forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ftrace.c
6061 lines (4999 loc) · 141 KB
/
ftrace.c
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
/*
* Infrastructure for profiling code inserted by 'gcc -pg'.
*
* Copyright (C) 2007-2008 Steven Rostedt <[email protected]>
* Copyright (C) 2004-2008 Ingo Molnar <[email protected]>
*
* Originally ported from the -rt patch by:
* Copyright (C) 2007 Arnaldo Carvalho de Melo <[email protected]>
*
* Based on code in the latency_tracer, that is:
*
* Copyright (C) 2004-2006 Ingo Molnar
* Copyright (C) 2004 Nadia Yvette Chambers
*/
#include <linux/stop_machine.h>
#include <linux/clocksource.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/suspend.h>
#include <linux/tracefs.h>
#include <linux/hardirq.h>
#include <linux/kthread.h>
#include <linux/uaccess.h>
#include <linux/bsearch.h>
#include <linux/module.h>
#include <linux/ftrace.h>
#include <linux/sysctl.h>
#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/sort.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/rcupdate.h>
#include <trace/events/sched.h>
#include <asm/setup.h>
#include "trace_output.h"
#include "trace_stat.h"
#define FTRACE_WARN_ON(cond) \
({ \
int ___r = cond; \
if (WARN_ON(___r)) \
ftrace_kill(); \
___r; \
})
#define FTRACE_WARN_ON_ONCE(cond) \
({ \
int ___r = cond; \
if (WARN_ON_ONCE(___r)) \
ftrace_kill(); \
___r; \
})
/* hash bits for specific function selection */
#define FTRACE_HASH_BITS 7
#define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS)
#define FTRACE_HASH_DEFAULT_BITS 10
#define FTRACE_HASH_MAX_BITS 12
#ifdef CONFIG_DYNAMIC_FTRACE
#define INIT_OPS_HASH(opsname) \
.func_hash = &opsname.local_hash, \
.local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock),
#define ASSIGN_OPS_HASH(opsname, val) \
.func_hash = val, \
.local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock),
#else
#define INIT_OPS_HASH(opsname)
#define ASSIGN_OPS_HASH(opsname, val)
#endif
static struct ftrace_ops ftrace_list_end __read_mostly = {
.func = ftrace_stub,
.flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB,
INIT_OPS_HASH(ftrace_list_end)
};
/* ftrace_enabled is a method to turn ftrace on or off */
int ftrace_enabled __read_mostly;
static int last_ftrace_enabled;
/* Current function tracing op */
struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
/* What to set function_trace_op to */
static struct ftrace_ops *set_function_trace_op;
static bool ftrace_pids_enabled(struct ftrace_ops *ops)
{
struct trace_array *tr;
if (!(ops->flags & FTRACE_OPS_FL_PID) || !ops->private)
return false;
tr = ops->private;
return tr->function_pids != NULL;
}
static void ftrace_update_trampoline(struct ftrace_ops *ops);
/*
* ftrace_disabled is set when an anomaly is discovered.
* ftrace_disabled is much stronger than ftrace_enabled.
*/
static int ftrace_disabled __read_mostly;
static DEFINE_MUTEX(ftrace_lock);
static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
static struct ftrace_ops global_ops;
#if ARCH_SUPPORTS_FTRACE_OPS
static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *regs);
#else
/* See comment below, where ftrace_ops_list_func is defined */
static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
#endif
/*
* Traverse the ftrace_global_list, invoking all entries. The reason that we
* can use rcu_dereference_raw_notrace() is that elements removed from this list
* are simply leaked, so there is no need to interact with a grace-period
* mechanism. The rcu_dereference_raw_notrace() calls are needed to handle
* concurrent insertions into the ftrace_global_list.
*
* Silly Alpha and silly pointer-speculation compiler optimizations!
*/
#define do_for_each_ftrace_op(op, list) \
op = rcu_dereference_raw_notrace(list); \
do
/*
* Optimized for just a single item in the list (as that is the normal case).
*/
#define while_for_each_ftrace_op(op) \
while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \
unlikely((op) != &ftrace_list_end))
static inline void ftrace_ops_init(struct ftrace_ops *ops)
{
#ifdef CONFIG_DYNAMIC_FTRACE
if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) {
mutex_init(&ops->local_hash.regex_lock);
ops->func_hash = &ops->local_hash;
ops->flags |= FTRACE_OPS_FL_INITIALIZED;
}
#endif
}
/**
* ftrace_nr_registered_ops - return number of ops registered
*
* Returns the number of ftrace_ops registered and tracing functions
*/
int ftrace_nr_registered_ops(void)
{
struct ftrace_ops *ops;
int cnt = 0;
mutex_lock(&ftrace_lock);
for (ops = ftrace_ops_list;
ops != &ftrace_list_end; ops = ops->next)
cnt++;
mutex_unlock(&ftrace_lock);
return cnt;
}
static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *regs)
{
struct trace_array *tr = op->private;
if (tr && this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid))
return;
op->saved_func(ip, parent_ip, op, regs);
}
/**
* clear_ftrace_function - reset the ftrace function
*
* This NULLs the ftrace function and in essence stops
* tracing. There may be lag
*/
void clear_ftrace_function(void)
{
ftrace_trace_function = ftrace_stub;
}
static void per_cpu_ops_disable_all(struct ftrace_ops *ops)
{
int cpu;
for_each_possible_cpu(cpu)
*per_cpu_ptr(ops->disabled, cpu) = 1;
}
static int per_cpu_ops_alloc(struct ftrace_ops *ops)
{
int __percpu *disabled;
if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU)))
return -EINVAL;
disabled = alloc_percpu(int);
if (!disabled)
return -ENOMEM;
ops->disabled = disabled;
per_cpu_ops_disable_all(ops);
return 0;
}
static void ftrace_sync(struct work_struct *work)
{
/*
* This function is just a stub to implement a hard force
* of synchronize_sched(). This requires synchronizing
* tasks even in userspace and idle.
*
* Yes, function tracing is rude.
*/
}
static void ftrace_sync_ipi(void *data)
{
/* Probably not needed, but do it anyway */
smp_rmb();
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static void update_function_graph_func(void);
/* Both enabled by default (can be cleared by function_graph tracer flags */
static bool fgraph_sleep_time = true;
static bool fgraph_graph_time = true;
#else
static inline void update_function_graph_func(void) { }
#endif
static ftrace_func_t ftrace_ops_get_list_func(struct ftrace_ops *ops)
{
/*
* If this is a dynamic, RCU, or per CPU ops, or we force list func,
* then it needs to call the list anyway.
*/
if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU |
FTRACE_OPS_FL_RCU) || FTRACE_FORCE_LIST_FUNC)
return ftrace_ops_list_func;
return ftrace_ops_get_func(ops);
}
static void update_ftrace_function(void)
{
ftrace_func_t func;
/*
* Prepare the ftrace_ops that the arch callback will use.
* If there's only one ftrace_ops registered, the ftrace_ops_list
* will point to the ops we want.
*/
set_function_trace_op = ftrace_ops_list;
/* If there's no ftrace_ops registered, just call the stub function */
if (ftrace_ops_list == &ftrace_list_end) {
func = ftrace_stub;
/*
* If we are at the end of the list and this ops is
* recursion safe and not dynamic and the arch supports passing ops,
* then have the mcount trampoline call the function directly.
*/
} else if (ftrace_ops_list->next == &ftrace_list_end) {
func = ftrace_ops_get_list_func(ftrace_ops_list);
} else {
/* Just use the default ftrace_ops */
set_function_trace_op = &ftrace_list_end;
func = ftrace_ops_list_func;
}
update_function_graph_func();
/* If there's no change, then do nothing more here */
if (ftrace_trace_function == func)
return;
/*
* If we are using the list function, it doesn't care
* about the function_trace_ops.
*/
if (func == ftrace_ops_list_func) {
ftrace_trace_function = func;
/*
* Don't even bother setting function_trace_ops,
* it would be racy to do so anyway.
*/
return;
}
#ifndef CONFIG_DYNAMIC_FTRACE
/*
* For static tracing, we need to be a bit more careful.
* The function change takes affect immediately. Thus,
* we need to coorditate the setting of the function_trace_ops
* with the setting of the ftrace_trace_function.
*
* Set the function to the list ops, which will call the
* function we want, albeit indirectly, but it handles the
* ftrace_ops and doesn't depend on function_trace_op.
*/
ftrace_trace_function = ftrace_ops_list_func;
/*
* Make sure all CPUs see this. Yes this is slow, but static
* tracing is slow and nasty to have enabled.
*/
schedule_on_each_cpu(ftrace_sync);
/* Now all cpus are using the list ops. */
function_trace_op = set_function_trace_op;
/* Make sure the function_trace_op is visible on all CPUs */
smp_wmb();
/* Nasty way to force a rmb on all cpus */
smp_call_function(ftrace_sync_ipi, NULL, 1);
/* OK, we are all set to update the ftrace_trace_function now! */
#endif /* !CONFIG_DYNAMIC_FTRACE */
ftrace_trace_function = func;
}
int using_ftrace_ops_list_func(void)
{
return ftrace_trace_function == ftrace_ops_list_func;
}
static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
{
ops->next = *list;
/*
* We are entering ops into the list but another
* CPU might be walking that list. We need to make sure
* the ops->next pointer is valid before another CPU sees
* the ops pointer included into the list.
*/
rcu_assign_pointer(*list, ops);
}
static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
{
struct ftrace_ops **p;
/*
* If we are removing the last function, then simply point
* to the ftrace_stub.
*/
if (*list == ops && ops->next == &ftrace_list_end) {
*list = &ftrace_list_end;
return 0;
}
for (p = list; *p != &ftrace_list_end; p = &(*p)->next)
if (*p == ops)
break;
if (*p != ops)
return -1;
*p = (*p)->next;
return 0;
}
static void ftrace_update_trampoline(struct ftrace_ops *ops);
static int __register_ftrace_function(struct ftrace_ops *ops)
{
if (ops->flags & FTRACE_OPS_FL_DELETED)
return -EINVAL;
if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED))
return -EBUSY;
#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
/*
* If the ftrace_ops specifies SAVE_REGS, then it only can be used
* if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set.
* Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant.
*/
if (ops->flags & FTRACE_OPS_FL_SAVE_REGS &&
!(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED))
return -EINVAL;
if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)
ops->flags |= FTRACE_OPS_FL_SAVE_REGS;
#endif
if (!core_kernel_data((unsigned long)ops))
ops->flags |= FTRACE_OPS_FL_DYNAMIC;
if (ops->flags & FTRACE_OPS_FL_PER_CPU) {
if (per_cpu_ops_alloc(ops))
return -ENOMEM;
}
add_ftrace_ops(&ftrace_ops_list, ops);
/* Always save the function, and reset at unregistering */
ops->saved_func = ops->func;
if (ftrace_pids_enabled(ops))
ops->func = ftrace_pid_func;
ftrace_update_trampoline(ops);
if (ftrace_enabled)
update_ftrace_function();
return 0;
}
static int __unregister_ftrace_function(struct ftrace_ops *ops)
{
int ret;
if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
return -EBUSY;
ret = remove_ftrace_ops(&ftrace_ops_list, ops);
if (ret < 0)
return ret;
if (ftrace_enabled)
update_ftrace_function();
ops->func = ops->saved_func;
return 0;
}
static void ftrace_update_pid_func(void)
{
struct ftrace_ops *op;
/* Only do something if we are tracing something */
if (ftrace_trace_function == ftrace_stub)
return;
do_for_each_ftrace_op(op, ftrace_ops_list) {
if (op->flags & FTRACE_OPS_FL_PID) {
op->func = ftrace_pids_enabled(op) ?
ftrace_pid_func : op->saved_func;
ftrace_update_trampoline(op);
}
} while_for_each_ftrace_op(op);
update_ftrace_function();
}
#ifdef CONFIG_FUNCTION_PROFILER
struct ftrace_profile {
struct hlist_node node;
unsigned long ip;
unsigned long counter;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
unsigned long long time;
unsigned long long time_squared;
#endif
};
struct ftrace_profile_page {
struct ftrace_profile_page *next;
unsigned long index;
struct ftrace_profile records[];
};
struct ftrace_profile_stat {
atomic_t disabled;
struct hlist_head *hash;
struct ftrace_profile_page *pages;
struct ftrace_profile_page *start;
struct tracer_stat stat;
};
#define PROFILE_RECORDS_SIZE \
(PAGE_SIZE - offsetof(struct ftrace_profile_page, records))
#define PROFILES_PER_PAGE \
(PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
static int ftrace_profile_enabled __read_mostly;
/* ftrace_profile_lock - synchronize the enable and disable of the profiler */
static DEFINE_MUTEX(ftrace_profile_lock);
static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
#define FTRACE_PROFILE_HASH_BITS 10
#define FTRACE_PROFILE_HASH_SIZE (1 << FTRACE_PROFILE_HASH_BITS)
static void *
function_stat_next(void *v, int idx)
{
struct ftrace_profile *rec = v;
struct ftrace_profile_page *pg;
pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
again:
if (idx != 0)
rec++;
if ((void *)rec >= (void *)&pg->records[pg->index]) {
pg = pg->next;
if (!pg)
return NULL;
rec = &pg->records[0];
if (!rec->counter)
goto again;
}
return rec;
}
static void *function_stat_start(struct tracer_stat *trace)
{
struct ftrace_profile_stat *stat =
container_of(trace, struct ftrace_profile_stat, stat);
if (!stat || !stat->start)
return NULL;
return function_stat_next(&stat->start->records[0], 0);
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/* function graph compares on total time */
static int function_stat_cmp(void *p1, void *p2)
{
struct ftrace_profile *a = p1;
struct ftrace_profile *b = p2;
if (a->time < b->time)
return -1;
if (a->time > b->time)
return 1;
else
return 0;
}
#else
/* not function graph compares against hits */
static int function_stat_cmp(void *p1, void *p2)
{
struct ftrace_profile *a = p1;
struct ftrace_profile *b = p2;
if (a->counter < b->counter)
return -1;
if (a->counter > b->counter)
return 1;
else
return 0;
}
#endif
static int function_stat_headers(struct seq_file *m)
{
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
seq_puts(m, " Function "
"Hit Time Avg s^2\n"
" -------- "
"--- ---- --- ---\n");
#else
seq_puts(m, " Function Hit\n"
" -------- ---\n");
#endif
return 0;
}
static int function_stat_show(struct seq_file *m, void *v)
{
struct ftrace_profile *rec = v;
char str[KSYM_SYMBOL_LEN];
int ret = 0;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static struct trace_seq s;
unsigned long long avg;
unsigned long long stddev;
#endif
mutex_lock(&ftrace_profile_lock);
/* we raced with function_profile_reset() */
if (unlikely(rec->counter == 0)) {
ret = -EBUSY;
goto out;
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
avg = rec->time;
do_div(avg, rec->counter);
if (tracing_thresh && (avg < tracing_thresh))
goto out;
#endif
kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
seq_printf(m, " %-30.30s %10lu", str, rec->counter);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
seq_puts(m, " ");
/* Sample standard deviation (s^2) */
if (rec->counter <= 1)
stddev = 0;
else {
/*
* Apply Welford's method:
* s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
*/
stddev = rec->counter * rec->time_squared -
rec->time * rec->time;
/*
* Divide only 1000 for ns^2 -> us^2 conversion.
* trace_print_graph_duration will divide 1000 again.
*/
do_div(stddev, rec->counter * (rec->counter - 1) * 1000);
}
trace_seq_init(&s);
trace_print_graph_duration(rec->time, &s);
trace_seq_puts(&s, " ");
trace_print_graph_duration(avg, &s);
trace_seq_puts(&s, " ");
trace_print_graph_duration(stddev, &s);
trace_print_seq(m, &s);
#endif
seq_putc(m, '\n');
out:
mutex_unlock(&ftrace_profile_lock);
return ret;
}
static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
{
struct ftrace_profile_page *pg;
pg = stat->pages = stat->start;
while (pg) {
memset(pg->records, 0, PROFILE_RECORDS_SIZE);
pg->index = 0;
pg = pg->next;
}
memset(stat->hash, 0,
FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head));
}
int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
{
struct ftrace_profile_page *pg;
int functions;
int pages;
int i;
/* If we already allocated, do nothing */
if (stat->pages)
return 0;
stat->pages = (void *)get_zeroed_page(GFP_KERNEL);
if (!stat->pages)
return -ENOMEM;
#ifdef CONFIG_DYNAMIC_FTRACE
functions = ftrace_update_tot_cnt;
#else
/*
* We do not know the number of functions that exist because
* dynamic tracing is what counts them. With past experience
* we have around 20K functions. That should be more than enough.
* It is highly unlikely we will execute every function in
* the kernel.
*/
functions = 20000;
#endif
pg = stat->start = stat->pages;
pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
for (i = 1; i < pages; i++) {
pg->next = (void *)get_zeroed_page(GFP_KERNEL);
if (!pg->next)
goto out_free;
pg = pg->next;
}
return 0;
out_free:
pg = stat->start;
while (pg) {
unsigned long tmp = (unsigned long)pg;
pg = pg->next;
free_page(tmp);
}
stat->pages = NULL;
stat->start = NULL;
return -ENOMEM;
}
static int ftrace_profile_init_cpu(int cpu)
{
struct ftrace_profile_stat *stat;
int size;
stat = &per_cpu(ftrace_profile_stats, cpu);
if (stat->hash) {
/* If the profile is already created, simply reset it */
ftrace_profile_reset(stat);
return 0;
}
/*
* We are profiling all functions, but usually only a few thousand
* functions are hit. We'll make a hash of 1024 items.
*/
size = FTRACE_PROFILE_HASH_SIZE;
stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL);
if (!stat->hash)
return -ENOMEM;
/* Preallocate the function profiling pages */
if (ftrace_profile_pages_init(stat) < 0) {
kfree(stat->hash);
stat->hash = NULL;
return -ENOMEM;
}
return 0;
}
static int ftrace_profile_init(void)
{
int cpu;
int ret = 0;
for_each_possible_cpu(cpu) {
ret = ftrace_profile_init_cpu(cpu);
if (ret)
break;
}
return ret;
}
/* interrupts must be disabled */
static struct ftrace_profile *
ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
{
struct ftrace_profile *rec;
struct hlist_head *hhd;
unsigned long key;
key = hash_long(ip, FTRACE_PROFILE_HASH_BITS);
hhd = &stat->hash[key];
if (hlist_empty(hhd))
return NULL;
hlist_for_each_entry_rcu_notrace(rec, hhd, node) {
if (rec->ip == ip)
return rec;
}
return NULL;
}
static void ftrace_add_profile(struct ftrace_profile_stat *stat,
struct ftrace_profile *rec)
{
unsigned long key;
key = hash_long(rec->ip, FTRACE_PROFILE_HASH_BITS);
hlist_add_head_rcu(&rec->node, &stat->hash[key]);
}
/*
* The memory is already allocated, this simply finds a new record to use.
*/
static struct ftrace_profile *
ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
{
struct ftrace_profile *rec = NULL;
/* prevent recursion (from NMIs) */
if (atomic_inc_return(&stat->disabled) != 1)
goto out;
/*
* Try to find the function again since an NMI
* could have added it
*/
rec = ftrace_find_profiled_func(stat, ip);
if (rec)
goto out;
if (stat->pages->index == PROFILES_PER_PAGE) {
if (!stat->pages->next)
goto out;
stat->pages = stat->pages->next;
}
rec = &stat->pages->records[stat->pages->index++];
rec->ip = ip;
ftrace_add_profile(stat, rec);
out:
atomic_dec(&stat->disabled);
return rec;
}
static void
function_profile_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct pt_regs *regs)
{
struct ftrace_profile_stat *stat;
struct ftrace_profile *rec;
unsigned long flags;
if (!ftrace_profile_enabled)
return;
local_irq_save(flags);
stat = this_cpu_ptr(&ftrace_profile_stats);
if (!stat->hash || !ftrace_profile_enabled)
goto out;
rec = ftrace_find_profiled_func(stat, ip);
if (!rec) {
rec = ftrace_profile_alloc(stat, ip);
if (!rec)
goto out;
}
rec->counter++;
out:
local_irq_restore(flags);
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static int profile_graph_entry(struct ftrace_graph_ent *trace)
{
int index = trace->depth;
function_profile_call(trace->func, 0, NULL, NULL);
if (index >= 0 && index < FTRACE_RETFUNC_DEPTH)
current->ret_stack[index].subtime = 0;
return 1;
}
static void profile_graph_return(struct ftrace_graph_ret *trace)
{
struct ftrace_profile_stat *stat;
unsigned long long calltime;
struct ftrace_profile *rec;
unsigned long flags;
local_irq_save(flags);
stat = this_cpu_ptr(&ftrace_profile_stats);
if (!stat->hash || !ftrace_profile_enabled)
goto out;
/* If the calltime was zero'd ignore it */
if (!trace->calltime)
goto out;
calltime = trace->rettime - trace->calltime;
if (!fgraph_graph_time) {
int index;
index = trace->depth;
/* Append this call time to the parent time to subtract */
if (index)
current->ret_stack[index - 1].subtime += calltime;
if (current->ret_stack[index].subtime < calltime)
calltime -= current->ret_stack[index].subtime;
else
calltime = 0;
}
rec = ftrace_find_profiled_func(stat, trace->func);
if (rec) {
rec->time += calltime;
rec->time_squared += calltime * calltime;
}
out:
local_irq_restore(flags);
}
static int register_ftrace_profiler(void)
{
return register_ftrace_graph(&profile_graph_return,
&profile_graph_entry);
}
static void unregister_ftrace_profiler(void)
{
unregister_ftrace_graph();
}
#else
static struct ftrace_ops ftrace_profile_ops __read_mostly = {
.func = function_profile_call,
.flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
INIT_OPS_HASH(ftrace_profile_ops)
};
static int register_ftrace_profiler(void)
{
return register_ftrace_function(&ftrace_profile_ops);
}
static void unregister_ftrace_profiler(void)
{
unregister_ftrace_function(&ftrace_profile_ops);
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
static ssize_t
ftrace_profile_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
unsigned long val;
int ret;
ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
if (ret)
return ret;
val = !!val;
mutex_lock(&ftrace_profile_lock);
if (ftrace_profile_enabled ^ val) {
if (val) {
ret = ftrace_profile_init();
if (ret < 0) {
cnt = ret;
goto out;
}
ret = register_ftrace_profiler();
if (ret < 0) {
cnt = ret;
goto out;
}
ftrace_profile_enabled = 1;
} else {
ftrace_profile_enabled = 0;
/*
* unregister_ftrace_profiler calls stop_machine
* so this acts like an synchronize_sched.
*/
unregister_ftrace_profiler();
}
}
out:
mutex_unlock(&ftrace_profile_lock);
*ppos += cnt;
return cnt;
}