Files
android_kernel_xiaomi_sm8450/kernel/sched/idle.c
Brendan Jackman aa8b37baac FROMLIST: sched/fair: Use wake_q length as a hint for wake_wide
This patch adds a parameter to select_task_rq, sibling_count_hint
allowing the caller, where it has this information, to inform the
sched_class the number of tasks that are being woken up as part of
the same event.

The wake_q mechanism is one case where this information is available.

select_task_rq_fair can then use the information to detect that it
needs to widen the search space for task placement in order to avoid
overloading the last-level cache domain's CPUs.

                               * * *

The reason I am investigating this change is the following use case
on ARM big.LITTLE (asymmetrical CPU capacity): 1 task per CPU, which
all repeatedly do X amount of work then
pthread_barrier_wait (i.e. sleep until the last task finishes its X
and hits the barrier). On big.LITTLE, the tasks which get a "big" CPU
finish faster, and then those CPUs pull over the tasks that are still
running:

     v CPU v           ->time->

                    -------------
   0  (big)         11111  /333
                    -------------
   1  (big)         22222   /444|
                    -------------
   2  (LITTLE)      333333/
                    -------------
   3  (LITTLE)      444444/
                    -------------

Now when task 4 hits the barrier (at |) and wakes the others up,
there are 4 tasks with prev_cpu=<big> and 0 tasks with
prev_cpu=<little>. want_affine therefore means that we'll only look
in CPUs 0 and 1 (sd_llc), so tasks will be unnecessarily coscheduled
on the bigs until the next load balance, something like this:

     v CPU v           ->time->

                    ------------------------
   0  (big)         11111  /333  31313\33333
                    ------------------------
   1  (big)         22222   /444|424\4444444
                    ------------------------
   2  (LITTLE)      333333/          \222222
                    ------------------------
   3  (LITTLE)      444444/            \1111
                    ------------------------
                                 ^^^
                           underutilization

So, I'm trying to get want_affine = 0 for these tasks.

I don't _think_ any incarnation of the wakee_flips mechanism can help
us here because which task is waker and which tasks are wakees
generally changes with each iteration.

However pthread_barrier_wait (or more accurately FUTEX_WAKE) has the
nice property that we know exactly how many tasks are being woken, so
we can cheat.

It might be a disadvantage that we "widen" _every_ task that's woken in
an event, while select_idle_sibling would work fine for the first
sd_llc_size - 1 tasks.

IIUC, if wake_affine() behaves correctly this trick wouldn't be
necessary on SMP systems, so it might be best guarded by the presence
of SD_ASYM_CPUCAPACITY?

                               * * *

Final note..

In order to observe "perfect" behaviour for this use case, I also had
to disable the TTWU_QUEUE sched feature. Suppose during the wakeup
above we are working through the work queue and have placed tasks 3
and 2, and are about to place task 1:

     v CPU v           ->time->

                    --------------
   0  (big)         11111  /333  3
                    --------------
   1  (big)         22222   /444|4
                    --------------
   2  (LITTLE)      333333/      2
                    --------------
   3  (LITTLE)      444444/          <- Task 1 should go here
                    --------------

If TTWU_QUEUE is enabled, we will not yet have enqueued task
2 (having instead sent a reschedule IPI) or attached its load to CPU
2. So we are likely to also place task 1 on cpu 2. Disabling
TTWU_QUEUE means that we enqueue task 2 before placing task 1,
solving this issue. TTWU_QUEUE is there to minimise rq lock
contention, and I guess that this contention is less of an issue on
big.LITTLE systems since they have relatively few CPUs, which
suggests the trade-off makes sense here.

Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
( - Applied from https://patchwork.kernel.org/patch/9895261/
  - Fixed trivial conflict in kernel/sched/core.c
  - Fixed select_task_rq_idle, now in kernel/sched/idle.c
  - Fixed trivial conflict in select_task_rq_fair )
Signed-off-by: Quentin Perret <quentin.perret@arm.com>
Change-Id: I3cfc4bf48c3d7feef969db4d22449f4fbb4f795d
[satyap@codeaurora.org: port to 5.4 and fix trivial merge conflicts]
Signed-off-by: Satya Durga Srinivasu Prabhala <satyap@codeaurora.org>
2019-12-10 12:51:22 -08:00

486 lines
11 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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, int index)
{
idle_set_state(this_rq(), idle_state);
idle_set_state_idx(this_rq(), index);
}
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() ||
is_reserved(smp_processor_id())))
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_tick_stopped())
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()) {
rmb();
local_irq_disable();
if (cpu_is_offline(cpu)) {
tick_nohz_idle_stop_tick();
cpuhp_report_idle_dead();
arch_cpu_idle_dead();
}
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() ||
is_reserved(smp_processor_id())) {
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_us)
{
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_us);
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, ns_to_ktime(duration_us * NSEC_PER_USEC),
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)
{
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,
int sibling_count_hint)
{
return task_cpu(p); /* IDLE tasks as never migrated */
}
static int
balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
return WARN_ON_ONCE(1);
}
#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 void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
{
}
static void set_next_task_idle(struct rq *rq, struct task_struct *next)
{
update_idle_core(rq);
schedstat_inc(rq->sched_goidle);
}
static struct task_struct *
pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *next = rq->idle;
if (prev)
put_prev_task(rq, prev);
set_next_task_idle(rq, next);
return next;
}
/*
* 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);
}
/*
* 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 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,
.set_next_task = set_next_task_idle,
#ifdef CONFIG_SMP
.balance = balance_idle,
.select_task_rq = select_task_rq_idle,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
.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,
};