linux-stable/kernel/sched/idle.c
Rafael J. Wysocki 554c8aa8ec sched: idle: Select idle state before stopping the tick
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>
2018-04-09 11:54:07 +02:00

482 lines
11 KiB
C

/*
* Generic entry points for the idle threads and
* implementation of the idle task scheduling class.
*
* (NOTE: these are not related to SCHED_IDLE batch scheduled
* tasks which are handled in sched/fair.c )
*/
#include "sched.h"
#include <trace/events/power.h>
/* Linker adds these: start and end of __cpuidle functions */
extern char __cpuidle_text_start[], __cpuidle_text_end[];
/**
* sched_idle_set_state - Record idle state for the current CPU.
* @idle_state: State to record.
*/
void sched_idle_set_state(struct cpuidle_state *idle_state)
{
idle_set_state(this_rq(), idle_state);
}
static int __read_mostly cpu_idle_force_poll;
void cpu_idle_poll_ctrl(bool enable)
{
if (enable) {
cpu_idle_force_poll++;
} else {
cpu_idle_force_poll--;
WARN_ON_ONCE(cpu_idle_force_poll < 0);
}
}
#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
static int __init cpu_idle_poll_setup(char *__unused)
{
cpu_idle_force_poll = 1;
return 1;
}
__setup("nohlt", cpu_idle_poll_setup);
static int __init cpu_idle_nopoll_setup(char *__unused)
{
cpu_idle_force_poll = 0;
return 1;
}
__setup("hlt", cpu_idle_nopoll_setup);
#endif
static noinline int __cpuidle cpu_idle_poll(void)
{
rcu_idle_enter();
trace_cpu_idle_rcuidle(0, smp_processor_id());
local_irq_enable();
stop_critical_timings();
while (!tif_need_resched() &&
(cpu_idle_force_poll || tick_check_broadcast_expired()))
cpu_relax();
start_critical_timings();
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
rcu_idle_exit();
return 1;
}
/* Weak implementations for optional arch specific functions */
void __weak arch_cpu_idle_prepare(void) { }
void __weak arch_cpu_idle_enter(void) { }
void __weak arch_cpu_idle_exit(void) { }
void __weak arch_cpu_idle_dead(void) { }
void __weak arch_cpu_idle(void)
{
cpu_idle_force_poll = 1;
local_irq_enable();
}
/**
* default_idle_call - Default CPU idle routine.
*
* To use when the cpuidle framework cannot be used.
*/
void __cpuidle default_idle_call(void)
{
if (current_clr_polling_and_test()) {
local_irq_enable();
} else {
stop_critical_timings();
arch_cpu_idle();
start_critical_timings();
}
}
static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
int next_state)
{
/*
* The idle task must be scheduled, it is pointless to go to idle, just
* update no idle residency and return.
*/
if (current_clr_polling_and_test()) {
dev->last_residency = 0;
local_irq_enable();
return -EBUSY;
}
/*
* Enter the idle state previously returned by the governor decision.
* This function will block until an interrupt occurs and will take
* care of re-enabling the local interrupts
*/
return cpuidle_enter(drv, dev, next_state);
}
/**
* cpuidle_idle_call - the main idle function
*
* NOTE: no locks or semaphores should be used here
*
* On archs that support TIF_POLLING_NRFLAG, is called with polling
* set, and it returns with polling set. If it ever stops polling, it
* must clear the polling bit.
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = cpuidle_get_device();
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
*/
if (need_resched()) {
local_irq_enable();
return;
}
/*
* 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
*/
if (cpuidle_not_available(drv, dev)) {
tick_nohz_idle_stop_tick();
rcu_idle_enter();
default_idle_call();
goto exit_idle;
}
/*
* Suspend-to-idle ("s2idle") is a system state in which all user space
* has been frozen, all I/O devices have been suspended and the only
* activity happens here and in iterrupts (if any). In that case bypass
* the cpuidle governor and go stratight for the deepest idle state
* available. Possibly also suspend the local tick and the entire
* timekeeping to prevent timer interrupts from kicking us out of idle
* until a proper wakeup interrupt happens.
*/
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, &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
*/
cpuidle_reflect(dev, entered_state);
}
exit_idle:
__current_set_polling();
/*
* It is up to the idle functions to reenable local interrupts
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
rcu_idle_exit();
}
/*
* Generic idle loop implementation
*
* Called with polling cleared.
*/
static void do_idle(void)
{
int cpu = smp_processor_id();
/*
* If the arch has a polling bit, we maintain an invariant:
*
* Our polling bit is clear if we're not scheduled (i.e. if rq->curr !=
* rq->idle). This means that, if rq->idle has the polling bit set,
* then setting need_resched is guaranteed to cause the CPU to
* reschedule.
*/
__current_set_polling();
tick_nohz_idle_enter();
while (!need_resched()) {
check_pgt_cache();
rmb();
if (cpu_is_offline(cpu)) {
tick_nohz_idle_stop_tick_protected();
cpuhp_report_idle_dead();
arch_cpu_idle_dead();
}
local_irq_disable();
arch_cpu_idle_enter();
/*
* In poll mode we reenable interrupts and spin. Also if we
* detected in the wakeup from idle path that the tick
* 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()) {
tick_nohz_idle_restart_tick();
cpu_idle_poll();
} else {
cpuidle_idle_call();
}
arch_cpu_idle_exit();
}
/*
* Since we fell out of the loop above, we know TIF_NEED_RESCHED must
* be set, propagate it into PREEMPT_NEED_RESCHED.
*
* This is required because for polling idle loops we will not have had
* an IPI to fold the state for us.
*/
preempt_set_need_resched();
tick_nohz_idle_exit();
__current_clr_polling();
/*
* We promise to call sched_ttwu_pending() and reschedule if
* need_resched() is set while polling is set. That means that clearing
* polling needs to be visible before doing these things.
*/
smp_mb__after_atomic();
sched_ttwu_pending();
schedule_idle();
if (unlikely(klp_patch_pending(current)))
klp_update_patch_state(current);
}
bool cpu_in_idle(unsigned long pc)
{
return pc >= (unsigned long)__cpuidle_text_start &&
pc < (unsigned long)__cpuidle_text_end;
}
struct idle_timer {
struct hrtimer timer;
int done;
};
static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
{
struct idle_timer *it = container_of(timer, struct idle_timer, timer);
WRITE_ONCE(it->done, 1);
set_tsk_need_resched(current);
return HRTIMER_NORESTART;
}
void play_idle(unsigned long duration_ms)
{
struct idle_timer it;
/*
* Only FIFO tasks can disable the tick since they don't need the forced
* preemption.
*/
WARN_ON_ONCE(current->policy != SCHED_FIFO);
WARN_ON_ONCE(current->nr_cpus_allowed != 1);
WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
WARN_ON_ONCE(!duration_ms);
rcu_sleep_check();
preempt_disable();
current->flags |= PF_IDLE;
cpuidle_use_deepest_state(true);
it.done = 0;
hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
it.timer.function = idle_inject_timer_fn;
hrtimer_start(&it.timer, ms_to_ktime(duration_ms), HRTIMER_MODE_REL_PINNED);
while (!READ_ONCE(it.done))
do_idle();
cpuidle_use_deepest_state(false);
current->flags &= ~PF_IDLE;
preempt_fold_need_resched();
preempt_enable();
}
EXPORT_SYMBOL_GPL(play_idle);
void cpu_startup_entry(enum cpuhp_state state)
{
/*
* This #ifdef needs to die, but it's too late in the cycle to
* make this generic (ARM and SH have never invoked the canary
* init for the non boot CPUs!). Will be fixed in 3.11
*/
#ifdef CONFIG_X86
/*
* If we're the non-boot CPU, nothing set the stack canary up
* for us. The boot CPU already has it initialized but no harm
* in doing it again. This is a good place for updating it, as
* we wont ever return from this function (so the invalid
* canaries already on the stack wont ever trigger).
*/
boot_init_stack_canary();
#endif
arch_cpu_idle_prepare();
cpuhp_online_idle(state);
while (1)
do_idle();
}
/*
* idle-task scheduling class.
*/
#ifdef CONFIG_SMP
static int
select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
{
return task_cpu(p); /* IDLE tasks as never migrated */
}
#endif
/*
* Idle tasks are unconditionally rescheduled:
*/
static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
{
resched_curr(rq);
}
static struct task_struct *
pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
put_prev_task(rq, prev);
update_idle_core(rq);
schedstat_inc(rq->sched_goidle);
return rq->idle;
}
/*
* It is not legal to sleep in the idle task - print a warning
* message if some code attempts to do it:
*/
static void
dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
{
raw_spin_unlock_irq(&rq->lock);
printk(KERN_ERR "bad: scheduling from the idle thread!\n");
dump_stack();
raw_spin_lock_irq(&rq->lock);
}
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
{
}
/*
* scheduler tick hitting a task of our scheduling class.
*
* NOTE: This function can be called remotely by the tick offload that
* goes along full dynticks. Therefore no local assumption can be made
* and everything must be accessed through the @rq and @curr passed in
* parameters.
*/
static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
{
}
static void set_curr_task_idle(struct rq *rq)
{
}
static void switched_to_idle(struct rq *rq, struct task_struct *p)
{
BUG();
}
static void
prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
{
BUG();
}
static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
{
return 0;
}
static void update_curr_idle(struct rq *rq)
{
}
/*
* Simple, special scheduling class for the per-CPU idle tasks:
*/
const struct sched_class idle_sched_class = {
/* .next is NULL */
/* no enqueue/yield_task for idle tasks */
/* dequeue is not valid, we print a debug message there: */
.dequeue_task = dequeue_task_idle,
.check_preempt_curr = check_preempt_curr_idle,
.pick_next_task = pick_next_task_idle,
.put_prev_task = put_prev_task_idle,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_idle,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
.set_curr_task = set_curr_task_idle,
.task_tick = task_tick_idle,
.get_rr_interval = get_rr_interval_idle,
.prio_changed = prio_changed_idle,
.switched_to = switched_to_idle,
.update_curr = update_curr_idle,
};