summaryrefslogtreecommitdiff
path: root/tools/perf/util/dso.c
blob: f87cf864e980aff258d2547283bf63d56efb0935 (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
#include <asm/bug.h>
#include <sys/time.h>
#include <sys/resource.h>
#include "symbol.h"
#include "dso.h"
#include "machine.h"
#include "auxtrace.h"
#include "util.h"
#include "debug.h"

char dso__symtab_origin(const struct dso *dso)
{
	static const char origin[] = {
		[DSO_BINARY_TYPE__KALLSYMS]			= 'k',
		[DSO_BINARY_TYPE__VMLINUX]			= 'v',
		[DSO_BINARY_TYPE__JAVA_JIT]			= 'j',
		[DSO_BINARY_TYPE__DEBUGLINK]			= 'l',
		[DSO_BINARY_TYPE__BUILD_ID_CACHE]		= 'B',
		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]		= 'f',
		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]		= 'u',
		[DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO]	= 'x',
		[DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO]	= 'o',
		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]		= 'b',
		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]		= 'd',
		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]		= 'K',
		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP]	= 'm',
		[DSO_BINARY_TYPE__GUEST_KALLSYMS]		= 'g',
		[DSO_BINARY_TYPE__GUEST_KMODULE]		= 'G',
		[DSO_BINARY_TYPE__GUEST_KMODULE_COMP]		= 'M',
		[DSO_BINARY_TYPE__GUEST_VMLINUX]		= 'V',
	};

	if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
		return '!';
	return origin[dso->symtab_type];
}

int dso__read_binary_type_filename(const struct dso *dso,
				   enum dso_binary_type type,
				   char *root_dir, char *filename, size_t size)
{
	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
	int ret = 0;
	size_t len;

	switch (type) {
	case DSO_BINARY_TYPE__DEBUGLINK: {
		char *debuglink;

		len = __symbol__join_symfs(filename, size, dso->long_name);
		debuglink = filename + len;
		while (debuglink != filename && *debuglink != '/')
			debuglink--;
		if (*debuglink == '/')
			debuglink++;
		ret = filename__read_debuglink(filename, debuglink,
					       size - (debuglink - filename));
		}
		break;
	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
		/* skip the locally configured cache if a symfs is given */
		if (symbol_conf.symfs[0] ||
		    (dso__build_id_filename(dso, filename, size) == NULL))
			ret = -1;
		break;

	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
		snprintf(filename + len, size - len, "%s.debug", dso->long_name);
		break;

	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
		snprintf(filename + len, size - len, "%s", dso->long_name);
		break;

	case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO:
		/*
		 * Ubuntu can mixup /usr/lib with /lib, putting debuginfo in
		 * /usr/lib/debug/lib when it is expected to be in
		 * /usr/lib/debug/usr/lib
		 */
		if (strlen(dso->long_name) < 9 ||
		    strncmp(dso->long_name, "/usr/lib/", 9)) {
			ret = -1;
			break;
		}
		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
		snprintf(filename + len, size - len, "%s", dso->long_name + 4);
		break;

	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
	{
		const char *last_slash;
		size_t dir_size;

		last_slash = dso->long_name + dso->long_name_len;
		while (last_slash != dso->long_name && *last_slash != '/')
			last_slash--;

		len = __symbol__join_symfs(filename, size, "");
		dir_size = last_slash - dso->long_name + 2;
		if (dir_size > (size - len)) {
			ret = -1;
			break;
		}
		len += scnprintf(filename + len, dir_size, "%s",  dso->long_name);
		len += scnprintf(filename + len , size - len, ".debug%s",
								last_slash);
		break;
	}

	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
		if (!dso->has_build_id) {
			ret = -1;
			break;
		}

		build_id__sprintf(dso->build_id,
				  sizeof(dso->build_id),
				  build_id_hex);
		len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/");
		snprintf(filename + len, size - len, "%.2s/%s.debug",
			 build_id_hex, build_id_hex + 2);
		break;

	case DSO_BINARY_TYPE__VMLINUX:
	case DSO_BINARY_TYPE__GUEST_VMLINUX:
	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
		__symbol__join_symfs(filename, size, dso->long_name);
		break;

	case DSO_BINARY_TYPE__GUEST_KMODULE:
	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
		path__join3(filename, size, symbol_conf.symfs,
			    root_dir, dso->long_name);
		break;

	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
		__symbol__join_symfs(filename, size, dso->long_name);
		break;

	case DSO_BINARY_TYPE__KCORE:
	case DSO_BINARY_TYPE__GUEST_KCORE:
		snprintf(filename, size, "%s", dso->long_name);
		break;

	default:
	case DSO_BINARY_TYPE__KALLSYMS:
	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
	case DSO_BINARY_TYPE__JAVA_JIT:
	case DSO_BINARY_TYPE__NOT_FOUND:
		ret = -1;
		break;
	}

	return ret;
}

static const struct {
	const char *fmt;
	int (*decompress)(const char *input, int output);
} compressions[] = {
#ifdef HAVE_ZLIB_SUPPORT
	{ "gz", gzip_decompress_to_file },
#endif
#ifdef HAVE_LZMA_SUPPORT
	{ "xz", lzma_decompress_to_file },
#endif
	{ NULL, NULL },
};

bool is_supported_compression(const char *ext)
{
	unsigned i;

	for (i = 0; compressions[i].fmt; i++) {
		if (!strcmp(ext, compressions[i].fmt))
			return true;
	}
	return false;
}

bool is_kernel_module(const char *pathname, int cpumode)
{
	struct kmod_path m;
	int mode = cpumode & PERF_RECORD_MISC_CPUMODE_MASK;

	WARN_ONCE(mode != cpumode,
		  "Internal error: passing unmasked cpumode (%x) to is_kernel_module",
		  cpumode);

	switch (mode) {
	case PERF_RECORD_MISC_USER:
	case PERF_RECORD_MISC_HYPERVISOR:
	case PERF_RECORD_MISC_GUEST_USER:
		return false;
	/* Treat PERF_RECORD_MISC_CPUMODE_UNKNOWN as kernel */
	default:
		if (kmod_path__parse(&m, pathname)) {
			pr_err("Failed to check whether %s is a kernel module or not. Assume it is.",
					pathname);
			return true;
		}
	}

	return m.kmod;
}

bool decompress_to_file(const char *ext, const char *filename, int output_fd)
{
	unsigned i;

	for (i = 0; compressions[i].fmt; i++) {
		if (!strcmp(ext, compressions[i].fmt))
			return !compressions[i].decompress(filename,
							   output_fd);
	}
	return false;
}

bool dso__needs_decompress(struct dso *dso)
{
	return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
}

/*
 * Parses kernel module specified in @path and updates
 * @m argument like:
 *
 *    @comp - true if @path contains supported compression suffix,
 *            false otherwise
 *    @kmod - true if @path contains '.ko' suffix in right position,
 *            false otherwise
 *    @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name
 *            of the kernel module without suffixes, otherwise strudup-ed
 *            base name of @path
 *    @ext  - if (@alloc_ext && @comp) is true, it contains strdup-ed string
 *            the compression suffix
 *
 * Returns 0 if there's no strdup error, -ENOMEM otherwise.
 */
int __kmod_path__parse(struct kmod_path *m, const char *path,
		       bool alloc_name, bool alloc_ext)
{
	const char *name = strrchr(path, '/');
	const char *ext  = strrchr(path, '.');
	bool is_simple_name = false;

	memset(m, 0x0, sizeof(*m));
	name = name ? name + 1 : path;

	/*
	 * '.' is also a valid character for module name. For example:
	 * [aaa.bbb] is a valid module name. '[' should have higher
	 * priority than '.ko' suffix.
	 *
	 * The kernel names are from machine__mmap_name. Such
	 * name should belong to kernel itself, not kernel module.
	 */
	if (name[0] == '[') {
		is_simple_name = true;
		if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) ||
		    (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) ||
		    (strncmp(name, "[vdso]", 6) == 0) ||
		    (strncmp(name, "[vdso32]", 8) == 0) ||
		    (strncmp(name, "[vdsox32]", 9) == 0) ||
		    (strncmp(name, "[vsyscall]", 10) == 0)) {
			m->kmod = false;

		} else
			m->kmod = true;
	}

	/* No extension, just return name. */
	if ((ext == NULL) || is_simple_name) {
		if (alloc_name) {
			m->name = strdup(name);
			return m->name ? 0 : -ENOMEM;
		}
		return 0;
	}

	if (is_supported_compression(ext + 1)) {
		m->comp = true;
		ext -= 3;
	}

	/* Check .ko extension only if there's enough name left. */
	if (ext > name)
		m->kmod = !strncmp(ext, ".ko", 3);

	if (alloc_name) {
		if (m->kmod) {
			if (asprintf(&m->name, "[%.*s]", (int) (ext - name), name) == -1)
				return -ENOMEM;
		} else {
			if (asprintf(&m->name, "%s", name) == -1)
				return -ENOMEM;
		}

		strxfrchar(m->name, '-', '_');
	}

	if (alloc_ext && m->comp) {
		m->ext = strdup(ext + 4);
		if (!m->ext) {
			free((void *) m->name);
			return -ENOMEM;
		}
	}

	return 0;
}

/*
 * Global list of open DSOs and the counter.
 */
static LIST_HEAD(dso__data_open);
static long dso__data_open_cnt;
static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER;

static void dso__list_add(struct dso *dso)
{
	list_add_tail(&dso->data.open_entry, &dso__data_open);
	dso__data_open_cnt++;
}

static void dso__list_del(struct dso *dso)
{
	list_del(&dso->data.open_entry);
	WARN_ONCE(dso__data_open_cnt <= 0,
		  "DSO data fd counter out of bounds.");
	dso__data_open_cnt--;
}

static void close_first_dso(void);

static int do_open(char *name)
{
	int fd;
	char sbuf[STRERR_BUFSIZE];

	do {
		fd = open(name, O_RDONLY);
		if (fd >= 0)
			return fd;

		pr_debug("dso open failed: %s\n",
			 strerror_r(errno, sbuf, sizeof(sbuf)));
		if (!dso__data_open_cnt || errno != EMFILE)
			break;

		close_first_dso();
	} while (1);

	return -1;
}

static int __open_dso(struct dso *dso, struct machine *machine)
{
	int fd;
	char *root_dir = (char *)"";
	char *name = malloc(PATH_MAX);

	if (!name)
		return -ENOMEM;

	if (machine)
		root_dir = machine->root_dir;

	if (dso__read_binary_type_filename(dso, dso->binary_type,
					    root_dir, name, PATH_MAX)) {
		free(name);
		return -EINVAL;
	}

	fd = do_open(name);
	free(name);
	return fd;
}

static void check_data_close(void);

/**
 * dso_close - Open DSO data file
 * @dso: dso object
 *
 * Open @dso's data file descriptor and updates
 * list/count of open DSO objects.
 */
static int open_dso(struct dso *dso, struct machine *machine)
{
	int fd = __open_dso(dso, machine);

	if (fd >= 0) {
		dso__list_add(dso);
		/*
		 * Check if we crossed the allowed number
		 * of opened DSOs and close one if needed.
		 */
		check_data_close();
	}

	return fd;
}

static void close_data_fd(struct dso *dso)
{
	if (dso->data.fd >= 0) {
		close(dso->data.fd);
		dso->data.fd = -1;
		dso->data.file_size = 0;
		dso__list_del(dso);
	}
}

/**
 * dso_close - Close DSO data file
 * @dso: dso object
 *
 * Close @dso's data file descriptor and updates
 * list/count of open DSO objects.
 */
static void close_dso(struct dso *dso)
{
	close_data_fd(dso);
}

static void close_first_dso(void)
{
	struct dso *dso;

	dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
	close_dso(dso);
}

static rlim_t get_fd_limit(void)
{
	struct rlimit l;
	rlim_t limit = 0;

	/* Allow half of the current open fd limit. */
	if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
		if (l.rlim_cur == RLIM_INFINITY)
			limit = l.rlim_cur;
		else
			limit = l.rlim_cur / 2;
	} else {
		pr_err("failed to get fd limit\n");
		limit = 1;
	}

	return limit;
}

static bool may_cache_fd(void)
{
	static rlim_t limit;

	if (!limit)
		limit = get_fd_limit();

	if (limit == RLIM_INFINITY)
		return true;

	return limit > (rlim_t) dso__data_open_cnt;
}

/*
 * Check and close LRU dso if we crossed allowed limit
 * for opened dso file descriptors. The limit is half
 * of the RLIMIT_NOFILE files opened.
*/
static void check_data_close(void)
{
	bool cache_fd = may_cache_fd();

	if (!cache_fd)
		close_first_dso();
}

/**
 * dso__data_close - Close DSO data file
 * @dso: dso object
 *
 * External interface to close @dso's data file descriptor.
 */
void dso__data_close(struct dso *dso)
{
	pthread_mutex_lock(&dso__data_open_lock);
	close_dso(dso);
	pthread_mutex_unlock(&dso__data_open_lock);
}

static void try_to_open_dso(struct dso *dso, struct machine *machine)
{
	enum dso_binary_type binary_type_data[] = {
		DSO_BINARY_TYPE__BUILD_ID_CACHE,
		DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
		DSO_BINARY_TYPE__NOT_FOUND,
	};
	int i = 0;

	if (dso->data.fd >= 0)
		return;

	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
		dso->data.fd = open_dso(dso, machine);
		goto out;
	}

	do {
		dso->binary_type = binary_type_data[i++];

		dso->data.fd = open_dso(dso, machine);
		if (dso->data.fd >= 0)
			goto out;

	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
out:
	if (dso->data.fd >= 0)
		dso->data.status = DSO_DATA_STATUS_OK;
	else
		dso->data.status = DSO_DATA_STATUS_ERROR;
}

/**
 * dso__data_get_fd - Get dso's data file descriptor
 * @dso: dso object
 * @machine: machine object
 *
 * External interface to find dso's file, open it and
 * returns file descriptor.  It should be paired with
 * dso__data_put_fd() if it returns non-negative value.
 */
int dso__data_get_fd(struct dso *dso, struct machine *machine)
{
	if (dso->data.status == DSO_DATA_STATUS_ERROR)
		return -1;

	if (pthread_mutex_lock(&dso__data_open_lock) < 0)
		return -1;

	try_to_open_dso(dso, machine);

	if (dso->data.fd < 0)
		pthread_mutex_unlock(&dso__data_open_lock);

	return dso->data.fd;
}

void dso__data_put_fd(struct dso *dso __maybe_unused)
{
	pthread_mutex_unlock(&dso__data_open_lock);
}

bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
{
	u32 flag = 1 << by;

	if (dso->data.status_seen & flag)
		return true;

	dso->data.status_seen |= flag;

	return false;
}

static void
dso_cache__free(struct dso *dso)
{
	struct rb_root *root = &dso->data.cache;
	struct rb_node *next = rb_first(root);

	pthread_mutex_lock(&dso->lock);
	while (next) {
		struct dso_cache *cache;

		cache = rb_entry(next, struct dso_cache, rb_node);
		next = rb_next(&cache->rb_node);
		rb_erase(&cache->rb_node, root);
		free(cache);
	}
	pthread_mutex_unlock(&dso->lock);
}

static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
{
	const struct rb_root *root = &dso->data.cache;
	struct rb_node * const *p = &root->rb_node;
	const struct rb_node *parent = NULL;
	struct dso_cache *cache;

	while (*p != NULL) {
		u64 end;

		parent = *p;
		cache = rb_entry(parent, struct dso_cache, rb_node);
		end = cache->offset + DSO__DATA_CACHE_SIZE;

		if (offset < cache->offset)
			p = &(*p)->rb_left;
		else if (offset >= end)
			p = &(*p)->rb_right;
		else
			return cache;
	}

	return NULL;
}

static struct dso_cache *
dso_cache__insert(struct dso *dso, struct dso_cache *new)
{
	struct rb_root *root = &dso->data.cache;
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct dso_cache *cache;
	u64 offset = new->offset;

	pthread_mutex_lock(&dso->lock);
	while (*p != NULL) {
		u64 end;

		parent = *p;
		cache = rb_entry(parent, struct dso_cache, rb_node);
		end = cache->offset + DSO__DATA_CACHE_SIZE;

		if (offset < cache->offset)
			p = &(*p)->rb_left;
		else if (offset >= end)
			p = &(*p)->rb_right;
		else
			goto out;
	}

	rb_link_node(&new->rb_node, parent, p);
	rb_insert_color(&new->rb_node, root);

	cache = NULL;
out:
	pthread_mutex_unlock(&dso->lock);
	return cache;
}

static ssize_t
dso_cache__memcpy(struct dso_cache *cache, u64 offset,
		  u8 *data, u64 size)
{
	u64 cache_offset = offset - cache->offset;
	u64 cache_size   = min(cache->size - cache_offset, size);

	memcpy(data, cache->data + cache_offset, cache_size);
	return cache_size;
}

static ssize_t
dso_cache__read(struct dso *dso, struct machine *machine,
		u64 offset, u8 *data, ssize_t size)
{
	struct dso_cache *cache;
	struct dso_cache *old;
	ssize_t ret;

	do {
		u64 cache_offset;

		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
		if (!cache)
			return -ENOMEM;

		pthread_mutex_lock(&dso__data_open_lock);

		/*
		 * dso->data.fd might be closed if other thread opened another
		 * file (dso) due to open file limit (RLIMIT_NOFILE).
		 */
		try_to_open_dso(dso, machine);

		if (dso->data.fd < 0) {
			ret = -errno;
			dso->data.status = DSO_DATA_STATUS_ERROR;
			break;
		}

		cache_offset = offset & DSO__DATA_CACHE_MASK;

		ret = pread(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE, cache_offset);
		if (ret <= 0)
			break;

		cache->offset = cache_offset;
		cache->size   = ret;
	} while (0);

	pthread_mutex_unlock(&dso__data_open_lock);

	if (ret > 0) {
		old = dso_cache__insert(dso, cache);
		if (old) {
			/* we lose the race */
			free(cache);
			cache = old;
		}

		ret = dso_cache__memcpy(cache, offset, data, size);
	}

	if (ret <= 0)
		free(cache);

	return ret;
}

static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
			      u64 offset, u8 *data, ssize_t size)
{
	struct dso_cache *cache;

	cache = dso_cache__find(dso, offset);
	if (cache)
		return dso_cache__memcpy(cache, offset, data, size);
	else
		return dso_cache__read(dso, machine, offset, data, size);
}

/*
 * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks
 * in the rb_tree. Any read to already cached data is served
 * by cached data.
 */
static ssize_t cached_read(struct dso *dso, struct machine *machine,
			   u64 offset, u8 *data, ssize_t size)
{
	ssize_t r = 0;
	u8 *p = data;

	do {
		ssize_t ret;

		ret = dso_cache_read(dso, machine, offset, p, size);
		if (ret < 0)
			return ret;

		/* Reached EOF, return what we have. */
		if (!ret)
			break;

		BUG_ON(ret > size);

		r      += ret;
		p      += ret;
		offset += ret;
		size   -= ret;

	} while (size);

	return r;
}

static int data_file_size(struct dso *dso, struct machine *machine)
{
	int ret = 0;
	struct stat st;
	char sbuf[STRERR_BUFSIZE];

	if (dso->data.file_size)
		return 0;

	if (dso->data.status == DSO_DATA_STATUS_ERROR)
		return -1;

	pthread_mutex_lock(&dso__data_open_lock);

	/*
	 * dso->data.fd might be closed if other thread opened another
	 * file (dso) due to open file limit (RLIMIT_NOFILE).
	 */
	try_to_open_dso(dso, machine);

	if (dso->data.fd < 0) {
		ret = -errno;
		dso->data.status = DSO_DATA_STATUS_ERROR;
		goto out;
	}

	if (fstat(dso->data.fd, &st) < 0) {
		ret = -errno;
		pr_err("dso cache fstat failed: %s\n",
		       strerror_r(errno, sbuf, sizeof(sbuf)));
		dso->data.status = DSO_DATA_STATUS_ERROR;
		goto out;
	}
	dso->data.file_size = st.st_size;

out:
	pthread_mutex_unlock(&dso__data_open_lock);
	return ret;
}

/**
 * dso__data_size - Return dso data size
 * @dso: dso object
 * @machine: machine object
 *
 * Return: dso data size
 */
off_t dso__data_size(struct dso *dso, struct machine *machine)
{
	if (data_file_size(dso, machine))
		return -1;

	/* For now just estimate dso data size is close to file size */
	return dso->data.file_size;
}

static ssize_t data_read_offset(struct dso *dso, struct machine *machine,
				u64 offset, u8 *data, ssize_t size)
{
	if (data_file_size(dso, machine))
		return -1;

	/* Check the offset sanity. */
	if (offset > dso->data.file_size)
		return -1;

	if (offset + size < offset)
		return -1;

	return cached_read(dso, machine, offset, data, size);
}

/**
 * dso__data_read_offset - Read data from dso file offset
 * @dso: dso object
 * @machine: machine object
 * @offset: file offset
 * @data: buffer to store data
 * @size: size of the @data buffer
 *
 * External interface to read data from dso file offset. Open
 * dso data file and use cached_read to get the data.
 */
ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
			      u64 offset, u8 *data, ssize_t size)
{
	if (dso->data.status == DSO_DATA_STATUS_ERROR)
		return -1;

	return data_read_offset(dso, machine, offset, data, size);
}

/**
 * dso__data_read_addr - Read data from dso address
 * @dso: dso object
 * @machine: machine object
 * @add: virtual memory address
 * @data: buffer to store data
 * @size: size of the @data buffer
 *
 * External interface to read data from dso address.
 */
ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
			    struct machine *machine, u64 addr,
			    u8 *data, ssize_t size)
{
	u64 offset = map->map_ip(map, addr);
	return dso__data_read_offset(dso, machine, offset, data, size);
}

struct map *dso__new_map(const char *name)
{
	struct map *map = NULL;
	struct dso *dso = dso__new(name);

	if (dso)
		map = map__new2(0, dso, MAP__FUNCTION);

	return map;
}

struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
				    const char *short_name, int dso_type)
{
	/*
	 * The kernel dso could be created by build_id processing.
	 */
	struct dso *dso = machine__findnew_dso(machine, name);

	/*
	 * We need to run this in all cases, since during the build_id
	 * processing we had no idea this was the kernel dso.
	 */
	if (dso != NULL) {
		dso__set_short_name(dso, short_name, false);
		dso->kernel = dso_type;
	}

	return dso;
}

/*
 * Find a matching entry and/or link current entry to RB tree.
 * Either one of the dso or name parameter must be non-NULL or the
 * function will not work.
 */
static struct dso *__dso__findlink_by_longname(struct rb_root *root,
					       struct dso *dso, const char *name)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node  *parent = NULL;

	if (!name)
		name = dso->long_name;
	/*
	 * Find node with the matching name
	 */
	while (*p) {
		struct dso *this = rb_entry(*p, struct dso, rb_node);
		int rc = strcmp(name, this->long_name);

		parent = *p;
		if (rc == 0) {
			/*
			 * In case the new DSO is a duplicate of an existing
			 * one, print an one-time warning & put the new entry
			 * at the end of the list of duplicates.
			 */
			if (!dso || (dso == this))
				return this;	/* Find matching dso */
			/*
			 * The core kernel DSOs may have duplicated long name.
			 * In this case, the short name should be different.
			 * Comparing the short names to differentiate the DSOs.
			 */
			rc = strcmp(dso->short_name, this->short_name);
			if (rc == 0) {
				pr_err("Duplicated dso name: %s\n", name);
				return NULL;
			}
		}
		if (rc < 0)
			p = &parent->rb_left;
		else
			p = &parent->rb_right;
	}
	if (dso) {
		/* Add new node and rebalance tree */
		rb_link_node(&dso->rb_node, parent, p);
		rb_insert_color(&dso->rb_node, root);
		dso->root = root;
	}
	return NULL;
}

static inline struct dso *__dso__find_by_longname(struct rb_root *root,
						  const char *name)
{
	return __dso__findlink_by_longname(root, NULL, name);
}

void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
{
	struct rb_root *root = dso->root;

	if (name == NULL)
		return;

	if (dso->long_name_allocated)
		free((char *)dso->long_name);

	if (root) {
		rb_erase(&dso->rb_node, root);
		/*
		 * __dso__findlink_by_longname() isn't guaranteed to add it
		 * back, so a clean removal is required here.
		 */
		RB_CLEAR_NODE(&dso->rb_node);
		dso->root = NULL;
	}

	dso->long_name		 = name;
	dso->long_name_len	 = strlen(name);
	dso->long_name_allocated = name_allocated;

	if (root)
		__dso__findlink_by_longname(root, dso, NULL);
}

void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
{
	if (name == NULL)
		return;

	if (dso->short_name_allocated)
		free((char *)dso->short_name);

	dso->short_name		  = name;
	dso->short_name_len	  = strlen(name);
	dso->short_name_allocated = name_allocated;
}

static void dso__set_basename(struct dso *dso)
{
       /*
        * basename() may modify path buffer, so we must pass
        * a copy.
        */
       char *base, *lname = strdup(dso->long_name);

       if (!lname)
               return;

       /*
        * basename() may return a pointer to internal
        * storage which is reused in subsequent calls
        * so copy the result.
        */
       base = strdup(basename(lname));

       free(lname);

       if (!base)
               return;

       dso__set_short_name(dso, base, true);
}

int dso__name_len(const struct dso *dso)
{
	if (!dso)
		return strlen("[unknown]");
	if (verbose)
		return dso->long_name_len;

	return dso->short_name_len;
}

bool dso__loaded(const struct dso *dso, enum map_type type)
{
	return dso->loaded & (1 << type);
}

bool dso__sorted_by_name(const struct dso *dso, enum map_type type)
{
	return dso->sorted_by_name & (1 << type);
}

void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
{
	dso->sorted_by_name |= (1 << type);
}

struct dso *dso__new(const char *name)
{
	struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);

	if (dso != NULL) {
		int i;
		strcpy(dso->name, name);
		dso__set_long_name(dso, dso->name, false);
		dso__set_short_name(dso, dso->name, false);
		for (i = 0; i < MAP__NR_TYPES; ++i)
			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
		dso->data.cache = RB_ROOT;
		dso->data.fd = -1;
		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
		dso->is_64_bit = (sizeof(void *) == 8);
		dso->loaded = 0;
		dso->rel = 0;
		dso->sorted_by_name = 0;
		dso->has_build_id = 0;
		dso->has_srcline = 1;
		dso->a2l_fails = 1;
		dso->kernel = DSO_TYPE_USER;
		dso->needs_swap = DSO_SWAP__UNSET;
		RB_CLEAR_NODE(&dso->rb_node);
		dso->root = NULL;
		INIT_LIST_HEAD(&dso->node);
		INIT_LIST_HEAD(&dso->data.open_entry);
		pthread_mutex_init(&dso->lock, NULL);
		atomic_set(&dso->refcnt, 1);
	}

	return dso;
}

void dso__delete(struct dso *dso)
{
	int i;

	if (!RB_EMPTY_NODE(&dso->rb_node))
		pr_err("DSO %s is still in rbtree when being deleted!\n",
		       dso->long_name);
	for (i = 0; i < MAP__NR_TYPES; ++i)
		symbols__delete(&dso->symbols[i]);

	if (dso->short_name_allocated) {
		zfree((char **)&dso->short_name);
		dso->short_name_allocated = false;
	}

	if (dso->long_name_allocated) {
		zfree((char **)&dso->long_name);
		dso->long_name_allocated = false;
	}

	dso__data_close(dso);
	auxtrace_cache__free(dso->auxtrace_cache);
	dso_cache__free(dso);
	dso__free_a2l(dso);
	zfree(&dso->symsrc_filename);
	pthread_mutex_destroy(&dso->lock);
	free(dso);
}

struct dso *dso__get(struct dso *dso)
{
	if (dso)
		atomic_inc(&dso->refcnt);
	return dso;
}

void dso__put(struct dso *dso)
{
	if (dso && atomic_dec_and_test(&dso->refcnt))
		dso__delete(dso);
}

void dso__set_build_id(struct dso *dso, void *build_id)
{
	memcpy(dso->build_id, build_id, sizeof(dso->build_id));
	dso->has_build_id = 1;
}

bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
{
	return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0;
}

void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
{
	char path[PATH_MAX];

	if (machine__is_default_guest(machine))
		return;
	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
	if (sysfs__read_build_id(path, dso->build_id,
				 sizeof(dso->build_id)) == 0)
		dso->has_build_id = true;
}

int dso__kernel_module_get_build_id(struct dso *dso,
				    const char *root_dir)
{
	char filename[PATH_MAX];
	/*
	 * kernel module short names are of the form "[module]" and
	 * we need just "module" here.
	 */
	const char *name = dso->short_name + 1;

	snprintf(filename, sizeof(filename),
		 "%s/sys/module/%.*s/notes/.note.gnu.build-id",
		 root_dir, (int)strlen(name) - 1, name);

	if (sysfs__read_build_id(filename, dso->build_id,
				 sizeof(dso->build_id)) == 0)
		dso->has_build_id = true;

	return 0;
}

bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
{
	bool have_build_id = false;
	struct dso *pos;

	list_for_each_entry(pos, head, node) {
		if (with_hits && !pos->hit)
			continue;
		if (pos->has_build_id) {
			have_build_id = true;
			continue;
		}
		if (filename__read_build_id(pos->long_name, pos->build_id,
					    sizeof(pos->build_id)) > 0) {
			have_build_id	  = true;
			pos->has_build_id = true;
		}
	}

	return have_build_id;
}

void __dsos__add(struct dsos *dsos, struct dso *dso)
{
	list_add_tail(&dso->node, &dsos->head);
	__dso__findlink_by_longname(&dsos->root, dso, NULL);
	/*
	 * It is now in the linked list, grab a reference, then garbage collect
	 * this when needing memory, by looking at LRU dso instances in the
	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
	 * anywhere besides the one for the list, do, under a lock for the
	 * list: remove it from the list, then a dso__put(), that probably will
	 * be the last and will then call dso__delete(), end of life.
	 *
	 * That, or at the end of the 'struct machine' lifetime, when all
	 * 'struct dso' instances will be removed from the list, in
	 * dsos__exit(), if they have no other reference from some other data
	 * structure.
	 *
	 * E.g.: after processing a 'perf.data' file and storing references
	 * to objects instantiated while processing events, we will have
	 * references to the 'thread', 'map', 'dso' structs all from 'struct
	 * hist_entry' instances, but we may not need anything not referenced,
	 * so we might as well call machines__exit()/machines__delete() and
	 * garbage collect it.
	 */
	dso__get(dso);
}

void dsos__add(struct dsos *dsos, struct dso *dso)
{
	pthread_rwlock_wrlock(&dsos->lock);
	__dsos__add(dsos, dso);
	pthread_rwlock_unlock(&dsos->lock);
}

struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
{
	struct dso *pos;

	if (cmp_short) {
		list_for_each_entry(pos, &dsos->head, node)
			if (strcmp(pos->short_name, name) == 0)
				return pos;
		return NULL;
	}
	return __dso__find_by_longname(&dsos->root, name);
}

struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
{
	struct dso *dso;
	pthread_rwlock_rdlock(&dsos->lock);
	dso = __dsos__find(dsos, name, cmp_short);
	pthread_rwlock_unlock(&dsos->lock);
	return dso;
}

struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
{
	struct dso *dso = dso__new(name);

	if (dso != NULL) {
		__dsos__add(dsos, dso);
		dso__set_basename(dso);
	}
	return dso;
}

struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
{
	struct dso *dso = __dsos__find(dsos, name, false);

	return dso ? dso : __dsos__addnew(dsos, name);
}

struct dso *dsos__findnew(struct dsos *dsos, const char *name)
{
	struct dso *dso;
	pthread_rwlock_wrlock(&dsos->lock);
	dso = dso__get(__dsos__findnew(dsos, name));
	pthread_rwlock_unlock(&dsos->lock);
	return dso;
}

size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
			       bool (skip)(struct dso *dso, int parm), int parm)
{
	struct dso *pos;
	size_t ret = 0;

	list_for_each_entry(pos, head, node) {
		if (skip && skip(pos, parm))
			continue;
		ret += dso__fprintf_buildid(pos, fp);
		ret += fprintf(fp, " %s\n", pos->long_name);
	}
	return ret;
}

size_t __dsos__fprintf(struct list_head *head, FILE *fp)
{
	struct dso *pos;
	size_t ret = 0;

	list_for_each_entry(pos, head, node) {
		int i;
		for (i = 0; i < MAP__NR_TYPES; ++i)
			ret += dso__fprintf(pos, i, fp);
	}

	return ret;
}

size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
{
	char sbuild_id[BUILD_ID_SIZE * 2 + 1];

	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
	return fprintf(fp, "%s", sbuild_id);
}

size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
{
	struct rb_node *nd;
	size_t ret = fprintf(fp, "dso: %s (", dso->short_name);

	if (dso->short_name != dso->long_name)
		ret += fprintf(fp, "%s, ", dso->long_name);
	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
		       dso__loaded(dso, type) ? "" : "NOT ");
	ret += dso__fprintf_buildid(dso, fp);
	ret += fprintf(fp, ")\n");
	for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
		ret += symbol__fprintf(pos, fp);
	}

	return ret;
}

enum dso_type dso__type(struct dso *dso, struct machine *machine)
{
	int fd;
	enum dso_type type = DSO__TYPE_UNKNOWN;

	fd = dso__data_get_fd(dso, machine);
	if (fd >= 0) {
		type = dso__type_fd(fd);
		dso__data_put_fd(dso);
	}

	return type;
}

int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
{
	int idx, errnum = dso->load_errno;
	/*
	 * This must have a same ordering as the enum dso_load_errno.
	 */
	static const char *dso_load__error_str[] = {
	"Internal tools/perf/ library error",
	"Invalid ELF file",
	"Can not read build id",
	"Mismatching build id",
	"Decompression failure",
	};

	BUG_ON(buflen == 0);

	if (errnum >= 0) {
		const char *err = strerror_r(errnum, buf, buflen);

		if (err != buf)
			scnprintf(buf, buflen, "%s", err);

		return 0;
	}

	if (errnum <  __DSO_LOAD_ERRNO__START || errnum >= __DSO_LOAD_ERRNO__END)
		return -1;

	idx = errnum - __DSO_LOAD_ERRNO__START;
	scnprintf(buf, buflen, "%s", dso_load__error_str[idx]);
	return 0;
}