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
|
/*
* Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
*
*/
#include <linux/stacktrace.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/uaccess.h>
#include <linux/debugfs.h>
#include <linux/ftrace.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <asm/setup.h>
#include "trace.h"
#define STACK_TRACE_ENTRIES 500
#ifdef CC_USING_FENTRY
# define fentry 1
#else
# define fentry 0
#endif
static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
{ [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
/*
* Reserve one entry for the passed in ip. This will allow
* us to remove most or all of the stack size overhead
* added by the stack tracer itself.
*/
static struct stack_trace max_stack_trace = {
.max_entries = STACK_TRACE_ENTRIES - 1,
.entries = &stack_dump_trace[1],
};
static unsigned long max_stack_size;
static arch_spinlock_t max_stack_lock =
(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
static DEFINE_PER_CPU(int, trace_active);
static DEFINE_MUTEX(stack_sysctl_mutex);
int stack_tracer_enabled;
static int last_stack_tracer_enabled;
static inline void
check_stack(unsigned long ip, unsigned long *stack)
{
unsigned long this_size, flags;
unsigned long *p, *top, *start;
static int tracer_frame;
int frame_size = ACCESS_ONCE(tracer_frame);
int i;
this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
this_size = THREAD_SIZE - this_size;
/* Remove the frame of the tracer */
this_size -= frame_size;
if (this_size <= max_stack_size)
return;
/* we do not handle interrupt stacks yet */
if (!object_is_on_stack(stack))
return;
local_irq_save(flags);
arch_spin_lock(&max_stack_lock);
/* In case another CPU set the tracer_frame on us */
if (unlikely(!frame_size))
this_size -= tracer_frame;
/* a race could have already updated it */
if (this_size <= max_stack_size)
goto out;
max_stack_size = this_size;
max_stack_trace.nr_entries = 0;
max_stack_trace.skip = 3;
save_stack_trace(&max_stack_trace);
/*
* Add the passed in ip from the function tracer.
* Searching for this on the stack will skip over
* most of the overhead from the stack tracer itself.
*/
stack_dump_trace[0] = ip;
max_stack_trace.nr_entries++;
/*
* Now find where in the stack these are.
*/
i = 0;
start = stack;
top = (unsigned long *)
(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
/*
* Loop through all the entries. One of the entries may
* for some reason be missed on the stack, so we may
* have to account for them. If they are all there, this
* loop will only happen once. This code only takes place
* on a new max, so it is far from a fast path.
*/
while (i < max_stack_trace.nr_entries) {
int found = 0;
stack_dump_index[i] = this_size;
p = start;
for (; p < top && i < max_stack_trace.nr_entries; p++) {
if (*p == stack_dump_trace[i]) {
this_size = stack_dump_index[i++] =
(top - p) * sizeof(unsigned long);
found = 1;
/* Start the search from here */
start = p + 1;
/*
* We do not want to show the overhead
* of the stack tracer stack in the
* max stack. If we haven't figured
* out what that is, then figure it out
* now.
*/
if (unlikely(!tracer_frame) && i == 1) {
tracer_frame = (p - stack) *
sizeof(unsigned long);
max_stack_size -= tracer_frame;
}
}
}
if (!found)
i++;
}
out:
arch_spin_unlock(&max_stack_lock);
local_irq_restore(flags);
}
static void
stack_trace_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
{
unsigned long stack;
int cpu;
preempt_disable_notrace();
cpu = raw_smp_processor_id();
/* no atomic needed, we only modify this variable by this cpu */
if (per_cpu(trace_active, cpu)++ != 0)
goto out;
/*
* When fentry is used, the traced function does not get
* its stack frame set up, and we lose the parent.
* The ip is pretty useless because the function tracer
* was called before that function set up its stack frame.
* In this case, we use the parent ip.
*
* By adding the return address of either the parent ip
* or the current ip we can disregard most of the stack usage
* caused by the stack tracer itself.
*
* The function tracer always reports the address of where the
* mcount call was, but the stack will hold the return address.
*/
if (fentry)
ip = parent_ip;
else
ip += MCOUNT_INSN_SIZE;
check_stack(ip, &stack);
out:
per_cpu(trace_active, cpu)--;
/* prevent recursion in schedule */
preempt_enable_notrace();
}
static struct ftrace_ops trace_ops __read_mostly =
{
.func = stack_trace_call,
.flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
static ssize_t
stack_max_size_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
unsigned long *ptr = filp->private_data;
char buf[64];
int r;
r = snprintf(buf, sizeof(buf), "%ld\n", *ptr);
if (r > sizeof(buf))
r = sizeof(buf);
return simple_read_from_buffer(ubuf, count, ppos, buf, r);
}
static ssize_t
stack_max_size_write(struct file *filp, const char __user *ubuf,
size_t count, loff_t *ppos)
{
long *ptr = filp->private_data;
unsigned long val, flags;
int ret;
int cpu;
ret = kstrtoul_from_user(ubuf, count, 10, &val);
if (ret)
return ret;
local_irq_save(flags);
/*
* In case we trace inside arch_spin_lock() or after (NMI),
* we will cause circular lock, so we also need to increase
* the percpu trace_active here.
*/
cpu = smp_processor_id();
per_cpu(trace_active, cpu)++;
arch_spin_lock(&max_stack_lock);
*ptr = val;
arch_spin_unlock(&max_stack_lock);
per_cpu(trace_active, cpu)--;
local_irq_restore(flags);
return count;
}
static const struct file_operations stack_max_size_fops = {
.open = tracing_open_generic,
.read = stack_max_size_read,
.write = stack_max_size_write,
.llseek = default_llseek,
};
static void *
__next(struct seq_file *m, loff_t *pos)
{
long n = *pos - 1;
if (n >= max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX)
return NULL;
m->private = (void *)n;
return &m->private;
}
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
(*pos)++;
return __next(m, pos);
}
static void *t_start(struct seq_file *m, loff_t *pos)
{
int cpu;
local_irq_disable();
cpu = smp_processor_id();
per_cpu(trace_active, cpu)++;
arch_spin_lock(&max_stack_lock);
if (*pos == 0)
return SEQ_START_TOKEN;
return __next(m, pos);
}
static void t_stop(struct seq_file *m, void *p)
{
int cpu;
arch_spin_unlock(&max_stack_lock);
cpu = smp_processor_id();
per_cpu(trace_active, cpu)--;
local_irq_enable();
}
static int trace_lookup_stack(struct seq_file *m, long i)
{
unsigned long addr = stack_dump_trace[
|