
 * is trivially achieved by using USDT spec string (Arguments string from USDT
 * note) as a lookup key in a hashmap. USDT spec string uniquely defines
 * everything about how to fetch USDT arguments, so two USDT call sites
 * sharing USDT spec string can safely share the same USDT spec and spec ID.
 * Note, this spec string deduplication is happening only during the same USDT
 * attachment, so each USDT spec shares the same USDT cookie value. This is
 * not generally true for other USDT attachments within the same BPF object,
 * as even if USDT spec string is the same, USDT cookie value can be
 * different. It was deemed excessive to try to deduplicate across independent
 * USDT attachments by taking into account USDT spec string *and* USDT cookie
 * value, which would complicated spec ID accounting significantly for little
 * gain.
 */

#define USDT_BASE_SEC ".stapsdt.base"
#define USDT_SEMA_SEC ".probes"
#define USDT_NOTE_SEC  ".note.stapsdt"
#define USDT_NOTE_TYPE 3
#define USDT_NOTE_NAME "stapsdt"

/* should match exactly enum __bpf_usdt_arg_type from usdt.bpf.h */
enum usdt_arg_type {
	USDT_ARG_CONST,
	USDT_ARG_REG,
	USDT_ARG_REG_DEREF,
};

/* should match exactly struct __bpf_usdt_arg_spec from usdt.bpf.h */
struct usdt_arg_spec {
	__u64 val_off;
	enum usdt_arg_type arg_type;
	short reg_off;
	bool arg_signed;
	char arg_bitshift;
};

/* should match BPF_USDT_MAX_ARG_CNT in usdt.bpf.h */
#define USDT_MAX_ARG_CNT 12

/* should match struct __bpf_usdt_spec from usdt.bpf.h */
struct usdt_spec {
	struct usdt_arg_spec args[USDT_MAX_ARG_CNT];
	__u64 usdt_cookie;
	short arg_cnt;
};

struct usdt_note {
	const char *provider;
	const char *name;
	/* USDT args specification string, e.g.:
	 * "-4@%esi -4@-24(%rbp) -4@%ecx 2@%ax 8@%rdx"
	 */
	const char *args;
	long loc_addr;
	long base_addr;
	long sema_addr;
};

struct usdt_target {
	long abs_ip;
	long rel_ip;
	long sema_off;
	struct usdt_spec spec;
	const char *spec_str;
};

struct usdt_manager {
	struct bpf_map *specs_map;
	struct bpf_map *ip_to_spec_id_map;

	int *free_spec_ids;
	size_t free_spec_cnt;
	size_t next_free_spec_id;

	bool has_bpf_cookie;
	bool has_sema_refcnt;
};

struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
{
	static const char *ref_ctr_sysfs_path = "/sys/bus/event_source/devices/uprobe/format/ref_ctr_offset";
	struct usdt_manager *man;
	struct bpf_map *specs_map, *ip_to_spec_id_map;

	specs_map = bpf_object__find_map_by_name(obj, "__bpf_usdt_specs");
	ip_to_spec_id_map = bpf_object__find_map_by_name(obj, "__bpf_usdt_ip_to_spec_id");
	if (!specs_map || !ip_to_spec_id_map) {
		pr_warn("usdt: failed to find USDT support BPF maps, did you forget to include bpf/usdt.bpf.h?\n");
		return ERR_PTR(-ESRCH);
	}

	man = calloc(1, sizeof(*man));
	if (!man)
		return ERR_PTR(-ENOMEM);

	man->specs_map = specs_map;
	man->ip_to_spec_id_map = ip_to_spec_id_map;

	/* Detect if BPF cookie is supported for kprobes.
	 * We don't need IP-to-ID mapping if we can use BPF cookies.
	 * Added in: 7adfc6c9b315 ("bpf: Add bpf_get_attach_cookie() BPF helper to access bpf_cookie value")
	 */
	man->has_bpf_cookie = kernel_supports(obj, FEAT_BPF_COOKIE);

	/* Detect kernel support for automatic refcounting of USDT semaphore.
	 * If this is not supported, USDTs with semaphores will not be supported.
	 * Added in: a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe")
	 */
	man->has_sema_refcnt = access(ref_ctr_sysfs_path, F_OK) == 0;

	return man;
}

void usdt_manager_free(struct usdt_manager *man)
{
	if (IS_ERR_OR_NULL(man))
		return;

	free(man->free_spec_ids);
	free(man);
}

static int sanity_check_usdt_elf(Elf *elf, const char *path)
{
	GElf_Ehdr ehdr;
	int endianness;

	if (elf_kind(elf) != ELF_K_ELF) {
		pr_warn("usdt: unrecognized ELF kind %d for '%s'\n", elf_kind(elf), path);
		return -EBADF;
	}

	switch (gelf_getclass(elf)) {
	case ELFCLASS64:
		if (sizeof(void *) != 8) {
			pr_warn("usdt: attaching to 64-bit ELF binary '%s' is not supported\n", path);
			return -EBADF;
		}
		break;
	case ELFCLASS32:
		if (sizeof(void *) != 4) {
			pr_warn("usdt: attaching to 32-bit ELF binary '%s' is not supported\n", path);
			return -EBADF;
		}
		break;
	default:
		pr_warn("usdt: unsupported ELF class for '%s'\n", path);
		return -EBADF;
	}

	if (!gelf_getehdr(elf, &ehdr))
		return -EINVAL;

	if (ehdr.e_type != ET_EXEC && ehdr.e_type != ET_DYN) {
		pr_warn("usdt: unsupported type of ELF binary '%s' (%d), only ET_EXEC and ET_DYN are supported\n",
			path, ehdr.e_type);
		return -EBADF;
	}

#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
	endianness = ELFDATA2LSB;
#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
	endianness = ELFDATA2MSB;
#else
# error "Unrecognized __BYTE_ORDER__"
#endif
	if (endianness != ehdr.e_ident[EI_DATA]) {
		pr_warn("usdt: ELF endianness mismatch for '%s'\n", path);
		return -EBADF;
	}

	return 0;
}

static int find_elf_sec_by_name(Elf *elf, const char *sec_name, GElf_Shdr *shdr, Elf_Scn **scn)
{
	Elf_Scn *sec = NULL;
	size_t shstrndx;

	if (elf_getshdrstrndx(elf, &shstrndx))
		return -EINVAL;

	/* check if ELF is corrupted and avoid calling elf_strptr if yes */
	if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL))
		return -EINVAL;

	while ((sec = elf_nextscn(elf, sec)) != NULL) {
		char *name;

		if (!gelf_getshdr(sec, shdr))
			return -EINVAL;

		name = elf_strptr(elf, shstrndx, shdr->sh_name);
		if (name && strcmp(sec_name, name) == 0) {
			*scn = sec;
			return 0;
		}
	}

	return -ENOENT;
}

struct elf_seg {
	long start;
	long end;
	long offset;
	bool is_exec;
};

static int cmp_elf_segs(const void *_a, const void *_b)
{
	const struct elf_seg *a = _a;
	const struct elf_seg *b = _b;

	return a->start < b->start ? -1 : 1;
}

static int parse_elf_segs(Elf *elf, const char *path, struct elf_seg **segs, size_t *seg_cnt)
{
	GElf_Phdr phdr;
	size_t n;
	int i, err;
	struct elf_seg *seg;
	void *tmp;

	*seg_cnt = 0;

	if (elf_getphdrnum(elf, &n)) {
		err = -errno;
		return err;
	}

	for (i = 0; i < n; i++) {
		if (!gelf_getphdr(elf, i, &phdr)) {
			err = -errno;
			return err;
		}

		pr_debug("usdt: discovered PHDR #%d in '%s': vaddr 0x%lx memsz 0x%lx offset 0x%lx type 0x%lx flags 0x%lx\n",
			 i, path, (long)phdr.p_vaddr, (long)phdr.p_memsz, (long)phdr.p_offset,
			 (long)phdr.p_type, (long)phdr.p_flags);
		if (phdr.p_type != PT_LOAD)
			continue;

		tmp = libbpf_reallocarray(*segs, *seg_cnt + 1, sizeof(**segs));
		if (!tmp)
			return -ENOMEM;

		*segs = tmp;
		seg = *segs + *seg_cnt;
		(*seg_cnt)++;

		seg->start = phdr.p_vaddr;
		seg->end = phdr.p_vaddr + phdr.p_memsz;
		seg->offset = phdr.p_offset;
		seg->is_exec = phdr.p_flags & PF_X;
	}

	if (*seg_cnt == 0) {
		pr_warn("usdt: failed to find PT_LOAD program headers in '%s'\n", path);
		return -ESRCH;
	}

	qsort(*segs, *seg_cnt, sizeof(**segs), cmp_elf_segs);
	return 0;
}

static int parse_lib_segs(int pid, const char *lib_path, struct elf_seg **segs, size_t *seg_cnt)
{
	char path[PATH_MAX], line[PATH_MAX], mode[16];
	size_t seg_start, seg_end, seg_off;
	struct elf_seg *seg;
	int tmp_pid, i, err;
	FILE *f;

	*seg_cnt = 0;

	/* Handle containerized binaries only accessible from
	 * /proc/<pid>/root/<path>. They will be reported as just /<path> in
	 * /proc/<pid>/maps.
	 */
	if (sscanf(lib_path, "/proc/%d/root%s", &tmp_pid, path) == 2 && pid == tmp_pid)
		goto proceed;

	if (!realpath(lib_path, path)) {
		pr_warn("usdt: failed to get absolute path of '%s' (err %d), using path as is...\n",
			lib_path, -errno);
		libbpf_strlcpy(path, lib_path, sizeof(path));
	}

proceed:
	sprintf(line, "/proc/%d/maps", pid);
	f = fopen(line, "r");
	if (!f) {
		err = -errno;
		pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n",
			line, lib_path, err);
		return err;
	}

	/* We need to handle lines with no path at the end:
	 *
	 * 7f5c6f5d1000-7f5c6f5d3000 rw-p 001c7000 08:04 21238613      /usr/lib64/libc-2.17.so
	 * 7f5c6f5d3000-7f5c6f5d8000 rw-p 00000000 00:00 0
	 * 7f5c6f5d8000-7f5c6f5d9000 r-xp 00000000 103:01 362990598    /data/users/andriin/linux/tools/bpf/usdt/libhello_usdt.so
	 */
	while (fscanf(f, "%zx-%zx %s %zx %*s %*d%[^\n]\n",
		      &seg_start, &seg_end, mode, &seg_off, line) == 5) {
		void *tmp;

		/* to handle no path case (see above) we need to capture line
		 * without skipping any whitespaces. So we need to strip
		 * leading whitespaces manually here
		 */
		i = 0;
		while (isblank(line[i]))
			i++;
		if (strcmp(line + i, path) != 0)
			continue;

		pr_debug("usdt: discovered segment for lib '%s': addrs %zx-%zx mode %s offset %zx\n",
			 path, seg_start, seg_end, mode, seg_off);

		/* ignore non-executable sections for shared libs */
		if (mode[2] != 'x')
			continue;

		tmp = libbpf_reallocarray(*segs, *seg_cnt + 1, sizeof(**segs));
		if (!tmp) {
			err = -ENOMEM;
			goto err_out;
		}

		*segs = tmp;
		seg = *segs + *seg_cnt;
		*seg_cnt += 1;

		seg->start = seg_start;
		seg->end = seg_end;
		seg->offset = seg_off;
		seg->is_exec = true;
	}

	if (*seg_cnt == 0) {
		pr_warn("usdt: failed to find '%s' (resolved to '%s') within PID %d memory mappings\n",
			lib_path, path, pid);
		err = -ESRCH;
		goto err_out;
	}

	qsort(*segs, *seg_cnt, sizeof(**segs), cmp_elf_segs);
	err = 0;
err_out:
	fclose(f);
	return err;
}

static struct elf_seg *find_elf_seg(struct elf_seg *segs, size_t seg_cnt, long addr, bool relative)
{
	struct elf_seg *seg;
	int i;

	if (relative) {
		/* for shared libraries, address is relative offset and thus
		 * should be fall within logical offset-based range of
		 * [offset_start, offset_end)
		 */
		for (i = 0, seg = segs; i < seg_cnt; i++, seg++) {
			if (seg->offset <= addr && addr < seg->offset + (seg->end - seg->start))
				return seg;
		}
	} else {
		/* for binaries, address is absolute and thus should be within
		 * absolute address range of [seg_start, seg_end)
		 */
		for (i = 0, seg = segs; i < seg_cnt; i++, seg++) {
			if (seg->start <= addr && addr < seg->end)
				return seg;
		}
	}

	return NULL;
}

static int parse_usdt_note(Elf *elf, const char *path, long base_addr,
			   GElf_Nhdr *nhdr, const char *data, size_t name_off, size_t desc_off,
			   struct usdt_note *usdt_note);

static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie);

static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *path, pid_t pid,
				const char *usdt_provider, const char *usdt_name, __u64 usdt_cookie,
				struct usdt_target **out_targets, size_t *out_target_cnt)
{
	size_t off, name_off, desc_off, seg_cnt = 0, lib_seg_cnt = 0, target_cnt = 0;
	struct elf_seg *segs = NULL, *lib_segs = NULL;
	struct usdt_target *targets = NULL, *target;
	long base_addr = 0;
	Elf_Scn *notes_scn, *base_scn;
	GElf_Shdr base_shdr, notes_shdr;
	GElf_Ehdr ehdr;
	GElf_Nhdr nhdr;
	Elf_Data *data;
	int err;

	*out_targets = NULL;
	*out_target_cnt = 0;

	err = find_elf_sec_by_name(elf, USDT_NOTE_SEC, &notes_shdr, &notes_scn);
	if (err) {
		pr_warn("usdt: no USDT notes section (%s) found in '%s'\n", USDT_NOTE_SEC, path);
		return err;
	}

	if (notes_shdr.sh_type != SHT_NOTE || !gelf_getehdr(elf, &ehdr)) {
		pr_warn("usdt: invalid USDT notes section (%s) in '%s'\n", USDT_NOTE_SEC, path);
		return -EINVAL;
	}

	err = parse_elf_segs(elf, path, &segs, &seg_cnt);
	if (err) {
		pr_warn("usdt: failed to process ELF program segments for '%s': %d\n", path, err);
		goto err_out;
	}

	/* .stapsdt.base ELF section is optional, but is used for prelink
	 * offset compensation (see a big comment further below)
	 */
	if (find_elf_sec_by_name(elf, USDT_BASE_SEC, &base_shdr, &base_scn) == 0)
		base_addr = base_shdr.sh_addr;

	data = elf_getdata(notes_scn, 0);
	off = 0;
	while ((off = gelf_getnote(data, off, &nhdr, &name_off, &desc_off)) > 0) {
		long usdt_abs_ip, usdt_rel_ip, usdt_sema_off = 0;
		struct usdt_note note;
		struct elf_seg *seg = NULL;
		void *tmp;

		err = parse_usdt_note(elf, path, base_addr, &nhdr,
				      data->d_buf, name_off, desc_off, &note);
		if (err)
			goto err_out;

		if (strcmp(note.provider, usdt_provider) != 0 || strcmp(note.name, usdt_name) != 0)
			continue;

		/* We need to compensate "prelink effect". See [0] for details,
		 * relevant parts quoted here:
		 *
		 * Each SDT probe also expands into a non-allocated ELF note. You can
		 * find this by looking at SHT_NOTE sections and decoding the format;
		 * see below for details. Because the note is non-allocated, it means
		 * there is no runtime cost, and also preserved in both stripped files
		 * and .debug files.
		 *
		 * However, this means that prelink won't adjust the note's contents
		 * for address offsets. Instead, this is done via the .stapsdt.base
		 * section. This is a special section that is added to the text. We
		 * will only ever have one of these sections in a final link and it
		 * will only ever be one byte long. Nothing about this section itself
		 * matters, we just use it as a marker to detect prelink address
		 * adjustments.
		 *
		 * Each probe note records the link-time address of the .stapsdt.base
		 * section alongside the probe PC address. The decoder compares the
		 * base address stored in the note with the .stapsdt.base section's
		 * sh_addr. Initially these are the same, but the section header will
		 * be adjusted by prelink. So the decoder applies the difference to
		 * the probe PC address to get the correct prelinked PC address; the
		 * same adjustment is applied to the semaphore address, if any.
		 *
		 *   [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation
		 */
		usdt_rel_ip = usdt_abs_ip = note.loc_addr;
		if (base_addr) {
			usdt_abs_ip += base_addr - note.base_addr;
			usdt_rel_ip += base_addr - note.base_addr;
		}

		if (ehdr.e_type == ET_EXEC) {
			/* When attaching uprobes (which what USDTs basically
			 * are) kernel expects a relative IP to be specified,
			 * so if we are attaching to an executable ELF binary
			 * (i.e., not a shared library), we need to calculate
			 * proper relative IP based on ELF's load address
			 */
			seg = find_elf_seg(segs, seg_cnt, usdt_abs_ip, false /* relative */);
			if (!seg) {
				err = -ESRCH;
				pr_warn("usdt: failed to find ELF program segment for '%s:%s' in '%s' at IP 0x%lx\n",
					usdt_provider, usdt_name, path, usdt_abs_ip);
				goto err_out;
			}
			if (!seg->is_exec) {
				err = -ESRCH;
				pr_warn("usdt: matched ELF binary '%s' segment [0x%lx, 0x%lx) for '%s:%s' at IP 0x%lx is not executable\n",
					path, seg->start, seg->end, usdt_provider, usdt_name,
					usdt_abs_ip);
				goto err_out;
			}

			usdt_rel_ip = usdt_abs_ip - (seg->start - seg->offset);
		} else if (!man->has_bpf_cookie) { /* ehdr.e_type == ET_DYN */
			/* If we don't have BPF cookie support but need to
			 * attach to a shared library, we'll need to know and
			 * record absolute addresses of attach points due to
			 * the need to lookup USDT spec by absolute IP of
			 * triggered uprobe. Doing this resolution is only
			 * possible when we have a specific PID of the process
			 * that's using specified shared library. BPF cookie
			 * removes the absolute address limitation as we don't
			 * need to do this lookup (we just use BPF cookie as
			 * an index of USDT spec), so for newer kernels with
			 * BPF cookie support libbpf supports USDT attachment
			 * to shared libraries with no PID filter.
			 */
			if (pid < 0) {
				pr_warn("usdt: attaching to shared libraries without specific PID is not supported on current kernel\n");
				err = -ENOTSUP;
				goto err_out;
			}

			/* lib_segs are lazily initialized only if necessary */
			if (lib_seg_cnt == 0) {
				err = parse_lib_segs(pid, path, &lib_segs, &lib_seg_cnt);
				if (err) {
					pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %d\n",
						pid, path, err);
					goto err_out;
				}
			}

			seg = find_elf_seg(lib_segs, lib_seg_cnt, usdt_rel_ip, true /* relative */);
			if (!seg) {
				err = -ESRCH;
				pr_warn("usdt: failed to find shared lib memory segment for '%s:%s' in '%s' at relative IP 0x%lx\n",
					usdt_provider, usdt_name, path, usdt_rel_ip);
				goto err_out;
			}

			usdt_abs_ip = seg->start + (usdt_rel_ip - seg->offset);
		}

		pr_debug("usdt: probe for '%s:%s' in %s '%s': addr 0x%lx base 0x%lx (resolved abs_ip 0x%lx rel_ip 0x%lx) args '%s' in segment [0x%lx, 0x%lx) at offset 0x%lx\n",
			 usdt_provider, usdt_name, ehdr.e_type == ET_EXEC ? "exec" : "lib ", path,
			 note.loc_addr, note.base_addr, usdt_abs_ip, usdt_rel_ip, note.args,
			 seg ? seg->start : 0, seg ? seg->end : 0, seg ? seg->offset : 0);

		/* Adjust semaphore address to be a relative offset */
		if (note.sema_addr) {
			if (!man->has_sema_refcnt) {
				pr_warn("usdt: kernel doesn't support USDT semaphore refcounting for '%s:%s' in '%s'\n",
					usdt_provider, usdt_name, path);
				err = -ENOTSUP;
				goto err_out;
			}

			seg = find_elf_seg(segs, seg_cnt, note.sema_addr, false /* relative */);
			if (!seg) {
				err = -ESRCH;
				pr_warn("usdt: failed to find ELF loadable segment with semaphore of '%s:%s' in '%s' at 0x%lx\n",
					usdt_provider, usdt_name, path, note.sema_addr);
				goto err_out;
			}
			if (seg->is_exec) {
				err = -ESRCH;
				pr_warn("usdt: matched ELF binary '%s' segment [0x%lx, 0x%lx] for semaphore of '%s:%s' at 0x%lx is executable\n",
					path, seg->start, seg->end, usdt_provider, usdt_name,
					note.sema_addr);
				goto err_out;
			}

			usdt_sema_off = note.sema_addr - (seg->start - seg->offset);

			pr_debug("usdt: sema  for '%s:%s' in %s '%s': addr 0x%lx base 0x%lx (resolved 0x%lx) in segment [0x%lx, 0x%lx] at offset 0x%lx\n",
				 usdt_provider, usdt_name, ehdr.e_type == ET_EXEC ? "exec" : "lib ",
				 path, note.sema_addr, note.base_addr, usdt_sema_off,
				 seg->start, seg->end, seg->offset);
		}

		/* Record adjusted addresses and offsets and parse USDT spec */
		tmp = libbpf_reallocarray(targets, target_cnt + 1, sizeof(*targets));
		if (!tmp) {
			err = -ENOMEM;
			goto err_out;
		}
		targets = tmp;

		target = &targets[target_cnt];
		memset(target, 0, sizeof(*target));

		target->abs_ip = usdt_abs_ip;
		target->rel_ip = usdt_rel_ip;
		target->sema_off = usdt_sema_off;

		/* notes->args references strings from Elf itself, so they can
		 * be referenced safely until elf_end() call
		 */
		target->spec_str = note.args;

		err = parse_usdt_spec(&target->spec, &note, usdt_cookie);
		if (err)
			goto err_out;

		target_cnt++;
	}

	*out_targets = targets;
	*out_target_cnt = target_cnt;
	err = target_cnt;

err_out:
	free(segs);
	free(lib_segs);
	if (err < 0)
		free(targets);
	return err;
}

struct bpf_link_usdt {
	struct bpf_link link;

	struct usdt_manager *usdt_man;

	size_t spec_cnt;
	int *spec_ids;

	size_t uprobe_cnt;
	struct {
		long abs_ip;
		struct bpf_link *link;
	} *uprobes;
};

static int bpf_link_usdt_detach(struct bpf_link *link)
{
	struct bpf_link_usdt *usdt_link = container_of(link, struct bpf_link_usdt, link);
	struct usdt_manager *man = usdt_link->usdt_man;
	int i;

	for (i = 0; i < usdt_link->uprobe_cnt; i++) {
		/* detach underlying uprobe link */
		bpf_link__destroy(usdt_link->uprobes[i].link);
		/* there is no need to update specs map because it will be
		 * unconditionally overwritten on subsequent USDT attaches,
		 * but if BPF cookies are not used we need to remove entry
		 * from ip_to_spec_id map, otherwise we'll run into false
		 * conflicting IP errors
		 */
		if (!man->has_bpf_cookie) {
			/* not much we can do about errors here */
			(void)bpf_map_delete_elem(bpf_map__fd(man->ip_to_spec_id_map),
						  &usdt_link->uprobes[i].abs_ip);
		}
	}

	/* try to return the list of previously used spec IDs to usdt_manager
	 * for future reuse for subsequent USDT attaches
	 */
	if (!man->free_spec_ids) {
		/* if there were no free spec IDs yet, just transfer our IDs */
		man->free_spec_ids = usdt_link->spec_ids;
		man->free_spec_cnt = usdt_link->spec_cnt;
		usdt_link->spec_ids = NULL;
	} else {
		/* otherwise concat IDs */
		size_t new_cnt = man->free_spec_cnt + usdt_link->spec_cnt;
		int *new_free_ids;

		new_free_ids = libbpf_reallocarray(man->free_spec_ids, new_cnt,
						   sizeof(*new_free_ids));
		/* If we couldn't resize free_spec_ids, we'll just leak
		 * a bunch of free IDs; this is very unlikely to happen and if
		 * system is so exhausted on memory, it's the least of user's
		 * concerns, probably.
		 * So just do our best here to return those IDs to usdt_manager.
		 */
		if (new_free_ids) {
			memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids,
			       usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids));
			man->free_spec_ids = new_free_ids;
			man->free_spec_cnt = new_cnt;
		}
	}

	return 0;
}

static void bpf_link_usdt_dealloc(struct bpf_link *link)
{
	struct bpf_link_usdt *usdt_link = container_of(link, struct bpf_link_usdt, link);

	free(usdt_link->spec_ids);
	free(usdt_link->uprobes);
	free(usdt_link);
}

static size_t specs_hash_fn(const void *key, void *ctx)
{
	const char *s = key;

	return str_hash(s);
}

static bool specs_equal_fn(const void *key1, const void *key2, void *ctx)
{
	const char *s1 = key1;
	const char *s2 = key2;

	return strcmp(s1, s2) == 0;
}

static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash,
			    struct bpf_link_usdt *link, struct usdt_target *target,
			    int *spec_id, bool *is_new)
{
	void *tmp;
	int err;

	/* check if we already allocated spec ID for this spec string */
	if (hashmap__find(specs_hash, target->spec_str, &tmp)) {
		*spec_id = (long)tmp;
		*is_new = false;
		return 0;
	}

	/* otherwise it's a new ID that needs to be set up in specs map and
	 * returned back to usdt_manager when USDT link is detached
	 */
	tmp = libbpf_reallocarray(link->spec_ids, link->spec_cnt + 1, sizeof(*link->spec_ids));
	if (!tmp)
		return -ENOMEM;
	link->spec_ids = tmp;

	/* get next free spec ID, giving preference to free list, if not empty */
	if (man->free_spec_cnt) {
		*spec_id = man->free_spec_ids[man->free_spec_cnt - 1];

		/* cache spec ID for current spec string for future lookups */
		err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id);
		if (err)
			 return err;

		man->free_spec_cnt--;
	} else {
		/* don't allocate spec ID bigger than what fits in specs map */
		if (man->next_free_spec_id >= bpf_map__max_entries(man->specs_map))
			return -E2BIG;

		*spec_id = man->next_free_spec_id;

		/* cache spec ID for current spec string for future lookups */
		err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id);
		if (err)
			 return err;

		man->next_free_spec_id++;
	}

	/* remember new spec ID in the link for later return back to free list on detach */
	link->spec_ids[link->spec_cnt] = *spec_id;
	link->spec_cnt++;
	*is_new = true;
	return 0;
}

struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct bpf_program *prog,
					  pid_t pid, const char *path,
					  const char *usdt_provider, const char *usdt_name,
					  __u64 usdt_cookie)
{
	int i, fd, err, spec_map_fd, ip_map_fd;
	LIBBPF_OPTS(bpf_uprobe_opts, opts);
	struct hashmap *specs_hash = NULL;
	struct bpf_link_usdt *link = NULL;
	struct usdt_target *targets = NULL;
	size_t target_cnt;
	Elf *elf;

	spec_map_fd = bpf_map__fd(man->specs_map);
	ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map);

	/* TODO: perform path resolution similar to uprobe's */
	fd = open(path, O_RDONLY);
	if (fd < 0) {
		err = -errno;
		pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err);
		return libbpf_err_ptr(err);
	}

	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
	if (!elf) {
		err = -EBADF;
		pr_warn("usdt: failed to parse ELF binary '%s': %s\n", path, elf_errmsg(-1));
		goto err_out;
	}

	err = sanity_check_usdt_elf(elf, path);
	if (err)
		goto err_out;

	/* normalize PID filter */
	if (pid < 0)
		pid = -1;
	else if (pid == 0)
		pid = getpid();

	/* discover USDT in given binary, optionally limiting
	 * activations to a given PID, if pid > 0
	 */
	err = collect_usdt_targets(man, elf, path, pid, usdt_provider, usdt_name,
				   usdt_cookie, &targets, &target_cnt);
	if (err <= 0) {
		err = (err == 0) ? -ENOENT : err;
		goto err_out;
	}

	specs_hash = hashmap__new(specs_hash_fn, specs_equal_fn, NULL);
	if (IS_ERR(specs_hash)) {
		err = PTR_ERR(specs_hash);
		goto err_out;
	}

	link = calloc(1, sizeof(*link));
	if (!link) {
		err = -ENOMEM;
		goto err_out;
	}

	link->usdt_man = man;
	link->link.detach = &bpf_link_usdt_detach;
	link->link.dealloc = &bpf_link_usdt_dealloc;

	link->uprobes = calloc(target_cnt, sizeof(*link->uprobes));
	if (!link->uprobes) {
		err = -ENOMEM;
		goto err_out;
	}

	for (i = 0; i < target_cnt; i++) {
		struct usdt_target *target = &targets[i];
		struct bpf_link *uprobe_link;
		bool is_new;
		int spec_id;

		/* Spec ID can be either reused or newly allocated. If it is
		 * newly allocated, we'll need to fill out spec map, otherwise
		 * entire spec should be valid and can be just used by a new
		 * uprobe. We reuse spec when USDT arg spec is identical. We
		 * also never share specs between two different USDT
		 * attachments ("links"), so all the reused specs already
		 * share USDT cookie value implicitly.
		 */
		err = allocate_spec_id(man, specs_hash, link, target, &spec_id, &is_new);
		if (err)
			goto err_out;

		if (is_new && bpf_map_update_elem(spec_map_fd, &spec_id, &target->spec, BPF_ANY)) {
			err = -errno;
			pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %d\n",
				spec_id, usdt_provider, usdt_name, path, err);
			goto err_out;
		}
		if (!man->has_bpf_cookie &&
		    bpf_map_update_elem(ip_map_fd, &target->abs_ip, &spec_id, BPF_NOEXIST)) {
			err = -errno;
			if (err == -EEXIST) {
				pr_warn("usdt: IP collision detected for spec #%d for '%s:%s' in '%s'\n",
				        spec_id, usdt_provider, usdt_name, path);
			} else {
				pr_warn("usdt: failed to map IP 0x%lx to spec #%d for '%s:%s' in '%s': %d\n",
					target->abs_ip, spec_id, usdt_provider, usdt_name,
					path, err);
			}
			goto err_out;
		}

		opts.ref_ctr_offset = target->sema_off;
		opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0;
		uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path,
							      target->rel_ip, &opts);
		err = libbpf_get_error(uprobe_link);
		if (err) {
			pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n",
				i, usdt_provider, usdt_name, path, err);
			goto err_out;
		}

		link->uprobes[i].link = uprobe_link;
		link->uprobes[i].abs_ip = target->abs_ip;
		link->uprobe_cnt++;
	}

	free(targets);
	hashmap__free(specs_hash);
	elf_end(elf);
	close(fd);

	return &link->link;

err_out:
	if (link)
		bpf_link__destroy(&link->link);
	free(targets);
	hashmap__free(specs_hash);
	if (elf)
		elf_end(elf);
	close(fd);
	return libbpf_err_ptr(err);
}

/* Parse out USDT ELF note from '.note.stapsdt' section.
 * Logic inspired by perf's code.
 */
static int parse_usdt_note(Elf *elf, const char *path, long base_addr,
			   GElf_Nhdr *nhdr, const char *data, size_t name_off, size_t desc_off,
			   struct usdt_note *note)
{
	const char *provider, *name, *args;
	long addrs[3];
	size_t len;

	/* sanity check USDT note name and type first */
	if (strncmp(data + name_off, USDT_NOTE_NAME, nhdr->n_namesz) != 0)
		return -EINVAL;
	if (nhdr->n_type != USDT_NOTE_TYPE)
		return -EINVAL;

	/* sanity check USDT note contents ("description" in ELF terminology) */
	len = nhdr->n_descsz;
	data = data + desc_off;

	/* +3 is the very minimum required to store three empty strings */
	if (len < sizeof(addrs) + 3)
		return -EINVAL;

	/* get location, base, and semaphore addrs */
	memcpy(&addrs, data, sizeof(addrs));

	/* parse string fields: provider, name, args */
	provider = data + sizeof(addrs);

	name = (const char *)memchr(provider, '\0', data + len - provider);
	if (!name) /* non-zero-terminated provider */
		return -EINVAL;
	name++;
	if (name >= data + len || *name == '\0') /* missing or empty name */
		return -EINVAL;

	args = memchr(name, '\0', data + len - name);
	if (!args) /* non-zero-terminated name */
		return -EINVAL;
	++args;
	if (args >= data + len) /* missing arguments spec */
		return -EINVAL;

	note->provider = provider;
	note->name = name;
	if (*args == '\0' || *args == ':')
		note->args = "";
	else
		note->args = args;
	note->loc_addr = addrs[0];
	note->base_addr = addrs[1];
	note->sema_addr = addrs[2];

	return 0;
}

static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg);

static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie)
{
	const char *s;
	int len;

	spec->usdt_cookie = usdt_cookie;
	spec->arg_cnt = 0;

	s = note->args;
	while (s[0]) {
		if (spec->arg_cnt >= USDT_MAX_ARG_CNT) {
			pr_warn("usdt: too many USDT arguments (> %d) for '%s:%s' with args spec '%s'\n",
				USDT_MAX_ARG_CNT, note->provider, note->name, note->args);
			return -E2BIG;
		}

		len = parse_usdt_arg(s, spec->arg_cnt, &spec->args[spec->arg_cnt]);
		if (len < 0)
			return len;

		s += len;
		spec->arg_cnt++;
	}

	return 0;
}

/* Architecture-specific logic for parsing USDT argument location specs */

#if defined(__x86_64__) || defined(__i386__)

static int calc_pt_regs_off(const char *reg_name)
{
	static struct {
		const char *names[4];
		size_t pt_regs_off;
	} reg_map[] = {
#ifdef __x86_64__
#define reg_off(reg64, reg32) offsetof(struct pt_regs, reg64)
#else
#define reg_off(reg64, reg32) offsetof(struct pt_regs, reg32)
#endif
		{ {"rip", "eip", "", ""}, reg_off(rip, eip) },
		{ {"rax", "eax", "ax", "al"}, reg_off(rax, eax) },
		{ {"rbx", "ebx", "bx", "bl"}, reg_off(rbx, ebx) },
		{ {"rcx", "ecx", "cx", "cl"}, reg_off(rcx, ecx) },
		{ {"rdx", "edx", "dx", "dl"}, reg_off(rdx, edx) },
		{ {"rsi", "esi", "si", "sil"}, reg_off(rsi, esi) },
		{ {"rdi", "edi", "di", "dil"}, reg_off(rdi, edi) },
		{ {"rbp", "ebp", "bp", "bpl"}, reg_off(rbp, ebp) },
		{ {"rsp", "esp", "sp", "spl"}, reg_off(rsp, esp) },
#undef reg_off
#ifdef __x86_64__
		{ {"r8", "r8d", "r8w", "r8b"}, offsetof(struct pt_regs, r8) },
		{ {"r9", "r9d", "r9w", "r9b"}, offsetof(struct pt_regs, r9) },
		{ {"r10", "r10d", "r10w", "r10b"}, offsetof(struct pt_regs, r10) },
		{ {"r11", "r11d", "r11w", "r11b"}, offsetof(struct pt_regs, r11) },
		{ {"r12", "r12d", "r12w", "r12b"}, offsetof(struct pt_regs, r12) },
		{ {"r13", "r13d", "r13w", "r13b"}, offsetof(struct pt_regs, r13) },
		{ {"r14", "r14d", "r14w", "r14b"}, offsetof(struct pt_regs, r14) },
		{ {"r15", "r15d", "r15w", "r15b"}, offsetof(struct pt_regs, r15) },
#endif
	};
	int i, j;

	for (i = 0; i < ARRAY_SIZE(reg_map); i++) {
		for (j = 0; j < ARRAY_SIZE(reg_map[i].names); j++) {
			if (strcmp(reg_name, reg_map[i].names[j]) == 0)
				return reg_map[i].pt_regs_off;
		}
	}

	pr_warn("usdt: unrecognized register '%s'\n", reg_name);
	return -ENOENT;
}

static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
{
	char *reg_name = NULL;
	int arg_sz, len, reg_off;
	long off;

	if (sscanf(arg_str, " %d @ %ld ( %%%m[^)] ) %n", &arg_sz, &off, &reg_name, &len) == 3) {
		/* Memory dereference case, e.g., -4@-20(%rbp) */
		arg->arg_type = USDT_ARG_REG_DEREF;
		arg->val_off = off;
		reg_off = calc_pt_regs_off(reg_name);
		free(reg_name);
		if (reg_off < 0)
			return reg_off;
		arg->reg_off = reg_off;
	} else if (sscanf(arg_str, " %d @ %%%ms %n", &arg_sz, &reg_name, &len) == 2) {
		/* Register read case, e.g., -4@%eax */
		arg->arg_type = USDT_ARG_REG;
		arg->val_off = 0;

		reg_off = calc_pt_regs_off(reg_name);
		free(reg_name);
		if (reg_off < 0)
			return reg_off;
		arg->reg_off = reg_off;
	} else if (sscanf(arg_str, " %d @ $%ld %n", &arg_sz, &off, &len) == 2) {
		/* Constant value case, e.g., 4@$71 */
		arg->arg_type = USDT_ARG_CONST;
		arg->val_off = off;
		arg->reg_off = 0;
	} else {
		pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str);
		return -EINVAL;
	}

	arg->arg_signed = arg_sz < 0;
	if (arg_sz < 0)
		arg_sz = -arg_sz;

	switch (arg_sz) {
	case 1: case 2: case 4: case 8:
		arg->arg_bitshift = 64 - arg_sz * 8;
		break;
	default:
		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
			arg_num, arg_str, arg_sz);
		return -EINVAL;
	}

	return len;
}

#elif defined(__s390x__)

/* Do not support __s390__ for now, since user_pt_regs is broken with -m31. */

static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
{
	unsigned int reg;
	int arg_sz, len;
	long off;

	if (sscanf(arg_str, " %d @ %ld ( %%r%u ) %n", &arg_sz, &off, &reg, &len) == 3) {
		/* Memory dereference case, e.g., -2@-28(%r15) */
		arg->arg_type = USDT_ARG_REG_DEREF;
		arg->val_off = off;
		if (reg > 15) {
			pr_warn("usdt: unrecognized register '%%r%u'\n", reg);
			return -EINVAL;
		}
		arg->reg_off = offsetof(user_pt_regs, gprs[reg]);
	} else if (sscanf(arg_str, " %d @ %%r%u %n", &arg_sz, &reg, &len) == 2) {
		/* Register read case, e.g., -8@%r0 */
		arg->arg_type = USDT_ARG_REG;
		arg->val_off = 0;
		if (reg > 15) {
			pr_warn("usdt: unrecognized register '%%r%u'\n", reg);
			return -EINVAL;
		}
		arg->reg_off = offsetof(user_pt_regs, gprs[reg]);
	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
		/* Constant value case, e.g., 4@71 */
		arg->arg_type = USDT_ARG_CONST;
		arg->val_off = off;
		arg->reg_off = 0;
	} else {
		pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str);
		return -EINVAL;
	}

	arg->arg_signed = arg_sz < 0;
	if (arg_sz < 0)
		arg_sz = -arg_sz;

	switch (arg_sz) {
	case 1: case 2: case 4: case 8:
		arg->arg_bitshift = 64 - arg_sz * 8;
		break;
	default:
		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
			arg_num, arg_str, arg_sz);
		return -EINVAL;
	}

	return len;
}

#elif defined(__aarch64__)

static int calc_pt_regs_off(const char *reg_name)
{
	int reg_num;

	if (sscanf(reg_name, "x%d", &reg_num) == 1) {
		if (reg_num >= 0 && reg_num < 31)
			return offsetof(struct user_pt_regs, regs[reg_num]);
	} else if (strcmp(reg_name, "sp") == 0) {
		return offsetof(struct user_pt_regs, sp);
	}
	pr_warn("usdt: unrecognized register '%s'\n", reg_name);
	return -ENOENT;
}

static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
{
	char *reg_name = NULL;
	int arg_sz, len, reg_off;
	long off;

	if (sscanf(arg_str, " %d @ \[ %m[a-z0-9], %ld ] %n", &arg_sz, &reg_name, &off, &len) == 3) {
		/* Memory dereference case, e.g., -4@[sp, 96] */
		arg->arg_type = USDT_ARG_REG_DEREF;
		arg->val_off = off;
		reg_off = calc_pt_regs_off(reg_name);
		free(reg_name);
		if (reg_off < 0)
			return reg_off;
		arg->reg_off = reg_off;
	} else if (sscanf(arg_str, " %d @ \[ %m[a-z0-9] ] %n", &arg_sz, &reg_name, &len) == 2) {
		/* Memory dereference case, e.g., -4@[sp] */
		arg->arg_type = USDT_ARG_REG_DEREF;
		arg->val_off = 0;
		reg_off = calc_pt_regs_off(reg_name);
		free(reg_name);
		if (reg_off < 0)
			return reg_off;
		arg->reg_off = reg_off;
	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
		/* Constant value case, e.g., 4@5 */
		arg->arg_type = USDT_ARG_CONST;
		arg->val_off = off;
		arg->reg_off = 0;
	} else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, &reg_name, &len) == 2) {
		/* Register read case, e.g., -8@x4 */
		arg->arg_type = USDT_ARG_REG;
		arg->val_off = 0;
		reg_off = calc_pt_regs_off(reg_name);
		free(reg_name);
		if (reg_off < 0)
			return reg_off;
		arg->reg_off = reg_off;
	} else {
		pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str);
		return -EINVAL;
	}

	arg->arg_signed = arg_sz < 0;
	if (arg_sz < 0)
		arg_sz = -arg_sz;

	switch (arg_sz) {
	case 1: case 2: case 4: case 8:
		arg->arg_bitshift = 64 - arg_sz * 8;
		break;
	default:
		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
			arg_num, arg_str, arg_sz);
		return -EINVAL;
	}

	return len;
}

#elif defined(__riscv)

static int calc_pt_regs_off(const char *reg_name)
{
	static struct {
		const char *name;
		size_t pt_regs_off;
	} reg_map[] = {
		{ "ra", offsetof(struct user_regs_struct, ra) },
		{ "sp", offsetof(struct user_regs_struct, sp) },
		{ "gp", offsetof(struct user_regs_struct, gp) },
		{ "tp", offsetof(struct user_regs_struct, tp) },
		{ "a0", offsetof(struct user_regs_struct, a0) },
		{ "a1", offsetof(struct user_regs_struct, a1) },
		{ "a2", offsetof(struct user_regs_struct, a2) },
		{ "a3", offsetof(struct user_regs_struct, a3) },
		{ "a4", offsetof(struct user_regs_struct, a4) },
		{ "a5", offsetof(struct user_regs_struct, a5) },
		{ "a6", offsetof(struct user_regs_struct, a6) },
		{ "a7", offsetof(struct user_regs_struct, a7) },
		{ "s0", offsetof(struct user_regs_struct, s0) },
		{ "s1", offsetof(struct user_regs_struct, s1) },
		{ "s2", offsetof(struct user_regs_struct, s2) },
		{ "s3", offsetof(struct user_regs_struct, s3) },
		{ "s4", offsetof(struct user_regs_struct, s4) },
		{ "s5", offsetof(struct user_regs_struct, s5) },
		{ "s6", offsetof(struct user_regs_struct, s6) },
		{ "s7", offsetof(struct user_regs_struct, s7) },
		{ "s8", offsetof(struct user_regs_struct, rv_s8) },
		{ "s9", offsetof(struct user_regs_struct, s9) },
		{ "s10", offsetof(struct user_regs_struct, s10) },
		{ "s11", offsetof(struct user_regs_struct, s11) },
		{ "t0", offsetof(struct user_regs_struct, t0) },
		{ "t1", offsetof(struct user_regs_struct, t1) },
		{ "t2", offsetof(struct user_regs_struct, t2) },
		{ "t3", offsetof(struct user_regs_struct, t3) },
		{ "t4", offsetof(struct user_regs_struct, t4) },
		{ "t5", offsetof(struct user_regs_struct, t5) },
		{ "t6", offsetof(struct user_regs_struct, t6) },
	};
	int i;

	for (i = 0; i < ARRAY_SIZE(reg_map); i++) {
		if (strcmp(reg_name, reg_map[i].name) == 0)
			return reg_map[i].pt_regs_off;
	}

	pr_warn("usdt: unrecognized register '%s'\n", reg_name);
	return -ENOENT;
}

static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
{
	char *reg_name = NULL;
	int arg_sz, len, reg_off;
	long off;

	if (sscanf(arg_str, " %d @ %ld ( %m[a-z0-9] ) %n", &arg_sz, &off, &reg_name, &len) == 3) {
		/* Memory dereference case, e.g., -8@-88(s0) */
		arg->arg_type = USDT_ARG_REG_DEREF;
		arg->val_off = off;
		reg_off = calc_pt_regs_off(reg_name);
		free(reg_name);
		if (reg_off < 0)
			return reg_off;
		arg->reg_off = reg_off;
	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
		/* Constant value case, e.g., 4@5 */
		arg->arg_type = USDT_ARG_CONST;
		arg->val_off = off;
		arg->reg_off = 0;
	} else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, &reg_name, &len) == 2) {
		/* Register read case, e.g., -8@a1 */
		arg->arg_type = USDT_ARG_REG;
		arg->val_off = 0;
		reg_off = calc_pt_regs_off(reg_name);
		free(reg_name);
		if (reg_off < 0)
			return reg_off;
		arg->reg_off = reg_off;
	} else {
		pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str);
		return -EINVAL;
	}

	arg->arg_signed = arg_sz < 0;
	if (arg_sz < 0)
		arg_sz = -arg_sz;

	switch (arg_sz) {
	case 1: case 2: case 4: case 8:
		arg->arg_bitshift = 64 - arg_sz * 8;
		break;
	default:
		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
			arg_num, arg_str, arg_sz);
		return -EINVAL;
	}

	return len;
}

#else

static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
{
	pr_warn("usdt: libbpf doesn't support USDTs on current architecture\n");
	return -ENOTSUP;
}

#endif