#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
#include <linux/module.h>
#include <asm/irq_regs.h>
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
unsigned long flags;
- cpumask_clear_cpu(cpu, nohz_cpu_mask);
ts->idle_waketime = now;
local_irq_save(flags);
/*
* Updates the per cpu time idle statistics counters
*/
-static void update_ts_time_stats(struct tick_sched *ts, ktime_t now)
+static void
+update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time)
{
ktime_t delta;
- ts->idle_lastupdate = now;
if (ts->idle_active) {
delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ if (nr_iowait_cpu(cpu) > 0)
+ ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+ else
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
ts->idle_entrytime = now;
}
+
+ if (last_update_time)
+ *last_update_time = ktime_to_us(now);
+
}
static void tick_nohz_stop_idle(int cpu, ktime_t now)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
- update_ts_time_stats(ts, now);
+ update_ts_time_stats(cpu, ts, now, NULL);
ts->idle_active = 0;
sched_clock_idle_wakeup_event(0);
}
-static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
+static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
{
ktime_t now;
now = ktime_get();
- update_ts_time_stats(ts, now);
+ update_ts_time_stats(cpu, ts, now, NULL);
ts->idle_entrytime = now;
ts->idle_active = 1;
/**
* get_cpu_idle_time_us - get the total idle time of a cpu
* @cpu: CPU number to query
- * @last_update_time: variable to store update time in
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
*
* Return the cummulative idle time (since boot) for a given
- * CPU, in microseconds. The idle time returned includes
- * the iowait time (unlike what "top" and co report).
+ * CPU, in microseconds.
*
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
- ktime_t now;
+ ktime_t now, idle;
if (!tick_nohz_enabled)
return -1;
now = ktime_get();
- update_ts_time_stats(ts, now);
+ if (last_update_time) {
+ update_ts_time_stats(cpu, ts, now, last_update_time);
+ idle = ts->idle_sleeptime;
+ } else {
+ if (ts->idle_active && !nr_iowait_cpu(cpu)) {
+ ktime_t delta = ktime_sub(now, ts->idle_entrytime);
- if (ts->idle_active)
- *last_update_time = ktime_to_us(ts->idle_lastupdate);
- else
- *last_update_time = ktime_to_us(now);
+ idle = ktime_add(ts->idle_sleeptime, delta);
+ } else {
+ idle = ts->idle_sleeptime;
+ }
+ }
+
+ return ktime_to_us(idle);
- return ktime_to_us(ts->idle_sleeptime);
}
EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
/**
+ * get_cpu_iowait_time_us - get the total iowait time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
+ *
+ * Return the cummulative iowait time (since boot) for a given
+ * CPU, in microseconds.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
+u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now, iowait;
+
+ if (!tick_nohz_enabled)
+ return -1;
+
+ now = ktime_get();
+ if (last_update_time) {
+ update_ts_time_stats(cpu, ts, now, last_update_time);
+ iowait = ts->iowait_sleeptime;
+ } else {
+ if (ts->idle_active && nr_iowait_cpu(cpu) > 0) {
+ ktime_t delta = ktime_sub(now, ts->idle_entrytime);
+
+ iowait = ktime_add(ts->iowait_sleeptime, delta);
+ } else {
+ iowait = ts->iowait_sleeptime;
+ }
+ }
+
+ return ktime_to_us(iowait);
+}
+EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
+
+/**
* tick_nohz_stop_sched_tick - stop the idle tick from the idle task
*
* When the next event is more than a tick into the future, stop the idle tick
*/
ts->inidle = 1;
- now = tick_nohz_start_idle(ts);
+ now = tick_nohz_start_idle(cpu, ts);
/*
* If this cpu is offline and it is the one which updates
goto end;
}
- if (nohz_ratelimit(cpu))
- goto end;
-
ts->idle_calls++;
/* Read jiffies and the time when jiffies were updated last */
do {
else
expires.tv64 = KTIME_MAX;
- if (delta_jiffies > 1)
- cpumask_set_cpu(cpu, nohz_cpu_mask);
-
/* Skip reprogram of event if its not changed */
if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
goto out;
* the scheduler tick in nohz_restart_sched_tick.
*/
if (!ts->tick_stopped) {
- if (select_nohz_load_balancer(1)) {
- /*
- * sched tick not stopped!
- */
- cpumask_clear_cpu(cpu, nohz_cpu_mask);
- goto out;
- }
+ select_nohz_load_balancer(1);
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
* softirq.
*/
tick_do_update_jiffies64(ktime_get());
- cpumask_clear_cpu(cpu, nohz_cpu_mask);
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
hrtimer_get_expires(&ts->sched_timer), 0))
break;
}
- /* Update jiffies and reread time */
- tick_do_update_jiffies64(now);
+ /* Reread time and update jiffies */
now = ktime_get();
+ tick_do_update_jiffies64(now);
}
}
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
- cpumask_clear_cpu(cpu, nohz_cpu_mask);
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
/*
next = ktime_add(next, tick_period);
}
local_irq_enable();
-
- printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n",
- smp_processor_id());
}
/*
{
struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t now = ktime_get();
- u64 offset;
/*
* Emulate tick processing via per-CPU hrtimers:
/* Get the next period (per cpu) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
- offset = ktime_to_ns(tick_period) >> 1;
- do_div(offset, num_possible_cpus());
- offset *= smp_processor_id();
- hrtimer_add_expires_ns(&ts->sched_timer, offset);
for (;;) {
hrtimer_forward(&ts->sched_timer, now, tick_period);