Commit 9269d27e authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'timers-nohz-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull timers/nohz updates from Ingo Molnar:

 - Micro-optimize tick_nohz_full_cpu()

 - Optimize idle exit tick restarts to be less eager

 - Optimize tick_nohz_dep_set_task() to only wake up a single CPU.
   This reduces IPIs and interruptions on nohz_full CPUs.

 - Optimize tick_nohz_dep_set_signal() in a similar fashion.

 - Skip IPIs in tick_nohz_kick_task() when trying to kick a
   non-running task.

 - Micro-optimize tick_nohz_task_switch() IRQ flags handling to
   reduce context switching costs.

 - Misc cleanups and fixes

* tag 'timers-nohz-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  MAINTAINERS: Add myself as context tracking maintainer
  tick/nohz: Call tick_nohz_task_switch() with interrupts disabled
  tick/nohz: Kick only _queued_ task whose tick dependency is updated
  tick/nohz: Change signal tick dependency to wake up CPUs of member tasks
  tick/nohz: Only wake up a single target cpu when kicking a task
  tick/nohz: Update nohz_full Kconfig help
  tick/nohz: Update idle_exittime on actual idle exit
  tick/nohz: Remove superflous check for CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
  tick/nohz: Conditionally restart tick on idle exit
  tick/nohz: Evaluate the CPU expression after the static key
parents 54a728dc 09fe880e

MAINTAINERS

+6 −0
Original line number Diff line number Diff line
@@ -4610,6 +4610,12 @@ S: Supported 
F:	drivers/video/console/

F:	include/linux/console*









CONTEXT TRACKING









M:	Frederic Weisbecker <frederic@kernel.org>









S:	Maintained









F:	kernel/context_tracking.c









F:	include/linux/context_tracking*

















CONTROL GROUP (CGROUP)









M:	Tejun Heo <tj@kernel.org>









M:	Zefan Li <lizefan.x@bytedance.com>
































include/linux/sched.h



+2
−0






























Original line number
Diff line number
Diff line







@@ -2028,6 +2028,8 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)

















#endif /* CONFIG_SMP */



















extern bool sched_task_on_rq(struct task_struct *p);



















/*









 * In order to reduce various lock holder preemption latencies provide an









 * interface to see if a vCPU is currently running or not.
































include/linux/tick.h



+15
−11






























Original line number
Diff line number
Diff line







@@ -186,13 +186,17 @@ static inline bool tick_nohz_full_enabled(void)







	return tick_nohz_full_running;









}



















static inline bool tick_nohz_full_cpu(int cpu)









{









	if (!tick_nohz_full_enabled())









		return false;



















	return cpumask_test_cpu(cpu, tick_nohz_full_mask);









}









/*









 * Check if a CPU is part of the nohz_full subset. Arrange for evaluating









 * the cpu expression (typically smp_processor_id()) _after_ the static









 * key.









 */









#define tick_nohz_full_cpu(_cpu) ({					\









	bool __ret = false;						\









	if (tick_nohz_full_enabled())					\









		__ret = cpumask_test_cpu((_cpu), tick_nohz_full_mask);	\









	__ret;								\









})



















static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask)









{








@@ -208,7 +212,7 @@ extern void tick_nohz_dep_set_task(struct task_struct *tsk,







				   enum tick_dep_bits bit);









extern void tick_nohz_dep_clear_task(struct task_struct *tsk,









				     enum tick_dep_bits bit);









extern void tick_nohz_dep_set_signal(struct signal_struct *signal,









extern void tick_nohz_dep_set_signal(struct task_struct *tsk,









				     enum tick_dep_bits bit);









extern void tick_nohz_dep_clear_signal(struct signal_struct *signal,









				       enum tick_dep_bits bit);








@@ -253,11 +257,11 @@ static inline void tick_dep_clear_task(struct task_struct *tsk,







	if (tick_nohz_full_enabled())









		tick_nohz_dep_clear_task(tsk, bit);









}









static inline void tick_dep_set_signal(struct signal_struct *signal,









static inline void tick_dep_set_signal(struct task_struct *tsk,









				       enum tick_dep_bits bit)









{









	if (tick_nohz_full_enabled())









		tick_nohz_dep_set_signal(signal, bit);









		tick_nohz_dep_set_signal(tsk, bit);









}









static inline void tick_dep_clear_signal(struct signal_struct *signal,









					 enum tick_dep_bits bit)








@@ -285,7 +289,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk,







				     enum tick_dep_bits bit) { }









static inline void tick_dep_clear_task(struct task_struct *tsk,









				       enum tick_dep_bits bit) { }









static inline void tick_dep_set_signal(struct signal_struct *signal,









static inline void tick_dep_set_signal(struct task_struct *tsk,









				       enum tick_dep_bits bit) { }









static inline void tick_dep_clear_signal(struct signal_struct *signal,









					 enum tick_dep_bits bit) { }
































kernel/sched/core.c



+6
−1






























Original line number
Diff line number
Diff line







@@ -1928,6 +1928,11 @@ static inline void uclamp_post_fork(struct task_struct *p) { }







static inline void init_uclamp(void) { }









#endif /* CONFIG_UCLAMP_TASK */



















bool sched_task_on_rq(struct task_struct *p)









{









	return task_on_rq_queued(p);









}



















static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)









{









	if (!(flags & ENQUEUE_NOCLOCK))








@@ -4546,6 +4551,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)







	vtime_task_switch(prev);









	perf_event_task_sched_in(prev, current);









	finish_task(prev);









	tick_nohz_task_switch();









	finish_lock_switch(rq);









	finish_arch_post_lock_switch();









	kcov_finish_switch(current);








@@ -4591,7 +4597,6 @@ static struct rq *finish_task_switch(struct task_struct *prev)







		put_task_struct_rcu_user(prev);









	}



















	tick_nohz_task_switch();









	return rq;









}










































kernel/time/Kconfig



+6
−5






























Original line number
Diff line number
Diff line







@@ -117,13 +117,14 @@ config NO_HZ_FULL







	 the task mostly runs in userspace and has few kernel activity.



















	 You need to fill up the nohz_full boot parameter with the









	 desired range of dynticks CPUs.









	 desired range of dynticks CPUs to use it. This is implemented at









	 the expense of some overhead in user <-> kernel transitions:









	 syscalls, exceptions and interrupts.



















	 This is implemented at the expense of some overhead in user <-> kernel









	 transitions: syscalls, exceptions and interrupts. Even when it's









	 dynamically off.









	 By default, without passing the nohz_full parameter, this behaves just









	 like NO_HZ_IDLE.



















	 Say N.









	 If you're a distro say Y.



















endchoice