2019-05-19 20:08:55 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2014-01-27 12:42:01 +08:00
|
|
|
/*
|
2018-03-03 22:44:39 +08:00
|
|
|
* 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 )
|
2014-01-27 12:42:01 +08:00
|
|
|
*/
|
|
|
|
|
2016-10-08 08:02:55 +08:00
|
|
|
/* Linker adds these: start and end of __cpuidle functions */
|
|
|
|
extern char __cpuidle_text_start[], __cpuidle_text_end[];
|
|
|
|
|
2015-05-10 07:18:03 +08:00
|
|
|
/**
|
|
|
|
* 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);
|
|
|
|
}
|
|
|
|
|
2014-01-27 12:42:01 +08:00
|
|
|
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;
|
2018-03-03 22:44:39 +08:00
|
|
|
|
2014-01-27 12:42:01 +08:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
__setup("nohlt", cpu_idle_poll_setup);
|
|
|
|
|
|
|
|
static int __init cpu_idle_nopoll_setup(char *__unused)
|
|
|
|
{
|
|
|
|
cpu_idle_force_poll = 0;
|
2018-03-03 22:44:39 +08:00
|
|
|
|
2014-01-27 12:42:01 +08:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
__setup("hlt", cpu_idle_nopoll_setup);
|
|
|
|
#endif
|
|
|
|
|
2016-10-08 08:02:55 +08:00
|
|
|
static noinline int __cpuidle cpu_idle_poll(void)
|
2014-01-27 12:42:01 +08:00
|
|
|
{
|
2023-01-13 03:43:27 +08:00
|
|
|
instrumentation_begin();
|
2020-08-08 02:50:19 +08:00
|
|
|
trace_cpu_idle(0, smp_processor_id());
|
|
|
|
stop_critical_timings();
|
2023-01-13 03:43:27 +08:00
|
|
|
ct_cpuidle_enter();
|
2018-03-03 22:44:39 +08:00
|
|
|
|
2023-01-13 03:43:27 +08:00
|
|
|
raw_local_irq_enable();
|
2015-01-21 18:57:25 +08:00
|
|
|
while (!tif_need_resched() &&
|
2020-08-08 02:50:19 +08:00
|
|
|
(cpu_idle_force_poll || tick_check_broadcast_expired()))
|
2014-01-27 12:42:01 +08:00
|
|
|
cpu_relax();
|
2023-01-13 03:43:27 +08:00
|
|
|
raw_local_irq_disable();
|
2020-08-08 02:50:19 +08:00
|
|
|
|
2023-01-13 03:43:27 +08:00
|
|
|
ct_cpuidle_exit();
|
2020-08-08 02:50:19 +08:00
|
|
|
start_critical_timings();
|
|
|
|
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
|
2023-01-13 03:43:27 +08:00
|
|
|
local_irq_enable();
|
|
|
|
instrumentation_end();
|
2018-03-03 22:44:39 +08:00
|
|
|
|
2014-01-27 12:42:01 +08:00
|
|
|
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) { }
|
2023-02-14 15:05:58 +08:00
|
|
|
void __weak __noreturn arch_cpu_idle_dead(void) { while (1); }
|
2014-01-27 12:42:01 +08:00
|
|
|
void __weak arch_cpu_idle(void)
|
|
|
|
{
|
|
|
|
cpu_idle_force_poll = 1;
|
|
|
|
}
|
|
|
|
|
2015-05-10 07:18:46 +08:00
|
|
|
/**
|
|
|
|
* default_idle_call - Default CPU idle routine.
|
|
|
|
*
|
|
|
|
* To use when the cpuidle framework cannot be used.
|
|
|
|
*/
|
2016-10-08 08:02:55 +08:00
|
|
|
void __cpuidle default_idle_call(void)
|
2015-05-05 04:53:22 +08:00
|
|
|
{
|
2023-01-13 03:43:27 +08:00
|
|
|
instrumentation_begin();
|
|
|
|
if (!current_clr_polling_and_test()) {
|
2020-08-12 18:27:10 +08:00
|
|
|
trace_cpu_idle(1, smp_processor_id());
|
2015-07-21 00:34:50 +08:00
|
|
|
stop_critical_timings();
|
2020-11-20 18:50:35 +08:00
|
|
|
|
2023-01-13 03:43:27 +08:00
|
|
|
ct_cpuidle_enter();
|
2015-05-05 04:53:22 +08:00
|
|
|
arch_cpu_idle();
|
2023-01-13 03:43:27 +08:00
|
|
|
ct_cpuidle_exit();
|
2020-11-20 18:50:35 +08:00
|
|
|
|
2015-07-21 00:34:50 +08:00
|
|
|
start_critical_timings();
|
2020-08-12 18:27:10 +08:00
|
|
|
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
|
2015-07-21 00:34:50 +08:00
|
|
|
}
|
2023-01-13 03:43:27 +08:00
|
|
|
local_irq_enable();
|
|
|
|
instrumentation_end();
|
2015-05-05 04:53:22 +08:00
|
|
|
}
|
|
|
|
|
2020-06-25 19:52:53 +08:00
|
|
|
static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
|
|
|
|
struct cpuidle_device *dev)
|
|
|
|
{
|
|
|
|
if (current_clr_polling_and_test())
|
|
|
|
return -EBUSY;
|
|
|
|
|
|
|
|
return cpuidle_enter_s2idle(drv, dev);
|
|
|
|
}
|
|
|
|
|
2015-05-05 04:53:35 +08:00
|
|
|
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()) {
|
2019-11-07 22:25:12 +08:00
|
|
|
dev->last_residency_ns = 0;
|
2015-05-05 04:53:35 +08:00
|
|
|
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
|
|
|
|
*/
|
2015-05-10 07:18:46 +08:00
|
|
|
return cpuidle_enter(drv, dev, next_state);
|
2015-05-05 04:53:35 +08:00
|
|
|
}
|
|
|
|
|
2014-03-03 15:48:51 +08:00
|
|
|
/**
|
|
|
|
* cpuidle_idle_call - the main idle function
|
|
|
|
*
|
|
|
|
* NOTE: no locks or semaphores should be used here
|
2014-06-05 01:31:16 +08:00
|
|
|
*
|
2021-03-18 20:38:50 +08:00
|
|
|
* On architectures that support TIF_POLLING_NRFLAG, is called with polling
|
2014-06-05 01:31:16 +08:00
|
|
|
* set, and it returns with polling set. If it ever stops polling, it
|
|
|
|
* must clear the polling bit.
|
2014-03-03 15:48:51 +08:00
|
|
|
*/
|
2014-04-21 07:26:58 +08:00
|
|
|
static void cpuidle_idle_call(void)
|
2014-03-03 15:48:51 +08:00
|
|
|
{
|
2016-06-02 01:52:16 +08:00
|
|
|
struct cpuidle_device *dev = cpuidle_get_device();
|
2014-03-03 15:48:51 +08:00
|
|
|
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
|
2014-04-11 19:55:48 +08:00
|
|
|
int next_state, entered_state;
|
2014-03-03 15:48:51 +08:00
|
|
|
|
2014-03-03 15:48:54 +08:00
|
|
|
/*
|
|
|
|
* Check if the idle task must be rescheduled. If it is the
|
2014-04-11 19:47:16 +08:00
|
|
|
* case, exit the function after re-enabling the local irq.
|
2014-03-03 15:48:54 +08:00
|
|
|
*/
|
2014-04-11 19:47:16 +08:00
|
|
|
if (need_resched()) {
|
2014-03-03 15:48:53 +08:00
|
|
|
local_irq_enable();
|
2014-04-21 07:26:58 +08:00
|
|
|
return;
|
2014-03-03 15:48:53 +08:00
|
|
|
}
|
|
|
|
|
2014-03-03 15:48:54 +08:00
|
|
|
/*
|
2018-03-16 06:07:41 +08:00
|
|
|
* 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
|
2014-03-03 15:48:54 +08:00
|
|
|
* step to the grace period
|
|
|
|
*/
|
2014-03-03 15:48:52 +08:00
|
|
|
|
2015-05-05 04:53:22 +08:00
|
|
|
if (cpuidle_not_available(drv, dev)) {
|
2018-03-16 06:07:41 +08:00
|
|
|
tick_nohz_idle_stop_tick();
|
|
|
|
|
2015-05-05 04:53:22 +08:00
|
|
|
default_idle_call();
|
|
|
|
goto exit_idle;
|
|
|
|
}
|
2015-03-03 05:26:55 +08:00
|
|
|
|
2015-02-13 06:33:15 +08:00
|
|
|
/*
|
2017-08-10 06:13:56 +08:00
|
|
|
* Suspend-to-idle ("s2idle") is a system state in which all user space
|
2015-02-13 06:33:15 +08:00
|
|
|
* has been frozen, all I/O devices have been suspended and the only
|
2020-01-10 10:56:04 +08:00
|
|
|
* activity happens here and in interrupts (if any). In that case bypass
|
2021-03-18 20:38:50 +08:00
|
|
|
* the cpuidle governor and go straight for the deepest idle state
|
2015-02-13 06:33:15 +08:00
|
|
|
* 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.
|
|
|
|
*/
|
2016-11-29 15:03:04 +08:00
|
|
|
|
cpuidle: Allow idle injection to apply exit latency limit
In some cases it may be useful to specify an exit latency limit for
the idle state to be used during CPU idle time injection.
Instead of duplicating the information in struct cpuidle_device
or propagating the latency limit in the call stack, replace the
use_deepest_state field with forced_latency_limit_ns to represent
that limit, so that the deepest idle state with exit latency within
that limit is forced (i.e. no governors) when it is set.
A zero exit latency limit for forced idle means to use governors in
the usual way (analogous to use_deepest_state equal to "false" before
this change).
Additionally, add play_idle_precise() taking two arguments, the
duration of forced idle and the idle state exit latency limit, both
in nanoseconds, and redefine play_idle() as a wrapper around that
new function.
This change is preparatory, no functional impact is expected.
Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Subject, changelog, cpuidle_use_deepest_state() kerneldoc, whitespace ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-11-16 21:16:12 +08:00
|
|
|
if (idle_should_enter_s2idle() || dev->forced_idle_latency_limit_ns) {
|
2019-11-16 21:16:13 +08:00
|
|
|
u64 max_latency_ns;
|
|
|
|
|
2017-08-10 06:13:56 +08:00
|
|
|
if (idle_should_enter_s2idle()) {
|
2018-03-16 06:07:41 +08:00
|
|
|
|
2020-06-25 19:52:53 +08:00
|
|
|
entered_state = call_cpuidle_s2idle(drv, dev);
|
|
|
|
if (entered_state > 0)
|
2016-11-29 15:03:04 +08:00
|
|
|
goto exit_idle;
|
2018-03-16 06:07:41 +08:00
|
|
|
|
2019-11-16 21:16:13 +08:00
|
|
|
max_latency_ns = U64_MAX;
|
|
|
|
} else {
|
|
|
|
max_latency_ns = dev->forced_idle_latency_limit_ns;
|
2015-03-03 05:26:55 +08:00
|
|
|
}
|
|
|
|
|
2018-03-16 06:07:41 +08:00
|
|
|
tick_nohz_idle_stop_tick();
|
|
|
|
|
2019-11-16 21:16:13 +08:00
|
|
|
next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
|
2015-05-05 04:53:35 +08:00
|
|
|
call_cpuidle(drv, dev, next_state);
|
2015-03-03 05:26:55 +08:00
|
|
|
} else {
|
cpuidle: Return nohz hint from cpuidle_select()
Add a new pointer argument to cpuidle_select() and to the ->select
cpuidle governor callback to allow a boolean value indicating
whether or not the tick should be stopped before entering the
selected state to be returned from there.
Make the ladder governor ignore that pointer (to preserve its
current behavior) and make the menu governor return 'false" through
it if:
(1) the idle exit latency is constrained at 0, or
(2) the selected state is a polling one, or
(3) the expected idle period duration is within the tick period
range.
In addition to that, the correction factor computations in the menu
governor need to take the possibility that the tick may not be
stopped into account to avoid artificially small correction factor
values. To that end, add a mechanism to record tick wakeups, as
suggested by Peter Zijlstra, and use it to modify the menu_update()
behavior when tick wakeup occurs. Namely, if the CPU is woken up by
the tick and the return value of tick_nohz_get_sleep_length() is not
within the tick boundary, the predicted idle duration is likely too
short, so make menu_update() try to compensate for that by updating
the governor statistics as though the CPU was idle for a long time.
Since the value returned through the new argument pointer of
cpuidle_select() is not used by its caller yet, this change by
itself is not expected to alter the functionality of the code.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
2018-03-23 00:50:49 +08:00
|
|
|
bool stop_tick = true;
|
|
|
|
|
2015-03-03 05:26:55 +08:00
|
|
|
/*
|
|
|
|
* Ask the cpuidle framework to choose a convenient idle state.
|
|
|
|
*/
|
cpuidle: Return nohz hint from cpuidle_select()
Add a new pointer argument to cpuidle_select() and to the ->select
cpuidle governor callback to allow a boolean value indicating
whether or not the tick should be stopped before entering the
selected state to be returned from there.
Make the ladder governor ignore that pointer (to preserve its
current behavior) and make the menu governor return 'false" through
it if:
(1) the idle exit latency is constrained at 0, or
(2) the selected state is a polling one, or
(3) the expected idle period duration is within the tick period
range.
In addition to that, the correction factor computations in the menu
governor need to take the possibility that the tick may not be
stopped into account to avoid artificially small correction factor
values. To that end, add a mechanism to record tick wakeups, as
suggested by Peter Zijlstra, and use it to modify the menu_update()
behavior when tick wakeup occurs. Namely, if the CPU is woken up by
the tick and the return value of tick_nohz_get_sleep_length() is not
within the tick boundary, the predicted idle duration is likely too
short, so make menu_update() try to compensate for that by updating
the governor statistics as though the CPU was idle for a long time.
Since the value returned through the new argument pointer of
cpuidle_select() is not used by its caller yet, this change by
itself is not expected to alter the functionality of the code.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
2018-03-23 00:50:49 +08:00
|
|
|
next_state = cpuidle_select(drv, dev, &stop_tick);
|
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>
2018-04-04 05:17:11 +08:00
|
|
|
|
2018-08-10 01:08:34 +08:00
|
|
|
if (stop_tick || tick_nohz_tick_stopped())
|
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>
2018-04-04 05:17:11 +08:00
|
|
|
tick_nohz_idle_stop_tick();
|
|
|
|
else
|
|
|
|
tick_nohz_idle_retain_tick();
|
|
|
|
|
2015-05-05 04:53:35 +08:00
|
|
|
entered_state = call_cpuidle(drv, dev, next_state);
|
|
|
|
/*
|
|
|
|
* Give the governor an opportunity to reflect on the outcome
|
|
|
|
*/
|
2015-03-03 05:26:55 +08:00
|
|
|
cpuidle_reflect(dev, entered_state);
|
2015-05-05 04:53:35 +08:00
|
|
|
}
|
2014-04-11 19:55:48 +08:00
|
|
|
|
|
|
|
exit_idle:
|
2014-03-03 15:48:53 +08:00
|
|
|
__current_set_polling();
|
2014-03-03 15:48:51 +08:00
|
|
|
|
2014-03-03 15:48:54 +08:00
|
|
|
/*
|
2014-04-11 19:55:48 +08:00
|
|
|
* It is up to the idle functions to reenable local interrupts
|
2014-03-03 15:48:54 +08:00
|
|
|
*/
|
2014-03-03 15:48:52 +08:00
|
|
|
if (WARN_ON_ONCE(irqs_disabled()))
|
|
|
|
local_irq_enable();
|
2014-03-03 15:48:51 +08:00
|
|
|
}
|
|
|
|
|
2014-01-27 12:42:01 +08:00
|
|
|
/*
|
|
|
|
* Generic idle loop implementation
|
2014-06-05 01:31:16 +08:00
|
|
|
*
|
|
|
|
* Called with polling cleared.
|
2014-01-27 12:42:01 +08:00
|
|
|
*/
|
2016-11-29 15:03:05 +08:00
|
|
|
static void do_idle(void)
|
2014-01-27 12:42:01 +08:00
|
|
|
{
|
sched/idle: Micro-optimize the idle loop
Move the loop-invariant calculation of 'cpu' in do_idle() out of the loop body,
because the current CPU is always constant.
This improves the generated code both on x86-64 and ARM64:
x86-64:
Before patch (execution in loop):
864: 0f ae e8 lfence
867: 65 8b 05 c2 38 f1 7e mov %gs:0x7ef138c2(%rip),%eax
86e: 89 c0 mov %eax,%eax
870: 48 0f a3 05 68 19 08 bt %rax,0x1081968(%rip)
877: 01
After patch (execution in loop):
872: 0f ae e8 lfence
875: 4c 0f a3 25 63 19 08 bt %r12,0x1081963(%rip)
87c: 01
ARM64:
Before patch (execution in loop):
c58: d5033d9f dsb ld
c5c: d538d080 mrs x0, tpidr_el1
c60: b8606a61 ldr w1, [x19,x0]
c64: 1100fc20 add w0, w1, #0x3f
c68: 7100003f cmp w1, #0x0
c6c: 1a81b000 csel w0, w0, w1, lt
c70: 13067c00 asr w0, w0, #6
c74: 93407c00 sxtw x0, w0
c78: f8607a80 ldr x0, [x20,x0,lsl #3]
c7c: 9ac12401 lsr x1, x0, x1
c80: 36000581 tbz w1, #0, d30 <do_idle+0x128>
After patch (execution in loop):
c84: d5033d9f dsb ld
c88: f9400260 ldr x0, [x19]
c8c: ea14001f tst x0, x20
c90: 54000580 b.eq d40 <do_idle+0x138>
Signed-off-by: Cheng Jian <cj.chengjian@huawei.com>
[ Rewrote the title and the changelog. ]
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: huawei.libin@huawei.com
Cc: xiexiuqi@huawei.com
Link: http://lkml.kernel.org/r/1508930907-107755-1-git-send-email-cj.chengjian@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-25 19:28:27 +08:00
|
|
|
int cpu = smp_processor_id();
|
2021-02-24 21:30:06 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Check if we need to update blocked load
|
|
|
|
*/
|
|
|
|
nohz_run_idle_balance(cpu);
|
|
|
|
|
2016-11-29 15:03:05 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2014-01-27 12:42:01 +08:00
|
|
|
|
2016-11-29 15:03:05 +08:00
|
|
|
__current_set_polling();
|
|
|
|
tick_nohz_idle_enter();
|
2014-01-27 12:42:01 +08:00
|
|
|
|
2016-11-29 15:03:05 +08:00
|
|
|
while (!need_resched()) {
|
|
|
|
rmb();
|
2014-01-27 12:42:01 +08:00
|
|
|
|
2019-06-05 22:46:43 +08:00
|
|
|
local_irq_disable();
|
|
|
|
|
sched/idle: Micro-optimize the idle loop
Move the loop-invariant calculation of 'cpu' in do_idle() out of the loop body,
because the current CPU is always constant.
This improves the generated code both on x86-64 and ARM64:
x86-64:
Before patch (execution in loop):
864: 0f ae e8 lfence
867: 65 8b 05 c2 38 f1 7e mov %gs:0x7ef138c2(%rip),%eax
86e: 89 c0 mov %eax,%eax
870: 48 0f a3 05 68 19 08 bt %rax,0x1081968(%rip)
877: 01
After patch (execution in loop):
872: 0f ae e8 lfence
875: 4c 0f a3 25 63 19 08 bt %r12,0x1081963(%rip)
87c: 01
ARM64:
Before patch (execution in loop):
c58: d5033d9f dsb ld
c5c: d538d080 mrs x0, tpidr_el1
c60: b8606a61 ldr w1, [x19,x0]
c64: 1100fc20 add w0, w1, #0x3f
c68: 7100003f cmp w1, #0x0
c6c: 1a81b000 csel w0, w0, w1, lt
c70: 13067c00 asr w0, w0, #6
c74: 93407c00 sxtw x0, w0
c78: f8607a80 ldr x0, [x20,x0,lsl #3]
c7c: 9ac12401 lsr x1, x0, x1
c80: 36000581 tbz w1, #0, d30 <do_idle+0x128>
After patch (execution in loop):
c84: d5033d9f dsb ld
c88: f9400260 ldr x0, [x19]
c8c: ea14001f tst x0, x20
c90: 54000580 b.eq d40 <do_idle+0x138>
Signed-off-by: Cheng Jian <cj.chengjian@huawei.com>
[ Rewrote the title and the changelog. ]
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: huawei.libin@huawei.com
Cc: xiexiuqi@huawei.com
Link: http://lkml.kernel.org/r/1508930907-107755-1-git-send-email-cj.chengjian@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-25 19:28:27 +08:00
|
|
|
if (cpu_is_offline(cpu)) {
|
2019-06-05 22:46:43 +08:00
|
|
|
tick_nohz_idle_stop_tick();
|
2016-11-29 15:03:05 +08:00
|
|
|
cpuhp_report_idle_dead();
|
|
|
|
arch_cpu_idle_dead();
|
2014-01-27 12:42:01 +08:00
|
|
|
}
|
2014-02-25 01:22:07 +08:00
|
|
|
|
2016-11-29 15:03:05 +08:00
|
|
|
arch_cpu_idle_enter();
|
2021-02-01 07:05:45 +08:00
|
|
|
rcu_nocb_flush_deferred_wakeup();
|
2014-06-05 01:31:16 +08:00
|
|
|
|
|
|
|
/*
|
2016-11-29 15:03:05 +08:00
|
|
|
* 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.
|
2014-06-05 01:31:16 +08:00
|
|
|
*/
|
2018-03-16 06:05:50 +08:00
|
|
|
if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
|
|
|
|
tick_nohz_idle_restart_tick();
|
2016-11-29 15:03:05 +08:00
|
|
|
cpu_idle_poll();
|
2018-03-16 06:05:50 +08:00
|
|
|
} else {
|
2016-11-29 15:03:05 +08:00
|
|
|
cpuidle_idle_call();
|
2018-03-16 06:05:50 +08:00
|
|
|
}
|
2016-11-29 15:03:05 +08:00
|
|
|
arch_cpu_idle_exit();
|
2014-01-27 12:42:01 +08:00
|
|
|
}
|
2016-11-29 15:03:05 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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();
|
|
|
|
|
2020-05-27 00:11:01 +08:00
|
|
|
/*
|
|
|
|
* RCU relies on this call to be done outside of an RCU read-side
|
|
|
|
* critical section.
|
|
|
|
*/
|
2022-04-13 21:31:03 +08:00
|
|
|
flush_smp_call_function_queue();
|
sched/core: Call __schedule() from do_idle() without enabling preemption
I finally got around to creating trampolines for dynamically allocated
ftrace_ops with using synchronize_rcu_tasks(). For users of the ftrace
function hook callbacks, like perf, that allocate the ftrace_ops
descriptor via kmalloc() and friends, ftrace was not able to optimize
the functions being traced to use a trampoline because they would also
need to be allocated dynamically. The problem is that they cannot be
freed when CONFIG_PREEMPT is set, as there's no way to tell if a task
was preempted on the trampoline. That was before Paul McKenney
implemented synchronize_rcu_tasks() that would make sure all tasks
(except idle) have scheduled out or have entered user space.
While testing this, I triggered this bug:
BUG: unable to handle kernel paging request at ffffffffa0230077
...
RIP: 0010:0xffffffffa0230077
...
Call Trace:
schedule+0x5/0xe0
schedule_preempt_disabled+0x18/0x30
do_idle+0x172/0x220
What happened was that the idle task was preempted on the trampoline.
As synchronize_rcu_tasks() ignores the idle thread, there's nothing
that lets ftrace know that the idle task was preempted on a trampoline.
The idle task shouldn't need to ever enable preemption. The idle task
is simply a loop that calls schedule or places the cpu into idle mode.
In fact, having preemption enabled is inefficient, because it can
happen when idle is just about to call schedule anyway, which would
cause schedule to be called twice. Once for when the interrupt came in
and was returning back to normal context, and then again in the normal
path that the idle loop is running in, which would be pointless, as it
had already scheduled.
The only reason schedule_preempt_disable() enables preemption is to be
able to call sched_submit_work(), which requires preemption enabled. As
this is a nop when the task is in the RUNNING state, and idle is always
in the running state, there's no reason that idle needs to enable
preemption. But that means it cannot use schedule_preempt_disable() as
other callers of that function require calling sched_submit_work().
Adding a new function local to kernel/sched/ that allows idle to call
the scheduler without enabling preemption, fixes the
synchronize_rcu_tasks() issue, as well as removes the pointless spurious
schedule calls caused by interrupts happening in the brief window where
preemption is enabled just before it calls schedule.
Reviewed: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170414084809.3dacde2a@gandalf.local.home
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-14 20:48:09 +08:00
|
|
|
schedule_idle();
|
livepatch: change to a per-task consistency model
Change livepatch to use a basic per-task consistency model. This is the
foundation which will eventually enable us to patch those ~10% of
security patches which change function or data semantics. This is the
biggest remaining piece needed to make livepatch more generally useful.
This code stems from the design proposal made by Vojtech [1] in November
2014. It's a hybrid of kGraft and kpatch: it uses kGraft's per-task
consistency and syscall barrier switching combined with kpatch's stack
trace switching. There are also a number of fallback options which make
it quite flexible.
Patches are applied on a per-task basis, when the task is deemed safe to
switch over. When a patch is enabled, livepatch enters into a
transition state where tasks are converging to the patched state.
Usually this transition state can complete in a few seconds. The same
sequence occurs when a patch is disabled, except the tasks converge from
the patched state to the unpatched state.
An interrupt handler inherits the patched state of the task it
interrupts. The same is true for forked tasks: the child inherits the
patched state of the parent.
Livepatch uses several complementary approaches to determine when it's
safe to patch tasks:
1. The first and most effective approach is stack checking of sleeping
tasks. If no affected functions are on the stack of a given task,
the task is patched. In most cases this will patch most or all of
the tasks on the first try. Otherwise it'll keep trying
periodically. This option is only available if the architecture has
reliable stacks (HAVE_RELIABLE_STACKTRACE).
2. The second approach, if needed, is kernel exit switching. A
task is switched when it returns to user space from a system call, a
user space IRQ, or a signal. It's useful in the following cases:
a) Patching I/O-bound user tasks which are sleeping on an affected
function. In this case you have to send SIGSTOP and SIGCONT to
force it to exit the kernel and be patched.
b) Patching CPU-bound user tasks. If the task is highly CPU-bound
then it will get patched the next time it gets interrupted by an
IRQ.
c) In the future it could be useful for applying patches for
architectures which don't yet have HAVE_RELIABLE_STACKTRACE. In
this case you would have to signal most of the tasks on the
system. However this isn't supported yet because there's
currently no way to patch kthreads without
HAVE_RELIABLE_STACKTRACE.
3. For idle "swapper" tasks, since they don't ever exit the kernel, they
instead have a klp_update_patch_state() call in the idle loop which
allows them to be patched before the CPU enters the idle state.
(Note there's not yet such an approach for kthreads.)
All the above approaches may be skipped by setting the 'immediate' flag
in the 'klp_patch' struct, which will disable per-task consistency and
patch all tasks immediately. This can be useful if the patch doesn't
change any function or data semantics. Note that, even with this flag
set, it's possible that some tasks may still be running with an old
version of the function, until that function returns.
There's also an 'immediate' flag in the 'klp_func' struct which allows
you to specify that certain functions in the patch can be applied
without per-task consistency. This might be useful if you want to patch
a common function like schedule(), and the function change doesn't need
consistency but the rest of the patch does.
For architectures which don't have HAVE_RELIABLE_STACKTRACE, the user
must set patch->immediate which causes all tasks to be patched
immediately. This option should be used with care, only when the patch
doesn't change any function or data semantics.
In the future, architectures which don't have HAVE_RELIABLE_STACKTRACE
may be allowed to use per-task consistency if we can come up with
another way to patch kthreads.
The /sys/kernel/livepatch/<patch>/transition file shows whether a patch
is in transition. Only a single patch (the topmost patch on the stack)
can be in transition at a given time. A patch can remain in transition
indefinitely, if any of the tasks are stuck in the initial patch state.
A transition can be reversed and effectively canceled by writing the
opposite value to the /sys/kernel/livepatch/<patch>/enabled file while
the transition is in progress. Then all the tasks will attempt to
converge back to the original patch state.
[1] https://lkml.kernel.org/r/20141107140458.GA21774@suse.cz
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Miroslav Benes <mbenes@suse.cz>
Acked-by: Ingo Molnar <mingo@kernel.org> # for the scheduler changes
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2017-02-14 09:42:40 +08:00
|
|
|
|
|
|
|
if (unlikely(klp_patch_pending(current)))
|
|
|
|
klp_update_patch_state(current);
|
2014-01-27 12:42:01 +08:00
|
|
|
}
|
|
|
|
|
2016-10-08 08:02:55 +08:00
|
|
|
bool cpu_in_idle(unsigned long pc)
|
|
|
|
{
|
|
|
|
return pc >= (unsigned long)__cpuidle_text_start &&
|
|
|
|
pc < (unsigned long)__cpuidle_text_end;
|
|
|
|
}
|
|
|
|
|
2016-11-29 15:03:05 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
cpuidle: Allow idle injection to apply exit latency limit
In some cases it may be useful to specify an exit latency limit for
the idle state to be used during CPU idle time injection.
Instead of duplicating the information in struct cpuidle_device
or propagating the latency limit in the call stack, replace the
use_deepest_state field with forced_latency_limit_ns to represent
that limit, so that the deepest idle state with exit latency within
that limit is forced (i.e. no governors) when it is set.
A zero exit latency limit for forced idle means to use governors in
the usual way (analogous to use_deepest_state equal to "false" before
this change).
Additionally, add play_idle_precise() taking two arguments, the
duration of forced idle and the idle state exit latency limit, both
in nanoseconds, and redefine play_idle() as a wrapper around that
new function.
This change is preparatory, no functional impact is expected.
Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Subject, changelog, cpuidle_use_deepest_state() kerneldoc, whitespace ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-11-16 21:16:12 +08:00
|
|
|
void play_idle_precise(u64 duration_ns, u64 latency_ns)
|
2016-11-29 15:03:05 +08:00
|
|
|
{
|
|
|
|
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));
|
cpuidle: Allow idle injection to apply exit latency limit
In some cases it may be useful to specify an exit latency limit for
the idle state to be used during CPU idle time injection.
Instead of duplicating the information in struct cpuidle_device
or propagating the latency limit in the call stack, replace the
use_deepest_state field with forced_latency_limit_ns to represent
that limit, so that the deepest idle state with exit latency within
that limit is forced (i.e. no governors) when it is set.
A zero exit latency limit for forced idle means to use governors in
the usual way (analogous to use_deepest_state equal to "false" before
this change).
Additionally, add play_idle_precise() taking two arguments, the
duration of forced idle and the idle state exit latency limit, both
in nanoseconds, and redefine play_idle() as a wrapper around that
new function.
This change is preparatory, no functional impact is expected.
Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Subject, changelog, cpuidle_use_deepest_state() kerneldoc, whitespace ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-11-16 21:16:12 +08:00
|
|
|
WARN_ON_ONCE(!duration_ns);
|
2020-10-20 21:47:14 +08:00
|
|
|
WARN_ON_ONCE(current->mm);
|
2016-11-29 15:03:05 +08:00
|
|
|
|
|
|
|
rcu_sleep_check();
|
|
|
|
preempt_disable();
|
|
|
|
current->flags |= PF_IDLE;
|
cpuidle: Allow idle injection to apply exit latency limit
In some cases it may be useful to specify an exit latency limit for
the idle state to be used during CPU idle time injection.
Instead of duplicating the information in struct cpuidle_device
or propagating the latency limit in the call stack, replace the
use_deepest_state field with forced_latency_limit_ns to represent
that limit, so that the deepest idle state with exit latency within
that limit is forced (i.e. no governors) when it is set.
A zero exit latency limit for forced idle means to use governors in
the usual way (analogous to use_deepest_state equal to "false" before
this change).
Additionally, add play_idle_precise() taking two arguments, the
duration of forced idle and the idle state exit latency limit, both
in nanoseconds, and redefine play_idle() as a wrapper around that
new function.
This change is preparatory, no functional impact is expected.
Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Subject, changelog, cpuidle_use_deepest_state() kerneldoc, whitespace ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-11-16 21:16:12 +08:00
|
|
|
cpuidle_use_deepest_state(latency_ns);
|
2016-11-29 15:03:05 +08:00
|
|
|
|
|
|
|
it.done = 0;
|
2021-09-06 19:30:34 +08:00
|
|
|
hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
|
2016-11-29 15:03:05 +08:00
|
|
|
it.timer.function = idle_inject_timer_fn;
|
cpuidle: Allow idle injection to apply exit latency limit
In some cases it may be useful to specify an exit latency limit for
the idle state to be used during CPU idle time injection.
Instead of duplicating the information in struct cpuidle_device
or propagating the latency limit in the call stack, replace the
use_deepest_state field with forced_latency_limit_ns to represent
that limit, so that the deepest idle state with exit latency within
that limit is forced (i.e. no governors) when it is set.
A zero exit latency limit for forced idle means to use governors in
the usual way (analogous to use_deepest_state equal to "false" before
this change).
Additionally, add play_idle_precise() taking two arguments, the
duration of forced idle and the idle state exit latency limit, both
in nanoseconds, and redefine play_idle() as a wrapper around that
new function.
This change is preparatory, no functional impact is expected.
Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Subject, changelog, cpuidle_use_deepest_state() kerneldoc, whitespace ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-11-16 21:16:12 +08:00
|
|
|
hrtimer_start(&it.timer, ns_to_ktime(duration_ns),
|
2021-09-06 19:30:34 +08:00
|
|
|
HRTIMER_MODE_REL_PINNED_HARD);
|
2016-11-29 15:03:05 +08:00
|
|
|
|
|
|
|
while (!READ_ONCE(it.done))
|
|
|
|
do_idle();
|
|
|
|
|
cpuidle: Allow idle injection to apply exit latency limit
In some cases it may be useful to specify an exit latency limit for
the idle state to be used during CPU idle time injection.
Instead of duplicating the information in struct cpuidle_device
or propagating the latency limit in the call stack, replace the
use_deepest_state field with forced_latency_limit_ns to represent
that limit, so that the deepest idle state with exit latency within
that limit is forced (i.e. no governors) when it is set.
A zero exit latency limit for forced idle means to use governors in
the usual way (analogous to use_deepest_state equal to "false" before
this change).
Additionally, add play_idle_precise() taking two arguments, the
duration of forced idle and the idle state exit latency limit, both
in nanoseconds, and redefine play_idle() as a wrapper around that
new function.
This change is preparatory, no functional impact is expected.
Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Subject, changelog, cpuidle_use_deepest_state() kerneldoc, whitespace ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-11-16 21:16:12 +08:00
|
|
|
cpuidle_use_deepest_state(0);
|
2016-11-29 15:03:05 +08:00
|
|
|
current->flags &= ~PF_IDLE;
|
|
|
|
|
|
|
|
preempt_fold_need_resched();
|
|
|
|
preempt_enable();
|
|
|
|
}
|
cpuidle: Allow idle injection to apply exit latency limit
In some cases it may be useful to specify an exit latency limit for
the idle state to be used during CPU idle time injection.
Instead of duplicating the information in struct cpuidle_device
or propagating the latency limit in the call stack, replace the
use_deepest_state field with forced_latency_limit_ns to represent
that limit, so that the deepest idle state with exit latency within
that limit is forced (i.e. no governors) when it is set.
A zero exit latency limit for forced idle means to use governors in
the usual way (analogous to use_deepest_state equal to "false" before
this change).
Additionally, add play_idle_precise() taking two arguments, the
duration of forced idle and the idle state exit latency limit, both
in nanoseconds, and redefine play_idle() as a wrapper around that
new function.
This change is preparatory, no functional impact is expected.
Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Subject, changelog, cpuidle_use_deepest_state() kerneldoc, whitespace ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-11-16 21:16:12 +08:00
|
|
|
EXPORT_SYMBOL_GPL(play_idle_precise);
|
2016-11-29 15:03:05 +08:00
|
|
|
|
2014-01-27 12:42:01 +08:00
|
|
|
void cpu_startup_entry(enum cpuhp_state state)
|
|
|
|
{
|
2023-09-16 01:44:44 +08:00
|
|
|
current->flags |= PF_IDLE;
|
2014-01-27 12:42:01 +08:00
|
|
|
arch_cpu_idle_prepare();
|
2016-02-27 02:43:41 +08:00
|
|
|
cpuhp_online_idle(state);
|
2016-11-29 15:03:05 +08:00
|
|
|
while (1)
|
|
|
|
do_idle();
|
2014-01-27 12:42:01 +08:00
|
|
|
}
|
2018-03-03 22:44:39 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* idle-task scheduling class.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
static int
|
2020-11-03 02:45:13 +08:00
|
|
|
select_task_rq_idle(struct task_struct *p, int cpu, int flags)
|
2018-03-03 22:44:39 +08:00
|
|
|
{
|
|
|
|
return task_cpu(p); /* IDLE tasks as never migrated */
|
|
|
|
}
|
2019-11-08 18:11:52 +08:00
|
|
|
|
|
|
|
static int
|
|
|
|
balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
|
|
|
|
{
|
|
|
|
return WARN_ON_ONCE(1);
|
|
|
|
}
|
2018-03-03 22:44:39 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Idle tasks are unconditionally rescheduled:
|
|
|
|
*/
|
|
|
|
static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
|
|
|
|
{
|
|
|
|
resched_curr(rq);
|
|
|
|
}
|
|
|
|
|
2019-11-08 18:11:52 +08:00
|
|
|
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
|
2019-05-30 04:36:41 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2019-11-08 21:16:00 +08:00
|
|
|
static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
|
2018-03-03 22:44:39 +08:00
|
|
|
{
|
|
|
|
update_idle_core(rq);
|
|
|
|
schedstat_inc(rq->sched_goidle);
|
2019-05-30 04:36:41 +08:00
|
|
|
}
|
|
|
|
|
2020-11-18 07:19:32 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
static struct task_struct *pick_task_idle(struct rq *rq)
|
|
|
|
{
|
|
|
|
return rq->idle;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2019-11-08 21:15:58 +08:00
|
|
|
struct task_struct *pick_next_task_idle(struct rq *rq)
|
2018-03-03 22:44:39 +08:00
|
|
|
{
|
2019-05-30 04:36:41 +08:00
|
|
|
struct task_struct *next = rq->idle;
|
|
|
|
|
2019-11-08 21:16:00 +08:00
|
|
|
set_next_task_idle(rq, next, true);
|
2018-03-03 22:44:39 +08:00
|
|
|
|
2019-05-30 04:36:41 +08:00
|
|
|
return next;
|
2018-03-03 22:44:39 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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)
|
|
|
|
{
|
2020-11-18 07:19:31 +08:00
|
|
|
raw_spin_rq_unlock_irq(rq);
|
2018-03-03 22:44:39 +08:00
|
|
|
printk(KERN_ERR "bad: scheduling from the idle thread!\n");
|
|
|
|
dump_stack();
|
2020-11-18 07:19:31 +08:00
|
|
|
raw_spin_rq_lock_irq(rq);
|
2018-03-03 22:44:39 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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 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 void update_curr_idle(struct rq *rq)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Simple, special scheduling class for the per-CPU idle tasks:
|
|
|
|
*/
|
2020-10-21 21:45:33 +08:00
|
|
|
DEFINE_SCHED_CLASS(idle) = {
|
|
|
|
|
2018-03-03 22:44:39 +08:00
|
|
|
/* 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,
|
2019-05-30 04:36:41 +08:00
|
|
|
.set_next_task = set_next_task_idle,
|
2018-03-03 22:44:39 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
2019-11-08 18:11:52 +08:00
|
|
|
.balance = balance_idle,
|
2020-11-18 07:19:32 +08:00
|
|
|
.pick_task = pick_task_idle,
|
2018-03-03 22:44:39 +08:00
|
|
|
.select_task_rq = select_task_rq_idle,
|
|
|
|
.set_cpus_allowed = set_cpus_allowed_common,
|
|
|
|
#endif
|
|
|
|
|
|
|
|
.task_tick = task_tick_idle,
|
|
|
|
|
|
|
|
.prio_changed = prio_changed_idle,
|
|
|
|
.switched_to = switched_to_idle,
|
|
|
|
.update_curr = update_curr_idle,
|
|
|
|
};
|