summaryrefslogtreecommitdiffstats
path: root/kernel/time/tick-common.c
blob: 3ae6afa1eb98e71cc82272cd0a79a25101eff429 (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
/*
 * linux/kernel/time/tick-common.c
 *
 * This file contains the base functions to manage periodic tick
 * related events.
 *
 * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
 * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
 * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
 *
 * This code is licenced under the GPL version 2. For details see
 * kernel-base/COPYING.
 */
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
#include <linux/module.h>

#include <asm/irq_regs.h>

#include "tick-internal.h"

/*
 * Tick devices
 */
DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
/*
 * Tick next event: keeps track of the tick time
 */
ktime_t tick_next_period;
ktime_t tick_period;

/*
 * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
 * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
 * variable has two functions:
 *
 * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
 *    timekeeping lock all at once. Only the CPU which is assigned to do the
 *    update is handling it.
 *
 * 2) Hand off the duty in the NOHZ idle case by setting the value to
 *    TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
 *    at it will take over and keep the time keeping alive.  The handover
 *    procedure also covers cpu hotplug.
 */
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;

/*
 * Debugging: see timer_list.c
 */
struct tick_device *tick_get_device(int cpu)
{
	return &per_cpu(tick_cpu_device, cpu);
}

/**
 * tick_is_oneshot_available - check for a oneshot capable event device
 */
int tick_is_oneshot_available(void)
{
	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);

	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
		return 0;
	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
		return 1;
	return tick_broadcast_oneshot_available();
}

/*
 * Periodic tick
 */
static void tick_periodic(int cpu)
{
	if (tick_do_timer_cpu == cpu) {
		write_seqlock(&jiffies_lock);

		/* Keep track of the next tick event */
		tick_next_period = ktime_add(tick_next_period, tick_period);

		do_timer(1);
		write_sequnlock(&jiffies_lock);
		update_wall_time();
	}

	update_process_times(user_mode(get_irq_regs()));
	profile_tick(CPU_PROFILING);
}

/*
 * Event handler for periodic ticks
 */
void tick_handle_periodic(struct clock_event_device *dev)
{
	int cpu = smp_processor_id();
	ktime_t next = dev->next_event;

	tick_periodic(cpu);

	if (dev->state != CLOCK_EVT_STATE_ONESHOT)
		return;
	for (;;) {
		/*
		 * Setup the next period for devices, which do not have
		 * periodic mode:
		 */
		next = ktime_add(next, tick_period);

		if (!clockevents_program_event(dev, next, false))
			return;
		/*
		 * Have to be careful here. If we're in oneshot mode,
		 * before we call tick_periodic() in a loop, we need
		 * to be sure we're using a real hardware clocksource.
		 * Otherwise we could get trapped in an infinite
		 * loop, as the tick_periodic() increments jiffies,
		 * which then will increment time, possibly causing
		 * the loop to trigger again and again.
		 */
		if (timekeeping_valid_for_hres())
			tick_periodic(cpu);
	}
}

/*
 * Setup the device for a periodic tick
 */
void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
{
	tick_set_periodic_handler(dev, broadcast);

	/* Broadcast setup ? */
	if (!tick_device_is_functional(dev))
		return;

	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
	    !tick_broadcast_oneshot_active()) {
		clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
	} else {
		unsigned long seq;
		ktime_t next;

		do {
			seq = read_seqbegin(&jiffies_lock);
			next = tick_next_period;
		} while (read_seqretry(&jiffies_lock, seq));

		clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);

		for (;;) {
			if (!clockevents_program_event(dev, next, false))
				return;
			next = ktime_add(next, tick_period);
		}
	}
}

/*
 * Setup the tick device
 */
static void tick_setup_device(struct tick_device *td,
			      struct clock_event_device *newdev, int cpu,
			      const struct cpumask *cpumask)
{
	ktime_t next_event;
	void (*handler)(struct clock_event_device *) = NULL;

	/*
	 * First device setup ?
	 */
	if (!td->evtdev) {
		/*
		 * If no cpu took the do_timer update, assign it to
		 * this cpu:
		 */
		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
			if (!tick_nohz_full_cpu(cpu))
				tick_do_timer_cpu = cpu;
			else
				tick_do_timer_cpu = TICK_DO_TIMER_NONE;
			tick_next_period = ktime_get();
			tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
		}

		/*
		 * Startup in periodic mode first.
		 */
		td->mode = TICKDEV_MODE_PERIODIC;
	} else {
		handler = td->evtdev->event_handler;
		next_event = td->evtdev->next_event;
		td->evtdev->event_handler = clockevents_handle_noop;
	}

	td->evtdev = newdev;

	/*
	 * When the device is not per cpu, pin the interrupt to the
	 * current cpu:
	 */
	if (!cpumask_equal(newdev->cpumask, cpumask))
		irq_set_affinity(newdev->irq, cpumask);

	/*
	 * When global broadcasting is active, check if the current
	 * device is registered as a placeholder for broadcast mode.
	 * This allows us to handle this x86 misfeature in a generic
	 * way. This function also returns !=0 when we keep the
	 * current active broadcast state for this CPU.
	 */
	if (tick_device_uses_broadcast(newdev, cpu))
		return;

	if (td->mode == TICKDEV_MODE_PERIODIC)
		tick_setup_periodic(newdev, 0);
	else
		tick_setup_oneshot(newdev, handler, next_event);
}

void tick_install_replacement(struct clock_event_device *newdev)
{
	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
	int cpu = smp_processor_id();

	clockevents_exchange_device(td->evtdev, newdev);
	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
		tick_oneshot_notify();
}

static bool tick_check_percpu(struct clock_event_device *curdev,
			      struct clock_event_device *newdev, int cpu)
{
	if (!cpumask_test_cpu(cpu, newdev->cpumask))
		return false;
	if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
		return true;
	/* Check if irq affinity can be set */
	if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
		return false;
	/* Prefer an existing cpu local device */
	if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
		return false;
	return true;
}

static bool tick_check_preferred(struct clock_event_device *curdev,
				 struct clock_event_device *newdev)
{
	/* Prefer oneshot capable device */
	if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
		if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
			return false;
		if (tick_oneshot_mode_active())
			return false;
	}

	/*
	 * Use the higher rated one, but prefer a CPU local device with a lower
	 * rating than a non-CPU local device
	 */
	return !curdev ||
		newdev->rating > curdev->rating ||
	       !cpumask_equal(curdev->cpumask, newdev->cpumask);
}

/*
 * Check whether the new device is a better fit than curdev. curdev
 * can be NULL !
 */
bool tick_check_replacement(struct clock_event_device *curdev,
			    struct clock_event_device *newdev)
{
	if (!tick_check_percpu(curdev, newdev, smp_processor_id()))
		return false;

	return tick_check_preferred(curdev, newdev);
}

/*
 * Check, if the new registered device should be used. Called with
 * clockevents_lock held and interrupts disabled.
 */
void tick_check_new_device(struct clock_event_device *newdev)
{
	struct clock_event_device *curdev;
	struct tick_device *td;
	int cpu;

	cpu = smp_processor_id();
	if (!cpumask_test_cpu(cpu, newdev->cpumask))
		goto out_bc;

	td = &per_cpu(tick_cpu_device, cpu);
	curdev = td->evtdev;

	/* cpu local device ? */
	if (!tick_check_percpu(curdev, newdev, cpu))
		goto out_bc;

	/* Preference decision */
	if (!tick_check_preferred(curdev, newdev))
		goto out_bc;

	if (!try_module_get(newdev->owner))
		return;

	/*
	 * Replace the eventually existing device by the new
	 * device. If the current device is the broadcast device, do
	 * not give it back to the clockevents layer !
	 */
	if (tick_is_broadcast_device(curdev)) {
		clockevents_shutdown(curdev);
		curdev = NULL;
	}
	clockevents_exchange_device(curdev, newdev);
	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
		tick_oneshot_notify();
	return;

out_bc:
	/*
	 * Can the new device be used as a broadcast device ?
	 */
	tick_install_broadcast_device(newdev);
}

#ifdef CONFIG_HOTPLUG_CPU
/*
 * Transfer the do_timer job away from a dying cpu.
 *
 * Called with interrupts disabled. Not locking required. If
 * tick_do_timer_cpu is owned by this cpu, nothing can change it.
 */
void tick_handover_do_timer(void)
{
	if (tick_do_timer_cpu == smp_processor_id()) {
		int cpu = cpumask_first(cpu_online_mask);

		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
			TICK_DO_TIMER_NONE;
	}
}

/*
 * Shutdown an event device on a given cpu:
 *
 * This is called on a life CPU, when a CPU is dead. So we cannot
 * access the hardware device itself.
 * We just set the mode and remove it from the lists.
 */
void tick_shutdown(unsigned int cpu)
{
	struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
	struct clock_event_device *dev = td->evtdev;

	td->mode = TICKDEV_MODE_PERIODIC;
	if (dev) {
		/*
		 * Prevent that the clock events layer tries to call
		 * the set mode function!
		 */
		dev->state = CLOCK_EVT_STATE_DETACHED;
		dev->mode = CLOCK_EVT_MODE_UNUSED;
		clockevents_exchange_device(dev, NULL);
		dev->event_handler = clockevents_handle_noop;
		td->evtdev = NULL;
	}
}
#endif

/**
 * tick_suspend_local - Suspend the local tick device
 *
 * Called from the local cpu for freeze with interrupts disabled.
 *
 * No locks required. Nothing can change the per cpu device.
 */
void tick_suspend_local(void)
{
	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);

	clockevents_shutdown(td->evtdev);
}

/**
 * tick_resume_local - Resume the local tick device
 *
 * Called from the local CPU for unfreeze or XEN resume magic.
 *
 * No locks required. Nothing can change the per cpu device.
 */
void tick_resume_local(void)
{
	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
	bool broadcast = tick_resume_check_broadcast();

	clockevents_tick_resume(td->evtdev);
	if (!broadcast) {
		if (td->mode == TICKDEV_MODE_PERIODIC)
			tick_setup_periodic(td->evtdev, 0);
		else
			tick_resume_oneshot();
	}
}

/**
 * tick_suspend - Suspend the tick and the broadcast device
 *
 * Called from syscore_suspend() via timekeeping_suspend with only one
 * CPU online and interrupts disabled or from tick_unfreeze() under
 * tick_freeze_lock.
 *
 * No locks required. Nothing can change the per cpu device.
 */
void tick_suspend(void)
{
	tick_suspend_local();
	tick_suspend_broadcast();
}

/**
 * tick_resume - Resume the tick and the broadcast device
 *
 * Called from syscore_resume() via timekeeping_resume with only one
 * CPU online and interrupts disabled.
 *
 * No locks required. Nothing can change the per cpu device.
 */
void tick_resume(void)
{
	tick_resume_broadcast();
	tick_resume_local();
}

static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
static unsigned int tick_freeze_depth;

/**
 * tick_freeze - Suspend the local tick and (possibly) timekeeping.
 *
 * Check if this is the last online CPU executing the function and if so,
 * suspend timekeeping.  Otherwise suspend the local tick.
 *
 * Call with interrupts disabled.  Must be balanced with %tick_unfreeze().
 * Interrupts must not be enabled before the subsequent %tick_unfreeze().
 */
void tick_freeze(void)
{
	raw_spin_lock(&tick_freeze_lock);

	tick_freeze_depth++;
	if (tick_freeze_depth == num_online_cpus())
		timekeeping_suspend();
	else
		tick_suspend_local();

	raw_spin_unlock(&tick_freeze_lock);
}

/**
 * tick_unfreeze - Resume the local tick and (possibly) timekeeping.
 *
 * Check if this is the first CPU executing the function and if so, resume
 * timekeeping.  Otherwise resume the local tick.
 *
 * Call with interrupts disabled.  Must be balanced with %tick_freeze().
 * Interrupts must not be enabled after the preceding %tick_freeze().
 */
void tick_unfreeze(void)
{
	raw_spin_lock(&tick_freeze_lock);

	if (tick_freeze_depth == num_online_cpus())
		timekeeping_resume();
	else
		tick_resume_local();

	tick_freeze_depth--;

	raw_spin_unlock(&tick_freeze_lock);
}

/**
 * tick_init - initialize the tick control
 */
void __init tick_init(void)
{
	tick_broadcast_init();
	tick_nohz_init();
}