summaryrefslogtreecommitdiffstats
path: root/kernel/trace/ftrace.c
blob: 6d4d2e86debc76f2c85ebca6f686bc2c4cf96463 (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
/*
 * Infrastructure for profiling code inserted by 'gcc -pg'.
 *
 * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
 * Copyright (C) 2004-2008 Ingo Molnar <mingo@redhat.com>
 *
 * Originally ported from the -rt patch by:
 *   Copyright (C) 2007 Arnaldo Carvalho de Melo <acme@redhat.com>
 *
 * Based on code in the latency_tracer, that is:
 *
 *  Copyright (C) 2004-2006 Ingo Molnar
 *  Copyright (C) 2004 William Lee Irwin III
 */

#include <linux/stop_machine.h>
#include <linux/clocksource.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/kthread.h>
#include <linux/hardirq.h>
#include <linux/ftrace.h>
#include <linux/uaccess.h>
#include <linux/sysctl.h>
#include <linux/hash.h>
#include <linux/ctype.h>
#include <linux/list.h>

#include "trace.h"

int ftrace_enabled;
static int last_ftrace_enabled;

static DEFINE_SPINLOCK(ftrace_lock);
static DEFINE_MUTEX(ftrace_sysctl_lock);

static struct ftrace_ops ftrace_list_end __read_mostly =
{
	.func = ftrace_stub,
};

static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;

/* mcount is defined per arch in assembly */
EXPORT_SYMBOL(mcount);

notrace void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
	struct ftrace_ops *op = ftrace_list;

	/* in case someone actually ports this to alpha! */
	read_barrier_depends();

	while (op != &ftrace_list_end) {
		/* silly alpha */
		read_barrier_depends();
		op->func(ip, parent_ip);
		op = op->next;
	};
}

/**
 * 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 int notrace __register_ftrace_function(struct ftrace_ops *ops)
{
	/* Should never be called by interrupts */
	spin_lock(&ftrace_lock);

	ops->next = ftrace_list;
	/*
	 * We are entering ops into the ftrace_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 ftrace_list.
	 */
	smp_wmb();
	ftrace_list = ops;

	if (ftrace_enabled) {
		/*
		 * For one func, simply call it directly.
		 * For more than one func, call the chain.
		 */
		if (ops->next == &ftrace_list_end)
			ftrace_trace_function = ops->func;
		else
			ftrace_trace_function = ftrace_list_func;
	}

	spin_unlock(&ftrace_lock);

	return 0;
}

static int notrace __unregister_ftrace_function(struct ftrace_ops *ops)
{
	struct ftrace_ops **p;
	int ret = 0;

	spin_lock(&ftrace_lock);

	/*
	 * If we are removing the last function, then simply point
	 * to the ftrace_stub.
	 */
	if (ftrace_list == ops && ops->next == &ftrace_list_end) {
		ftrace_trace_function = ftrace_stub;
		ftrace_list = &ftrace_list_end;
		goto out;
	}

	for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next)
		if (*p == ops)
			break;

	if (*p != ops) {
		ret = -1;
		goto out;
	}

	*p = (*p)->next;

	if (ftrace_enabled) {
		/* If we only have one func left, then call that directly */
		if (ftrace_list == &ftrace_list_end ||
		    ftrace_list->next == &ftrace_list_end)
			ftrace_trace_function = ftrace_list->func;
	}

 out:
	spin_unlock(&ftrace_lock);

	return ret;
}

#ifdef CONFIG_DYNAMIC_FTRACE

static struct task_struct *ftraced_task;
static DECLARE_WAIT_QUEUE_HEAD(ftraced_waiters);
static unsigned long ftraced_iteration_counter;

enum {
	FTRACE_ENABLE_CALLS		= (1 << 0),
	FTRACE_DISABLE_CALLS		= (1 << 1),
	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
	FTRACE_ENABLE_MCOUNT		= (1 << 3),
	FTRACE_DISABLE_MCOUNT		= (1 << 4),
};

static int ftrace_filtered;

static struct hlist_head ftrace_hash[FTRACE_HASHSIZE];

static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu);

static DEFINE_SPINLOCK(ftrace_shutdown_lock);
static DEFINE_MUTEX(ftraced_lock);
static DEFINE_MUTEX(ftrace_filter_lock);

struct ftrace_page {
	struct ftrace_page	*next;
	int			index;
	struct dyn_ftrace	records[];
} __attribute__((packed));

#define ENTRIES_PER_PAGE \
  ((PAGE_SIZE - sizeof(struct ftrace_page)) / sizeof(struct dyn_ftrace))

/* estimate from running different kernels */
#define NR_TO_INIT		10000

static struct ftrace_page	*ftrace_pages_start;
static struct ftrace_page	*ftrace_pages;

static int ftraced_trigger;
static int ftraced_suspend;

static int ftrace_record_suspend;

static inline int
notrace ftrace_ip_in_hash(unsigned long ip, unsigned long key)
{
	struct dyn_ftrace *p;
	struct hlist_node *t;
	int found = 0;

	hlist_for_each_entry(p, t, &ftrace_hash[key], node) {
		if (p->ip == ip) {
			found = 1;
			break;
		}
	}

	return found;
}

static inline void notrace
ftrace_add_hash(struct dyn_ftrace *node, unsigned long key)
{
	hlist_add_head(&node->node, &ftrace_hash[key]);
}

static notrace struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
{
	if (ftrace_pages->index == ENTRIES_PER_PAGE) {
		if (!ftrace_pages->next)
			return NULL;
		ftrace_pages = ftrace_pages->next;
	}

	return &ftrace_pages->records[ftrace_pages->index++];
}

static void notrace
ftrace_record_ip(unsigned long ip)
{
	struct dyn_ftrace *node;
	unsigned long flags;
	unsigned long key;
	int resched;
	int atomic;

	if (!ftrace_enabled)
		return;

	resched = need_resched();
	preempt_disable_notrace();

	/* We simply need to protect against recursion */
	__get_cpu_var(ftrace_shutdown_disable_cpu)++;
	if (__get_cpu_var(ftrace_shutdown_disable_cpu) != 1)
		goto out;

	if (unlikely(ftrace_record_suspend))
		goto out;

	key = hash_long(ip, FTRACE_HASHBITS);

	WARN_ON_ONCE(key >= FTRACE_HASHSIZE);

	if (ftrace_ip_in_hash(ip, key))
		goto out;

	atomic = irqs_disabled();

	spin_lock_irqsave(&ftrace_shutdown_lock, flags);

	/* This ip may have hit the hash before the lock */
	if (ftrace_ip_in_hash(ip, key))
		goto out_unlock;

	/*
	 * There's a slight race that the ftraced will update the
	 * hash and reset here. If it is already converted, skip it.
	 */
	if (ftrace_ip_converted(ip))
		goto out_unlock;

	node = ftrace_alloc_dyn_node(ip);
	if (!node)
		goto out_unlock;

	node->ip = ip;

	ftrace_add_hash(node, key);

	ftraced_trigger = 1;

 out_unlock:
	spin_unlock_irqrestore(&ftrace_shutdown_lock, flags);
 out:
	__get_cpu_var(ftrace_shutdown_disable_cpu)--;

	/* prevent recursion with scheduler */
	if (resched)
		preempt_enable_no_resched_notrace();
	else
		preempt_enable_notrace();
}

#define FTRACE_ADDR ((long)(&ftrace_caller))
#define MCOUNT_ADDR ((long)(&mcount))

static void notrace
__ftrace_replace_code(struct dyn_ftrace *rec,
		      unsigned char *old, unsigned char *new, int enable)
{
	unsigned long ip;
	int failed;

	ip = rec->ip;

	if (ftrace_filtered && enable) {
		unsigned long fl;
		/*
		 * If filtering is on:
		 *
		 * If this record is set to be filtered and
		 * is enabled then do nothing.
		 *
		 * If this record is set to be filtered and
		 * it is not enabled, enable it.
		 *
		 * If this record is not set to be filtered
		 * and it is not enabled do nothing.
		 *
		 * If this record is not set to be filtered and
		 * it is enabled, disable it.
		 */
		fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED);

		if ((fl ==  (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) ||
		    (fl == 0))
			return;

		/*
		 * If it is enabled disable it,
		 * otherwise enable it!
		 */
		if (fl == FTRACE_FL_ENABLED) {
			/* swap new and old */
			new = old;
			old = ftrace_call_replace(ip, FTRACE_ADDR);
			rec->flags &= ~FTRACE_FL_ENABLED;
		} else {
			new = ftrace_call_replace(ip, FTRACE_ADDR);
			rec->flags |= FTRACE_FL_ENABLED;
		}
	} else {

		if (enable)
			new = ftrace_call_replace(ip, FTRACE_ADDR);
		else
			old = ftrace_call_replace(ip, FTRACE_ADDR);

		if (enable) {
			if (rec->flags & FTRACE_FL_ENABLED)
				return;
			rec->flags |= FTRACE_FL_ENABLED;
		} else {
			if (!(rec->flags & FTRACE_FL_ENABLED))
				return;
			rec->flags &= ~FTRACE_FL_ENABLED;
		}
	}

	failed = ftrace_modify_code(ip, old, new);
	if (failed)
		rec->flags |= FTRACE_FL_FAILED;
}

static void notrace ftrace_replace_code(int enable)
{
	unsigned char *new = NULL, *old = NULL;
	struct dyn_ftrace *rec;
	struct ftrace_page *pg;
	int i;

	if (enable)
		old = ftrace_nop_replace();
	else
		new = ftrace_nop_replace();

	for (pg = ftrace_pages_start; pg; pg = pg->next) {
		for (i = 0; i < pg->index; i++) {
			rec = &pg->records[i];

			/* don't modify code that has already faulted */
			if (rec->flags & FTRACE_FL_FAILED)
				continue;

			__ftrace_replace_code(rec, old, new, enable);
		}
	}
}

static notrace void ftrace_shutdown_replenish(void)
{
	if (ftrace_pages->next)
		return;

	/* allocate another page */
	ftrace_pages->next = (void *)get_zeroed_page(GFP_KERNEL);
}

static notrace void
ftrace_code_disable(struct dyn_ftrace *rec)
{
	unsigned long ip;
	unsigned char *nop, *call;
	int failed;

	ip = rec->ip;

	nop = ftrace_nop_replace();
	call = ftrace_call_replace(ip, MCOUNT_ADDR);

	failed = ftrace_modify_code(ip, call, nop);
	if (failed)
		rec->flags |= FTRACE_FL_FAILED;
}

static int notrace __ftrace_modify_code(void *data)
{
	unsigned long addr;
	int *command = data;

	if (*command & FTRACE_ENABLE_CALLS)
		ftrace_replace_code(1);
	else if (*command & FTRACE_DISABLE_CALLS)
		ftrace_replace_code(0);

	if (*command & FTRACE_UPDATE_TRACE_FUNC)
		ftrace_update_ftrace_func(ftrace_trace_function);

	if (*command & FTRACE_ENABLE_MCOUNT) {
		addr = (unsigned long)ftrace_record_ip;
		ftrace_mcount_set(&addr);
	} else if (*command & FTRACE_DISABLE_MCOUNT) {
		addr = (unsigned long)ftrace_stub;
		ftrace_mcount_set(&addr);
	}

	return 0;
}

static void notrace ftrace_run_update_code(int command)
{
	stop_machine_run(__ftrace_modify_code, &command, NR_CPUS);
}

static ftrace_func_t saved_ftrace_func;

static void notrace ftrace_startup(void)
{
	int command = 0;

	mutex_lock(&ftraced_lock);
	ftraced_suspend++;
	if (ftraced_suspend == 1)
		command |= FTRACE_ENABLE_CALLS;

	if (saved_ftrace_func != ftrace_trace_function) {
		saved_ftrace_func = ftrace_trace_function;
		command |= FTRACE_UPDATE_TRACE_FUNC;
	}

	if (!command || !ftrace_enabled)
		goto out;

	ftrace_run_update_code(command);
 out:
	mutex_unlock(&ftraced_lock);
}

static void notrace ftrace_shutdown(void)
{
	int command = 0;

	mutex_lock(&ftraced_lock);
	ftraced_suspend--;
	if (!ftraced_suspend)
		command |= FTRACE_DISABLE_CALLS;

	if (saved_ftrace_func != ftrace_trace_function) {
		saved_ftrace_func = ftrace_trace_function;
		command |= FTRACE_UPDATE_TRACE_FUNC;
	}

	if (!command || !ftrace_enabled)
		goto out;

	ftrace_run_update_code(command);
 out:
	mutex_unlock(&ftraced_lock);
}

static void notrace ftrace_startup_sysctl(void)
{
	int command = FTRACE_ENABLE_MCOUNT;

	mutex_lock(&ftraced_lock);
	/* Force update next time */
	saved_ftrace_func = NULL;
	/* ftraced_suspend is true if we want ftrace running */
	if (ftraced_suspend)
		command |= FTRACE_ENABLE_CALLS;

	ftrace_run_update_code(command);
	mutex_unlock(&ftraced_lock);
}

static void notrace ftrace_shutdown_sysctl(void)
{
	int command = FTRACE_DISABLE_MCOUNT;

	mutex_lock(&ftraced_lock);
	/* ftraced_suspend is true if ftrace is running */
	if (ftraced_suspend)
		command |= FTRACE_DISABLE_CALLS;

	ftrace_run_update_code(command);
	mutex_unlock(&ftraced_lock);
}

static cycle_t		ftrace_update_time;
static unsigned long	ftrace_update_cnt;
unsigned long		ftrace_update_tot_cnt;

static int notrace __ftrace_update_code(void *ignore)
{
	struct dyn_ftrace *p;
	struct hlist_head head;
	struct hlist_node *t;
	int save_ftrace_enabled;
	cycle_t start, stop;
	int i;

	/* Don't be recording funcs now */
	save_ftrace_enabled = ftrace_enabled;
	ftrace_enabled = 0;

	start = now(raw_smp_processor_id());
	ftrace_update_cnt = 0;

	/* No locks needed, the machine is stopped! */
	for (i = 0; i < FTRACE_HASHSIZE; i++) {
		if (hlist_empty(&ftrace_hash[i]))
			continue;

		head = ftrace_hash[i];
		INIT_HLIST_HEAD(&ftrace_hash[i]);

		/* all CPUS are stopped, we are safe to modify code */
		hlist_for_each_entry(p, t, &head, node) {
			ftrace_code_disable(p);
			ftrace_update_cnt++;
		}

	}

	stop = now(raw_smp_processor_id());
	ftrace_update_time = stop - start;
	ftrace_update_tot_cnt += ftrace_update_cnt;

	ftrace_enabled = save_ftrace_enabled;

	return 0;
}

static void notrace ftrace_update_code(void)
{
	stop_machine_run(__ftrace_update_code, NULL, NR_CPUS);
}

static int notrace ftraced(void *ignore)
{
	unsigned long usecs;

	set_current_state(TASK_INTERRUPTIBLE);

	while (!kthread_should_stop()) {

		/* check once a second */
		schedule_timeout(HZ);

		mutex_lock(&ftrace_sysctl_lock);
		mutex_lock(&ftraced_lock);
		if (ftrace_enabled && ftraced_trigger && !ftraced_suspend) {
			ftrace_record_suspend++;
			ftrace_update_code();
			usecs = nsecs_to_usecs(ftrace_update_time);
			if (ftrace_update_tot_cnt > 100000) {
				ftrace_update_tot_cnt = 0;
				pr_info("hm, dftrace overflow: %lu change%s"
					 " (%lu total) in %lu usec%s\n",
					ftrace_update_cnt,
					ftrace_update_cnt != 1 ? "s" : "",
					ftrace_update_tot_cnt,
					usecs, usecs != 1 ? "s" : "");
				WARN_ON_ONCE(1);
			}
			ftraced_trigger = 0;
			ftrace_record_suspend--;
		}
		ftraced_iteration_counter++;
		mutex_unlock(&ftraced_lock);
		mutex_unlock(&ftrace_sysctl_lock);

		wake_up_interruptible(&ftraced_waiters);

		ftrace_shutdown_replenish();

		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);
	return 0;
}

static int __init ftrace_dyn_table_alloc(void)
{
	struct ftrace_page *pg;
	int cnt;
	int i;

	/* allocate a few pages */
	ftrace_pages_start = (void *)get_zeroed_page(GFP_KERNEL);
	if (!ftrace_pages_start)
		return -1;

	/*
	 * Allocate a few more pages.
	 *
	 * TODO: have some parser search vmlinux before
	 *   final linking to find all calls to ftrace.
	 *   Then we can:
	 *    a) know how many pages to allocate.
	 *     and/or
	 *    b) set up the table then.
	 *
	 *  The dynamic code is still necessary for
	 *  modules.
	 */

	pg = ftrace_pages = ftrace_pages_start;

	cnt = NR_TO_INIT / ENTRIES_PER_PAGE;

	for (i = 0; i < cnt; i++) {
		pg->next = (void *)get_zeroed_page(GFP_KERNEL);

		/* If we fail, we'll try later anyway */
		if (!pg->next)
			break;

		pg = pg->next;
	}

	return 0;
}

enum {
	FTRACE_ITER_FILTER	= (1 << 0),
	FTRACE_ITER_CONT	= (1 << 1),
};

#define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */

struct ftrace_iterator {
	loff_t			pos;
	struct ftrace_page	*pg;
	unsigned		idx;
	unsigned		flags;
	unsigned char		buffer[FTRACE_BUFF_MAX+1];
	unsigned		buffer_idx;
	unsigned		filtered;
};

static void notrace *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct ftrace_iterator *iter = m->private;
	struct dyn_ftrace *rec = NULL;

	(*pos)++;

 retry:
	if (iter->idx >= iter->pg->index) {
		if (iter->pg->next) {
			iter->pg = iter->pg->next;
			iter->idx = 0;
			goto retry;
		}
	} else {
		rec = &iter->pg->records[iter->idx++];
		if ((rec->flags & FTRACE_FL_FAILED) ||
		    ((iter->flags & FTRACE_ITER_FILTER) &&
		     !(rec->flags & FTRACE_FL_FILTER))) {
			rec = NULL;
			goto retry;
		}
	}

	iter->pos = *pos;

	return rec;
}

static void *t_start(struct seq_file *m, loff_t *pos)
{
	struct ftrace_iterator *iter = m->private;
	void *p = NULL;
	loff_t l = -1;

	if (*pos != iter->pos) {
		for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l))
			;
	} else {
		l = *pos;
		p = t_next(m, p, &l);
	}

	return p;
}

static void t_stop(struct seq_file *m, void *p)
{
}

static int t_show(struct seq_file *m, void *v)
{
	struct dyn_ftrace *rec = v;
	char str[KSYM_SYMBOL_LEN];

	if (!rec)
		return 0;

	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);

	seq_printf(m, "%s\n", str);

	return 0;
}

static struct seq_operations show_ftrace_seq_ops = {
	.start = t_start,
	.next = t_next,
	.stop = t_stop,
	.show = t_show,
};

static int notrace
ftrace_avail_open(struct inode *inode, struct file *file)
{
	struct ftrace_iterator *iter;
	int ret;

	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
	if (!iter)
		return -ENOMEM;

	iter->pg = ftrace_pages_start;
	iter->pos = -1;

	ret = seq_open(file, &show_ftrace_seq_ops);
	if (!ret) {
		struct seq_file *m = file->private_data;
		m->private = iter;
	} else
		kfree(iter);

	return ret;
}

int ftrace_avail_release(struct inode *inode, struct file *file)
{
	struct seq_file *m = (struct seq_file *)file->private_data;
	struct ftrace_iterator *iter = m->private;

	seq_release(inode, file);
	kfree(iter);
	return 0;
}

static void notrace ftrace_filter_reset(void)
{
	struct ftrace_page *pg;
	struct dyn_ftrace *rec;
	unsigned i;

	/* keep kstop machine from running */
	preempt_disable();
	ftrace_filtered = 0;
	pg = ftrace_pages_start;
	while (pg) {
		for (i = 0; i < pg->index; i++) {
			rec = &pg->records[i];
			if (rec->flags & FTRACE_FL_FAILED)
				continue;
			rec->flags &= ~FTRACE_FL_FILTER;
		}
		pg = pg->next;
	}
	preempt_enable();
}

static int notrace
ftrace_filter_open(struct inode *inode, struct file *file)
{
	struct ftrace_iterator *iter;
	int ret = 0;

	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
	if (!iter)
		return -ENOMEM;

	mutex_lock(&ftrace_filter_lock);
	if ((file->f_mode & FMODE_WRITE) &&
	    !(file->f_flags & O_APPEND))
		ftrace_filter_reset();

	if (file->f_mode & FMODE_READ) {
		iter->pg = ftrace_pages_start;
		iter->pos = -1;
		iter->flags = FTRACE_ITER_FILTER;

		ret = seq_open(file, &show_ftrace_seq_ops);
		if (!ret) {
			struct seq_file *m = file->private_data;
			m->private = iter;
		} else
			kfree(iter);
	} else
		file->private_data = iter;
	mutex_unlock(&ftrace_filter_lock);

	return ret;
}

static ssize_t notrace
ftrace_filter_read(struct file *file, char __user *ubuf,
		       size_t cnt, loff_t *ppos)
{
	if (file->f_mode & FMODE_READ)
		return seq_read(file, ubuf, cnt, ppos);
	else
		return -EPERM;
}

static loff_t notrace
ftrace_filter_lseek(struct file *file, loff_t offset, int origin)
{
	loff_t ret;

	if (file->f_mode & FMODE_READ)
		ret = seq_lseek(file, offset, origin);
	else
		file->f_pos = ret = 1;

	return ret;
}

enum {
	MATCH_FULL,
	MATCH_FRONT_ONLY,
	MATCH_MIDDLE_ONLY,
	MATCH_END_ONLY,
};

static void notrace
ftrace_match(unsigned char *buff, int len)
{
	char str[KSYM_SYMBOL_LEN];
	char *search = NULL;
	struct ftrace_page *pg;
	struct dyn_ftrace *rec;
	int type = MATCH_FULL;
	unsigned i, match = 0, search_len = 0;

	for (i = 0; i < len; i++) {
		if (buff[i] == '*') {
			if (!i) {
				search = buff + i + 1;
				type = MATCH_END_ONLY;
				search_len = len - (i + 1);
			} else {
				if (type == MATCH_END_ONLY) {
					type = MATCH_MIDDLE_ONLY;
				} else {
					match = i;
					type = MATCH_FRONT_ONLY;
				}
				buff[i] = 0;
				break;
			}
		}
	}

	/* keep kstop machine from running */
	preempt_disable();
	ftrace_filtered = 1;
	pg = ftrace_pages_start;
	while (pg) {
		for (i = 0; i < pg->index; i++) {
			int matched = 0;
			char *ptr;

			rec = &pg->records[i];
			if (rec->flags & FTRACE_FL_FAILED)
				continue;
			kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
			switch (type) {
			case MATCH_FULL:
				if (strcmp(str, buff) == 0)
					matched = 1;
				break;
			case MATCH_FRONT_ONLY:
				if (memcmp(str, buff, match) == 0)
					matched = 1;
				break;
			case MATCH_MIDDLE_ONLY:
				if (strstr(str, search))
					matched = 1;
				break;
			case MATCH_END_ONLY:
				ptr = strstr(str, search);
				if (ptr && (ptr[search_len] == 0))
					matched = 1;
				break;
			}
			if (matched)
				rec->flags |= FTRACE_FL_FILTER;
		}
		pg = pg->next;
	}
	preempt_enable();
}

static ssize_t notrace
ftrace_filter_write(struct file *file, const char __user *ubuf,
		    size_t cnt, loff_t *ppos)
{
	struct ftrace_iterator *iter;
	char ch;
	size_t read = 0;
	ssize_t ret;

	if (!cnt || cnt < 0)
		return 0;

	mutex_lock(&ftrace_filter_lock);

	if (file->f_mode & FMODE_READ) {
		struct seq_file *m = file->private_data;
		iter = m->private;
	} else
		iter = file->private_data;

	if (!*ppos) {
		iter->flags &= ~FTRACE_ITER_CONT;
		iter->buffer_idx = 0;
	}

	ret = get_user(ch, ubuf++);
	if (ret)
		goto out;
	read++;
	cnt--;

	if (!(iter->flags & ~FTRACE_ITER_CONT)) {
		/* skip white space */
		while (cnt && isspace(ch)) {
			ret = get_user(ch, ubuf++);
			if (ret)
				goto out;
			read++;
			cnt--;
		}


		if (isspace(ch)) {
			file->f_pos += read;
			ret = read;
			goto out;
		}

		iter->buffer_idx = 0;
	}

	while (cnt && !isspace(ch)) {
		if (iter->buffer_idx < FTRACE_BUFF_MAX)
			iter->buffer[iter->buffer_idx++] = ch;
		else {
			ret = -EINVAL;
			goto out;
		}
		ret = get_user(ch, ubuf++);
		if (ret)
			goto out;
		read++;
		cnt--;
	}

	if (isspace(ch)) {
		iter->filtered++;
		iter->buffer[iter->buffer_idx] = 0;
		ftrace_match(iter->buffer, iter->buffer_idx);
		iter->buffer_idx = 0;
	} else
		iter->flags |= FTRACE_ITER_CONT;


	file->f_pos += read;

	ret = read;
 out:
	mutex_unlock(&ftrace_filter_lock);

	return ret;
}

static int notrace
ftrace_filter_release(struct inode *inode, struct file *file)
{
	struct seq_file *m = (struct seq_file *)file->private_data;
	struct ftrace_iterator *iter;

	mutex_lock(&ftrace_filter_lock);
	if (file->f_mode & FMODE_READ) {
		iter = m->private;

		seq_release(inode, file);
	} else
		iter = file->private_data;

	if (iter->buffer_idx) {
		iter->filtered++;
		iter->buffer[iter->buffer_idx] = 0;
		ftrace_match(iter->buffer, iter->buffer_idx);
	}

	mutex_lock(&ftrace_sysctl_lock);
	mutex_lock(&ftraced_lock);
	if (iter->filtered && ftraced_suspend && ftrace_enabled)
		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
	mutex_unlock(&ftraced_lock);
	mutex_unlock(&ftrace_sysctl_lock);

	kfree(iter);
	mutex_unlock(&ftrace_filter_lock);
	return 0;
}

static struct file_operations ftrace_avail_fops = {
	.open = ftrace_avail_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = ftrace_avail_release,
};

static struct file_operations ftrace_filter_fops = {
	.open = ftrace_filter_open,
	.read = ftrace_filter_read,
	.write = ftrace_filter_write,
	.llseek = ftrace_filter_lseek,
	.release = ftrace_filter_release,
};

/**
 * ftrace_force_update - force an update to all recording ftrace functions
 *
 * The ftrace dynamic update daemon only wakes up once a second.
 * There may be cases where an update needs to be done immediately
 * for tests or internal kernel tracing to begin. This function
 * wakes the daemon to do an update and will not return until the
 * update is complete.
 */
int ftrace_force_update(void)
{
	unsigned long last_counter;
	DECLARE_WAITQUEUE(wait, current);
	int ret = 0;

	if (!ftraced_task)
		return -ENODEV;

	mutex_lock(&ftraced_lock);
	last_counter = ftraced_iteration_counter;

	set_current_state(TASK_INTERRUPTIBLE);
	add_wait_queue(&ftraced_waiters, &wait);

	do {
		mutex_unlock(&ftraced_lock);
		wake_up_process(ftraced_task);
		schedule();
		mutex_lock(&ftraced_lock);
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}
		set_current_state(TASK_INTERRUPTIBLE);
	} while (last_counter == ftraced_iteration_counter);

	mutex_unlock(&ftraced_lock);
	remove_wait_queue(&ftraced_waiters, &wait);
	set_current_state(TASK_RUNNING);

	return ret;
}

static __init int ftrace_init_debugfs(void)
{
	struct dentry *d_tracer;
	struct dentry *entry;

	d_tracer = tracing_init_dentry();

	entry = debugfs_create_file("available_filter_functions", 0444,
				    d_tracer, NULL, &ftrace_avail_fops);
	if (!entry)
		pr_warning("Could not create debugfs "
			   "'available_filter_functions' entry\n");

	entry = debugfs_create_file("set_ftrace_filter", 0644, d_tracer,
				    NULL, &ftrace_filter_fops);
	if (!entry)
		pr_warning("Could not create debugfs "
			   "'set_ftrace_filter' entry\n");
	return 0;
}

fs_initcall(ftrace_init_debugfs);

static int __init notrace ftrace_dynamic_init(void)
{
	struct task_struct *p;
	unsigned long addr;
	int ret;

	addr = (unsigned long)ftrace_record_ip;
	stop_machine_run(ftrace_dyn_arch_init, &addr, NR_CPUS);

	/* ftrace_dyn_arch_init places the return code in addr */
	if (addr)
		return addr;

	ret = ftrace_dyn_table_alloc();
	if (ret)
		return ret;

	p = kthread_run(ftraced, NULL, "ftraced");
	if (IS_ERR(p))
		return -1;

	last_ftrace_enabled = ftrace_enabled = 1;
	ftraced_task = p;

	return 0;
}

core_initcall(ftrace_dynamic_init);
#else
# define ftrace_startup()		do { } while (0)
# define ftrace_shutdown()		do { } while (0)
# define ftrace_startup_sysctl()	do { } while (0)
# define ftrace_shutdown_sysctl()	do { } while (0)
#endif /* CONFIG_DYNAMIC_FTRACE */

/**
 * register_ftrace_function - register a function for profiling
 * @ops - ops structure that holds the function for profiling.
 *
 * Register a function to be called by all functions in the
 * kernel.
 *
 * Note: @ops->func and all the functions it calls must be labeled
 *       with "notrace", otherwise it will go into a
 *       recursive loop.
 */
int register_ftrace_function(struct ftrace_ops *ops)
{
	int ret;

	mutex_lock(&ftrace_sysctl_lock);
	ret = __register_ftrace_function(ops);
	ftrace_startup();
	mutex_unlock(&ftrace_sysctl_lock);

	return ret;
}

/**
 * unregister_ftrace_function - unresgister a function for profiling.
 * @ops - ops structure that holds the function to unregister
 *
 * Unregister a function that was added to be called by ftrace profiling.
 */
int unregister_ftrace_function(struct ftrace_ops *ops)
{
	int ret;

	mutex_lock(&ftrace_sysctl_lock);
	ret = __unregister_ftrace_function(ops);
	ftrace_shutdown();
	mutex_unlock(&ftrace_sysctl_lock);

	return ret;
}

notrace int
ftrace_enable_sysctl(struct ctl_table *table, int write,
		     struct file *file, void __user *buffer, size_t *lenp,
		     loff_t *ppos)
{
	int ret;

	mutex_lock(&ftrace_sysctl_lock);

	ret  = proc_dointvec(table, write, file, buffer, lenp, ppos);

	if (ret || !write || (last_ftrace_enabled == ftrace_enabled))
		goto out;

	last_ftrace_enabled = ftrace_enabled;

	if (ftrace_enabled) {

		ftrace_startup_sysctl();

		/* we are starting ftrace again */
		if (ftrace_list != &ftrace_list_end) {
			if (ftrace_list->next == &ftrace_list_end)
				ftrace_trace_function = ftrace_list->func;
			else
				ftrace_trace_function = ftrace_list_func;
		}

	} else {
		/* stopping ftrace calls (just send to ftrace_stub) */
		ftrace_trace_function = ftrace_stub;

		ftrace_shutdown_sysctl();
	}

 out:
	mutex_unlock(&ftrace_sysctl_lock);
	return ret;
}