mirror of
https://github.com/torvalds/linux.git
synced 2024-12-09 20:51:43 +00:00
554c8aa8ec
In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
91 lines
2.7 KiB
C
91 lines
2.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _TICK_SCHED_H
|
|
#define _TICK_SCHED_H
|
|
|
|
#include <linux/hrtimer.h>
|
|
|
|
enum tick_device_mode {
|
|
TICKDEV_MODE_PERIODIC,
|
|
TICKDEV_MODE_ONESHOT,
|
|
};
|
|
|
|
struct tick_device {
|
|
struct clock_event_device *evtdev;
|
|
enum tick_device_mode mode;
|
|
};
|
|
|
|
enum tick_nohz_mode {
|
|
NOHZ_MODE_INACTIVE,
|
|
NOHZ_MODE_LOWRES,
|
|
NOHZ_MODE_HIGHRES,
|
|
};
|
|
|
|
/**
|
|
* struct tick_sched - sched tick emulation and no idle tick control/stats
|
|
* @sched_timer: hrtimer to schedule the periodic tick in high
|
|
* resolution mode
|
|
* @last_tick: Store the last tick expiry time when the tick
|
|
* timer is modified for nohz sleeps. This is necessary
|
|
* to resume the tick timer operation in the timeline
|
|
* when the CPU returns from nohz sleep.
|
|
* @next_tick: Next tick to be fired when in dynticks mode.
|
|
* @tick_stopped: Indicator that the idle tick has been stopped
|
|
* @idle_jiffies: jiffies at the entry to idle for idle time accounting
|
|
* @idle_calls: Total number of idle calls
|
|
* @idle_sleeps: Number of idle calls, where the sched tick was stopped
|
|
* @idle_entrytime: Time when the idle call was entered
|
|
* @idle_waketime: Time when the idle was interrupted
|
|
* @idle_exittime: Time when the idle state was left
|
|
* @idle_sleeptime: Sum of the time slept in idle with sched tick stopped
|
|
* @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding
|
|
* @timer_expires: Anticipated timer expiration time (in case sched tick is stopped)
|
|
* @timer_expires_base: Base time clock monotonic for @timer_expires
|
|
* @do_timer_lst: CPU was the last one doing do_timer before going idle
|
|
*/
|
|
struct tick_sched {
|
|
struct hrtimer sched_timer;
|
|
unsigned long check_clocks;
|
|
enum tick_nohz_mode nohz_mode;
|
|
ktime_t last_tick;
|
|
ktime_t next_tick;
|
|
int inidle;
|
|
int tick_stopped;
|
|
unsigned long idle_jiffies;
|
|
unsigned long idle_calls;
|
|
unsigned long idle_sleeps;
|
|
int idle_active;
|
|
ktime_t idle_entrytime;
|
|
ktime_t idle_waketime;
|
|
ktime_t idle_exittime;
|
|
ktime_t idle_sleeptime;
|
|
ktime_t iowait_sleeptime;
|
|
unsigned long last_jiffies;
|
|
u64 timer_expires;
|
|
u64 timer_expires_base;
|
|
u64 next_timer;
|
|
ktime_t idle_expires;
|
|
int do_timer_last;
|
|
atomic_t tick_dep_mask;
|
|
};
|
|
|
|
extern struct tick_sched *tick_get_tick_sched(int cpu);
|
|
|
|
extern void tick_setup_sched_timer(void);
|
|
#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
|
|
extern void tick_cancel_sched_timer(int cpu);
|
|
#else
|
|
static inline void tick_cancel_sched_timer(int cpu) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
|
|
extern int __tick_broadcast_oneshot_control(enum tick_broadcast_state state);
|
|
#else
|
|
static inline int
|
|
__tick_broadcast_oneshot_control(enum tick_broadcast_state state)
|
|
{
|
|
return -EBUSY;
|
|
}
|
|
#endif
|
|
|
|
#endif
|