summaryrefslogtreecommitdiff
path: root/kernel/sched/clock.c
blob: 0e9dbb2d9aea59962d758efaeb29de4b18e33b06 (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
/*
 * sched_clock() for unstable CPU clocks
 *
 *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra
 *
 *  Updates and enhancements:
 *    Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
 *
 * Based on code by:
 *   Ingo Molnar <mingo@redhat.com>
 *   Guillaume Chazarain <guichaz@gmail.com>
 *
 *
 * What this file implements:
 *
 * cpu_clock(i) provides a fast (execution time) high resolution
 * clock with bounded drift between CPUs. The value of cpu_clock(i)
 * is monotonic for constant i. The timestamp returned is in nanoseconds.
 *
 * ######################### BIG FAT WARNING ##########################
 * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
 * # go backwards !!                                                  #
 * ####################################################################
 *
 * There is no strict promise about the base, although it tends to start
 * at 0 on boot (but people really shouldn't rely on that).
 *
 * cpu_clock(i)       -- can be used from any context, including NMI.
 * local_clock()      -- is cpu_clock() on the current CPU.
 *
 * sched_clock_cpu(i)
 *
 * How it is implemented:
 *
 * The implementation either uses sched_clock() when
 * !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK, which means in that case the
 * sched_clock() is assumed to provide these properties (mostly it means
 * the architecture provides a globally synchronized highres time source).
 *
 * Otherwise it tries to create a semi stable clock from a mixture of other
 * clocks, including:
 *
 *  - GTOD (clock monotomic)
 *  - sched_clock()
 *  - explicit idle events
 *
 * We use GTOD as base and use sched_clock() deltas to improve resolution. The
 * deltas are filtered to provide monotonicity and keeping it within an
 * expected window.
 *
 * Furthermore, explicit sleep and wakeup hooks allow us to account for time
 * that is otherwise invisible (TSC gets stopped).
 *
 */
#include "sched.h"
#include <linux/sched_clock.h>

/*
 * Scheduler clock - returns current time in nanosec units.
 * This is default implementation.
 * Architectures and sub-architectures can override this.
 */
unsigned long long __weak sched_clock(void)
{
	return (unsigned long long)(jiffies - INITIAL_JIFFIES)
					* (NSEC_PER_SEC / HZ);
}
EXPORT_SYMBOL_GPL(sched_clock);

__read_mostly int sched_clock_running;

#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
/*
 * We must start with !__sched_clock_stable because the unstable -> stable
 * transition is accurate, while the stable -> unstable transition is not.
 *
 * Similarly we start with __sched_clock_stable_early, thereby assuming we
 * will become stable, such that there's only a single 1 -> 0 transition.
 */
static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
static int __sched_clock_stable_early = 1;

/*
 * We want: ktime_get_ns() + __gtod_offset == sched_clock() + __sched_clock_offset
 */
__read_mostly u64 __sched_clock_offset;
static __read_mostly u64 __gtod_offset;

struct sched_clock_data {
	u64			tick_raw;
	u64			tick_gtod;
	u64			clock;
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);

static inline struct sched_clock_data *this_scd(void)
{
	return this_cpu_ptr(&sched_clock_data);
}

static inline struct sched_clock_data *cpu_sdc(int cpu)
{
	return &per_cpu(sched_clock_data, cpu);
}

int sched_clock_stable(void)
{
	return static_branch_likely(&__sched_clock_stable);
}

static void __scd_stamp(struct sched_clock_data *scd)
{
	scd->tick_gtod = ktime_get_ns();
	scd->tick_raw = sched_clock();
}

static void __set_sched_clock_stable(void)
{
	struct sched_clock_data *scd;

	/*
	 * Since we're still unstable and the tick is already running, we have
	 * to disable IRQs in order to get a consistent scd->tick* reading.
	 */
	local_irq_disable();
	scd = this_scd();
	/*
	 * Attempt to make the (initial) unstable->stable transition continuous.
	 */
	__sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw);
	local_irq_enable();

	printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
			scd->tick_gtod, __gtod_offset,
			scd->tick_raw,  __sched_clock_offset);

	static_branch_enable(&__sched_clock_stable);
	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
}

/*
 * If we ever get here, we're screwed, because we found out -- typically after
 * the fact -- that TSC wasn't good. This means all our clocksources (including
 * ktime) could have reported wrong values.
 *
 * What we do here is an attempt to fix up and continue sort of where we left
 * off in a coherent manner.
 *
 * The only way to fully avoid random clock jumps is to boot with:
 * "tsc=unstable".
 */
static void __sched_clock_work(struct work_struct *work)
{
	struct sched_clock_data *scd;
	int cpu;

	/* take a current timestamp and set 'now' */
	preempt_disable();
	scd = this_scd();
	__scd_stamp(scd);
	scd->clock = scd->tick_gtod + __gtod_offset;
	preempt_enable();

	/* clone to all CPUs */
	for_each_possible_cpu(cpu)
		per_cpu(sched_clock_data, cpu) = *scd;

	printk(KERN_WARNING "TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'.\n");
	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
			scd->tick_gtod, __gtod_offset,
			scd->tick_raw,  __sched_clock_offset);

	static_branch_disable(&__sched_clock_stable);
}

static DECLARE_WORK(sched_clock_work, __sched_clock_work);

static void __clear_sched_clock_stable(void)
{
	if (!sched_clock_stable())
		return;

	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
	schedule_work(&sched_clock_work);
}

void clear_sched_clock_stable(void)
{
	__sched_clock_stable_early = 0;

	smp_mb(); /* matches sched_clock_init_late() */

	if (sched_clock_running == 2)
		__clear_sched_clock_stable();
}

static void __sched_clock_gtod_offset(void)
{
	__gtod_offset = (sched_clock() + __sched_clock_offset) - ktime_get_ns();
}

void __init sched_clock_init(void)
{
	sched_clock_running = 1;
}
/*
 * We run this as late_initcall() such that it runs after all built-in drivers,
 * notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
 */
static int __init sched_clock_init_late(void)
{
	sched_clock_running = 2;
	/*
	 * Ensure that it is impossible to not do a static_key update.
	 *
	 * Either {set,clear}_sched_clock_stable() must see sched_clock_running
	 * and do the update, or we must see their __sched_clock_stable_early
	 * and do the update, or both.
	 */
	smp_mb(); /* matches {set,clear}_sched_clock_stable() */

	if (__sched_clock_stable_early)
		__set_sched_clock_stable();

	return 0;
}
late_initcall(sched_clock_init_late);

/*
 * min, max except they take wrapping into account
 */

static inline u64 wrap_min(u64 x, u64 y)
{
	return (s64)(x - y) < 0 ? x : y;
}

static inline u64 wrap_max(u64 x, u64 y)
{
	return (s64)(x - y) > 0 ? x : y;
}

/*
 * update the percpu scd from the raw @now value
 *
 *  - filter out backward motion
 *  - use the GTOD tick value to create a window to filter crazy TSC values
 */
static u64 sched_clock_local(struct sched_clock_data *scd)
{
	u64 now, clock, old_clock, min_clock, max_clock, gtod;
	s64 delta;

again:
	now = sched_clock();
	delta = now - scd->tick_raw;
	if (unlikely(delta < 0))
		delta = 0;

	old_clock = scd->clock;

	/*
	 * scd->clock = clamp(scd->tick_gtod + delta,
	 *		      max(scd->tick_gtod, scd->clock),
	 *		      scd->tick_gtod + TICK_NSEC);
	 */

	gtod = scd->tick_gtod + __gtod_offset;
	clock = gtod + delta;
	min_clock = wrap_max(gtod, old_clock);
	max_clock = wrap_max(old_clock, gtod + TICK_NSEC);

	clock = wrap_max(clock, min_clock);
	clock = wrap_min(clock, max_clock);

	if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock)
		goto again;

	return clock;
}

static u64 sched_clock_remote(struct sched_clock_data *scd)
{
	struct sched_clock_data *my_scd = this_scd();
	u64 this_clock, remote_clock;
	u64 *ptr, old_val, val;

#if BITS_PER_LONG != 64
again:
	/*
	 * Careful here: The local and the remote clock values need to
	 * be read out atomic as we need to compare the values and
	 * then update either the local or the remote side. So the
	 * cmpxchg64 below only protects one readout.
	 *
	 * We must reread via sched_clock_local() in the retry case on
	 * 32-bit kernels as an NMI could use sched_clock_local() via the
	 * tracer and hit between the readout of
	 * the low 32-bit and the high 32-bit portion.
	 */
	this_clock = sched_clock_local(my_scd);
	/*
	 * We must enforce atomic readout on 32-bit, otherwise the
	 * update on the remote CPU can hit inbetween the readout of
	 * the low 32-bit and the high 32-bit portion.
	 */
	remote_clock = cmpxchg64(&scd->clock, 0, 0);
#else
	/*
	 * On 64-bit kernels the read of [my]scd->clock is atomic versus the
	 * update, so we can avoid the above 32-bit dance.
	 */
	sched_clock_local(my_scd);
again:
	this_clock = my_scd->clock;
	remote_clock = scd->clock;
#endif

	/*
	 * Use the opportunity that we have both locks
	 * taken to couple the two clocks: we take the
	 * larger time as the latest time for both
	 * runqueues. (this creates monotonic movement)
	 */
	if (likely((s64)(remote_clock - this_clock) < 0)) {
		ptr = &scd->clock;
		old_val = remote_clock;
		val = this_clock;
	} else {
		/*
		 * Should be rare, but possible:
		 */
		ptr = &my_scd->clock;
		old_val = this_clock;
		val = remote_clock;
	}

	if (cmpxchg64(ptr, old_val, val) != old_val)
		goto again;

	return val;
}

/*
 * Similar to cpu_clock(), but requires local IRQs to be disabled.
 *
 * See cpu_clock().
 */
u64 sched_clock_cpu(int cpu)
{
	struct sched_clock_data *scd;
	u64 clock;

	if (sched_clock_stable())
		return sched_clock() + __sched_clock_offset;

	if (unlikely(!sched_clock_running))
		return 0ull;

	preempt_disable_notrace();
	scd = cpu_sdc(cpu);

	if (cpu != smp_processor_id())
		clock = sched_clock_remote(scd);
	else
		clock = sched_clock_local(scd);
	preempt_enable_notrace();

	return clock;
}
EXPORT_SYMBOL_GPL(sched_clock_cpu);

void sched_clock_tick(void)
{
	struct sched_clock_data *scd;

	if (sched_clock_stable())
		return;

	if (unlikely(!sched_clock_running))
		return;

	lockdep_assert_irqs_disabled();

	scd = this_scd();
	__scd_stamp(scd);
	sched_clock_local(scd);
}

void sched_clock_tick_stable(void)
{
	if (!sched_clock_stable())
		return;

	/*
	 * Called under watchdog_lock.
	 *
	 * The watchdog just found this TSC to (still) be stable, so now is a
	 * good moment to update our __gtod_offset. Because once we find the
	 * TSC to be unstable, any computation will be computing crap.
	 */
	local_irq_disable();
	__sched_clock_gtod_offset();
	local_irq_enable();
}

/*
 * We are going deep-idle (irqs are disabled):
 */
void sched_clock_idle_sleep_event(void)
{
	sched_clock_cpu(smp_processor_id());
}
EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);

/*
 * We just idled; resync with ktime.
 */
void sched_clock_idle_wakeup_event(void)
{
	unsigned long flags;

	if (sched_clock_stable())
		return;

	if (unlikely(timekeeping_suspended))
		return;

	local_irq_save(flags);
	sched_clock_tick();
	local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);

#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */

void __init sched_clock_init(void)
{
	sched_clock_running = 1;
	generic_sched_clock_init();
}

u64 sched_clock_cpu(int cpu)
{
	if (unlikely(!sched_clock_running))
		return 0;

	return sched_clock();
}

#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */

/*
 * Running clock - returns the time that has elapsed while a guest has been
 * running.
 * On a guest this value should be local_clock minus the time the guest was
 * suspended by the hypervisor (for any reason).
 * On bare metal this function should return the same as local_clock.
 * Architectures and sub-architectures can override this.
 */
u64 __weak running_clock(void)
{
	return local_clock();
}