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
|
#define JEMALLOC_PROF_C_
#include "jemalloc/internal/jemalloc_internal.h"
/******************************************************************************/
#ifdef JEMALLOC_PROF_LIBUNWIND
#define UNW_LOCAL_ONLY
#include <libunwind.h>
#endif
#ifdef JEMALLOC_PROF_LIBGCC
#include <unwind.h>
#endif
/******************************************************************************/
/* Data. */
malloc_tsd_data(, prof_tdata, prof_tdata_t *, NULL)
bool opt_prof = false;
bool opt_prof_active = true;
size_t opt_lg_prof_sample = LG_PROF_SAMPLE_DEFAULT;
ssize_t opt_lg_prof_interval = LG_PROF_INTERVAL_DEFAULT;
bool opt_prof_gdump = false;
bool opt_prof_final = true;
bool opt_prof_leak = false;
bool opt_prof_accum = false;
char opt_prof_prefix[PATH_MAX + 1];
uint64_t prof_interval = 0;
bool prof_promote;
/*
* Table of mutexes that are shared among ctx's. These are leaf locks, so
* there is no problem with using them for more than one ctx at the same time.
* The primary motivation for this sharing though is that ctx's are ephemeral,
* and destroying mutexes causes complications for systems that allocate when
* creating/destroying mutexes.
*/
static malloc_mutex_t *ctx_locks;
static unsigned cum_ctxs; /* Atomic counter. */
/*
* Global hash of (prof_bt_t *)-->(prof_ctx_t *). This is the master data
* structure that knows about all backtraces currently captured.
*/
static ckh_t bt2ctx;
static malloc_mutex_t bt2ctx_mtx;
static malloc_mutex_t prof_dump_seq_mtx;
static uint64_t prof_dump_seq;
static uint64_t prof_dump_iseq;
static uint64_t prof_dump_mseq;
static uint64_t prof_dump_useq;
/*
* This buffer is rather large for stack allocation, so use a single buffer for
* all profile dumps. The buffer is implicitly protected by bt2ctx_mtx, since
* it must be locked anyway during dumping.
*/
static char prof_dump_buf[PROF_DUMP_BUFSIZE];
static unsigned prof_dump_buf_end;
static int prof_dump_fd;
/* Do not dump any profiles until bootstrapping is complete. */
static bool prof_booted = false;
/******************************************************************************/
/* Function prototypes for non-inline static functions. */
static prof_bt_t *bt_dup(prof_bt_t *bt);
static void bt_destroy(prof_bt_t *bt);
#ifdef JEMALLOC_PROF_LIBGCC
static _Unwind_Reason_Code prof_unwind_init_callback(
struct _Unwind_Context *context, void *arg);
static _Unwind_Reason_Code prof_unwind_callback(
struct _Unwind_Context *context, void *arg);
#endif
static bool prof_flush(bool propagate_err);
static bool prof_write(bool propagate_err, const char *s);
static bool prof_printf(bool propagate_err, const char *format, ...)
JEMALLOC_ATTR(format(printf, 2, 3));
static void prof_ctx_sum(prof_ctx_t *ctx, prof_cnt_t *cnt_all,
size_t *leak_nctx);
static void prof_ctx_destroy(prof_ctx_t *ctx);
static void prof_ctx_merge(prof_ctx_t *ctx, prof_thr_cnt_t *cnt);
static bool prof_dump_ctx(bool propagate_err, prof_ctx_t *ctx,
prof_bt_t *bt);
static bool prof_dump_maps(bool propagate_err);
static bool prof_dump(bool propagate_err, const char *filename,
bool leakcheck);
static void prof_dump_filename(char *filename, char v, int64_t vseq);
static void prof_fdump(void);
static void prof_bt_hash(const void *key, size_t r_hash[2]);
static bool prof_bt_keycomp(const void *k1, const void *k2);
static malloc_mutex_t *prof_ctx_mutex_choose(void);
/******************************************************************************/
void
bt_init(prof_bt_t *bt, void **vec)
{
cassert(config_prof);
bt->vec = vec;
bt->len = 0;
}
static void
bt_destroy(prof_bt_t *bt)
{
cassert(config_prof);
idalloc(bt);
}
static prof_bt_t *
bt_dup(prof_bt_t *bt)
{
prof_bt_t *ret;
cassert(config_prof);
/*
* Create a single allocation that has space for vec immediately
* following the prof_bt_t structure. The backtraces that get
* stored in the backtrace caches are copied from stack-allocated
* temporary variables, so size is known at creation time. Making this
* a contiguous object improves cache locality.
*/
ret = (prof_bt_t *)imalloc(QUANTUM_CEILING(sizeof(prof_bt_t)) +
(bt->len * sizeof(void *)));
if (ret == NULL)
return (NULL);
ret->vec = (void **)((uintptr_t)ret +
QUANTUM_CEILING(sizeof(prof_bt_t)));
memcpy(ret->vec, bt->vec, bt->len * sizeof(void *));
ret->len = bt->len;
return (ret);
}
static inline void
prof_enter(prof_tdata_t *prof_tdata)
{
cassert(config_prof);
assert(prof_tdata->enq == false);
prof_tdata->enq = true;
malloc_mutex_lock(&bt2ctx_mtx);
}
static inline void
prof_leave(prof_tdata_t *prof_tdata)
{
bool idump, gdump;
cassert(config_prof);
malloc_mutex_unlock(&bt2ctx_mtx);
assert(prof_tdata->enq);
prof_tdata->enq = false;
idump = prof_tdata->enq_idump;
prof_tdata->enq_idump = false;
gdump = prof_tdata->enq_gdump;
prof_tdata->enq_gdump = false;
if (idump)
prof_idump();
if (gdump)
prof_gdump();
}
#ifdef JEMALLOC_PROF_LIBUNWIND
void
prof_backtrace(prof_bt_t *bt, unsigned nignore)
{
unw_context_t uc;
unw_cursor_t cursor;
unsigned i;
int err;
cassert(config_prof);
assert(bt->len == 0);
assert(bt->vec != NULL);
unw_getcontext(&uc);
unw_init_local(&cursor, &uc);
/* Throw away (nignore+1) stack frames, if that many exist. */
for (i = 0; i < nignore + 1; i++) {
err = unw_step(&cursor);
if (err <= 0)
return;
}
/*
* Iterate over stack frames until there are no more, or until no space
* remains in bt.
*/
for (i = 0; i < PROF_BT_MAX; i++) {
unw_get_reg(&cursor, UNW_REG_IP, (unw_word_t *)&bt->vec[i]);
bt->len++;
err = unw_step(&cursor);
if (err <= 0)
break;
}
}
#elif (defined(JEMALLOC_PROF_LIBGCC))
static _Unwind_Reason_Code
prof_unwind_init_callback(struct _Unwind_Context *context, void *arg)
{
cassert(config_prof);
return (_URC_NO_REASON);
}
static _Unwind_Reason_Code
prof_unwind_callback(struct _Unwind_Context *context, void *arg)
{
prof_unwind_data_t *data = (prof_unwind_data_t *)arg;
cassert(config_prof);
if (data->nignore > 0)
data->nignore--;
else {
data->bt->vec[data->bt->len] = (void *)_Unwind_GetIP(context);
data->bt->len++;
if (data->bt->len == data->max)
return (_URC_END_OF_STACK);
}
return (_URC_NO_REASON);
}
void
prof_backtrace(prof_bt_t *bt, unsigned nignore)
{
prof_unwind_data_t data = {bt, nignore, PROF_BT_MAX};
cassert(config_prof);
_Unwind_Backtrace(prof_unwind_callback, &data);
}
#elif (defined(JEMALLOC_PROF_GCC))
void
prof_backtrace(prof_bt_t *bt, unsigned nignore)
{
#define BT_FRAME(i) \
if ((i) < nignore + PROF_BT_MAX) { \
void *p; \
if (__builtin_frame_address(i) == 0) \
return; \
p = __builtin_return_address(i); \
if (p == NULL) \
return; \
if (i >= nignore) { \
bt->vec[(i) - nignore] = p; \
bt->len = (i) - nignore + 1; \
} \
} else \
return;
cassert(config_prof);
assert(nignore <= 3);
BT_FRAME(0)
BT_FRAME(1)
BT_FRAME(2)
BT_FRAME(3)
BT_FRAME(4)
BT_FRAME(5)
BT_FRAME(6)
BT_FRAME(7)
BT_FRAME(8)
BT_FRAME(9)
BT_FRAME(10)
BT_FRAME(11)
BT_FRAME(12)
BT_FRAME(13)
BT_FRAME(14)
BT_FRAME(15)
BT_FRAME(16)
BT_FRAME(17)
BT_FRAME(18)
BT_FRAME(19)
BT_FRAME(20)
BT_FRAME(21)
BT_FRAME(22)
BT_FRAME(23)
BT_FRAME(24)
BT_FRAME(25)
BT_FRAME(26)
BT_FRAME(27)
BT_FRAME(28)
BT_FRAME(29)
BT_FRAME(30)
BT_FRAME(31)
BT_FRAME(32)
BT_FRAME(33)
BT_FRAME(34)
BT_FRAME(35)
BT_FRAME(36)
BT_FRAME(37)
BT_FRAME(38)
BT_FRAME(39)
BT_FRAME(40)
BT_FRAME(41)
BT_FRAME(42)
BT_FRAME(43)
BT_FRAME(44)
BT_FRAME(45)
BT_FRAME(46)
BT_FRAME(47)
BT_FRAME(48)
BT_FRAME(49)
BT_FRAME(50)
BT_FRAME(51)
BT_FRAME(52)
BT_FRAME(53)
BT_FRAME(54)
BT_FRAME(55)
BT_FRAME(56)
BT_FRAME(57)
BT_FRAME(58)
BT_FRAME(59)
BT_FRAME(60)
BT_FRAME(61)
BT_FRAME(62)
BT_FRAME(63)
BT_FRAME(64)
BT_FRAME(65)
BT_FRAME(66)
BT_FRAME(67)
BT_FRAME(68)
BT_FRAME(69)
BT_FRAME(70)
BT_FRAME(71)
BT_FRAME(72)
BT_FRAME(73)
BT_FRAME(74)
BT_FRAME(75)
BT_FRAME(76)
BT_FRAME(77)
BT_FRAME(78)
BT_FRAME(79)
BT_FRAME(80)
BT_FRAME(81)
BT_FRAME(82)
BT_FRAME(83)
BT_FRAME(84)
BT_FRAME(85)
BT_FRAME(86)
BT_FRAME(87)
BT_FRAME(88)
BT_FRAME(89)
BT_FRAME(90)
BT_FRAME(91)
BT_FRAME(92)
BT_FRAME(93)
BT_FRAME(94)
BT_FRAME(95)
BT_FRAME(96)
BT_FRAME(97)
BT_FRAME(98)
BT_FRAME(99)
BT_FRAME(100)
BT_FRAME(101)
BT_FRAME(102)
BT_FRAME(103)
BT_FRAME(104)
BT_FRAME(105)
BT_FRAME(106)
BT_FRAME(107)
BT_FRAME(108)
BT_FRAME(109)
BT_FRAME(110)
BT_FRAME(111)
BT_FRAME(112)
BT_FRAME(113)
BT_FRAME(114)
BT_FRAME(115)
BT_FRAME(116)
BT_FRAME(117)
BT_FRAME(118)
BT_FRAME(119)
BT_FRAME(120)
BT_FRAME(121)
BT_FRAME(122)
BT_FRAME(123)
BT_FRAME(124)
BT_FRAME(125)
BT_FRAME(126)
BT_FRAME(127)
/* Extras to compensate for nignore. */
BT_FRAME(128)
BT_FRAME(129)
BT_FRAME(130)
#undef BT_FRAME
}
#else
void
prof_backtrace(prof_bt_t *bt, unsigned nignore)
{
cassert(config_prof);
assert(false);
}
#endif
prof_thr_cnt_t *
prof_lookup(prof_bt_t *bt)
{
union {
prof_thr_cnt_t *p;
void *v;
} ret;
prof_tdata_t *prof_tdata;
cassert(config_prof);
prof_tdata = prof_tdata_get(false);
if ((uintptr_t)prof_tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)
return (NULL);
if (ckh_search(&prof_tdata->bt2cnt, bt, NULL, &ret.v)) {
union {
prof_bt_t *p;
void *v;
} btkey;
union {
prof_ctx_t *p;
void *v;
} ctx;
bool new_ctx;
/*
* This thread's cache lacks bt. Look for it in the global
* cache.
*/
prof_enter(prof_tdata);
if (ckh_search(&bt2ctx, bt, &btkey.v, &ctx.v)) {
/* bt has never been seen before. Insert it. */
ctx.v = imalloc(sizeof(prof_ctx_t));
if (ctx.v == NULL) {
prof_leave(prof_tdata);
return (NULL);
}
btkey.p = bt_dup(bt);
if (btkey.v == NULL) {
prof_leave(prof_tdata);
idalloc(ctx.v);
return (NULL);
}
ctx.p->bt = btkey.p;
ctx.p->lock = prof_ctx_mutex_choose();
/*
* Set nlimbo to 1, in order to avoid a race condition
* with prof_ctx_merge()/prof_ctx_destroy().
*/
ctx.p->nlimbo = 1;
memset(&ctx.p->cnt_merged, 0, sizeof(prof_cnt_t));
ql_new(&ctx.p->cnts_ql);
if (ckh_insert(&bt2ctx, btkey.v, ctx.v)) {
/* OOM. */
prof_leave(prof_tdata);
idalloc(btkey.v);
idalloc(ctx.v);
return (NULL);
}
new_ctx = true;
} else {
/*
* Increment nlimbo, in order to avoid a race condition
* with prof_ctx_merge()/prof_ctx_destroy().
*/
malloc_mutex_lock(ctx.p->lock);
ctx.p->nlimbo++;
malloc_mutex_unlock(ctx.p->lock);
new_ctx = false;
}
prof_leave(prof_tdata);
/* Link a prof_thd_cnt_t into ctx for this thread. */
if (ckh_count(&prof_tdata->bt2cnt) == PROF_TCMAX) {
assert(ckh_count(&prof_tdata->bt2cnt) > 0);
/*
* Flush the least recently used cnt in order to keep
* bt2cnt from becoming too large.
*/
ret.p = ql_last(&prof_tdata->lru_ql, lru_link);
assert(ret.v != NULL);
if (ckh_remove(&prof_tdata->bt2cnt, ret.p->ctx->bt,
NULL, NULL))
assert(false);
ql_remove(&prof_tdata->lru_ql, ret.p, lru_link);
prof_ctx_merge(ret.p->ctx, ret.p);
/* ret can now be re-used. */
} else {
assert(ckh_count(&prof_tdata->bt2cnt) < PROF_TCMAX);
/* Allocate and partially initialize a new cnt. */
ret.v = imalloc(sizeof(prof_thr_cnt_t));
if (ret.p == NULL) {
if (new_ctx)
prof_ctx_destroy(ctx.p);
return (NULL);
}
ql_elm_new(ret.p, cnts_link);
ql_elm_new(ret.p, lru_link);
}
/* Finish initializing ret. */
ret.p->ctx = ctx.p;
ret.p->epoch = 0;
memset(&ret.p->cnts, 0, sizeof(prof_cnt_t));
if (ckh_insert(&prof_tdata->bt2cnt, btkey.v, ret.v)) {
if (new_ctx)
prof_ctx_destroy(ctx.p);
idalloc(ret.v);
return (NULL);
}
ql_head_insert(&prof_tdata->lru_ql, ret.p, lru_link);
malloc_mutex_lock(ctx.p->lock);
ql_tail_insert(&ctx.p->cnts_ql, ret.p, cnts_link);
ctx.p->nlimbo--;
malloc_mutex_unlock(ctx.p->lock);
} else {
/* Move ret to the front of the LRU. */
ql_remove(&prof_tdata->lru_ql, ret.p, lru_link);
ql_head_insert(&prof_tdata->lru_ql, ret.p, lru_link);
}
return (ret.p);
}
static bool
prof_flush(bool propagate_err)
{
bool ret = false;
ssize_t err;
cassert(config_prof);
err = write(prof_dump_fd, prof_dump_buf, prof_dump_buf_end);
if (err == -1) {
if (propagate_err == false) {
malloc_write("<jemalloc>: write() failed during heap "
"profile flush\n");
if (opt_abort)
abort();
}
ret = true;
}
prof_dump_buf_end = 0;
return (ret);
}
static bool
prof_write(bool propagate_err, const char *s)
{
unsigned i, slen, n;
cassert(config_prof);
i = 0;
slen = strlen(s);
while (i < slen) {
/* Flush the buffer if it is full. */
if (prof_dump_buf_end == PROF_DUMP_BUFSIZE)
if (prof_flush(propagate_err) && propagate_err)
return (true);
if (prof_dump_buf_end + slen <= PROF_DUMP_BUFSIZE) {
/* Finish writing. */
n = slen - i;
} else {
/* Write as much of s as will fit. */
n = PROF_DUMP_BUFSIZE - prof_dump_buf_end;
}
memcpy(&prof_dump_buf[prof_dump_buf_end], &s[i], n);
prof_dump_buf_end += n;
i += n;
}
return (false);
}
JEMALLOC_ATTR(format(printf, 2, 3))
static bool
prof_printf(bool propagate_err, const char *format, ...)
{
bool ret;
va_list ap;
char buf[PROF_PRINTF_BUFSIZE];
va_start(ap, format);
malloc_vsnprintf(buf, sizeof(buf), format, ap);
va_end(ap);
ret = prof_write(propagate_err, buf);
return (ret);
}
static void
prof_ctx_sum(prof_ctx_t *ctx, prof_cnt_t *cnt_all, size_t *leak_nctx)
{
prof_thr_cnt_t *thr_cnt;
prof_cnt_t tcnt;
cassert(config_prof);
malloc_mutex_lock(ctx->lock);
memcpy(&ctx->cnt_summed, &ctx->cnt_merged, sizeof(prof_cnt_t));
ql_foreach(thr_cnt, &ctx->cnts_ql, cnts_link) {
volatile unsigned *epoch = &thr_cnt->epoch;
while (true) {
unsigned epoch0 = *epoch;
/* Make sure epoch is even. */
if (epoch0 & 1U)
continue;
memcpy(&tcnt, &thr_cnt->cnts, sizeof(prof_cnt_t));
/* Terminate if epoch didn't change while reading. */
if (*epoch == epoch0)
break;
}
ctx->cnt_summed.curobjs += tcnt.curobjs;
ctx->cnt_summed.curbytes += tcnt.curbytes;
if (opt_prof_accum) {
ctx->cnt_summed.accumobjs += tcnt.accumobjs;
ctx->cnt_summed.accumbytes += tcnt.accumbytes;
}
}
if (ctx->cnt_summed.curobjs != 0)
(*leak_nctx)++;
/* Add to cnt_all. */
cnt_all->curobjs += ctx->cnt_summed.curobjs;
cnt_all->curbytes += ctx->cnt_summed.curbytes;
if (opt_prof_accum) {
cnt_all->accumobjs += ctx->cnt_summed.accumobjs;
cnt_all->accumbytes += ctx->cnt_summed.accumbytes;
}
malloc_mutex_unlock(ctx->lock);
}
static void
prof_ctx_destroy(prof_ctx_t *ctx)
{
prof_tdata_t *prof_tdata;
cassert(config_prof);
/*
* Check that ctx is still unused by any thread cache before destroying
* it. prof_lookup() increments ctx->nlimbo in order to avoid a race
* condition with this function, as does prof_ctx_merge() in order to
* avoid a race between the main body of prof_ctx_merge() and entry
* into this function.
*/
prof_tdata = prof_tdata_get(false);
assert((uintptr_t)prof_tdata > (uintptr_t)PROF_TDATA_STATE_MAX);
prof_enter(prof_tdata);
malloc_mutex_lock(ctx->lock);
if (ql_first(&ctx->cnts_ql) == NULL && ctx->cnt_merged.curobjs == 0 &&
ctx->nlimbo == 1) {
assert(ctx->cnt_merged.curbytes == 0);
assert(ctx->cnt_merged.accumobjs == 0);
assert(ctx->cnt_merged.accumbytes == 0);
/* Remove ctx from bt2ctx. */
if (ckh_remove(&bt2ctx, ctx->bt, NULL, NULL))
assert(false);
prof_leave(prof_tdata);
/* Destroy ctx. */
malloc_mutex_unlock(ctx->lock);
bt_destroy(ctx->bt);
idalloc(ctx);
} else {
/*
* Compensate for increment in prof_ctx_merge() or
* prof_lookup().
*/
ctx->nlimbo--;
malloc_mutex_unlock(ctx->lock);
prof_leave(prof_tdata);
}
}
static void
prof_ctx_merge(prof_ctx_t *ctx, prof_thr_cnt_t *cnt)
{
bool destroy;
cassert(config_prof);
/* Merge cnt stats and detach from ctx. */
malloc_mutex_lock(ctx->lock);
ctx->cnt_merged.curobjs += cnt->cnts.curobjs;
ctx->cnt_merged.curbytes += cnt->cnts.curbytes;
ctx->cnt_merged.accumobjs += cnt->cnts.accumobjs;
ctx->cnt_merged.accumbytes += cnt->cnts.accumbytes;
ql_remove(&ctx->cnts_ql, cnt, cnts_link);
if (opt_prof_accum == false && ql_first(&ctx->cnts_ql) == NULL &&
ctx->cnt_merged.curobjs == 0 && ctx->nlimbo == 0) {
/*
* Increment ctx->nlimbo in order to keep another thread from
* winning the race to destroy ctx while this one has ctx->lock
* dropped. Without this, it would be possible for another
* thread to:
*
* 1) Sample an allocation associated with ctx.
* 2) Deallocate the sampled object.
* 3) Successfully prof_ctx_destroy(ctx).
*
* The result would be that ctx no longer exists by the time
* this thread accesses it in prof_ctx_destroy().
*/
ctx->nlimbo++;
destroy = true;
} else
destroy = false;
malloc_mutex_unlock(ctx->lock);
if (destroy)
prof_ctx_destroy(ctx);
}
static bool
prof_dump_ctx(bool propagate_err, prof_ctx_t *ctx, prof_bt_t *bt)
{
unsigned i;
cassert(config_prof);
/*
* Current statistics can sum to 0 as a result of unmerged per thread
* statistics. Additionally, interval- and growth-triggered dumps can
* occur between the time a ctx is created and when its statistics are
* filled in. Avoid dumping any ctx that is an artifact of either
* implementation detail.
*/
if ((opt_prof_accum == false && ctx->cnt_summed.curobjs == 0) ||
(opt_prof_accum && ctx->cnt_summed.accumobjs == 0)) {
assert(ctx->cnt_summed.curobjs == 0);
assert(ctx->cnt_summed.curbytes == 0);
assert(ctx->cnt_summed.accumobjs == 0);
assert(ctx->cnt_summed.accumbytes == 0);
return (false);
}
if (prof_printf(propagate_err, "%"PRId64": %"PRId64
" [%"PRIu64": %"PRIu64"] @",
ctx->cnt_summed.curobjs, ctx->cnt_summed.curbytes,
ctx->cnt_summed.accumobjs, ctx->cnt_summed.accumbytes))
return (true);
for (i = 0; i < bt->len; i++) {
if (prof_printf(propagate_err, " %#"PRIxPTR,
(uintptr_t)bt->vec[i]))
return (true);
}
if (prof_write(propagate_err, "\n"))
return (true);
return (false);
}
static bool
prof_dump_maps(bool propagate_err)
{
int mfd;
char filename[PATH_MAX + 1];
cassert(config_prof);
malloc_snprintf(filename, sizeof(filename), "/proc/%d/maps",
(int)getpid());
mfd = open(filename, O_RDONLY);
if (mfd != -1) {
ssize_t nread;
if (prof_write(propagate_err, "\nMAPPED_LIBRARIES:\n") &&
propagate_err)
return (true);
nread = 0;
do {
prof_dump_buf_end += nread;
if (prof_dump_buf_end == PROF_DUMP_BUFSIZE) {
/* Make space in prof_dump_buf before read(). */
if (prof_flush(propagate_err) && propagate_err)
return (true);
}
nread = read(mfd, &prof_dump_buf[prof_dump_buf_end],
PROF_DUMP_BUFSIZE - prof_dump_buf_end);
} while (nread > 0);
close(mfd);
} else
return (true);
return (false);
}
static bool
prof_dump(bool propagate_err, const char *filename, bool leakcheck)
{
prof_tdata_t *prof_tdata;
prof_cnt_t cnt_all;
size_t tabind;
union {
prof_bt_t *p;
void *v;
} bt;
union {
prof_ctx_t *p;
void *v;
} ctx;
size_t leak_nctx;
cassert(config_prof);
prof_tdata = prof_tdata_get(false);
if ((uintptr_t)prof_tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)
return (true);
prof_enter(prof_tdata);
prof_dump_fd = creat(filename, 0644);
if (prof_dump_fd == -1) {
if (propagate_err == false) {
malloc_printf(
"<jemalloc>: creat(\"%s\"), 0644) failed\n",
filename);
if (opt_abort)
abort();
}
goto label_error;
}
/* Merge per thread profile stats, and sum them in cnt_all. */
memset(&cnt_all, 0, sizeof(prof_cnt_t));
leak_nctx = 0;
for (tabind = 0; ckh_iter(&bt2ctx, &tabind, NULL, &ctx.v) == false;)
prof_ctx_sum(ctx.p, &cnt_all, &leak_nctx);
/* Dump profile header. */
if (opt_lg_prof_sample == 0) {
if (prof_printf(propagate_err,
"heap profile: %"PRId64": %"PRId64
" [%"PRIu64": %"PRIu64"] @ heapprofile\n",
cnt_all.curobjs, cnt_all.curbytes,
cnt_all.accumobjs, cnt_all.accumbytes))
goto label_error;
} else {
if (prof_printf(propagate_err,
"heap profile: %"PRId64": %"PRId64
" [%"PRIu64": %"PRIu64"] @ heap_v2/%"PRIu64"\n",
cnt_all.curobjs, cnt_all.curbytes,
cnt_all.accumobjs, cnt_all.accumbytes,
((uint64_t)1U << opt_lg_prof_sample)))
goto label_error;
}
/* Dump per ctx profile stats. */
for (tabind = 0; ckh_iter(&bt2ctx, &tabind, &bt.v, &ctx.v)
== false;) {
if (prof_dump_ctx(propagate_err, ctx.p, bt.p))
goto label_error;
}
/* Dump /proc/<pid>/maps if possible. */
if (prof_dump_maps(propagate_err))
goto label_error;
if (prof_flush(propagate_err))
goto label_error;
close(prof_dump_fd);
prof_leave(prof_tdata);
if (leakcheck && cnt_all.curbytes != 0) {
malloc_printf("<jemalloc>: Leak summary: %"PRId64" byte%s, %"
PRId64" object%s, %zu context%s\n",
cnt_all.curbytes, (cnt_all.curbytes != 1) ? "s" : "",
cnt_all.curobjs, (cnt_all.curobjs != 1) ? "s" : "",
leak_nctx, (leak_nctx != 1) ? "s" : "");
malloc_printf(
"<jemalloc>: Run pprof on \"%s\" for leak detail\n",
filename);
}
return (false);
label_error:
prof_leave(prof_tdata);
return (true);
}
#define DUMP_FILENAME_BUFSIZE (PATH_MAX + 1)
static void
prof_dump_filename(char *filename, char v, int64_t vseq)
{
cassert(config_prof);
if (vseq != UINT64_C(0xffffffffffffffff)) {
/* "<prefix>.<pid>.<seq>.v<vseq>.heap" */
malloc_snprintf(filename, DUMP_FILENAME_BUFSIZE,
"%s.%d.%"PRIu64".%c%"PRId64".heap",
opt_prof_prefix, (int)getpid(), prof_dump_seq, v, vseq);
} else {
/* "<prefix>.<pid>.<seq>.<v>.heap" */
malloc_snprintf(filename, DUMP_FILENAME_BUFSIZE,
"%s.%d.%"PRIu64".%c.heap",
opt_prof_prefix, (int)getpid(), prof_dump_seq, v);
}
prof_dump_seq++;
}
static void
prof_fdump(void)
{
char filename[DUMP_FILENAME_BUFSIZE];
cassert(config_prof);
if (prof_booted == false)
return;
if (opt_prof_final && opt_prof_prefix[0] != '\0') {
malloc_mutex_lock(&prof_dump_seq_mtx);
prof_dump_filename(filename, 'f', UINT64_C(0xffffffffffffffff));
malloc_mutex_unlock(&prof_dump_seq_mtx);
prof_dump(false, filename, opt_prof_leak);
}
}
void
prof_idump(void)
{
prof_tdata_t *prof_tdata;
char filename[PATH_MAX + 1];
cassert(config_prof);
if (prof_booted == false)
return;
prof_tdata = prof_tdata_get(false);
if ((uintptr_t)prof_tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)
return;
if (prof_tdata->enq) {
prof_tdata->enq_idump = true;
return;
}
if (opt_prof_prefix[0] != '\0') {
malloc_mutex_lock(&prof_dump_seq_mtx);
prof_dump_filename(filename, 'i', prof_dump_iseq);
prof_dump_iseq++;
malloc_mutex_unlock(&prof_dump_seq_mtx);
prof_dump(false, filename, false);
}
}
bool
prof_mdump(const char *filename)
{
char filename_buf[DUMP_FILENAME_BUFSIZE];
cassert(config_prof);
if (opt_prof == false || prof_booted == false)
return (true);
if (filename == NULL) {
/* No filename specified, so automatically generate one. */
if (opt_prof_prefix[0] == '\0')
return (true);
malloc_mutex_lock(&prof_dump_seq_mtx);
prof_dump_filename(filename_buf, 'm', prof_dump_mseq);
prof_dump_mseq++;
malloc_mutex_unlock(&prof_dump_seq_mtx);
filename = filename_buf;
}
return (prof_dump(true, filename, false));
}
void
prof_gdump(void)
{
prof_tdata_t *prof_tdata;
char filename[DUMP_FILENAME_BUFSIZE];
cassert(config_prof);
if (prof_booted == false)
return;
prof_tdata = prof_tdata_get(false);
if ((uintptr_t)prof_tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)
return;
if (prof_tdata->enq) {
prof_tdata->enq_gdump = true;
return;
}
if (opt_prof_prefix[0] != '\0') {
malloc_mutex_lock(&prof_dump_seq_mtx);
prof_dump_filename(filename, 'u', prof_dump_useq);
prof_dump_useq++;
malloc_mutex_unlock(&prof_dump_seq_mtx);
prof_dump(false, filename, false);
}
}
static void
prof_bt_hash(const void *key, size_t r_hash[2])
{
prof_bt_t *bt = (prof_bt_t *)key;
cassert(config_prof);
hash(bt->vec, bt->len * sizeof(void *), 0x94122f33U, r_hash);
}
static bool
prof_bt_keycomp(const void *k1, const void *k2)
{
const prof_bt_t *bt1 = (prof_bt_t *)k1;
const prof_bt_t *bt2 = (prof_bt_t *)k2;
cassert(config_prof);
if (bt1->len != bt2->len)
return (false);
return (memcmp(bt1->vec, bt2->vec, bt1->len * sizeof(void *)) == 0);
}
static malloc_mutex_t *
prof_ctx_mutex_choose(void)
{
unsigned nctxs = atomic_add_u(&cum_ctxs, 1);
return (&ctx_locks[(nctxs - 1) % PROF_NCTX_LOCKS]);
}
prof_tdata_t *
prof_tdata_init(void)
{
prof_tdata_t *prof_tdata;
cassert(config_prof);
/* Initialize an empty cache for this thread. */
prof_tdata = (prof_tdata_t *)imalloc(sizeof(prof_tdata_t));
if (prof_tdata == NULL)
return (NULL);
if (ckh_new(&prof_tdata->bt2cnt, PROF_CKH_MINITEMS,
prof_bt_hash, prof_bt_keycomp)) {
idalloc(prof_tdata);
return (NULL);
}
ql_new(&prof_tdata->lru_ql);
prof_tdata->vec = imalloc(sizeof(void *) * PROF_BT_MAX);
if (prof_tdata->vec == NULL) {
ckh_delete(&prof_tdata->bt2cnt);
idalloc(prof_tdata);
return (NULL);
}
prof_tdata->prng_state = 0;
prof_tdata->threshold = 0;
prof_tdata->accum = 0;
prof_tdata->enq = false;
prof_tdata->enq_idump = false;
prof_tdata->enq_gdump = false;
prof_tdata_tsd_set(&prof_tdata);
return (prof_tdata);
}
void
prof_tdata_cleanup(void *arg)
{
prof_thr_cnt_t *cnt;
prof_tdata_t *prof_tdata = *(prof_tdata_t **)arg;
cassert(config_prof);
if (prof_tdata == PROF_TDATA_STATE_REINCARNATED) {
/*
* Another destructor deallocated memory after this destructor
* was called. Reset prof_tdata to PROF_TDATA_STATE_PURGATORY
* in order to receive another callback.
*/
prof_tdata = PROF_TDATA_STATE_PURGATORY;
prof_tdata_tsd_set(&prof_tdata);
} else if (prof_tdata == PROF_TDATA_STATE_PURGATORY) {
/*
* The previous time this destructor was called, we set the key
* to PROF_TDATA_STATE_PURGATORY so that other destructors
* wouldn't cause re-creation of the prof_tdata. This time, do
* nothing, so that the destructor will not be called again.
*/
} else if (prof_tdata != NULL) {
/*
* Delete the hash table. All of its contents can still be
* iterated over via the LRU.
*/
ckh_delete(&prof_tdata->bt2cnt);
/*
* Iteratively merge cnt's into the global stats and delete
* them.
*/
while ((cnt = ql_last(&prof_tdata->lru_ql, lru_link)) != NULL) {
ql_remove(&prof_tdata->lru_ql, cnt, lru_link);
prof_ctx_merge(cnt->ctx, cnt);
idalloc(cnt);
}
idalloc(prof_tdata->vec);
idalloc(prof_tdata);
prof_tdata = PROF_TDATA_STATE_PURGATORY;
prof_tdata_tsd_set(&prof_tdata);
}
}
void
prof_boot0(void)
{
cassert(config_prof);
memcpy(opt_prof_prefix, PROF_PREFIX_DEFAULT,
sizeof(PROF_PREFIX_DEFAULT));
}
void
prof_boot1(void)
{
cassert(config_prof);
/*
* opt_prof and prof_promote must be in their final state before any
* arenas are initialized, so this function must be executed early.
*/
if (opt_prof_leak && opt_prof == false) {
/*
* Enable opt_prof, but in such a way that profiles are never
* automatically dumped.
*/
opt_prof = true;
opt_prof_gdump = false;
} else if (opt_prof) {
if (opt_lg_prof_interval >= 0) {
prof_interval = (((uint64_t)1U) <<
opt_lg_prof_interval);
}
}
prof_promote = (opt_prof && opt_lg_prof_sample > LG_PAGE);
}
bool
prof_boot2(void)
{
cassert(config_prof);
if (opt_prof) {
unsigned i;
if (ckh_new(&bt2ctx, PROF_CKH_MINITEMS, prof_bt_hash,
prof_bt_keycomp))
return (true);
if (malloc_mutex_init(&bt2ctx_mtx))
return (true);
if (prof_tdata_tsd_boot()) {
malloc_write(
"<jemalloc>: Error in pthread_key_create()\n");
abort();
}
if (malloc_mutex_init(&prof_dump_seq_mtx))
return (true);
if (atexit(prof_fdump) != 0) {
malloc_write("<jemalloc>: Error in atexit()\n");
if (opt_abort)
abort();
}
ctx_locks = (malloc_mutex_t *)base_alloc(PROF_NCTX_LOCKS *
sizeof(malloc_mutex_t));
if (ctx_locks == NULL)
return (true);
for (i = 0; i < PROF_NCTX_LOCKS; i++) {
if (malloc_mutex_init(&ctx_locks[i]))
return (true);
}
}
#ifdef JEMALLOC_PROF_LIBGCC
/*
* Cause the backtracing machinery to allocate its internal state
* before enabling profiling.
*/
_Unwind_Backtrace(prof_unwind_init_callback, NULL);
#endif
prof_booted = true;
return (false);
}
void
prof_prefork(void)
{
if (opt_prof) {
unsigned i;
malloc_mutex_lock(&bt2ctx_mtx);
malloc_mutex_lock(&prof_dump_seq_mtx);
for (i = 0; i < PROF_NCTX_LOCKS; i++)
malloc_mutex_lock(&ctx_locks[i]);
}
}
void
prof_postfork_parent(void)
{
if (opt_prof) {
unsigned i;
for (i = 0; i < PROF_NCTX_LOCKS; i++)
malloc_mutex_postfork_parent(&ctx_locks[i]);
malloc_mutex_postfork_parent(&prof_dump_seq_mtx);
malloc_mutex_postfork_parent(&bt2ctx_mtx);
}
}
void
prof_postfork_child(void)
{
if (opt_prof) {
unsigned i;
for (i = 0; i < PROF_NCTX_LOCKS; i++)
malloc_mutex_postfork_child(&ctx_locks[i]);
malloc_mutex_postfork_child(&prof_dump_seq_mtx);
malloc_mutex_postfork_child(&bt2ctx_mtx);
}
}
/******************************************************************************/
|