time: track accurate idle time with tick_sched.idle_sleeptime
Current idle time in kstat is based on jiffies and is coarse grained.
tick_sched.idle_sleeptime is making some attempt to keep track of idle time
in a fine grained manner. But, it is not handling the time spent in
interrupts fully.
Make tick_sched.idle_sleeptime accurate with respect to time spent on
handling interrupts and also add tick_sched.idle_lastupdate, which keeps
track of last time when idle_sleeptime was updated.
This statistics will be crucial for cpufreq-ondemand governor, which can
shed some conservative gaurd band that is uses today while setting the
frequency. The ondemand changes that uses the exact idle time is coming
soon.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 49e12f6..63f24b5 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -143,6 +143,44 @@
local_irq_restore(flags);
}
+void tick_nohz_stop_idle(int cpu)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+ if (ts->idle_active) {
+ ktime_t now, delta;
+ now = ktime_get();
+ delta = ktime_sub(now, ts->idle_entrytime);
+ ts->idle_lastupdate = now;
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ ts->idle_active = 0;
+ }
+}
+
+static ktime_t tick_nohz_start_idle(int cpu)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now, delta;
+
+ now = ktime_get();
+ if (ts->idle_active) {
+ delta = ktime_sub(now, ts->idle_entrytime);
+ ts->idle_lastupdate = now;
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ }
+ ts->idle_entrytime = now;
+ ts->idle_active = 1;
+ return now;
+}
+
+u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+ *last_update_time = ktime_to_us(ts->idle_lastupdate);
+ return ktime_to_us(ts->idle_sleeptime);
+}
+
/**
* tick_nohz_stop_sched_tick - stop the idle tick from the idle task
*
@@ -155,13 +193,14 @@
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
unsigned long rt_jiffies;
struct tick_sched *ts;
- ktime_t last_update, expires, now, delta;
+ ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
int cpu;
local_irq_save(flags);
cpu = smp_processor_id();
+ now = tick_nohz_start_idle(cpu);
ts = &per_cpu(tick_cpu_sched, cpu);
/*
@@ -193,19 +232,7 @@
}
}
- now = ktime_get();
- /*
- * When called from irq_exit we need to account the idle sleep time
- * correctly.
- */
- if (ts->tick_stopped) {
- delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
- }
-
- ts->idle_entrytime = now;
ts->idle_calls++;
-
/* Read jiffies and the time when jiffies were updated last */
do {
seq = read_seqbegin(&xtime_lock);
@@ -337,23 +364,22 @@
int cpu = smp_processor_id();
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
unsigned long ticks;
- ktime_t now, delta;
-
- if (!ts->tick_stopped)
- return;
-
- /* Update jiffies first */
- now = ktime_get();
+ ktime_t now;
local_irq_disable();
+ tick_nohz_stop_idle(cpu);
+
+ if (!ts->tick_stopped) {
+ local_irq_enable();
+ return;
+ }
+
+ /* Update jiffies first */
select_nohz_load_balancer(0);
+ now = ktime_get();
tick_do_update_jiffies64(now);
cpu_clear(cpu, nohz_cpu_mask);
- /* Account the idle time */
- delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-
/*
* We stopped the tick in idle. Update process times would miss the
* time we slept as update_process_times does only a 1 tick