ab86e974f0
Pull core timer updates from Ingo Molnar:
"The main changes in this cycle's merge are:
- Implement shadow timekeeper to shorten in kernel reader side
blocking, by Thomas Gleixner.
- Posix timers enhancements by Pavel Emelyanov:
- allocate timer ID per process, so that exact timer ID allocations
can be re-created be checkpoint/restore code.
- debuggability and tooling (/proc/PID/timers, etc.) improvements.
- suspend/resume enhancements by Feng Tang: on certain new Intel Atom
processors (Penwell and Cloverview), there is a feature that the
TSC won't stop in S3 state, so the TSC value won't be reset to 0
after resume. This can be taken advantage of by the generic via
the CLOCK_SOURCE_SUSPEND_NONSTOP flag: instead of using the RTC to
recover/approximate sleep time, the main (and precise) clocksource
can be used.
- Fix /proc/timer_list for 4096 CPUs by Nathan Zimmer: on so many
CPUs the file goes beyond 4MB of size and thus the current
simplistic seqfile approach fails. Convert /proc/timer_list to a
proper seq_file with its own iterator.
- Cleanups and refactorings of the core timekeeping code by John
Stultz.
- International Atomic Clock time is managed by the NTP code
internally currently but not exposed externally. Separate the TAI
code out and add CLOCK_TAI support and TAI support to the hrtimer
and posix-timer code, by John Stultz.
- Add deep idle support enhacement to the broadcast clockevents core
timer code, by Daniel Lezcano: add an opt-in CLOCK_EVT_FEAT_DYNIRQ
clockevents feature (which will be utilized by future clockevents
driver updates), which allows the use of IRQ affinities to avoid
spurious wakeups of idle CPUs - the right CPU with an expiring
timer will be woken.
- Add new ARM bcm281xx clocksource driver, by Christian Daudt
- ... various other fixes and cleanups"
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits)
clockevents: Set dummy handler on CPU_DEAD shutdown
timekeeping: Update tk->cycle_last in resume
posix-timers: Remove unused variable
clockevents: Switch into oneshot mode even if broadcast registered late
timer_list: Convert timer list to be a proper seq_file
timer_list: Split timer_list_show_tickdevices
posix-timers: Show sigevent info in proc file
posix-timers: Introduce /proc/PID/timers file
posix timers: Allocate timer id per process (v2)
timekeeping: Make sure to notify hrtimers when TAI offset changes
hrtimer: Fix ktime_add_ns() overflow on 32bit architectures
hrtimer: Add expiry time overflow check in hrtimer_interrupt
timekeeping: Shorten seq_count region
timekeeping: Implement a shadow timekeeper
timekeeping: Delay update of clock->cycle_last
timekeeping: Store cycle_last value in timekeeper struct as well
ntp: Remove ntp_lock, using the timekeeping locks to protect ntp state
timekeeping: Simplify tai updating from do_adjtimex
timekeeping: Hold timekeepering locks in do_adjtimex and hardpps
timekeeping: Move ADJ_SETOFFSET to top level do_adjtimex()
...
116 lines
2.4 KiB
C
116 lines
2.4 KiB
C
/*
|
|
* Generic entry point for the idle threads
|
|
*/
|
|
#include <linux/sched.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/mm.h>
|
|
|
|
#include <asm/tlb.h>
|
|
|
|
#include <trace/events/power.h>
|
|
|
|
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 inline int cpu_idle_poll(void)
|
|
{
|
|
trace_cpu_idle_rcuidle(0, smp_processor_id());
|
|
local_irq_enable();
|
|
while (!need_resched())
|
|
cpu_relax();
|
|
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
|
|
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;
|
|
}
|
|
|
|
/*
|
|
* Generic idle loop implementation
|
|
*/
|
|
static void cpu_idle_loop(void)
|
|
{
|
|
while (1) {
|
|
tick_nohz_idle_enter();
|
|
|
|
while (!need_resched()) {
|
|
check_pgt_cache();
|
|
rmb();
|
|
|
|
if (cpu_is_offline(smp_processor_id()))
|
|
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()) {
|
|
cpu_idle_poll();
|
|
} else {
|
|
current_clr_polling();
|
|
if (!need_resched()) {
|
|
stop_critical_timings();
|
|
rcu_idle_enter();
|
|
arch_cpu_idle();
|
|
WARN_ON_ONCE(irqs_disabled());
|
|
rcu_idle_exit();
|
|
start_critical_timings();
|
|
} else {
|
|
local_irq_enable();
|
|
}
|
|
current_set_polling();
|
|
}
|
|
arch_cpu_idle_exit();
|
|
}
|
|
tick_nohz_idle_exit();
|
|
schedule_preempt_disabled();
|
|
}
|
|
}
|
|
|
|
void cpu_startup_entry(enum cpuhp_state state)
|
|
{
|
|
current_set_polling();
|
|
arch_cpu_idle_prepare();
|
|
cpu_idle_loop();
|
|
}
|