summaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-04-11 17:03:20 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-04-11 17:03:20 -0700
commit1fe43114ea7355ec9f336c942aaf3e74d27483a0 (patch)
treea42dfb282f2e3fb3adaa9359494081c67da66293 /kernel/sched
parent96973767594fe9c5d8a7e8fc594c9e565ab0374e (diff)
parent51798deaffb738ef3bdd4f544b11ce2adaff40f3 (diff)
Merge tag 'pm-4.17-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull more power management updates from Rafael Wysocki: "These include one big-ticket item which is the rework of the idle loop in order to prevent CPUs from spending too much time in shallow idle states. It reduces idle power on some systems by 10% or more and may improve performance of workloads in which the idle loop overhead matters. This has been in the works for several weeks and it has been tested and reviewed quite thoroughly. Also included are changes that finalize the cpufreq cleanup moving frequency table validation from drivers to the core, a few fixes and cleanups of cpufreq drivers, a cpuidle documentation update and a PM QoS core update to mark the expected switch fall-throughs in it. Specifics: - Rework the idle loop in order to prevent CPUs from spending too much time in shallow idle states by making it stop the scheduler tick before putting the CPU into an idle state only if the idle duration predicted by the idle governor is long enough. That required the code to be reordered to invoke the idle governor before stopping the tick, among other things (Rafael Wysocki, Frederic Weisbecker, Arnd Bergmann). - Add the missing description of the residency sysfs attribute to the cpuidle documentation (Prashanth Prakash). - Finalize the cpufreq cleanup moving frequency table validation from drivers to the core (Viresh Kumar). - Fix a clock leak regression in the armada-37xx cpufreq driver (Gregory Clement). - Fix the initialization of the CPU performance data structures for shared policies in the CPPC cpufreq driver (Shunyong Yang). - Clean up the ti-cpufreq, intel_pstate and CPPC cpufreq drivers a bit (Viresh Kumar, Rafael Wysocki). - Mark the expected switch fall-throughs in the PM QoS core (Gustavo Silva)" * tag 'pm-4.17-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (23 commits) tick-sched: avoid a maybe-uninitialized warning cpufreq: Drop cpufreq_table_validate_and_show() cpufreq: SCMI: Don't validate the frequency table twice cpufreq: CPPC: Initialize shared perf capabilities of CPUs cpufreq: armada-37xx: Fix clock leak cpufreq: CPPC: Don't set transition_latency cpufreq: ti-cpufreq: Use builtin_platform_driver() cpufreq: intel_pstate: Do not include debugfs.h PM / QoS: mark expected switch fall-throughs cpuidle: Add definition of residency to sysfs documentation time: hrtimer: Use timerqueue_iterate_next() to get to the next timer nohz: Avoid duplication of code related to got_idle_tick nohz: Gather tick_sched booleans under a common flag field cpuidle: menu: Avoid selecting shallow states with stopped tick cpuidle: menu: Refine idle state selection for running tick sched: idle: Select idle state before stopping the tick time: hrtimer: Introduce hrtimer_next_event_without() time: tick-sched: Split tick_nohz_stop_sched_tick() cpuidle: Return nohz hint from cpuidle_select() jiffies: Introduce USER_TICK_USEC and redefine TICK_USEC ...
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/idle.c34
1 files changed, 28 insertions, 6 deletions
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 2975f195e1c4..1a3e9bddd17b 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -141,13 +141,15 @@ static void cpuidle_idle_call(void)
}
/*
- * Tell the RCU framework we are entering an idle section,
- * so no more rcu read side critical sections and one more
+ * The RCU framework needs to be told that we are entering an idle
+ * section, so no more rcu read side critical sections and one more
* step to the grace period
*/
- rcu_idle_enter();
if (cpuidle_not_available(drv, dev)) {
+ tick_nohz_idle_stop_tick();
+ rcu_idle_enter();
+
default_idle_call();
goto exit_idle;
}
@@ -164,20 +166,37 @@ static void cpuidle_idle_call(void)
if (idle_should_enter_s2idle() || dev->use_deepest_state) {
if (idle_should_enter_s2idle()) {
+ rcu_idle_enter();
+
entered_state = cpuidle_enter_s2idle(drv, dev);
if (entered_state > 0) {
local_irq_enable();
goto exit_idle;
}
+
+ rcu_idle_exit();
}
+ tick_nohz_idle_stop_tick();
+ rcu_idle_enter();
+
next_state = cpuidle_find_deepest_state(drv, dev);
call_cpuidle(drv, dev, next_state);
} else {
+ bool stop_tick = true;
+
/*
* Ask the cpuidle framework to choose a convenient idle state.
*/
- next_state = cpuidle_select(drv, dev);
+ next_state = cpuidle_select(drv, dev, &stop_tick);
+
+ if (stop_tick)
+ tick_nohz_idle_stop_tick();
+ else
+ tick_nohz_idle_retain_tick();
+
+ rcu_idle_enter();
+
entered_state = call_cpuidle(drv, dev, next_state);
/*
* Give the governor an opportunity to reflect on the outcome
@@ -222,6 +241,7 @@ static void do_idle(void)
rmb();
if (cpu_is_offline(cpu)) {
+ tick_nohz_idle_stop_tick_protected();
cpuhp_report_idle_dead();
arch_cpu_idle_dead();
}
@@ -235,10 +255,12 @@ static void do_idle(void)
* broadcast device expired for us, we don't want to go deep
* idle as we know that the IPI is going to arrive right away.
*/
- if (cpu_idle_force_poll || tick_check_broadcast_expired())
+ if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
+ tick_nohz_idle_restart_tick();
cpu_idle_poll();
- else
+ } else {
cpuidle_idle_call();
+ }
arch_cpu_idle_exit();
}