summaryrefslogtreecommitdiff
path: root/kernel/trace/trace_sched_wakeup.c
blob: 7547e36d483ec45ee758f7e680ba0a79bcf5b5a2 (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
/*
 * trace task wakeup timings
 *
 * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
 * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
 *
 * Based on code from the latency_tracer, that is:
 *
 *  Copyright (C) 2004-2006 Ingo Molnar
 *  Copyright (C) 2004 William Lee Irwin III
 */
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/debugfs.h>
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <trace/events/sched.h>

#include "trace.h"

static struct trace_array	*wakeup_trace;
static int __read_mostly	tracer_enabled;

static struct task_struct	*wakeup_task;
static int			wakeup_cpu;
static int			wakeup_current_cpu;
static unsigned			wakeup_prio = -1;
static int			wakeup_rt;

static arch_spinlock_t wakeup_lock =
	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;

static void wakeup_reset(struct trace_array *tr);
static void __wakeup_reset(struct trace_array *tr);
static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
static void wakeup_graph_return(struct ftrace_graph_ret *trace);

static int save_lat_flag;

#define TRACE_DISPLAY_GRAPH     1

static struct tracer_opt trace_opts[] = {
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
	/* display latency trace as call graph */
	{ TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
#endif
	{ } /* Empty entry */
};

static struct tracer_flags tracer_flags = {
	.val  = 0,
	.opts = trace_opts,
};

#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)

#ifdef CONFIG_FUNCTION_TRACER

/*
 * Prologue for the wakeup function tracers.
 *
 * Returns 1 if it is OK to continue, and preemption
 *            is disabled and data->disabled is incremented.
 *         0 if the trace is to be ignored, and preemption
 *            is not disabled and data->disabled is
 *            kept the same.
 *
 * Note, this function is also used outside this ifdef but
 *  inside the #ifdef of the function graph tracer below.
 *  This is OK, since the function graph tracer is
 *  dependent on the function tracer.
 */
static int
func_prolog_preempt_disable(struct trace_array *tr,
			    struct trace_array_cpu **data,
			    int *pc)
{
	long disabled;
	int cpu;

	if (likely(!wakeup_task))
		return 0;

	*pc = preempt_count();
	preempt_disable_notrace();

	cpu = raw_smp_processor_id();
	if (cpu != wakeup_current_cpu)
		goto out_enable;

	*data = tr->data[cpu];
	disabled = atomic_inc_return(&(*data)->disabled);
	if (unlikely(disabled != 1))
		goto out;

	return 1;

out:
	atomic_dec(&(*data)->disabled);

out_enable:
	preempt_enable_notrace();
	return 0;
}

/*
 * wakeup uses its own tracer function to keep the overhead down:
 */
static void
wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
		   struct ftrace_ops *op, struct pt_regs *pt_regs)
{
	struct trace_array *tr = wakeup_trace;
	struct trace_array_cpu *data;
	unsigned long flags;
	int pc;

	if (!func_prolog_preempt_disable(tr, &data, &pc))
		return;

	local_irq_save(flags);
	trace_function(tr, ip, parent_ip, flags, pc);
	local_irq_restore(flags);

	atomic_dec(&data->disabled);
	preempt_enable_notrace();
}

static struct ftrace_ops trace_ops __read_mostly =
{
	.func = wakeup_tracer_call,
	.flags = FTRACE_OPS_FL_GLOBAL,
};
#endif /* CONFIG_FUNCTION_TRACER */

static int start_func_tracer(int graph)
{
	int ret;

	if (!graph)
		ret = register_ftrace_function(&trace_ops);
	else
		ret = register_ftrace_graph(&wakeup_graph_return,
					    &wakeup_graph_entry);

	if (!ret && tracing_is_enabled())
		tracer_enabled = 1;
	else
		tracer_enabled = 0;

	return ret;
}

static void stop_func_tracer(int graph)
{
	tracer_enabled = 0;

	if (!graph)
		unregister_ftrace_function(&trace_ops);
	else
		unregister_ftrace_graph();
}

#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
{

	if (!(bit & TRACE_DISPLAY_GRAPH))
		return -EINVAL;

	if (!(is_graph() ^ set))
		return 0;

	stop_func_tracer(!set);

	wakeup_reset(wakeup_trace);
	tracing_max_latency = 0;

	return start_func_tracer(set);
}

static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
{
	struct trace_array *tr = wakeup_trace;
	struct trace_array_cpu *data;
	unsigned long flags;
	int pc, ret = 0;

	if (!func_prolog_preempt_disable(tr, &data, &pc))
		return 0;

	local_save_flags(flags);
	ret = __trace_graph_entry(tr, trace, flags, pc);
	atomic_dec(&data->disabled);
	preempt_enable_notrace();

	return ret;
}

static void wakeup_graph_return(struct ftrace_graph_ret *trace)
{
	struct trace_array *tr = wakeup_trace;
	struct trace_array_cpu *data;
	unsigned long flags;
	int pc;

	if (!func_prolog_preempt_disable(tr, &data, &pc))
		return;

	local_save_flags(flags);
	__trace_graph_return(tr, trace, flags, pc);
	atomic_dec(&data->disabled);

	preempt_enable_notrace();
	return;
}

static void wakeup_trace_open(struct trace_iterator *iter)
{
	if (is_graph())
		graph_trace_open(iter);
}

static void wakeup_trace_close(struct trace_iterator *iter)
{
	if (iter->private)
		graph_trace_close(iter);
}

#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC | \
			    TRACE_GRAPH_PRINT_ABS_TIME | \
			    TRACE_GRAPH_PRINT_DURATION)

static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
{
	/*
	 * In graph mode call the graph tracer output function,
	 * otherwise go with the TRACE_FN event handler
	 */
	if (is_graph())
		return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);

	return TRACE_TYPE_UNHANDLED;
}

static void wakeup_print_header(struct seq_file *s)
{
	if (is_graph())
		print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
	else
		trace_default_header(s);
}

static void
__trace_function(struct trace_array *tr,
		 unsigned long ip, unsigned long parent_ip,
		 unsigned long flags, int pc)
{
	if (is_graph())
		trace_graph_function(tr, ip, parent_ip, flags, pc);
	else
		trace_function(tr, ip, parent_ip, flags, pc);
}
#else
#define __trace_function trace_function

static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
{
	return -EINVAL;
}

static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
{
	return -1;
}

static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
{
	return TRACE_TYPE_UNHANDLED;
}

static void wakeup_graph_return(struct ftrace_graph_ret *trace) { }
static void wakeup_trace_open(struct trace_iterator *iter) { }
static void wakeup_trace_close(struct trace_iterator *iter) { }

#ifdef CONFIG_FUNCTION_TRACER
static void wakeup_print_header(struct seq_file *s)
{
	trace_default_header(s);
}
#else
static void wakeup_print_header(struct seq_file *s)
{
	trace_latency_header(s);
}
#endif /* CONFIG_FUNCTION_TRACER */
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */

/*
 * Should this new latency be reported/recorded?
 */
static int report_latency(cycle_t delta)
{
	if (tracing_thresh) {
		if (delta < tracing_thresh)
			return 0;
	} else {
		if (delta <= tracing_max_latency)
			return 0;
	}
	return 1;
}

static void
probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu)
{
	if (task != wakeup_task)
		return;

	wakeup_current_cpu = cpu;
}

static void notrace
probe_wakeup_sched_switch(void *ignore,
			  struct task_struct *prev, struct task_struct *next)
{
	struct trace_array_cpu *data;
	cycle_t T0, T1, delta;
	unsigned long flags;
	long disabled;
	int cpu;
	int pc;

	tracing_record_cmdline(prev);

	if (unlikely(!tracer_enabled))
		return;

	/*
	 * When we start a new trace, we set wakeup_task to NULL
	 * and then set tracer_enabled = 1. We want to make sure
	 * that another CPU does not see the tracer_enabled = 1
	 * and the wakeup_task with an older task, that might
	 * actually be the same as next.
	 */
	smp_rmb();

	if (next != wakeup_task)
		return;

	pc = preempt_count();

	/* disable local data, not wakeup_cpu data */
	cpu = raw_smp_processor_id();
	disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
	if (likely(disabled != 1))
		goto out;

	local_irq_save(flags);
	arch_spin_lock(&wakeup_lock);

	/* We could race with grabbing wakeup_lock */
	if (unlikely(!tracer_enabled || next != wakeup_task))
		goto out_unlock;

	/* The task we are waiting for is waking up */
	data = wakeup_trace->data[wakeup_cpu];

	__trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
	tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);

	T0 = data->preempt_timestamp;
	T1 = ftrace_now(cpu);
	delta = T1-T0;

	if (!report_latency(delta))
		goto out_unlock;

	if (likely(!is_tracing_stopped())) {
		tracing_max_latency = delta;
		update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
	}

out_unlock:
	__wakeup_reset(wakeup_trace);
	arch_spin_unlock(&wakeup_lock);
	local_irq_restore(flags);
out:
	atomic_dec(&wakeup_trace->data[cpu]->disabled);
}

static void __wakeup_reset(struct trace_array *tr)
{
	wakeup_cpu = -1;
	wakeup_prio = -1;

	if (wakeup_task)
		put_task_struct(wakeup_task);

	wakeup_task = NULL;
}

static void wakeup_reset(struct trace_array *tr)
{
	unsigned long flags;

	tracing_reset_online_cpus(tr);

	local_irq_save(flags);
	arch_spin_lock(&wakeup_lock);
	__wakeup_reset(tr);
	arch_spin_unlock(&wakeup_lock);
	local_irq_restore(flags);
}

static void
probe_wakeup(void *ignore, struct task_struct *p, int success)
{
	struct trace_array_cpu *data;
	int cpu = smp_processor_id();
	unsigned long flags;
	long disabled;
	int pc;

	if (likely(!tracer_enabled))
		return;

	tracing_record_cmdline(p);
	tracing_record_cmdline(current);

	if ((wakeup_rt && !rt_task(p)) ||
			p->prio >= wakeup_prio ||
			p->prio >= current->prio)
		return;

	pc = preempt_count();
	disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
	if (unlikely(disabled != 1))
		goto out;

	/* interrupts should be off from try_to_wake_up */
	arch_spin_lock(&wakeup_lock);

	/* check for races. */
	if (!tracer_enabled || p->prio >= wakeup_prio)
		goto out_locked;

	/* reset the trace */
	__wakeup_reset(wakeup_trace);

	wakeup_cpu = task_cpu(p);
	wakeup_current_cpu = wakeup_cpu;
	wakeup_prio = p->prio;

	wakeup_task = p;
	get_task_struct(wakeup_task);

	local_save_flags(flags);

	data = wakeup_trace->data[wakeup_cpu];
	data->preempt_timestamp = ftrace_now(cpu);
	tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc);

	/*
	 * We must be careful in using CALLER_ADDR2. But since wake_up
	 * is not called by an assembly function  (where as schedule is)
	 * it should be safe to use it here.
	 */
	__trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);

out_locked:
	arch_spin_unlock(&wakeup_lock);
out:
	atomic_dec(&wakeup_trace->data[cpu]->disabled);
}

static void start_wakeup_tracer(struct trace_array *tr)
{
	int ret;

	ret = register_trace_sched_wakeup(probe_wakeup, NULL);
	if (ret) {
		pr_info("wakeup trace: Couldn't activate tracepoint"
			" probe to kernel_sched_wakeup\n");
		return;
	}

	ret = register_trace_sched_wakeup_new(probe_wakeup, NULL);
	if (ret) {
		pr_info("wakeup trace: Couldn't activate tracepoint"
			" probe to kernel_sched_wakeup_new\n");
		goto fail_deprobe;
	}

	ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL);
	if (ret) {
		pr_info("sched trace: Couldn't activate tracepoint"
			" probe to kernel_sched_switch\n");
		goto fail_deprobe_wake_new;
	}

	ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
	if (ret) {
		pr_info("wakeup trace: Couldn't activate tracepoint"
			" probe to kernel_sched_migrate_task\n");
		return;
	}

	wakeup_reset(tr);

	/*
	 * Don't let the tracer_enabled = 1 show up before
	 * the wakeup_task is reset. This may be overkill since
	 * wakeup_reset does a spin_unlock after setting the
	 * wakeup_task to NULL, but I want to be safe.
	 * This is a slow path anyway.
	 */
	smp_wmb();

	if (start_func_tracer(is_graph()))
		printk(KERN_ERR "failed to start wakeup tracer\n");

	return;
fail_deprobe_wake_new:
	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
fail_deprobe:
	unregister_trace_sched_wakeup(probe_wakeup, NULL);
}

static void stop_wakeup_tracer(struct trace_array *tr)
{
	tracer_enabled = 0;
	stop_func_tracer(is_graph());
	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
	unregister_trace_sched_wakeup(probe_wakeup, NULL);
	unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
}

static int __wakeup_tracer_init(struct trace_array *tr)
{
	save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
	trace_flags |= TRACE_ITER_LATENCY_FMT;

	tracing_max_latency = 0;
	wakeup_trace = tr;
	start_wakeup_tracer(tr);
	return 0;
}

static int wakeup_tracer_init(struct trace_array *tr)
{
	wakeup_rt = 0;
	return __wakeup_tracer_init(tr);
}

static int wakeup_rt_tracer_init(struct trace_array *tr)
{
	wakeup_rt = 1;
	return __wakeup_tracer_init(tr);
}

static void wakeup_tracer_reset(struct trace_array *tr)
{
	stop_wakeup_tracer(tr);
	/* make sure we put back any tasks we are tracing */
	wakeup_reset(tr);

	if (!save_lat_flag)
		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
}

static void wakeup_tracer_start(struct trace_array *tr)
{
	wakeup_reset(tr);
	tracer_enabled = 1;
}

static void wakeup_tracer_stop(struct trace_array *tr)
{
	tracer_enabled = 0;
}

static struct tracer wakeup_tracer __read_mostly =
{
	.name		= "wakeup",
	.init		= wakeup_tracer_init,
	.reset		= wakeup_tracer_reset,
	.start		= wakeup_tracer_start,
	.stop		= wakeup_tracer_stop,
	.print_max	= 1,
	.print_header	= wakeup_print_header,
	.print_line	= wakeup_print_line,
	.flags		= &tracer_flags,
	.set_flag	= wakeup_set_flag,
#ifdef CONFIG_FTRACE_SELFTEST
	.selftest    = trace_selftest_startup_wakeup,
#endif
	.open		= wakeup_trace_open,
	.close		= wakeup_trace_close,
	.use_max_tr	= 1,
};

static struct tracer wakeup_rt_tracer __read_mostly =
{
	.name		= "wakeup_rt",
	.init		= wakeup_rt_tracer_init,
	.reset		= wakeup_tracer_reset,
	.start		= wakeup_tracer_start,
	.stop		= wakeup_tracer_stop,
	.wait_pipe	= poll_wait_pipe,
	.print_max	= 1,
	.print_header	= wakeup_print_header,
	.print_line	= wakeup_print_line,
	.flags		= &tracer_flags,
	.set_flag	= wakeup_set_flag,
#ifdef CONFIG_FTRACE_SELFTEST
	.selftest    = trace_selftest_startup_wakeup,
#endif
	.open		= wakeup_trace_open,
	.close		= wakeup_trace_close,
	.use_max_tr	= 1,
};

__init static int init_wakeup_tracer(void)
{
	int ret;

	ret = register_tracer(&wakeup_tracer);
	if (ret)
		return ret;

	ret = register_tracer(&wakeup_rt_tracer);
	if (ret)
		return ret;

	return 0;
}
device_initcall(init_wakeup_tracer);