forked from mirrors/linux
3785c7dbae
In architectures that use the polling bit, current_clr_polling() employs smp_mb() to ensure that the clearing of the polling bit is visible to other cores before checking TIF_NEED_RESCHED. However, smp_mb() can be costly. Given that clear_bit() is an atomic operation, replacing smp_mb() with smp_mb__after_atomic() is appropriate. Many architectures implement smp_mb__after_atomic() as a lighter-weight barrier compared to smp_mb(), leading to performance improvements. For instance, on x86, smp_mb__after_atomic() is a no-op. This change eliminates a smp_mb() instruction in the cpuidle wake-up path, saving several CPU cycles and thereby reducing wake-up latency. Architectures that do not use the polling bit will retain the original smp_mb() behavior to ensure that existing dependencies remain unaffected. Signed-off-by: Yujun Dong <yujundong@pascal-lab.net> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lore.kernel.org/r/20241230141624.155356-1-yujundong@pascal-lab.net
120 lines
2.6 KiB
C
120 lines
2.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_SCHED_IDLE_H
|
|
#define _LINUX_SCHED_IDLE_H
|
|
|
|
#include <linux/sched.h>
|
|
|
|
enum cpu_idle_type {
|
|
__CPU_NOT_IDLE = 0,
|
|
CPU_IDLE,
|
|
CPU_NEWLY_IDLE,
|
|
CPU_MAX_IDLE_TYPES
|
|
};
|
|
|
|
#ifdef CONFIG_SMP
|
|
extern void wake_up_if_idle(int cpu);
|
|
#else
|
|
static inline void wake_up_if_idle(int cpu) { }
|
|
#endif
|
|
|
|
/*
|
|
* Idle thread specific functions to determine the need_resched
|
|
* polling state.
|
|
*/
|
|
#ifdef TIF_POLLING_NRFLAG
|
|
|
|
#ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H
|
|
|
|
static __always_inline void __current_set_polling(void)
|
|
{
|
|
arch_set_bit(TIF_POLLING_NRFLAG,
|
|
(unsigned long *)(¤t_thread_info()->flags));
|
|
}
|
|
|
|
static __always_inline void __current_clr_polling(void)
|
|
{
|
|
arch_clear_bit(TIF_POLLING_NRFLAG,
|
|
(unsigned long *)(¤t_thread_info()->flags));
|
|
}
|
|
|
|
#else
|
|
|
|
static __always_inline void __current_set_polling(void)
|
|
{
|
|
set_bit(TIF_POLLING_NRFLAG,
|
|
(unsigned long *)(¤t_thread_info()->flags));
|
|
}
|
|
|
|
static __always_inline void __current_clr_polling(void)
|
|
{
|
|
clear_bit(TIF_POLLING_NRFLAG,
|
|
(unsigned long *)(¤t_thread_info()->flags));
|
|
}
|
|
|
|
#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H */
|
|
|
|
static __always_inline bool __must_check current_set_polling_and_test(void)
|
|
{
|
|
__current_set_polling();
|
|
|
|
/*
|
|
* Polling state must be visible before we test NEED_RESCHED,
|
|
* paired by resched_curr()
|
|
*/
|
|
smp_mb__after_atomic();
|
|
|
|
return unlikely(tif_need_resched());
|
|
}
|
|
|
|
static __always_inline bool __must_check current_clr_polling_and_test(void)
|
|
{
|
|
__current_clr_polling();
|
|
|
|
/*
|
|
* Polling state must be visible before we test NEED_RESCHED,
|
|
* paired by resched_curr()
|
|
*/
|
|
smp_mb__after_atomic();
|
|
|
|
return unlikely(tif_need_resched());
|
|
}
|
|
|
|
static __always_inline void current_clr_polling(void)
|
|
{
|
|
__current_clr_polling();
|
|
|
|
/*
|
|
* Ensure we check TIF_NEED_RESCHED after we clear the polling bit.
|
|
* Once the bit is cleared, we'll get IPIs with every new
|
|
* TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
|
|
* fold.
|
|
*/
|
|
smp_mb__after_atomic(); /* paired with resched_curr() */
|
|
|
|
preempt_fold_need_resched();
|
|
}
|
|
|
|
#else
|
|
static inline void __current_set_polling(void) { }
|
|
static inline void __current_clr_polling(void) { }
|
|
|
|
static inline bool __must_check current_set_polling_and_test(void)
|
|
{
|
|
return unlikely(tif_need_resched());
|
|
}
|
|
static inline bool __must_check current_clr_polling_and_test(void)
|
|
{
|
|
return unlikely(tif_need_resched());
|
|
}
|
|
|
|
static __always_inline void current_clr_polling(void)
|
|
{
|
|
__current_clr_polling();
|
|
|
|
smp_mb(); /* paired with resched_curr() */
|
|
|
|
preempt_fold_need_resched();
|
|
}
|
|
#endif
|
|
|
|
#endif /* _LINUX_SCHED_IDLE_H */
|