Re: [PATCH v3 5/5] softirq: Avoid unnecessary wakeup of ksoftirqd when a call to do_sofirq() is pending

[Sebastian Andrzej Siewior <bigeasy@linutronix.de>]

On 2024-10-14 09:03:39 [+0000], K Prateek Nayak wrote:
> Since commit b2a02fc43a1f4 ("smp: Optimize
> send_call_function_single_ipi()"), sending an actual interrupt to an
> idle CPU in TIF_POLLING_NRFLAG mode can be avoided by queuing the SMP
> call function on the call function queue of the CPU and setting the
> TIF_NEED_RESCHED bit in idle task's thread info. The call function is
> handled in the idle exit path when do_idle() calls
> flush_smp_call_function_queue().
> 
> However, since flush_smp_call_function_queue() is executed in idle
> thread's context, in_interrupt() check within a call function will
> return false. raise_softirq() uses this check to decide whether to wake
> ksoftirqd, since, a softirq raised from an interrupt context will be
> handled at irq exit. In all other cases, raise_softirq() wakes up
> ksoftirqd to handle the softirq on !PREEMPT_RT kernel.

Stupid question. You talk about the invocation from nohz_csd_func(),
right?.
Given that this is an IPI and always invoked from an IRQ then the
softirq is invoked on IRQ-exit. If it is flushed from
flush_smp_call_function_queue() then the softirq is handled via
do_softirq_post_smp_call_flush(). In that case couldn't you just tell
nohz_csd_func() to use __raise_softirq_irqoff(SCHED_SOFTIRQ) ? This
should solve this, right?

> diff --git a/kernel/softirq.c b/kernel/softirq.c
> index 0730c2b43ae4..3a6b3e67ea24 100644
> --- a/kernel/softirq.c
> +++ b/kernel/softirq.c
> @@ -99,6 +99,10 @@ EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
>   *
>   * The per CPU counter prevents pointless wakeups of ksoftirqd in case that
>   * the task which is in a softirq disabled section is preempted or blocks.
> + *
> + * The bottom bits of softirq_ctrl::cnt is used to indicate an impending call
> + * to do_softirq() to prevent pointless wakeups of ksoftirqd since the CPU
> + * promises to handle softirqs soon.
>   */

The comment that you are extending and the comment regarding
SOFTIRQ_OFFSET were nearby. I don't like that those two are now far
apart.

>  struct softirq_ctrl {
>  	local_lock_t	lock;
> @@ -109,6 +113,16 @@ static DEFINE_PER_CPU_ALIGNED(struct softirq_ctrl, softirq_ctrl) = {
>  	.lock	= INIT_LOCAL_LOCK(softirq_ctrl.lock),
>  };
>  
> +inline void set_do_softirq_pending(void)
> +{
> +	__this_cpu_inc(softirq_ctrl.cnt);
> +}
> +
> +inline void clr_do_softirq_pending(void)

there should be no inline here.

> +{
> +	__this_cpu_dec(softirq_ctrl.cnt);
> +}
> +
>  static inline bool should_wake_ksoftirqd(void)
>  {
>  	return !this_cpu_read(softirq_ctrl.cnt);

Sebastian