timer.c 53.5 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3
/*
 *  linux/kernel/timer.c
 *
4
 *  Kernel internal timers
L
Linus Torvalds 已提交
5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  1997-01-28  Modified by Finn Arne Gangstad to make timers scale better.
 *
 *  1997-09-10  Updated NTP code according to technical memorandum Jan '96
 *              "A Kernel Model for Precision Timekeeping" by Dave Mills
 *  1998-12-24  Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
 *              serialize accesses to xtime/lost_ticks).
 *                              Copyright (C) 1998  Andrea Arcangeli
 *  1999-03-10  Improved NTP compatibility by Ulrich Windl
 *  2002-05-31	Move sys_sysinfo here and make its locking sane, Robert Love
 *  2000-10-05  Implemented scalable SMP per-CPU timer handling.
 *                              Copyright (C) 2000, 2001, 2002  Ingo Molnar
 *              Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar
 */

#include <linux/kernel_stat.h>
23
#include <linux/export.h>
L
Linus Torvalds 已提交
24 25 26 27 28
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/swap.h>
29
#include <linux/pid_namespace.h>
L
Linus Torvalds 已提交
30 31 32 33 34 35 36
#include <linux/notifier.h>
#include <linux/thread_info.h>
#include <linux/time.h>
#include <linux/jiffies.h>
#include <linux/posix-timers.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
A
Adrian Bunk 已提交
37
#include <linux/delay.h>
38
#include <linux/tick.h>
39
#include <linux/kallsyms.h>
40
#include <linux/irq_work.h>
41
#include <linux/sched.h>
42
#include <linux/sched/sysctl.h>
43
#include <linux/slab.h>
44
#include <linux/compat.h>
L
Linus Torvalds 已提交
45 46 47 48 49 50 51

#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/div64.h>
#include <asm/timex.h>
#include <asm/io.h>

52 53
#include "tick-internal.h"

54 55 56
#define CREATE_TRACE_POINTS
#include <trace/events/timer.h>

A
Andi Kleen 已提交
57
__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
T
Thomas Gleixner 已提交
58 59 60

EXPORT_SYMBOL(jiffies_64);

L
Linus Torvalds 已提交
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
 * The timer wheel has LVL_DEPTH array levels. Each level provides an array of
 * LVL_SIZE buckets. Each level is driven by its own clock and therefor each
 * level has a different granularity.
 *
 * The level granularity is:		LVL_CLK_DIV ^ lvl
 * The level clock frequency is:	HZ / (LVL_CLK_DIV ^ level)
 *
 * The array level of a newly armed timer depends on the relative expiry
 * time. The farther the expiry time is away the higher the array level and
 * therefor the granularity becomes.
 *
 * Contrary to the original timer wheel implementation, which aims for 'exact'
 * expiry of the timers, this implementation removes the need for recascading
 * the timers into the lower array levels. The previous 'classic' timer wheel
 * implementation of the kernel already violated the 'exact' expiry by adding
 * slack to the expiry time to provide batched expiration. The granularity
 * levels provide implicit batching.
 *
 * This is an optimization of the original timer wheel implementation for the
 * majority of the timer wheel use cases: timeouts. The vast majority of
 * timeout timers (networking, disk I/O ...) are canceled before expiry. If
 * the timeout expires it indicates that normal operation is disturbed, so it
 * does not matter much whether the timeout comes with a slight delay.
 *
 * The only exception to this are networking timers with a small expiry
 * time. They rely on the granularity. Those fit into the first wheel level,
 * which has HZ granularity.
 *
 * We don't have cascading anymore. timers with a expiry time above the
 * capacity of the last wheel level are force expired at the maximum timeout
 * value of the last wheel level. From data sampling we know that the maximum
 * value observed is 5 days (network connection tracking), so this should not
 * be an issue.
 *
 * The currently chosen array constants values are a good compromise between
 * array size and granularity.
 *
 * This results in the following granularity and range levels:
 *
 * HZ 1000 steps
 * Level Offset  Granularity            Range
 *  0      0         1 ms                0 ms -         63 ms
 *  1     64         8 ms               64 ms -        511 ms
 *  2    128        64 ms              512 ms -       4095 ms (512ms - ~4s)
 *  3    192       512 ms             4096 ms -      32767 ms (~4s - ~32s)
 *  4    256      4096 ms (~4s)      32768 ms -     262143 ms (~32s - ~4m)
 *  5    320     32768 ms (~32s)    262144 ms -    2097151 ms (~4m - ~34m)
 *  6    384    262144 ms (~4m)    2097152 ms -   16777215 ms (~34m - ~4h)
 *  7    448   2097152 ms (~34m)  16777216 ms -  134217727 ms (~4h - ~1d)
 *  8    512  16777216 ms (~4h)  134217728 ms - 1073741822 ms (~1d - ~12d)
 *
 * HZ  300
 * Level Offset  Granularity            Range
 *  0	   0         3 ms                0 ms -        210 ms
 *  1	  64        26 ms              213 ms -       1703 ms (213ms - ~1s)
 *  2	 128       213 ms             1706 ms -      13650 ms (~1s - ~13s)
 *  3	 192      1706 ms (~1s)      13653 ms -     109223 ms (~13s - ~1m)
 *  4	 256     13653 ms (~13s)    109226 ms -     873810 ms (~1m - ~14m)
 *  5	 320    109226 ms (~1m)     873813 ms -    6990503 ms (~14m - ~1h)
 *  6	 384    873813 ms (~14m)   6990506 ms -   55924050 ms (~1h - ~15h)
 *  7	 448   6990506 ms (~1h)   55924053 ms -  447392423 ms (~15h - ~5d)
 *  8    512  55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d)
 *
 * HZ  250
 * Level Offset  Granularity            Range
 *  0	   0         4 ms                0 ms -        255 ms
 *  1	  64        32 ms              256 ms -       2047 ms (256ms - ~2s)
 *  2	 128       256 ms             2048 ms -      16383 ms (~2s - ~16s)
 *  3	 192      2048 ms (~2s)      16384 ms -     131071 ms (~16s - ~2m)
 *  4	 256     16384 ms (~16s)    131072 ms -    1048575 ms (~2m - ~17m)
 *  5	 320    131072 ms (~2m)    1048576 ms -    8388607 ms (~17m - ~2h)
 *  6	 384   1048576 ms (~17m)   8388608 ms -   67108863 ms (~2h - ~18h)
 *  7	 448   8388608 ms (~2h)   67108864 ms -  536870911 ms (~18h - ~6d)
 *  8    512  67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d)
 *
 * HZ  100
 * Level Offset  Granularity            Range
 *  0	   0         10 ms               0 ms -        630 ms
 *  1	  64         80 ms             640 ms -       5110 ms (640ms - ~5s)
 *  2	 128        640 ms            5120 ms -      40950 ms (~5s - ~40s)
 *  3	 192       5120 ms (~5s)     40960 ms -     327670 ms (~40s - ~5m)
 *  4	 256      40960 ms (~40s)   327680 ms -    2621430 ms (~5m - ~43m)
 *  5	 320     327680 ms (~5m)   2621440 ms -   20971510 ms (~43m - ~5h)
 *  6	 384    2621440 ms (~43m) 20971520 ms -  167772150 ms (~5h - ~1d)
 *  7	 448   20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d)
L
Linus Torvalds 已提交
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
/* Clock divisor for the next level */
#define LVL_CLK_SHIFT	3
#define LVL_CLK_DIV	(1UL << LVL_CLK_SHIFT)
#define LVL_CLK_MASK	(LVL_CLK_DIV - 1)
#define LVL_SHIFT(n)	((n) * LVL_CLK_SHIFT)
#define LVL_GRAN(n)	(1UL << LVL_SHIFT(n))

/*
 * The time start value for each level to select the bucket at enqueue
 * time.
 */
#define LVL_START(n)	((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT))

/* Size of each clock level */
#define LVL_BITS	6
#define LVL_SIZE	(1UL << LVL_BITS)
#define LVL_MASK	(LVL_SIZE - 1)
#define LVL_OFFS(n)	((n) * LVL_SIZE)

/* Level depth */
#if HZ > 100
# define LVL_DEPTH	9
# else
# define LVL_DEPTH	8
#endif

/* The cutoff (max. capacity of the wheel) */
#define WHEEL_TIMEOUT_CUTOFF	(LVL_START(LVL_DEPTH))
#define WHEEL_TIMEOUT_MAX	(WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1))

/*
 * The resulting wheel size. If NOHZ is configured we allocate two
 * wheels so we have a separate storage for the deferrable timers.
 */
#define WHEEL_SIZE	(LVL_SIZE * LVL_DEPTH)

#ifdef CONFIG_NO_HZ_COMMON
# define NR_BASES	2
# define BASE_STD	0
# define BASE_DEF	1
#else
# define NR_BASES	1
# define BASE_STD	0
# define BASE_DEF	0
#endif
L
Linus Torvalds 已提交
194

195
struct timer_base {
196 197 198
	spinlock_t		lock;
	struct timer_list	*running_timer;
	unsigned long		clk;
199
	unsigned long		next_expiry;
200 201 202
	unsigned int		cpu;
	bool			migration_enabled;
	bool			nohz_active;
203
	bool			is_idle;
204 205
	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
	struct hlist_head	vectors[WHEEL_SIZE];
206
} ____cacheline_aligned;
L
Linus Torvalds 已提交
207

208
static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]);
209

210 211 212
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
unsigned int sysctl_timer_migration = 1;

213
void timers_update_migration(bool update_nohz)
214 215 216 217 218
{
	bool on = sysctl_timer_migration && tick_nohz_active;
	unsigned int cpu;

	/* Avoid the loop, if nothing to update */
219
	if (this_cpu_read(timer_bases[BASE_STD].migration_enabled) == on)
220 221 222
		return;

	for_each_possible_cpu(cpu) {
223 224
		per_cpu(timer_bases[BASE_STD].migration_enabled, cpu) = on;
		per_cpu(timer_bases[BASE_DEF].migration_enabled, cpu) = on;
225
		per_cpu(hrtimer_bases.migration_enabled, cpu) = on;
226 227
		if (!update_nohz)
			continue;
228 229
		per_cpu(timer_bases[BASE_STD].nohz_active, cpu) = true;
		per_cpu(timer_bases[BASE_DEF].nohz_active, cpu) = true;
230
		per_cpu(hrtimer_bases.nohz_active, cpu) = true;
231 232 233 234 235 236 237 238 239 240 241 242 243
	}
}

int timer_migration_handler(struct ctl_table *table, int write,
			    void __user *buffer, size_t *lenp,
			    loff_t *ppos)
{
	static DEFINE_MUTEX(mutex);
	int ret;

	mutex_lock(&mutex);
	ret = proc_dointvec(table, write, buffer, lenp, ppos);
	if (!ret && write)
244
		timers_update_migration(false);
245 246 247 248 249
	mutex_unlock(&mutex);
	return ret;
}
#endif

250 251
static unsigned long round_jiffies_common(unsigned long j, int cpu,
		bool force_up)
252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272
{
	int rem;
	unsigned long original = j;

	/*
	 * We don't want all cpus firing their timers at once hitting the
	 * same lock or cachelines, so we skew each extra cpu with an extra
	 * 3 jiffies. This 3 jiffies came originally from the mm/ code which
	 * already did this.
	 * The skew is done by adding 3*cpunr, then round, then subtract this
	 * extra offset again.
	 */
	j += cpu * 3;

	rem = j % HZ;

	/*
	 * If the target jiffie is just after a whole second (which can happen
	 * due to delays of the timer irq, long irq off times etc etc) then
	 * we should round down to the whole second, not up. Use 1/4th second
	 * as cutoff for this rounding as an extreme upper bound for this.
273
	 * But never round down if @force_up is set.
274
	 */
275
	if (rem < HZ/4 && !force_up) /* round down */
276 277 278 279 280 281 282
		j = j - rem;
	else /* round up */
		j = j - rem + HZ;

	/* now that we have rounded, subtract the extra skew again */
	j -= cpu * 3;

283 284 285 286 287
	/*
	 * Make sure j is still in the future. Otherwise return the
	 * unmodified value.
	 */
	return time_is_after_jiffies(j) ? j : original;
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

/**
 * __round_jiffies - function to round jiffies to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * __round_jiffies() rounds an absolute time in the future (in jiffies)
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
 * The exact rounding is skewed for each processor to avoid all
 * processors firing at the exact same time, which could lead
 * to lock contention or spurious cache line bouncing.
 *
 * The return value is the rounded version of the @j parameter.
 */
unsigned long __round_jiffies(unsigned long j, int cpu)
{
	return round_jiffies_common(j, cpu, false);
}
314 315 316 317 318 319 320
EXPORT_SYMBOL_GPL(__round_jiffies);

/**
 * __round_jiffies_relative - function to round jiffies to a full second
 * @j: the time in (relative) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
321
 * __round_jiffies_relative() rounds a time delta  in the future (in jiffies)
322 323 324 325 326 327 328 329 330 331 332 333
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
 * The exact rounding is skewed for each processor to avoid all
 * processors firing at the exact same time, which could lead
 * to lock contention or spurious cache line bouncing.
 *
334
 * The return value is the rounded version of the @j parameter.
335 336 337
 */
unsigned long __round_jiffies_relative(unsigned long j, int cpu)
{
338 339 340 341
	unsigned long j0 = jiffies;

	/* Use j0 because jiffies might change while we run */
	return round_jiffies_common(j + j0, cpu, false) - j0;
342 343 344 345 346 347 348
}
EXPORT_SYMBOL_GPL(__round_jiffies_relative);

/**
 * round_jiffies - function to round jiffies to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 *
349
 * round_jiffies() rounds an absolute time in the future (in jiffies)
350 351 352 353 354 355 356 357
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
358
 * The return value is the rounded version of the @j parameter.
359 360 361
 */
unsigned long round_jiffies(unsigned long j)
{
362
	return round_jiffies_common(j, raw_smp_processor_id(), false);
363 364 365 366 367 368 369
}
EXPORT_SYMBOL_GPL(round_jiffies);

/**
 * round_jiffies_relative - function to round jiffies to a full second
 * @j: the time in (relative) jiffies that should be rounded
 *
370
 * round_jiffies_relative() rounds a time delta  in the future (in jiffies)
371 372 373 374 375 376 377 378
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
379
 * The return value is the rounded version of the @j parameter.
380 381 382 383 384 385 386
 */
unsigned long round_jiffies_relative(unsigned long j)
{
	return __round_jiffies_relative(j, raw_smp_processor_id());
}
EXPORT_SYMBOL_GPL(round_jiffies_relative);

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
/**
 * __round_jiffies_up - function to round jiffies up to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * This is the same as __round_jiffies() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long __round_jiffies_up(unsigned long j, int cpu)
{
	return round_jiffies_common(j, cpu, true);
}
EXPORT_SYMBOL_GPL(__round_jiffies_up);

/**
 * __round_jiffies_up_relative - function to round jiffies up to a full second
 * @j: the time in (relative) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * This is the same as __round_jiffies_relative() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long __round_jiffies_up_relative(unsigned long j, int cpu)
{
	unsigned long j0 = jiffies;

	/* Use j0 because jiffies might change while we run */
	return round_jiffies_common(j + j0, cpu, true) - j0;
}
EXPORT_SYMBOL_GPL(__round_jiffies_up_relative);

/**
 * round_jiffies_up - function to round jiffies up to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 *
 * This is the same as round_jiffies() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long round_jiffies_up(unsigned long j)
{
	return round_jiffies_common(j, raw_smp_processor_id(), true);
}
EXPORT_SYMBOL_GPL(round_jiffies_up);

/**
 * round_jiffies_up_relative - function to round jiffies up to a full second
 * @j: the time in (relative) jiffies that should be rounded
 *
 * This is the same as round_jiffies_relative() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long round_jiffies_up_relative(unsigned long j)
{
	return __round_jiffies_up_relative(j, raw_smp_processor_id());
}
EXPORT_SYMBOL_GPL(round_jiffies_up_relative);

452

453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473
static inline unsigned int timer_get_idx(struct timer_list *timer)
{
	return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT;
}

static inline void timer_set_idx(struct timer_list *timer, unsigned int idx)
{
	timer->flags = (timer->flags & ~TIMER_ARRAYMASK) |
			idx << TIMER_ARRAYSHIFT;
}

/*
 * Helper function to calculate the array index for a given expiry
 * time.
 */
static inline unsigned calc_index(unsigned expires, unsigned lvl)
{
	expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl);
	return LVL_OFFS(lvl) + (expires & LVL_MASK);
}

474
static void
475
__internal_add_timer(struct timer_base *base, struct timer_list *timer)
L
Linus Torvalds 已提交
476 477
{
	unsigned long expires = timer->expires;
478
	unsigned long delta = expires - base->clk;
479
	struct hlist_head *vec;
480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499
	unsigned int idx;

	if (delta < LVL_START(1)) {
		idx = calc_index(expires, 0);
	} else if (delta < LVL_START(2)) {
		idx = calc_index(expires, 1);
	} else if (delta < LVL_START(3)) {
		idx = calc_index(expires, 2);
	} else if (delta < LVL_START(4)) {
		idx = calc_index(expires, 3);
	} else if (delta < LVL_START(5)) {
		idx = calc_index(expires, 4);
	} else if (delta < LVL_START(6)) {
		idx = calc_index(expires, 5);
	} else if (delta < LVL_START(7)) {
		idx = calc_index(expires, 6);
	} else if (LVL_DEPTH > 8 && delta < LVL_START(8)) {
		idx = calc_index(expires, 7);
	} else if ((long) delta < 0) {
		idx = base->clk & LVL_MASK;
L
Linus Torvalds 已提交
500
	} else {
501 502 503
		/*
		 * Force expire obscene large timeouts to expire at the
		 * capacity limit of the wheel.
L
Linus Torvalds 已提交
504
		 */
505 506
		if (expires >= WHEEL_TIMEOUT_CUTOFF)
			expires = WHEEL_TIMEOUT_MAX;
T
Thomas Gleixner 已提交
507

508 509 510 511 512 513 514
		idx = calc_index(expires, LVL_DEPTH - 1);
	}
	/*
	 * Enqueue the timer into the array bucket, mark it pending in
	 * the bitmap and store the index in the timer flags.
	 */
	vec = base->vectors + idx;
515
	hlist_add_head(&timer->entry, vec);
516 517
	__set_bit(idx, base->pending_map);
	timer_set_idx(timer, idx);
L
Linus Torvalds 已提交
518 519
}

520
static void internal_add_timer(struct timer_base *base, struct timer_list *timer)
521 522
{
	__internal_add_timer(base, timer);
523

524 525 526
	if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
		return;

527
	/*
528 529
	 * TODO: This wants some optimizing similar to the code below, but we
	 * will do that when we switch from push to pull for deferrable timers.
530
	 */
531 532
	if (timer->flags & TIMER_DEFERRABLE) {
		if (tick_nohz_full_cpu(base->cpu))
533
			wake_up_nohz_cpu(base->cpu);
534
		return;
535
	}
536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554

	/*
	 * We might have to IPI the remote CPU if the base is idle and the
	 * timer is not deferrable. If the other CPU is on the way to idle
	 * then it can't set base->is_idle as we hold the base lock:
	 */
	if (!base->is_idle)
		return;

	/* Check whether this is the new first expiring timer: */
	if (time_after_eq(timer->expires, base->next_expiry))
		return;

	/*
	 * Set the next expiry time and kick the CPU so it can reevaluate the
	 * wheel:
	 */
	base->next_expiry = timer->expires;
	wake_up_nohz_cpu(base->cpu);
555 556
}

557 558 559 560 561 562 563 564 565 566
#ifdef CONFIG_TIMER_STATS
void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
{
	if (timer->start_site)
		return;

	timer->start_site = addr;
	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
	timer->start_pid = current->pid;
}
567 568 569

static void timer_stats_account_timer(struct timer_list *timer)
{
570 571 572 573 574 575 576 577
	void *site;

	/*
	 * start_site can be concurrently reset by
	 * timer_stats_timer_clear_start_info()
	 */
	site = READ_ONCE(timer->start_site);
	if (likely(!site))
578
		return;
579

580
	timer_stats_update_stats(timer, timer->start_pid, site,
581 582
				 timer->function, timer->start_comm,
				 timer->flags);
583 584 585 586
}

#else
static void timer_stats_account_timer(struct timer_list *timer) {}
587 588
#endif

589 590 591 592
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS

static struct debug_obj_descr timer_debug_descr;

593 594 595 596 597
static void *timer_debug_hint(void *addr)
{
	return ((struct timer_list *) addr)->function;
}

598 599 600 601 602 603 604 605
static bool timer_is_static_object(void *addr)
{
	struct timer_list *timer = addr;

	return (timer->entry.pprev == NULL &&
		timer->entry.next == TIMER_ENTRY_STATIC);
}

606 607 608
/*
 * fixup_init is called when:
 * - an active object is initialized
609
 */
610
static bool timer_fixup_init(void *addr, enum debug_obj_state state)
611 612 613 614 615 616 617
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		del_timer_sync(timer);
		debug_object_init(timer, &timer_debug_descr);
618
		return true;
619
	default:
620
		return false;
621 622 623
	}
}

624 625 626 627 628 629
/* Stub timer callback for improperly used timers. */
static void stub_timer(unsigned long data)
{
	WARN_ON(1);
}

630 631 632
/*
 * fixup_activate is called when:
 * - an active object is activated
633
 * - an unknown non-static object is activated
634
 */
635
static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
636 637 638 639 640
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_NOTAVAILABLE:
641 642
		setup_timer(timer, stub_timer, 0);
		return true;
643 644 645 646 647

	case ODEBUG_STATE_ACTIVE:
		WARN_ON(1);

	default:
648
		return false;
649 650 651 652 653 654 655
	}
}

/*
 * fixup_free is called when:
 * - an active object is freed
 */
656
static bool timer_fixup_free(void *addr, enum debug_obj_state state)
657 658 659 660 661 662 663
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		del_timer_sync(timer);
		debug_object_free(timer, &timer_debug_descr);
664
		return true;
665
	default:
666
		return false;
667 668 669
	}
}

670 671 672 673
/*
 * fixup_assert_init is called when:
 * - an untracked/uninit-ed object is found
 */
674
static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state)
675 676 677 678 679
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_NOTAVAILABLE:
680 681
		setup_timer(timer, stub_timer, 0);
		return true;
682
	default:
683
		return false;
684 685 686
	}
}

687
static struct debug_obj_descr timer_debug_descr = {
688 689
	.name			= "timer_list",
	.debug_hint		= timer_debug_hint,
690
	.is_static_object	= timer_is_static_object,
691 692 693 694
	.fixup_init		= timer_fixup_init,
	.fixup_activate		= timer_fixup_activate,
	.fixup_free		= timer_fixup_free,
	.fixup_assert_init	= timer_fixup_assert_init,
695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716
};

static inline void debug_timer_init(struct timer_list *timer)
{
	debug_object_init(timer, &timer_debug_descr);
}

static inline void debug_timer_activate(struct timer_list *timer)
{
	debug_object_activate(timer, &timer_debug_descr);
}

static inline void debug_timer_deactivate(struct timer_list *timer)
{
	debug_object_deactivate(timer, &timer_debug_descr);
}

static inline void debug_timer_free(struct timer_list *timer)
{
	debug_object_free(timer, &timer_debug_descr);
}

717 718 719 720 721
static inline void debug_timer_assert_init(struct timer_list *timer)
{
	debug_object_assert_init(timer, &timer_debug_descr);
}

T
Tejun Heo 已提交
722 723
static void do_init_timer(struct timer_list *timer, unsigned int flags,
			  const char *name, struct lock_class_key *key);
724

T
Tejun Heo 已提交
725 726
void init_timer_on_stack_key(struct timer_list *timer, unsigned int flags,
			     const char *name, struct lock_class_key *key)
727 728
{
	debug_object_init_on_stack(timer, &timer_debug_descr);
T
Tejun Heo 已提交
729
	do_init_timer(timer, flags, name, key);
730
}
731
EXPORT_SYMBOL_GPL(init_timer_on_stack_key);
732 733 734 735 736 737 738 739 740 741 742

void destroy_timer_on_stack(struct timer_list *timer)
{
	debug_object_free(timer, &timer_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_timer_on_stack);

#else
static inline void debug_timer_init(struct timer_list *timer) { }
static inline void debug_timer_activate(struct timer_list *timer) { }
static inline void debug_timer_deactivate(struct timer_list *timer) { }
743
static inline void debug_timer_assert_init(struct timer_list *timer) { }
744 745
#endif

746 747 748 749 750 751 752 753 754 755
static inline void debug_init(struct timer_list *timer)
{
	debug_timer_init(timer);
	trace_timer_init(timer);
}

static inline void
debug_activate(struct timer_list *timer, unsigned long expires)
{
	debug_timer_activate(timer);
756
	trace_timer_start(timer, expires, timer->flags);
757 758 759 760 761 762 763 764
}

static inline void debug_deactivate(struct timer_list *timer)
{
	debug_timer_deactivate(timer);
	trace_timer_cancel(timer);
}

765 766 767 768 769
static inline void debug_assert_init(struct timer_list *timer)
{
	debug_timer_assert_init(timer);
}

T
Tejun Heo 已提交
770 771
static void do_init_timer(struct timer_list *timer, unsigned int flags,
			  const char *name, struct lock_class_key *key)
772
{
773
	timer->entry.pprev = NULL;
774
	timer->flags = flags | raw_smp_processor_id();
775 776 777 778 779
#ifdef CONFIG_TIMER_STATS
	timer->start_site = NULL;
	timer->start_pid = -1;
	memset(timer->start_comm, 0, TASK_COMM_LEN);
#endif
780
	lockdep_init_map(&timer->lockdep_map, name, key, 0);
781
}
782 783

/**
R
Randy Dunlap 已提交
784
 * init_timer_key - initialize a timer
785
 * @timer: the timer to be initialized
T
Tejun Heo 已提交
786
 * @flags: timer flags
R
Randy Dunlap 已提交
787 788 789
 * @name: name of the timer
 * @key: lockdep class key of the fake lock used for tracking timer
 *       sync lock dependencies
790
 *
R
Randy Dunlap 已提交
791
 * init_timer_key() must be done to a timer prior calling *any* of the
792 793
 * other timer functions.
 */
T
Tejun Heo 已提交
794 795
void init_timer_key(struct timer_list *timer, unsigned int flags,
		    const char *name, struct lock_class_key *key)
796
{
797
	debug_init(timer);
T
Tejun Heo 已提交
798
	do_init_timer(timer, flags, name, key);
799
}
800
EXPORT_SYMBOL(init_timer_key);
801

802
static inline void detach_timer(struct timer_list *timer, bool clear_pending)
803
{
804
	struct hlist_node *entry = &timer->entry;
805

806
	debug_deactivate(timer);
807

808
	__hlist_del(entry);
809
	if (clear_pending)
810 811
		entry->pprev = NULL;
	entry->next = LIST_POISON2;
812 813
}

814
static int detach_if_pending(struct timer_list *timer, struct timer_base *base,
815 816
			     bool clear_pending)
{
817 818
	unsigned idx = timer_get_idx(timer);

819 820 821
	if (!timer_pending(timer))
		return 0;

822 823 824
	if (hlist_is_singular_node(&timer->entry, base->vectors + idx))
		__clear_bit(idx, base->pending_map);

825 826 827 828
	detach_timer(timer, clear_pending);
	return 1;
}

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
static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
{
	struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);

	/*
	 * If the timer is deferrable and nohz is active then we need to use
	 * the deferrable base.
	 */
	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
	    (tflags & TIMER_DEFERRABLE))
		base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);
	return base;
}

static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
{
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);

	/*
	 * If the timer is deferrable and nohz is active then we need to use
	 * the deferrable base.
	 */
	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
	    (tflags & TIMER_DEFERRABLE))
		base = this_cpu_ptr(&timer_bases[BASE_DEF]);
	return base;
}

static inline struct timer_base *get_timer_base(u32 tflags)
{
	return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK);
}

862 863 864
#ifdef CONFIG_NO_HZ_COMMON
static inline struct timer_base *
__get_target_base(struct timer_base *base, unsigned tflags)
865
{
866
#ifdef CONFIG_SMP
867 868 869 870 871 872 873 874
	if ((tflags & TIMER_PINNED) || !base->migration_enabled)
		return get_timer_this_cpu_base(tflags);
	return get_timer_cpu_base(tflags, get_nohz_timer_target());
#else
	return get_timer_this_cpu_base(tflags);
#endif
}

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
static inline void forward_timer_base(struct timer_base *base)
{
	/*
	 * We only forward the base when it's idle and we have a delta between
	 * base clock and jiffies.
	 */
	if (!base->is_idle || (long) (jiffies - base->clk) < 2)
		return;

	/*
	 * If the next expiry value is > jiffies, then we fast forward to
	 * jiffies otherwise we forward to the next expiry value.
	 */
	if (time_after(base->next_expiry, jiffies))
		base->clk = jiffies;
	else
		base->clk = base->next_expiry;
}
#else
static inline struct timer_base *
__get_target_base(struct timer_base *base, unsigned tflags)
{
	return get_timer_this_cpu_base(tflags);
}

static inline void forward_timer_base(struct timer_base *base) { }
#endif

static inline struct timer_base *
get_target_base(struct timer_base *base, unsigned tflags)
{
	struct timer_base *target = __get_target_base(base, tflags);

	forward_timer_base(target);
	return target;
}

912
/*
913 914 915
 * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means
 * that all timers which are tied to this base are locked, and the base itself
 * is locked too.
916 917
 *
 * So __run_timers/migrate_timers can safely modify all timers which could
918
 * be found in the base->vectors array.
919
 *
920 921
 * When a timer is migrating then the TIMER_MIGRATING flag is set and we need
 * to wait until the migration is done.
922
 */
923
static struct timer_base *lock_timer_base(struct timer_list *timer,
924
					  unsigned long *flags)
925
	__acquires(timer->base->lock)
926 927
{
	for (;;) {
928
		struct timer_base *base;
929
		u32 tf = timer->flags;
930 931

		if (!(tf & TIMER_MIGRATING)) {
932
			base = get_timer_base(tf);
933
			spin_lock_irqsave(&base->lock, *flags);
934
			if (timer->flags == tf)
935 936 937 938 939 940 941
				return base;
			spin_unlock_irqrestore(&base->lock, *flags);
		}
		cpu_relax();
	}
}

I
Ingo Molnar 已提交
942
static inline int
943
__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
L
Linus Torvalds 已提交
944
{
945
	struct timer_base *base, *new_base;
L
Linus Torvalds 已提交
946
	unsigned long flags;
947
	int ret = 0;
L
Linus Torvalds 已提交
948

949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969
	/*
	 * TODO: Calculate the array bucket of the timer right here w/o
	 * holding the base lock. This allows to check not only
	 * timer->expires == expires below, but also whether the timer
	 * ends up in the same bucket. If we really need to requeue
	 * the timer then we check whether base->clk have
	 * advanced between here and locking the timer base. If
	 * jiffies advanced we have to recalc the array bucket with the
	 * lock held.
	 */

	/*
	 * This is a common optimization triggered by the
	 * networking code - if the timer is re-modified
	 * to be the same thing then just return:
	 */
	if (timer_pending(timer)) {
		if (timer->expires == expires)
			return 1;
	}

970
	timer_stats_timer_set_start_info(timer);
L
Linus Torvalds 已提交
971 972
	BUG_ON(!timer->function);

973 974
	base = lock_timer_base(timer, &flags);

975 976 977
	ret = detach_if_pending(timer, base, false);
	if (!ret && pending_only)
		goto out_unlock;
978

979
	debug_activate(timer, expires);
980

981
	new_base = get_target_base(base, timer->flags);
982

983
	if (base != new_base) {
L
Linus Torvalds 已提交
984
		/*
985
		 * We are trying to schedule the timer on the new base.
986 987
		 * However we can't change timer's base while it is running,
		 * otherwise del_timer_sync() can't detect that the timer's
988 989
		 * handler yet has not finished. This also guarantees that the
		 * timer is serialized wrt itself.
L
Linus Torvalds 已提交
990
		 */
991
		if (likely(base->running_timer != timer)) {
992
			/* See the comment in lock_timer_base() */
993 994
			timer->flags |= TIMER_MIGRATING;

995
			spin_unlock(&base->lock);
996 997
			base = new_base;
			spin_lock(&base->lock);
998 999
			WRITE_ONCE(timer->flags,
				   (timer->flags & ~TIMER_BASEMASK) | base->cpu);
L
Linus Torvalds 已提交
1000 1001 1002 1003
		}
	}

	timer->expires = expires;
1004
	internal_add_timer(base, timer);
I
Ingo Molnar 已提交
1005 1006

out_unlock:
1007
	spin_unlock_irqrestore(&base->lock, flags);
L
Linus Torvalds 已提交
1008 1009 1010 1011

	return ret;
}

1012
/**
I
Ingo Molnar 已提交
1013 1014 1015
 * mod_timer_pending - modify a pending timer's timeout
 * @timer: the pending timer to be modified
 * @expires: new timeout in jiffies
L
Linus Torvalds 已提交
1016
 *
I
Ingo Molnar 已提交
1017 1018 1019 1020
 * mod_timer_pending() is the same for pending timers as mod_timer(),
 * but will not re-activate and modify already deleted timers.
 *
 * It is useful for unserialized use of timers.
L
Linus Torvalds 已提交
1021
 */
I
Ingo Molnar 已提交
1022
int mod_timer_pending(struct timer_list *timer, unsigned long expires)
L
Linus Torvalds 已提交
1023
{
1024
	return __mod_timer(timer, expires, true);
L
Linus Torvalds 已提交
1025
}
I
Ingo Molnar 已提交
1026
EXPORT_SYMBOL(mod_timer_pending);
L
Linus Torvalds 已提交
1027

1028
/**
L
Linus Torvalds 已提交
1029 1030
 * mod_timer - modify a timer's timeout
 * @timer: the timer to be modified
1031
 * @expires: new timeout in jiffies
L
Linus Torvalds 已提交
1032
 *
1033
 * mod_timer() is a more efficient way to update the expire field of an
L
Linus Torvalds 已提交
1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049
 * active timer (if the timer is inactive it will be activated)
 *
 * mod_timer(timer, expires) is equivalent to:
 *
 *     del_timer(timer); timer->expires = expires; add_timer(timer);
 *
 * Note that if there are multiple unserialized concurrent users of the
 * same timer, then mod_timer() is the only safe way to modify the timeout,
 * since add_timer() cannot modify an already running timer.
 *
 * The function returns whether it has modified a pending timer or not.
 * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an
 * active timer returns 1.)
 */
int mod_timer(struct timer_list *timer, unsigned long expires)
{
1050
	return __mod_timer(timer, expires, false);
L
Linus Torvalds 已提交
1051 1052 1053
}
EXPORT_SYMBOL(mod_timer);

I
Ingo Molnar 已提交
1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083
/**
 * add_timer - start a timer
 * @timer: the timer to be added
 *
 * The kernel will do a ->function(->data) callback from the
 * timer interrupt at the ->expires point in the future. The
 * current time is 'jiffies'.
 *
 * The timer's ->expires, ->function (and if the handler uses it, ->data)
 * fields must be set prior calling this function.
 *
 * Timers with an ->expires field in the past will be executed in the next
 * timer tick.
 */
void add_timer(struct timer_list *timer)
{
	BUG_ON(timer_pending(timer));
	mod_timer(timer, timer->expires);
}
EXPORT_SYMBOL(add_timer);

/**
 * add_timer_on - start a timer on a particular CPU
 * @timer: the timer to be added
 * @cpu: the CPU to start it on
 *
 * This is not very scalable on SMP. Double adds are not possible.
 */
void add_timer_on(struct timer_list *timer, int cpu)
{
1084
	struct timer_base *new_base, *base;
I
Ingo Molnar 已提交
1085 1086 1087 1088
	unsigned long flags;

	timer_stats_timer_set_start_info(timer);
	BUG_ON(timer_pending(timer) || !timer->function);
1089

1090 1091
	new_base = get_timer_cpu_base(timer->flags, cpu);

1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107
	/*
	 * If @timer was on a different CPU, it should be migrated with the
	 * old base locked to prevent other operations proceeding with the
	 * wrong base locked.  See lock_timer_base().
	 */
	base = lock_timer_base(timer, &flags);
	if (base != new_base) {
		timer->flags |= TIMER_MIGRATING;

		spin_unlock(&base->lock);
		base = new_base;
		spin_lock(&base->lock);
		WRITE_ONCE(timer->flags,
			   (timer->flags & ~TIMER_BASEMASK) | cpu);
	}

1108
	debug_activate(timer, timer->expires);
I
Ingo Molnar 已提交
1109 1110 1111
	internal_add_timer(base, timer);
	spin_unlock_irqrestore(&base->lock, flags);
}
A
Andi Kleen 已提交
1112
EXPORT_SYMBOL_GPL(add_timer_on);
I
Ingo Molnar 已提交
1113

1114
/**
L
Linus Torvalds 已提交
1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126
 * del_timer - deactive a timer.
 * @timer: the timer to be deactivated
 *
 * del_timer() deactivates a timer - this works on both active and inactive
 * timers.
 *
 * The function returns whether it has deactivated a pending timer or not.
 * (ie. del_timer() of an inactive timer returns 0, del_timer() of an
 * active timer returns 1.)
 */
int del_timer(struct timer_list *timer)
{
1127
	struct timer_base *base;
L
Linus Torvalds 已提交
1128
	unsigned long flags;
1129
	int ret = 0;
L
Linus Torvalds 已提交
1130

1131 1132
	debug_assert_init(timer);

1133
	timer_stats_timer_clear_start_info(timer);
1134 1135
	if (timer_pending(timer)) {
		base = lock_timer_base(timer, &flags);
1136
		ret = detach_if_pending(timer, base, true);
L
Linus Torvalds 已提交
1137 1138 1139
		spin_unlock_irqrestore(&base->lock, flags);
	}

1140
	return ret;
L
Linus Torvalds 已提交
1141 1142 1143
}
EXPORT_SYMBOL(del_timer);

1144 1145 1146 1147
/**
 * try_to_del_timer_sync - Try to deactivate a timer
 * @timer: timer do del
 *
1148 1149 1150 1151 1152
 * This function tries to deactivate a timer. Upon successful (ret >= 0)
 * exit the timer is not queued and the handler is not running on any CPU.
 */
int try_to_del_timer_sync(struct timer_list *timer)
{
1153
	struct timer_base *base;
1154 1155 1156
	unsigned long flags;
	int ret = -1;

1157 1158
	debug_assert_init(timer);

1159 1160
	base = lock_timer_base(timer, &flags);

1161 1162 1163
	if (base->running_timer != timer) {
		timer_stats_timer_clear_start_info(timer);
		ret = detach_if_pending(timer, base, true);
1164 1165 1166 1167 1168
	}
	spin_unlock_irqrestore(&base->lock, flags);

	return ret;
}
1169 1170
EXPORT_SYMBOL(try_to_del_timer_sync);

1171
#ifdef CONFIG_SMP
1172
/**
L
Linus Torvalds 已提交
1173 1174 1175 1176 1177 1178 1179
 * del_timer_sync - deactivate a timer and wait for the handler to finish.
 * @timer: the timer to be deactivated
 *
 * This function only differs from del_timer() on SMP: besides deactivating
 * the timer it also makes sure the handler has finished executing on other
 * CPUs.
 *
1180
 * Synchronization rules: Callers must prevent restarting of the timer,
L
Linus Torvalds 已提交
1181
 * otherwise this function is meaningless. It must not be called from
T
Tejun Heo 已提交
1182 1183 1184 1185
 * interrupt contexts unless the timer is an irqsafe one. The caller must
 * not hold locks which would prevent completion of the timer's
 * handler. The timer's handler must not call add_timer_on(). Upon exit the
 * timer is not queued and the handler is not running on any CPU.
L
Linus Torvalds 已提交
1186
 *
T
Tejun Heo 已提交
1187 1188 1189
 * Note: For !irqsafe timers, you must not hold locks that are held in
 *   interrupt context while calling this function. Even if the lock has
 *   nothing to do with the timer in question.  Here's why:
1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205
 *
 *    CPU0                             CPU1
 *    ----                             ----
 *                                   <SOFTIRQ>
 *                                   call_timer_fn();
 *                                     base->running_timer = mytimer;
 *  spin_lock_irq(somelock);
 *                                     <IRQ>
 *                                        spin_lock(somelock);
 *  del_timer_sync(mytimer);
 *   while (base->running_timer == mytimer);
 *
 * Now del_timer_sync() will never return and never release somelock.
 * The interrupt on the other CPU is waiting to grab somelock but
 * it has interrupted the softirq that CPU0 is waiting to finish.
 *
L
Linus Torvalds 已提交
1206 1207 1208 1209
 * The function returns whether it has deactivated a pending timer or not.
 */
int del_timer_sync(struct timer_list *timer)
{
1210
#ifdef CONFIG_LOCKDEP
1211 1212
	unsigned long flags;

1213 1214 1215 1216
	/*
	 * If lockdep gives a backtrace here, please reference
	 * the synchronization rules above.
	 */
1217
	local_irq_save(flags);
1218 1219
	lock_map_acquire(&timer->lockdep_map);
	lock_map_release(&timer->lockdep_map);
1220
	local_irq_restore(flags);
1221
#endif
1222 1223 1224 1225
	/*
	 * don't use it in hardirq context, because it
	 * could lead to deadlock.
	 */
1226
	WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE));
1227 1228 1229 1230
	for (;;) {
		int ret = try_to_del_timer_sync(timer);
		if (ret >= 0)
			return ret;
1231
		cpu_relax();
1232
	}
L
Linus Torvalds 已提交
1233
}
1234
EXPORT_SYMBOL(del_timer_sync);
L
Linus Torvalds 已提交
1235 1236
#endif

1237 1238 1239
static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
			  unsigned long data)
{
1240
	int count = preempt_count();
1241 1242 1243 1244 1245 1246 1247 1248 1249

#ifdef CONFIG_LOCKDEP
	/*
	 * It is permissible to free the timer from inside the
	 * function that is called from it, this we need to take into
	 * account for lockdep too. To avoid bogus "held lock freed"
	 * warnings as well as problems when looking into
	 * timer->lockdep_map, make a copy and use that here.
	 */
1250 1251 1252
	struct lockdep_map lockdep_map;

	lockdep_copy_map(&lockdep_map, &timer->lockdep_map);
1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266
#endif
	/*
	 * Couple the lock chain with the lock chain at
	 * del_timer_sync() by acquiring the lock_map around the fn()
	 * call here and in del_timer_sync().
	 */
	lock_map_acquire(&lockdep_map);

	trace_timer_expire_entry(timer);
	fn(data);
	trace_timer_expire_exit(timer);

	lock_map_release(&lockdep_map);

1267
	if (count != preempt_count()) {
1268
		WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n",
1269
			  fn, count, preempt_count());
1270 1271 1272 1273 1274 1275
		/*
		 * Restore the preempt count. That gives us a decent
		 * chance to survive and extract information. If the
		 * callback kept a lock held, bad luck, but not worse
		 * than the BUG() we had.
		 */
1276
		preempt_count_set(count);
1277 1278 1279
	}
}

1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307
static void expire_timers(struct timer_base *base, struct hlist_head *head)
{
	while (!hlist_empty(head)) {
		struct timer_list *timer;
		void (*fn)(unsigned long);
		unsigned long data;

		timer = hlist_entry(head->first, struct timer_list, entry);
		timer_stats_account_timer(timer);

		base->running_timer = timer;
		detach_timer(timer, true);

		fn = timer->function;
		data = timer->data;

		if (timer->flags & TIMER_IRQSAFE) {
			spin_unlock(&base->lock);
			call_timer_fn(timer, fn, data);
			spin_lock(&base->lock);
		} else {
			spin_unlock_irq(&base->lock);
			call_timer_fn(timer, fn, data);
			spin_lock_irq(&base->lock);
		}
	}
}

1308 1309
static int __collect_expired_timers(struct timer_base *base,
				    struct hlist_head *heads)
1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331
{
	unsigned long clk = base->clk;
	struct hlist_head *vec;
	int i, levels = 0;
	unsigned int idx;

	for (i = 0; i < LVL_DEPTH; i++) {
		idx = (clk & LVL_MASK) + i * LVL_SIZE;

		if (__test_and_clear_bit(idx, base->pending_map)) {
			vec = base->vectors + idx;
			hlist_move_list(vec, heads++);
			levels++;
		}
		/* Is it time to look at the next level? */
		if (clk & LVL_CLK_MASK)
			break;
		/* Shift clock for the next level granularity */
		clk >>= LVL_CLK_SHIFT;
	}
	return levels;
}
1332

1333
#ifdef CONFIG_NO_HZ_COMMON
L
Linus Torvalds 已提交
1334
/*
1335 1336 1337
 * Find the next pending bucket of a level. Search from level start (@offset)
 * + @clk upwards and if nothing there, search from start of the level
 * (@offset) up to @offset + clk.
1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353
 */
static int next_pending_bucket(struct timer_base *base, unsigned offset,
			       unsigned clk)
{
	unsigned pos, start = offset + clk;
	unsigned end = offset + LVL_SIZE;

	pos = find_next_bit(base->pending_map, end, start);
	if (pos < end)
		return pos - start;

	pos = find_next_bit(base->pending_map, start, offset);
	return pos < start ? pos + LVL_SIZE - start : -1;
}

/*
1354 1355
 * Search the first expiring timer in the various clock levels. Caller must
 * hold base->lock.
L
Linus Torvalds 已提交
1356
 */
1357
static unsigned long __next_timer_interrupt(struct timer_base *base)
L
Linus Torvalds 已提交
1358
{
1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372
	unsigned long clk, next, adj;
	unsigned lvl, offset = 0;

	next = base->clk + NEXT_TIMER_MAX_DELTA;
	clk = base->clk;
	for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) {
		int pos = next_pending_bucket(base, offset, clk & LVL_MASK);

		if (pos >= 0) {
			unsigned long tmp = clk + (unsigned long) pos;

			tmp <<= LVL_SHIFT(lvl);
			if (time_before(tmp, next))
				next = tmp;
L
Linus Torvalds 已提交
1373
		}
1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412
		/*
		 * Clock for the next level. If the current level clock lower
		 * bits are zero, we look at the next level as is. If not we
		 * need to advance it by one because that's going to be the
		 * next expiring bucket in that level. base->clk is the next
		 * expiring jiffie. So in case of:
		 *
		 * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
		 *  0    0    0    0    0    0
		 *
		 * we have to look at all levels @index 0. With
		 *
		 * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
		 *  0    0    0    0    0    2
		 *
		 * LVL0 has the next expiring bucket @index 2. The upper
		 * levels have the next expiring bucket @index 1.
		 *
		 * In case that the propagation wraps the next level the same
		 * rules apply:
		 *
		 * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
		 *  0    0    0    0    F    2
		 *
		 * So after looking at LVL0 we get:
		 *
		 * LVL5 LVL4 LVL3 LVL2 LVL1
		 *  0    0    0    1    0
		 *
		 * So no propagation from LVL1 to LVL2 because that happened
		 * with the add already, but then we need to propagate further
		 * from LVL2 to LVL3.
		 *
		 * So the simple check whether the lower bits of the current
		 * level are 0 or not is sufficient for all cases.
		 */
		adj = clk & LVL_CLK_MASK ? 1 : 0;
		clk >>= LVL_CLK_SHIFT;
		clk += adj;
L
Linus Torvalds 已提交
1413
	}
1414
	return next;
1415
}
1416

1417 1418 1419 1420
/*
 * Check, if the next hrtimer event is before the next timer wheel
 * event:
 */
1421
static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
1422
{
1423
	u64 nextevt = hrtimer_get_next_event();
1424

1425
	/*
1426 1427
	 * If high resolution timers are enabled
	 * hrtimer_get_next_event() returns KTIME_MAX.
1428
	 */
1429 1430
	if (expires <= nextevt)
		return expires;
1431 1432

	/*
1433 1434
	 * If the next timer is already expired, return the tick base
	 * time so the tick is fired immediately.
1435
	 */
1436 1437
	if (nextevt <= basem)
		return basem;
1438

1439
	/*
1440 1441 1442 1443 1444 1445
	 * Round up to the next jiffie. High resolution timers are
	 * off, so the hrtimers are expired in the tick and we need to
	 * make sure that this tick really expires the timer to avoid
	 * a ping pong of the nohz stop code.
	 *
	 * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3
1446
	 */
1447
	return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC;
L
Linus Torvalds 已提交
1448
}
1449 1450

/**
1451 1452 1453 1454 1455 1456
 * get_next_timer_interrupt - return the time (clock mono) of the next timer
 * @basej:	base time jiffies
 * @basem:	base time clock monotonic
 *
 * Returns the tick aligned clock monotonic time of the next pending
 * timer or KTIME_MAX if no timer is pending.
1457
 */
1458
u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
1459
{
1460
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
1461 1462
	u64 expires = KTIME_MAX;
	unsigned long nextevt;
1463

1464 1465 1466 1467 1468
	/*
	 * Pretend that there is no timer pending if the cpu is offline.
	 * Possible pending timers will be migrated later to an active cpu.
	 */
	if (cpu_is_offline(smp_processor_id()))
1469 1470
		return expires;

1471
	spin_lock(&base->lock);
1472
	nextevt = __next_timer_interrupt(base);
1473 1474 1475 1476 1477 1478 1479 1480
	base->next_expiry = nextevt;
	/*
	 * We have a fresh next event. Check whether we can forward the base:
	 */
	if (time_after(nextevt, jiffies))
		base->clk = jiffies;
	else if (time_after(nextevt, base->clk))
		base->clk = nextevt;
1481

1482
	if (time_before_eq(nextevt, basej)) {
1483
		expires = basem;
1484 1485
		base->is_idle = false;
	} else {
1486
		expires = basem + (nextevt - basej) * TICK_NSEC;
1487 1488 1489 1490 1491 1492 1493
		/*
		 * If we expect to sleep more than a tick, mark the base idle:
		 */
		if ((expires - basem) > TICK_NSEC)
			base->is_idle = true;
	}
	spin_unlock(&base->lock);
1494

1495
	return cmp_next_hrtimer_event(basem, expires);
1496
}
1497

1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515
/**
 * timer_clear_idle - Clear the idle state of the timer base
 *
 * Called with interrupts disabled
 */
void timer_clear_idle(void)
{
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);

	/*
	 * We do this unlocked. The worst outcome is a remote enqueue sending
	 * a pointless IPI, but taking the lock would just make the window for
	 * sending the IPI a few instructions smaller for the cost of taking
	 * the lock in the exit from idle path.
	 */
	base->is_idle = false;
}

1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528
static int collect_expired_timers(struct timer_base *base,
				  struct hlist_head *heads)
{
	/*
	 * NOHZ optimization. After a long idle sleep we need to forward the
	 * base to current jiffies. Avoid a loop by searching the bitfield for
	 * the next expiring timer.
	 */
	if ((long)(jiffies - base->clk) > 2) {
		unsigned long next = __next_timer_interrupt(base);

		/*
		 * If the next timer is ahead of time forward to current
1529
		 * jiffies, otherwise forward to the next expiry time:
1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545
		 */
		if (time_after(next, jiffies)) {
			/* The call site will increment clock! */
			base->clk = jiffies - 1;
			return 0;
		}
		base->clk = next;
	}
	return __collect_expired_timers(base, heads);
}
#else
static inline int collect_expired_timers(struct timer_base *base,
					 struct hlist_head *heads)
{
	return __collect_expired_timers(base, heads);
}
L
Linus Torvalds 已提交
1546 1547 1548
#endif

/*
D
Daniel Walker 已提交
1549
 * Called from the timer interrupt handler to charge one tick to the current
L
Linus Torvalds 已提交
1550 1551 1552 1553 1554 1555 1556
 * process.  user_tick is 1 if the tick is user time, 0 for system.
 */
void update_process_times(int user_tick)
{
	struct task_struct *p = current;

	/* Note: this timer irq context must be accounted for as well. */
1557
	account_process_tick(p, user_tick);
L
Linus Torvalds 已提交
1558
	run_local_timers();
1559
	rcu_check_callbacks(user_tick);
1560 1561
#ifdef CONFIG_IRQ_WORK
	if (in_irq())
1562
		irq_work_tick();
1563
#endif
L
Linus Torvalds 已提交
1564
	scheduler_tick();
1565
	run_posix_cpu_timers(p);
L
Linus Torvalds 已提交
1566 1567
}

1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593
/**
 * __run_timers - run all expired timers (if any) on this CPU.
 * @base: the timer vector to be processed.
 */
static inline void __run_timers(struct timer_base *base)
{
	struct hlist_head heads[LVL_DEPTH];
	int levels;

	if (!time_after_eq(jiffies, base->clk))
		return;

	spin_lock_irq(&base->lock);

	while (time_after_eq(jiffies, base->clk)) {

		levels = collect_expired_timers(base, heads);
		base->clk++;

		while (levels--)
			expire_timers(base, heads + levels);
	}
	base->running_timer = NULL;
	spin_unlock_irq(&base->lock);
}

L
Linus Torvalds 已提交
1594 1595 1596 1597 1598
/*
 * This function runs timers and the timer-tq in bottom half context.
 */
static void run_timer_softirq(struct softirq_action *h)
{
1599
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
L
Linus Torvalds 已提交
1600

1601 1602 1603
	__run_timers(base);
	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
L
Linus Torvalds 已提交
1604 1605 1606 1607 1608 1609 1610
}

/*
 * Called by the local, per-CPU timer interrupt on SMP.
 */
void run_local_timers(void)
{
1611 1612
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);

1613
	hrtimer_run_queues();
1614 1615 1616 1617 1618 1619 1620 1621 1622
	/* Raise the softirq only if required. */
	if (time_before(jiffies, base->clk)) {
		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
			return;
		/* CPU is awake, so check the deferrable base. */
		base++;
		if (time_before(jiffies, base->clk))
			return;
	}
L
Linus Torvalds 已提交
1623 1624 1625 1626 1627 1628 1629 1630 1631
	raise_softirq(TIMER_SOFTIRQ);
}

#ifdef __ARCH_WANT_SYS_ALARM

/*
 * For backwards compatibility?  This can be done in libc so Alpha
 * and all newer ports shouldn't need it.
 */
1632
SYSCALL_DEFINE1(alarm, unsigned int, seconds)
L
Linus Torvalds 已提交
1633
{
1634
	return alarm_setitimer(seconds);
L
Linus Torvalds 已提交
1635 1636 1637 1638 1639 1640
}

#endif

static void process_timeout(unsigned long __data)
{
1641
	wake_up_process((struct task_struct *)__data);
L
Linus Torvalds 已提交
1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669
}

/**
 * schedule_timeout - sleep until timeout
 * @timeout: timeout value in jiffies
 *
 * Make the current task sleep until @timeout jiffies have
 * elapsed. The routine will return immediately unless
 * the current task state has been set (see set_current_state()).
 *
 * You can set the task state as follows -
 *
 * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
 * pass before the routine returns. The routine will return 0
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task. In this case the remaining time
 * in jiffies will be returned, or 0 if the timer expired in time
 *
 * The current task state is guaranteed to be TASK_RUNNING when this
 * routine returns.
 *
 * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
 * the CPU away without a bound on the timeout. In this case the return
 * value will be %MAX_SCHEDULE_TIMEOUT.
 *
 * In all cases the return value is guaranteed to be non-negative.
 */
1670
signed long __sched schedule_timeout(signed long timeout)
L
Linus Torvalds 已提交
1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694
{
	struct timer_list timer;
	unsigned long expire;

	switch (timeout)
	{
	case MAX_SCHEDULE_TIMEOUT:
		/*
		 * These two special cases are useful to be comfortable
		 * in the caller. Nothing more. We could take
		 * MAX_SCHEDULE_TIMEOUT from one of the negative value
		 * but I' d like to return a valid offset (>=0) to allow
		 * the caller to do everything it want with the retval.
		 */
		schedule();
		goto out;
	default:
		/*
		 * Another bit of PARANOID. Note that the retval will be
		 * 0 since no piece of kernel is supposed to do a check
		 * for a negative retval of schedule_timeout() (since it
		 * should never happens anyway). You just have the printk()
		 * that will tell you if something is gone wrong and where.
		 */
1695
		if (timeout < 0) {
L
Linus Torvalds 已提交
1696
			printk(KERN_ERR "schedule_timeout: wrong timeout "
1697 1698
				"value %lx\n", timeout);
			dump_stack();
L
Linus Torvalds 已提交
1699 1700 1701 1702 1703 1704 1705
			current->state = TASK_RUNNING;
			goto out;
		}
	}

	expire = timeout + jiffies;

1706
	setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
1707
	__mod_timer(&timer, expire, false);
L
Linus Torvalds 已提交
1708 1709 1710
	schedule();
	del_singleshot_timer_sync(&timer);

1711 1712 1713
	/* Remove the timer from the object tracker */
	destroy_timer_on_stack(&timer);

L
Linus Torvalds 已提交
1714 1715 1716 1717 1718 1719 1720
	timeout = expire - jiffies;

 out:
	return timeout < 0 ? 0 : timeout;
}
EXPORT_SYMBOL(schedule_timeout);

1721 1722 1723 1724
/*
 * We can use __set_current_state() here because schedule_timeout() calls
 * schedule() unconditionally.
 */
1725 1726
signed long __sched schedule_timeout_interruptible(signed long timeout)
{
A
Andrew Morton 已提交
1727 1728
	__set_current_state(TASK_INTERRUPTIBLE);
	return schedule_timeout(timeout);
1729 1730 1731
}
EXPORT_SYMBOL(schedule_timeout_interruptible);

M
Matthew Wilcox 已提交
1732 1733 1734 1735 1736 1737 1738
signed long __sched schedule_timeout_killable(signed long timeout)
{
	__set_current_state(TASK_KILLABLE);
	return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_killable);

1739 1740
signed long __sched schedule_timeout_uninterruptible(signed long timeout)
{
A
Andrew Morton 已提交
1741 1742
	__set_current_state(TASK_UNINTERRUPTIBLE);
	return schedule_timeout(timeout);
1743 1744 1745
}
EXPORT_SYMBOL(schedule_timeout_uninterruptible);

1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756
/*
 * Like schedule_timeout_uninterruptible(), except this task will not contribute
 * to load average.
 */
signed long __sched schedule_timeout_idle(signed long timeout)
{
	__set_current_state(TASK_IDLE);
	return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_idle);

L
Linus Torvalds 已提交
1757
#ifdef CONFIG_HOTPLUG_CPU
1758
static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head)
L
Linus Torvalds 已提交
1759 1760
{
	struct timer_list *timer;
1761
	int cpu = new_base->cpu;
L
Linus Torvalds 已提交
1762

1763 1764
	while (!hlist_empty(head)) {
		timer = hlist_entry(head->first, struct timer_list, entry);
1765
		detach_timer(timer, false);
1766
		timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu;
L
Linus Torvalds 已提交
1767 1768 1769 1770
		internal_add_timer(new_base, timer);
	}
}

1771
static void migrate_timers(int cpu)
L
Linus Torvalds 已提交
1772
{
1773 1774
	struct timer_base *old_base;
	struct timer_base *new_base;
1775
	int b, i;
L
Linus Torvalds 已提交
1776 1777

	BUG_ON(cpu_online(cpu));
1778

1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792
	for (b = 0; b < NR_BASES; b++) {
		old_base = per_cpu_ptr(&timer_bases[b], cpu);
		new_base = get_cpu_ptr(&timer_bases[b]);
		/*
		 * The caller is globally serialized and nobody else
		 * takes two locks at once, deadlock is not possible.
		 */
		spin_lock_irq(&new_base->lock);
		spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);

		BUG_ON(old_base->running_timer);

		for (i = 0; i < WHEEL_SIZE; i++)
			migrate_timer_list(new_base, old_base->vectors + i);
1793

1794 1795 1796 1797
		spin_unlock(&old_base->lock);
		spin_unlock_irq(&new_base->lock);
		put_cpu_ptr(&timer_bases);
	}
L
Linus Torvalds 已提交
1798 1799
}

1800
static int timer_cpu_notify(struct notifier_block *self,
L
Linus Torvalds 已提交
1801 1802
				unsigned long action, void *hcpu)
{
1803
	switch (action) {
L
Linus Torvalds 已提交
1804
	case CPU_DEAD:
1805
	case CPU_DEAD_FROZEN:
1806
		migrate_timers((long)hcpu);
L
Linus Torvalds 已提交
1807 1808 1809 1810
		break;
	default:
		break;
	}
1811

L
Linus Torvalds 已提交
1812 1813 1814
	return NOTIFY_OK;
}

1815 1816 1817 1818 1819 1820 1821
static inline void timer_register_cpu_notifier(void)
{
	cpu_notifier(timer_cpu_notify, 0);
}
#else
static inline void timer_register_cpu_notifier(void) { }
#endif /* CONFIG_HOTPLUG_CPU */
L
Linus Torvalds 已提交
1822

1823
static void __init init_timer_cpu(int cpu)
1824
{
1825 1826
	struct timer_base *base;
	int i;
1827

1828 1829 1830 1831 1832 1833
	for (i = 0; i < NR_BASES; i++) {
		base = per_cpu_ptr(&timer_bases[i], cpu);
		base->cpu = cpu;
		spin_lock_init(&base->lock);
		base->clk = jiffies;
	}
1834 1835 1836
}

static void __init init_timer_cpus(void)
L
Linus Torvalds 已提交
1837
{
1838 1839
	int cpu;

1840 1841
	for_each_possible_cpu(cpu)
		init_timer_cpu(cpu);
1842
}
1843

1844 1845 1846
void __init init_timers(void)
{
	init_timer_cpus();
1847
	init_timer_stats();
1848
	timer_register_cpu_notifier();
1849
	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
L
Linus Torvalds 已提交
1850 1851 1852 1853 1854 1855 1856 1857 1858 1859
}

/**
 * msleep - sleep safely even with waitqueue interruptions
 * @msecs: Time in milliseconds to sleep for
 */
void msleep(unsigned int msecs)
{
	unsigned long timeout = msecs_to_jiffies(msecs) + 1;

1860 1861
	while (timeout)
		timeout = schedule_timeout_uninterruptible(timeout);
L
Linus Torvalds 已提交
1862 1863 1864 1865 1866
}

EXPORT_SYMBOL(msleep);

/**
1867
 * msleep_interruptible - sleep waiting for signals
L
Linus Torvalds 已提交
1868 1869 1870 1871 1872 1873
 * @msecs: Time in milliseconds to sleep for
 */
unsigned long msleep_interruptible(unsigned int msecs)
{
	unsigned long timeout = msecs_to_jiffies(msecs) + 1;

1874 1875
	while (timeout && !signal_pending(current))
		timeout = schedule_timeout_interruptible(timeout);
L
Linus Torvalds 已提交
1876 1877 1878 1879
	return jiffies_to_msecs(timeout);
}

EXPORT_SYMBOL(msleep_interruptible);
1880

1881
static void __sched do_usleep_range(unsigned long min, unsigned long max)
1882 1883
{
	ktime_t kmin;
1884
	u64 delta;
1885 1886

	kmin = ktime_set(0, min * NSEC_PER_USEC);
1887
	delta = (u64)(max - min) * NSEC_PER_USEC;
1888
	schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
1889 1890 1891 1892 1893 1894 1895
}

/**
 * usleep_range - Drop in replacement for udelay where wakeup is flexible
 * @min: Minimum time in usecs to sleep
 * @max: Maximum time in usecs to sleep
 */
1896
void __sched usleep_range(unsigned long min, unsigned long max)
1897 1898 1899 1900 1901
{
	__set_current_state(TASK_UNINTERRUPTIBLE);
	do_usleep_range(min, max);
}
EXPORT_SYMBOL(usleep_range);