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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Infrastructure to took into function calls and returns.
* Copyright (c) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com>
* Mostly borrowed from function tracer which
* is Copyright (c) Steven Rostedt <srostedt@redhat.com>
*
* Highly modified by Steven Rostedt (VMware).
*/
#include <linux/bits.h>
#include <linux/jump_label.h>
#include <linux/suspend.h>
#include <linux/ftrace.h>
#include <linux/slab.h>
#include <trace/events/sched.h>
#include "ftrace_internal.h"
#include "trace.h"
/*
* FGRAPH_FRAME_SIZE: Size in bytes of the meta data on the shadow stack
* FGRAPH_FRAME_OFFSET: Size in long words of the meta data frame
*/
#define FGRAPH_FRAME_SIZE sizeof(struct ftrace_ret_stack)
#define FGRAPH_FRAME_OFFSET DIV_ROUND_UP(FGRAPH_FRAME_SIZE, sizeof(long))
/*
* On entry to a function (via function_graph_enter()), a new fgraph frame
* (ftrace_ret_stack) is pushed onto the stack as well as a word that
* holds a bitmask and a type (called "bitmap"). The bitmap is defined as:
*
* bits: 0 - 9 offset in words from the previous ftrace_ret_stack
* Currently, this will always be set to FGRAPH_FRAME_OFFSET
* to get to the fgraph frame.
*
* bits: 10 - 11 Type of storage
* 0 - reserved
* 1 - bitmap of fgraph_array index
*
* For type with "bitmap of fgraph_array index" (FGRAPH_TYPE_BITMAP):
* bits: 12 - 27 The bitmap of fgraph_ops fgraph_array index
* That is, it's a bitmask of 0-15 (16 bits)
* where if a corresponding ops in the fgraph_array[]
* expects a callback from the return of the function
* it's corresponding bit will be set.
*
*
* The top of the ret_stack (when not empty) will always have a reference
* word that points to the last fgraph frame that was saved.
*
* That is, at the end of function_graph_enter, if the first and forth
* fgraph_ops on the fgraph_array[] (index 0 and 3) needs their retfunc called
* on the return of the function being traced, this is what will be on the
* task's shadow ret_stack: (the stack grows upward)
*
* ret_stack[SHADOW_STACK_MAX_OFFSET]
* ...
* | | <- task->curr_ret_stack
* +--------------------------------------------+
* | (9 << 12) | (1 << 10) | FGRAPH_FRAME_OFFSET|
* | *or put another way* |
* | (BIT(3)|BIT(0)) << FGRAPH_INDEX_SHIFT | \ |
* | FGRAPH_TYPE_BITMAP << FGRAPH_TYPE_SHIFT| \ |
* | (offset:FGRAPH_FRAME_OFFSET) | <- the offset is from here
* +--------------------------------------------+
* | struct ftrace_ret_stack |
* | (stores the saved ret pointer) | <- the offset points here
* +--------------------------------------------+
* | (X) | (N) | ( N words away from
* | | previous ret_stack)
* ...
* ret_stack[0]
*
* If a backtrace is required, and the real return pointer needs to be
* fetched, then it looks at the task's curr_ret_stack offset, if it
* is greater than zero (reserved, or right before popped), it would mask
* the value by FGRAPH_FRAME_OFFSET_MASK to get the offset of the
* ftrace_ret_stack structure stored on the shadow stack.
*/
/*
* The following is for the top word on the stack:
*
* FGRAPH_FRAME_OFFSET (0-9) holds the offset delta to the fgraph frame
* FGRAPH_TYPE (10-11) holds the type of word this is.
* (RESERVED or BITMAP)
*/
#define FGRAPH_FRAME_OFFSET_BITS 10
#define FGRAPH_FRAME_OFFSET_MASK GENMASK(FGRAPH_FRAME_OFFSET_BITS - 1, 0)
#define FGRAPH_TYPE_BITS 2
#define FGRAPH_TYPE_MASK GENMASK(FGRAPH_TYPE_BITS - 1, 0)
#define FGRAPH_TYPE_SHIFT FGRAPH_FRAME_OFFSET_BITS
enum {
FGRAPH_TYPE_RESERVED = 0,
FGRAPH_TYPE_BITMAP = 1,
};
/*
* For BITMAP type:
* FGRAPH_INDEX (12-27) bits holding the gops index wanting return callback called
*/
#define FGRAPH_INDEX_BITS 16
#define FGRAPH_INDEX_MASK GENMASK(FGRAPH_INDEX_BITS - 1, 0)
#define FGRAPH_INDEX_SHIFT (FGRAPH_TYPE_SHIFT + FGRAPH_TYPE_BITS)
#define FGRAPH_ARRAY_SIZE FGRAPH_INDEX_BITS
/*
* SHADOW_STACK_SIZE: The size in bytes of the entire shadow stack
* SHADOW_STACK_OFFSET: The size in long words of the shadow stack
* SHADOW_STACK_MAX_OFFSET: The max offset of the stack for a new frame to be added
*/
#define SHADOW_STACK_SIZE (PAGE_SIZE)
#define SHADOW_STACK_OFFSET (SHADOW_STACK_SIZE / sizeof(long))
/* Leave on a buffer at the end */
#define SHADOW_STACK_MAX_OFFSET (SHADOW_STACK_OFFSET - (FGRAPH_FRAME_OFFSET + 1))
/* RET_STACK(): Return the frame from a given @offset from task @t */
#define RET_STACK(t, offset) ((struct ftrace_ret_stack *)(&(t)->ret_stack[offset]))
DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
int ftrace_graph_active;
static int fgraph_array_cnt;
static struct fgraph_ops *fgraph_array[FGRAPH_ARRAY_SIZE];
/* Get the FRAME_OFFSET from the word from the @offset on ret_stack */
static inline int get_frame_offset(struct task_struct *t, int offset)
{
return t->ret_stack[offset] & FGRAPH_FRAME_OFFSET_MASK;
}
/* Get FGRAPH_TYPE from the word from the @offset at ret_stack */
static inline int get_fgraph_type(struct task_struct *t, int offset)
{
return (t->ret_stack[offset] >> FGRAPH_TYPE_SHIFT) & FGRAPH_TYPE_MASK;
}
/* For BITMAP type: get the bitmask from the @offset at ret_stack */
static inline unsigned long
get_bitmap_bits(struct task_struct *t, int offset)
{
return (t->ret_stack[offset] >> FGRAPH_INDEX_SHIFT) & FGRAPH_INDEX_MASK;
}
/* For BITMAP type: set the bits in the bitmap bitmask at @offset on ret_stack */
static inline void
set_bitmap_bits(struct task_struct *t, int offset, unsigned long bitmap)
{
t->ret_stack[offset] |= (bitmap << FGRAPH_INDEX_SHIFT);
}
/* Write the bitmap to the ret_stack at @offset (does index, offset and bitmask) */
static inline void
set_bitmap(struct task_struct *t, int offset, unsigned long bitmap)
{
t->ret_stack[offset] = (bitmap << FGRAPH_INDEX_SHIFT) |
(FGRAPH_TYPE_BITMAP << FGRAPH_TYPE_SHIFT) | FGRAPH_FRAME_OFFSET;
}
/* ftrace_graph_entry set to this to tell some archs to run function graph */
static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops)
{
return 0;
}
/* ftrace_graph_return set to this to tell some archs to run function graph */
static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops)
{
}
/*
* @offset: The offset into @t->ret_stack to find the ret_stack entry
* @frame_offset: Where to place the offset into @t->ret_stack of that entry
*
* Returns a pointer to the previous ret_stack below @offset or NULL
* when it reaches the bottom of the stack.
*
* Calling this with:
*
* offset = task->curr_ret_stack;
* do {
* ret_stack = get_ret_stack(task, offset, &offset);
* } while (ret_stack);
*
* Will iterate through all the ret_stack entries from curr_ret_stack
* down to the first one.
*/
static inline struct ftrace_ret_stack *
get_ret_stack(struct task_struct *t, int offset, int *frame_offset)
{
int offs;
BUILD_BUG_ON(FGRAPH_FRAME_SIZE % sizeof(long));
if (unlikely(offset <= 0))
return NULL;
offs = get_frame_offset(t, --offset);
if (WARN_ON_ONCE(offs <= 0 || offs > offset))
return NULL;
offset -= offs;
*frame_offset = offset;
return RET_STACK(t, offset);
}
/* Both enabled by default (can be cleared by function_graph tracer flags */
static bool fgraph_sleep_time = true;
#ifdef CONFIG_DYNAMIC_FTRACE
/*
* archs can override this function if they must do something
* to enable hook for graph tracer.
*/
int __weak ftrace_enable_ftrace_graph_caller(void)
{
return 0;
}
/*
* archs can override this function if they must do something
* to disable hook for graph tracer.
*/
int __weak ftrace_disable_ftrace_graph_caller(void)
{
return 0;
}
#endif
int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
struct fgraph_ops *gops)
{
return 0;
}
static void ftrace_graph_ret_stub(struct ftrace_graph_ret *trace,
struct fgraph_ops *gops)
{
}
static struct fgraph_ops fgraph_stub = {
.entryfunc = ftrace_graph_entry_stub,
.retfunc = ftrace_graph_ret_stub,
};
/**
* ftrace_graph_stop - set to permanently disable function graph tracing
*
* In case of an error int function graph tracing, this is called
* to try to keep function graph tracing from causing any more harm.
* Usually this is pretty severe and this is called to try to at least
* get a warning out to the user.
*/
void ftrace_graph_stop(void)
{
static_branch_enable(&kill_ftrace_graph);
}
/* Add a function return address to the trace stack on thread info.*/
static int
ftrace_push_return_trace(unsigned long ret, unsigned long func,
unsigned long frame_pointer, unsigned long *retp,
int fgraph_idx)
{
struct ftrace_ret_stack *ret_stack;
unsigned long long calltime;
unsigned long val;
int offset;
if (unlikely(ftrace_graph_is_dead()))
return -EBUSY;
if (!current->ret_stack)
return -EBUSY;
BUILD_BUG_ON(SHADOW_STACK_SIZE % sizeof(long));
/* Set val to "reserved" with the delta to the new fgraph frame */
val = (FGRAPH_TYPE_RESERVED << FGRAPH_TYPE_SHIFT) | FGRAPH_FRAME_OFFSET;
/*
* We must make sure the ret_stack is tested before we read
* anything else.
*/
smp_rmb();
/*
* Check if there's room on the shadow stack to fit a fraph frame
* and a bitmap word.
*/
if (current->curr_ret_stack + FGRAPH_FRAME_OFFSET + 1 >= SHADOW_STACK_MAX_OFFSET) {
atomic_inc(¤t->trace_overrun);
return -EBUSY;
}
calltime = trace_clock_local();
offset = READ_ONCE(current->curr_ret_stack);
ret_stack = RET_STACK(current, offset);
offset += FGRAPH_FRAME_OFFSET;
/* ret offset = FGRAPH_FRAME_OFFSET ; type = reserved */
current->ret_stack[offset] = val;
ret_stack->ret = ret;
/*
* The unwinders expect curr_ret_stack to point to either zero
* or an offset where to find the next ret_stack. Even though the
* ret stack might be bogus, we want to write the ret and the
* offset to find the ret_stack before we increment the stack point.
* If an interrupt comes in now before we increment the curr_ret_stack
* it may blow away what we wrote. But that's fine, because the
* offset will still be correct (even though the 'ret' won't be).
* What we worry about is the offset being correct after we increment
* the curr_ret_stack and before we update that offset, as if an
* interrupt comes in and does an unwind stack dump, it will need
* at least a correct offset!
*/
barrier();
WRITE_ONCE(current->curr_ret_stack, offset + 1);
/*
* This next barrier is to ensure that an interrupt coming in
* will not corrupt what we are about to write.
*/
barrier();
/* Still keep it reserved even if an interrupt came in */
current->ret_stack[offset] = val;
ret_stack->ret = ret;
ret_stack->func = func;
ret_stack->calltime = calltime;
#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
ret_stack->fp = frame_pointer;
#endif
#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
ret_stack->retp = retp;
#endif
return offset;
}
/*
* Not all archs define MCOUNT_INSN_SIZE which is used to look for direct
* functions. But those archs currently don't support direct functions
* anyway, and ftrace_find_rec_direct() is just a stub for them.
* Define MCOUNT_INSN_SIZE to keep those archs compiling.
*/
#ifndef MCOUNT_INSN_SIZE
/* Make sure this only works without direct calls */
# ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
# error MCOUNT_INSN_SIZE not defined with direct calls enabled
# endif
# define MCOUNT_INSN_SIZE 0
#endif
/* If the caller does not use ftrace, call this function. */
int function_graph_enter(unsigned long ret, unsigned long func,
unsigned long frame_pointer, unsigned long *retp)
{
struct ftrace_graph_ent trace;
unsigned long bitmap = 0;
int offset;
int i;
trace.func = func;
trace.depth = ++current->curr_ret_depth;
offset = ftrace_push_return_trace(ret, func, frame_pointer, retp, 0);
if (offset < 0)
goto out;
for (i = 0; i < fgraph_array_cnt; i++) {
struct fgraph_ops *gops = fgraph_array[i];
if (gops == &fgraph_stub)
continue;
if (ftrace_ops_test(&gops->ops, func, NULL) &&
gops->entryfunc(&trace, gops))
bitmap |= BIT(i);
}
if (!bitmap)
goto out_ret;
/*
* Since this function uses fgraph_idx = 0 as a tail-call checking
* flag, set that bit always.
*/
set_bitmap(current, offset, bitmap | BIT(0));
return 0;
out_ret:
current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1;
out:
current->curr_ret_depth--;
return -EBUSY;
}
/* Retrieve a function return address to the trace stack on thread info.*/
static struct ftrace_ret_stack *
ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
unsigned long frame_pointer, int *offset)
{
struct ftrace_ret_stack *ret_stack;
ret_stack = get_ret_stack(current, current->curr_ret_stack, offset);
if (unlikely(!ret_stack)) {
ftrace_graph_stop();
WARN(1, "Bad function graph ret_stack pointer: %d",
current->curr_ret_stack);
/* Might as well panic, otherwise we have no where to go */
*ret = (unsigned long)panic;
return NULL;
}
#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
/*
* The arch may choose to record the frame pointer used
* and check it here to make sure that it is what we expect it
* to be. If gcc does not set the place holder of the return
* address in the frame pointer, and does a copy instead, then
* the function graph trace will fail. This test detects this
* case.
*
* Currently, x86_32 with optimize for size (-Os) makes the latest
* gcc do the above.
*
* Note, -mfentry does not use frame pointers, and this test
* is not needed if CC_USING_FENTRY is set.
*/
if (unlikely(ret_stack->fp != frame_pointer)) {
ftrace_graph_stop();
WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
" from func %ps return to %lx\n",
ret_stack->fp,
frame_pointer,
(void *)ret_stack->func,
ret_stack->ret);
*ret = (unsigned long)panic;
return NULL;
}
#endif
*offset += FGRAPH_FRAME_OFFSET;
*ret = ret_stack->ret;
trace->func = ret_stack->func;
trace->calltime = ret_stack->calltime;
trace->overrun = atomic_read(¤t->trace_overrun);
trace->depth = current->curr_ret_depth;
/*
* We still want to trace interrupts coming in if
* max_depth is set to 1. Make sure the decrement is
* seen before ftrace_graph_return.
*/
barrier();
return ret_stack;
}
/*
* Hibernation protection.
* The state of the current task is too much unstable during
* suspend/restore to disk. We want to protect against that.
*/
static int
ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
void *unused)
{
switch (state) {
case PM_HIBERNATION_PREPARE:
pause_graph_tracing();
break;
case PM_POST_HIBERNATION:
unpause_graph_tracing();
break;
}
return NOTIFY_DONE;
}
static struct notifier_block ftrace_suspend_notifier = {
.notifier_call = ftrace_suspend_notifier_call,
};
/* fgraph_ret_regs is not defined without CONFIG_FUNCTION_GRAPH_RETVAL */
struct fgraph_ret_regs;
/*
* Send the trace to the ring-buffer.
* @return the original return address.
*/
static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs,
unsigned long frame_pointer)
{
struct ftrace_ret_stack *ret_stack;
struct ftrace_graph_ret trace;
unsigned long bitmap;
unsigned long ret;
int offset;
int i;
ret_stack = ftrace_pop_return_trace(&trace, &ret, frame_pointer, &offset);
if (unlikely(!ret_stack)) {
ftrace_graph_stop();
WARN_ON(1);
/* Might as well panic. What else to do? */
return (unsigned long)panic;
}
trace.rettime = trace_clock_local();
#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
trace.retval = fgraph_ret_regs_return_value(ret_regs);
#endif
bitmap = get_bitmap_bits(current, offset);
for (i = 0; i < FGRAPH_ARRAY_SIZE; i++) {
struct fgraph_ops *gops = fgraph_array[i];
if (!(bitmap & BIT(i)))
continue;
if (gops == &fgraph_stub)
continue;
gops->retfunc(&trace, gops);
}
/*
* The ftrace_graph_return() may still access the current
* ret_stack structure, we need to make sure the update of
* curr_ret_stack is after that.
*/
barrier();
current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1;
current->curr_ret_depth--;
return ret;
}
/*
* After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can
* leave only ftrace_return_to_handler(ret_regs).
*/
#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs)
{
return __ftrace_return_to_handler(ret_regs,
fgraph_ret_regs_frame_pointer(ret_regs));
}
#else
unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
{
return __ftrace_return_to_handler(NULL, frame_pointer);
}
#endif
/**
* ftrace_graph_get_ret_stack - return the entry of the shadow stack
* @task: The task to read the shadow stack from.
* @idx: Index down the shadow stack
*
* Return the ret_struct on the shadow stack of the @task at the
* call graph at @idx starting with zero. If @idx is zero, it
* will return the last saved ret_stack entry. If it is greater than
* zero, it will return the corresponding ret_stack for the depth
* of saved return addresses.
*/
struct ftrace_ret_stack *
ftrace_graph_get_ret_stack(struct task_struct *task, int idx)
{
struct ftrace_ret_stack *ret_stack = NULL;
int offset = task->curr_ret_stack;
if (offset < 0)
return NULL;
do {
ret_stack = get_ret_stack(task, offset, &offset);
} while (ret_stack && --idx >= 0);
return ret_stack;
}
/**
* ftrace_graph_ret_addr - convert a potentially modified stack return address
* to its original value
*
* This function can be called by stack unwinding code to convert a found stack
* return address ('ret') to its original value, in case the function graph
* tracer has modified it to be 'return_to_handler'. If the address hasn't
* been modified, the unchanged value of 'ret' is returned.
*
* 'idx' is a state variable which should be initialized by the caller to zero
* before the first call.
*
* 'retp' is a pointer to the return address on the stack. It's ignored if
* the arch doesn't have HAVE_FUNCTION_GRAPH_RET_ADDR_PTR defined.
*/
#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
unsigned long ret, unsigned long *retp)
{
struct ftrace_ret_stack *ret_stack;
unsigned long return_handler = (unsigned long)dereference_kernel_function_descriptor(return_to_handler);
int i = task->curr_ret_stack;
if (ret != return_handler)
return ret;
while (i > 0) {
ret_stack = get_ret_stack(current, i, &i);
if (!ret_stack)
break;
/*
* For the tail-call, there would be 2 or more ftrace_ret_stacks on
* the ret_stack, which records "return_to_handler" as the return
* address except for the last one.
* But on the real stack, there should be 1 entry because tail-call
* reuses the return address on the stack and jump to the next function.
* Thus we will continue to find real return address.
*/
if (ret_stack->retp == retp &&
ret_stack->ret != return_handler)
return ret_stack->ret;
}
return ret;
}
#else /* !HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
unsigned long ret, unsigned long *retp)
{
struct ftrace_ret_stack *ret_stack;
unsigned long return_handler = (unsigned long)dereference_kernel_function_descriptor(return_to_handler);
int offset = task->curr_ret_stack;
int i;
if (ret != return_handler)
return ret;
if (!idx)
return ret;
i = *idx;
do {
ret_stack = get_ret_stack(task, offset, &offset);
if (ret_stack && ret_stack->ret == return_handler)
continue;
i--;
} while (i >= 0 && ret_stack);
if (ret_stack)
return ret_stack->ret;
return ret;
}
#endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
static struct ftrace_ops graph_ops = {
.func = ftrace_graph_func,
.flags = FTRACE_OPS_GRAPH_STUB,
#ifdef FTRACE_GRAPH_TRAMP_ADDR
.trampoline = FTRACE_GRAPH_TRAMP_ADDR,
/* trampoline_size is only needed for dynamically allocated tramps */
#endif
};
void fgraph_init_ops(struct ftrace_ops *dst_ops,
struct ftrace_ops *src_ops)
{
dst_ops->flags = FTRACE_OPS_FL_PID | FTRACE_OPS_GRAPH_STUB;
#ifdef CONFIG_DYNAMIC_FTRACE
if (src_ops) {
dst_ops->func_hash = &src_ops->local_hash;
mutex_init(&dst_ops->local_hash.regex_lock);
INIT_LIST_HEAD(&dst_ops->subop_list);
dst_ops->flags |= FTRACE_OPS_FL_INITIALIZED;
}
#endif
}
void ftrace_graph_sleep_time_control(bool enable)
{
fgraph_sleep_time = enable;
}
/*
* Simply points to ftrace_stub, but with the proper protocol.
* Defined by the linker script in linux/vmlinux.lds.h
*/
void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops);
/* The callbacks that hook a function */
trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph;
trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
static int alloc_retstack_tasklist(unsigned long **ret_stack_list)
{
int i;
int ret = 0;
int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
struct task_struct *g, *t;
for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) {
ret_stack_list[i] = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
if (!ret_stack_list[i]) {
start = 0;
end = i;
ret = -ENOMEM;
goto free;
}
}
rcu_read_lock();
for_each_process_thread(g, t) {
if (start == end) {
ret = -EAGAIN;
goto unlock;
}
if (t->ret_stack == NULL) {
atomic_set(&t->trace_overrun, 0);
t->curr_ret_stack = 0;
t->curr_ret_depth = -1;
/* Make sure the tasks see the 0 first: */
smp_wmb();
t->ret_stack = ret_stack_list[start++];
}
}
unlock:
rcu_read_unlock();
free:
for (i = start; i < end; i++)
kfree(ret_stack_list[i]);
return ret;
}
static void
ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
struct task_struct *prev,
struct task_struct *next,
unsigned int prev_state)
{
struct ftrace_ret_stack *ret_stack;
unsigned long long timestamp;
int offset;
/*
* Does the user want to count the time a function was asleep.
* If so, do not update the time stamps.
*/
if (fgraph_sleep_time)
return;
timestamp = trace_clock_local();
prev->ftrace_timestamp = timestamp;
/* only process tasks that we timestamped */
if (!next->ftrace_timestamp)
return;
/*
* Update all the counters in next to make up for the
* time next was sleeping.
*/
timestamp -= next->ftrace_timestamp;
for (offset = next->curr_ret_stack; offset > 0; ) {
ret_stack = get_ret_stack(next, offset, &offset);
if (ret_stack)
ret_stack->calltime += timestamp;
}
}
static DEFINE_PER_CPU(unsigned long *, idle_ret_stack);
static void
graph_init_task(struct task_struct *t, unsigned long *ret_stack)
{
atomic_set(&t->trace_overrun, 0);
t->ftrace_timestamp = 0;
t->curr_ret_stack = 0;
t->curr_ret_depth = -1;
/* make curr_ret_stack visible before we add the ret_stack */
smp_wmb();
t->ret_stack = ret_stack;
}
/*
* Allocate a return stack for the idle task. May be the first
* time through, or it may be done by CPU hotplug online.
*/
void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
{
t->curr_ret_stack = 0;
t->curr_ret_depth = -1;
/*
* The idle task has no parent, it either has its own
* stack or no stack at all.
*/
if (t->ret_stack)
WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu));
if (ftrace_graph_active) {
unsigned long *ret_stack;
ret_stack = per_cpu(idle_ret_stack, cpu);
if (!ret_stack) {
ret_stack = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
if (!ret_stack)
return;
per_cpu(idle_ret_stack, cpu) = ret_stack;
}
graph_init_task(t, ret_stack);
}
}
/* Allocate a return stack for newly created task */
void ftrace_graph_init_task(struct task_struct *t)
{
/* Make sure we do not use the parent ret_stack */
t->ret_stack = NULL;
t->curr_ret_stack = 0;
t->curr_ret_depth = -1;
if (ftrace_graph_active) {
unsigned long *ret_stack;
ret_stack = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
if (!ret_stack)
return;
graph_init_task(t, ret_stack);
}
}
void ftrace_graph_exit_task(struct task_struct *t)
{
unsigned long *ret_stack = t->ret_stack;
t->ret_stack = NULL;
/* NULL must become visible to IRQs before we free it: */
barrier();
kfree(ret_stack);
}
/* Allocate a return stack for each task */
static int start_graph_tracing(void)
{
unsigned long **ret_stack_list;
int ret, cpu;
ret_stack_list = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
if (!ret_stack_list)
return -ENOMEM;
/* The cpu_boot init_task->ret_stack will never be freed */
for_each_online_cpu(cpu) {
if (!idle_task(cpu)->ret_stack)
ftrace_graph_init_idle_task(idle_task(cpu), cpu);
}
do {
ret = alloc_retstack_tasklist(ret_stack_list);
} while (ret == -EAGAIN);
if (!ret) {
ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
if (ret)
pr_info("ftrace_graph: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
}
kfree(ret_stack_list);
return ret;
}
int register_ftrace_graph(struct fgraph_ops *gops)
{
int command = 0;
int ret = 0;
int i;
mutex_lock(&ftrace_lock);
if (!fgraph_array[0]) {
/* The array must always have real data on it */
for (i = 0; i < FGRAPH_ARRAY_SIZE; i++)
fgraph_array[i] = &fgraph_stub;
}
/* Look for an available spot */
for (i = 0; i < FGRAPH_ARRAY_SIZE; i++) {
if (fgraph_array[i] == &fgraph_stub)
break;
}
if (i >= FGRAPH_ARRAY_SIZE) {
ret = -ENOSPC;
goto out;
}
fgraph_array[i] = gops;
if (i + 1 > fgraph_array_cnt)
fgraph_array_cnt = i + 1;
gops->idx = i;
ftrace_graph_active++;
if (ftrace_graph_active == 1) {
register_pm_notifier(&ftrace_suspend_notifier);
ret = start_graph_tracing();
if (ret)
goto error;
/*
* Some archs just test to see if these are not
* the default function
*/
ftrace_graph_return = return_run;
ftrace_graph_entry = entry_run;
command = FTRACE_START_FUNC_RET;
}
ret = ftrace_startup_subops(&graph_ops, &gops->ops, command);
error:
if (ret) {
fgraph_array[i] = &fgraph_stub;
ftrace_graph_active--;
}
out:
mutex_unlock(&ftrace_lock);
return ret;
}
void unregister_ftrace_graph(struct fgraph_ops *gops)
{
int command = 0;
int i;
mutex_lock(&ftrace_lock);
if (unlikely(!ftrace_graph_active))
goto out;
if (unlikely(gops->idx < 0 || gops->idx >= fgraph_array_cnt))
goto out;
WARN_ON_ONCE(fgraph_array[gops->idx] != gops);
fgraph_array[gops->idx] = &fgraph_stub;
if (gops->idx + 1 == fgraph_array_cnt) {
i = gops->idx;
while (i >= 0 && fgraph_array[i] == &fgraph_stub)
i--;
fgraph_array_cnt = i + 1;
}
ftrace_graph_active--;
if (!ftrace_graph_active)
command = FTRACE_STOP_FUNC_RET;
ftrace_shutdown_subops(&graph_ops, &gops->ops, command);
if (!ftrace_graph_active) {
ftrace_graph_return = ftrace_stub_graph;
ftrace_graph_entry = ftrace_graph_entry_stub;
unregister_pm_notifier(&ftrace_suspend_notifier);
unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
}
out:
mutex_unlock(&ftrace_lock);
}
|