aboutsummaryrefslogtreecommitdiffstats
path: root/init
diff options
context:
space:
mode:
Diffstat (limited to 'init')
-rw-r--r--init/main.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/init/main.c b/init/main.c
index 0ab82a453de5..6d38f9607d14 100644
--- a/init/main.c
+++ b/init/main.c
@@ -587,7 +587,6 @@ asmlinkage void __init start_kernel(void)
587 * kmem_cache_init() 587 * kmem_cache_init()
588 */ 588 */
589 pidhash_init(); 589 pidhash_init();
590 vmalloc_init();
591 vfs_caches_init_early(); 590 vfs_caches_init_early();
592 sort_main_extable(); 591 sort_main_extable();
593 trap_init(); 592 trap_init();
@@ -596,6 +595,7 @@ asmlinkage void __init start_kernel(void)
596 */ 595 */
597 mem_init(); 596 mem_init();
598 kmem_cache_init(); 597 kmem_cache_init();
598 vmalloc_init();
599 /* 599 /*
600 * Set up the scheduler prior starting any interrupts (such as the 600 * Set up the scheduler prior starting any interrupts (such as the
601 * timer interrupt). Full topology setup happens at smp_init() 601 * timer interrupt). Full topology setup happens at smp_init()
01'>401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576
/*
 * drivers/cpufreq/cpufreq_governor.c
 *
 * CPUFREQ governors common code
 *
 * Copyright	(C) 2001 Russell King
 *		(C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
 *		(C) 2003 Jun Nakajima <jun.nakajima@intel.com>
 *		(C) 2009 Alexander Clouter <alex@digriz.org.uk>
 *		(c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/export.h>
#include <linux/kernel_stat.h>
#include <linux/slab.h>

#include "cpufreq_governor.h"

static struct attribute_group *get_sysfs_attr(struct dbs_data *dbs_data)
{
	if (have_governor_per_policy())
		return dbs_data->cdata->attr_group_gov_pol;
	else
		return dbs_data->cdata->attr_group_gov_sys;
}

void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
{
	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
	struct cpufreq_policy *policy = cdbs->shared->policy;
	unsigned int sampling_rate;
	unsigned int max_load = 0;
	unsigned int ignore_nice;
	unsigned int j;

	if (dbs_data->cdata->governor == GOV_ONDEMAND) {
		struct od_cpu_dbs_info_s *od_dbs_info =
				dbs_data->cdata->get_cpu_dbs_info_s(cpu);

		/*
		 * Sometimes, the ondemand governor uses an additional
		 * multiplier to give long delays. So apply this multiplier to
		 * the 'sampling_rate', so as to keep the wake-up-from-idle
		 * detection logic a bit conservative.
		 */
		sampling_rate = od_tuners->sampling_rate;
		sampling_rate *= od_dbs_info->rate_mult;

		ignore_nice = od_tuners->ignore_nice_load;
	} else {
		sampling_rate = cs_tuners->sampling_rate;
		ignore_nice = cs_tuners->ignore_nice_load;
	}

	/* Get Absolute Load */
	for_each_cpu(j, policy->cpus) {
		struct cpu_dbs_info *j_cdbs;
		u64 cur_wall_time, cur_idle_time;
		unsigned int idle_time, wall_time;
		unsigned int load;
		int io_busy = 0;

		j_cdbs = dbs_data->cdata->get_cpu_cdbs(j);

		/*
		 * For the purpose of ondemand, waiting for disk IO is
		 * an indication that you're performance critical, and
		 * not that the system is actually idle. So do not add
		 * the iowait time to the cpu idle time.
		 */
		if (dbs_data->cdata->governor == GOV_ONDEMAND)
			io_busy = od_tuners->io_is_busy;
		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time, io_busy);

		wall_time = (unsigned int)
			(cur_wall_time - j_cdbs->prev_cpu_wall);
		j_cdbs->prev_cpu_wall = cur_wall_time;

		idle_time = (unsigned int)
			(cur_idle_time - j_cdbs->prev_cpu_idle);
		j_cdbs->prev_cpu_idle = cur_idle_time;

		if (ignore_nice) {
			u64 cur_nice;
			unsigned long cur_nice_jiffies;

			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
					 cdbs->prev_cpu_nice;
			/*
			 * Assumption: nice time between sampling periods will
			 * be less than 2^32 jiffies for 32 bit sys
			 */
			cur_nice_jiffies = (unsigned long)
					cputime64_to_jiffies64(cur_nice);

			cdbs->prev_cpu_nice =
				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
			idle_time += jiffies_to_usecs(cur_nice_jiffies);
		}

		if (unlikely(!wall_time || wall_time < idle_time))
			continue;

		/*
		 * If the CPU had gone completely idle, and a task just woke up
		 * on this CPU now, it would be unfair to calculate 'load' the
		 * usual way for this elapsed time-window, because it will show
		 * near-zero load, irrespective of how CPU intensive that task
		 * actually is. This is undesirable for latency-sensitive bursty
		 * workloads.
		 *
		 * To avoid this, we reuse the 'load' from the previous
		 * time-window and give this task a chance to start with a
		 * reasonably high CPU frequency. (However, we shouldn't over-do
		 * this copy, lest we get stuck at a high load (high frequency)
		 * for too long, even when the current system load has actually
		 * dropped down. So we perform the copy only once, upon the
		 * first wake-up from idle.)
		 *
		 * Detecting this situation is easy: the governor's deferrable
		 * timer would not have fired during CPU-idle periods. Hence
		 * an unusually large 'wall_time' (as compared to the sampling
		 * rate) indicates this scenario.
		 *
		 * prev_load can be zero in two cases and we must recalculate it
		 * for both cases:
		 * - during long idle intervals
		 * - explicitly set to zero
		 */
		if (unlikely(wall_time > (2 * sampling_rate) &&
			     j_cdbs->prev_load)) {
			load = j_cdbs->prev_load;

			/*
			 * Perform a destructive copy, to ensure that we copy
			 * the previous load only once, upon the first wake-up
			 * from idle.
			 */
			j_cdbs->prev_load = 0;
		} else {
			load = 100 * (wall_time - idle_time) / wall_time;
			j_cdbs->prev_load = load;
		}

		if (load > max_load)
			max_load = load;
	}

	dbs_data->cdata->gov_check_cpu(cpu, max_load);
}
EXPORT_SYMBOL_GPL(dbs_check_cpu);

static inline void __gov_queue_work(int cpu, struct dbs_data *dbs_data,
		unsigned int delay)
{
	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);

	mod_delayed_work_on(cpu, system_wq, &cdbs->dwork, delay);
}

void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
		unsigned int delay, bool all_cpus)
{
	int i;

	mutex_lock(&cpufreq_governor_lock);
	if (!policy->governor_enabled)
		goto out_unlock;

	if (!all_cpus) {
		/*
		 * Use raw_smp_processor_id() to avoid preemptible warnings.
		 * We know that this is only called with all_cpus == false from
		 * works that have been queued with *_work_on() functions and
		 * those works are canceled during CPU_DOWN_PREPARE so they
		 * can't possibly run on any other CPU.
		 */
		__gov_queue_work(raw_smp_processor_id(), dbs_data, delay);
	} else {
		for_each_cpu(i, policy->cpus)
			__gov_queue_work(i, dbs_data, delay);
	}

out_unlock:
	mutex_unlock(&cpufreq_governor_lock);
}
EXPORT_SYMBOL_GPL(gov_queue_work);

static inline void gov_cancel_work(struct dbs_data *dbs_data,
		struct cpufreq_policy *policy)
{
	struct cpu_dbs_info *cdbs;
	int i;

	for_each_cpu(i, policy->cpus) {
		cdbs = dbs_data->cdata->get_cpu_cdbs(i);
		cancel_delayed_work_sync(&cdbs->dwork);
	}
}

/* Will return if we need to evaluate cpu load again or not */
static bool need_load_eval(struct cpu_common_dbs_info *shared,
			   unsigned int sampling_rate)
{
	if (policy_is_shared(shared->policy)) {
		ktime_t time_now = ktime_get();
		s64 delta_us = ktime_us_delta(time_now, shared->time_stamp);

		/* Do nothing if we recently have sampled */
		if (delta_us < (s64)(sampling_rate / 2))
			return false;
		else
			shared->time_stamp = time_now;
	}

	return true;
}

static void dbs_timer(struct work_struct *work)
{
	struct cpu_dbs_info *cdbs = container_of(work, struct cpu_dbs_info,
						 dwork.work);
	struct cpu_common_dbs_info *shared = cdbs->shared;
	struct cpufreq_policy *policy = shared->policy;
	struct dbs_data *dbs_data = policy->governor_data;
	unsigned int sampling_rate, delay;
	bool modify_all = true;

	mutex_lock(&shared->timer_mutex);

	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;

		sampling_rate = cs_tuners->sampling_rate;
	} else {
		struct od_dbs_tuners *od_tuners = dbs_data->tuners;

		sampling_rate = od_tuners->sampling_rate;
	}

	if (!need_load_eval(cdbs->shared, sampling_rate))
		modify_all = false;

	delay = dbs_data->cdata->gov_dbs_timer(cdbs, dbs_data, modify_all);
	gov_queue_work(dbs_data, policy, delay, modify_all);

	mutex_unlock(&shared->timer_mutex);
}

static void set_sampling_rate(struct dbs_data *dbs_data,
		unsigned int sampling_rate)
{
	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
		cs_tuners->sampling_rate = sampling_rate;
	} else {
		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
		od_tuners->sampling_rate = sampling_rate;
	}
}

static int alloc_common_dbs_info(struct cpufreq_policy *policy,
				 struct common_dbs_data *cdata)
{
	struct cpu_common_dbs_info *shared;
	int j;

	/* Allocate memory for the common information for policy->cpus */