Re: [RFC PATCH 0/2] net: threadable napi poll loop

[Paolo Abeni]

On Wed, 2016-05-11 at 14:56 -0700, Eric Dumazet wrote:
> On Wed, 2016-05-11 at 08:55 +0200, Peter Zijlstra wrote:
> > On Tue, May 10, 2016 at 03:51:37PM -0700, Eric Dumazet wrote:
> > > diff --git a/kernel/softirq.c b/kernel/softirq.c
> > > index 17caf4b63342..22463217e3cf 100644
> > > --- a/kernel/softirq.c
> > > +++ b/kernel/softirq.c
> > > @@ -56,6 +56,7 @@ EXPORT_SYMBOL(irq_stat);
> > >  static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
> > >  
> > >  DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
> > > +DEFINE_PER_CPU(bool, ksoftirqd_scheduled);
> > >  
> > >  const char * const softirq_to_name[NR_SOFTIRQS] = {
> > >  	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
> > > @@ -73,8 +74,10 @@ static void wakeup_softirqd(void)
> > >  	/* Interrupts are disabled: no need to stop preemption */
> > >  	struct task_struct *tsk = __this_cpu_read(ksoftirqd);
> > >  
> > > -	if (tsk && tsk->state != TASK_RUNNING)
> > > +	if (tsk && tsk->state != TASK_RUNNING) {
> > > +		__this_cpu_write(ksoftirqd_scheduled, true);
> > >  		wake_up_process(tsk);
> > 
> > Since we're already looking at tsk->state, and the wake_up_process()
> > ensures the thing becomes TASK_RUNNING, you could add:
> > 
> > static inline bool ksoftirqd_running(void)
> > {
> > 	return __this_cpu_read(ksoftirqd)->state == TASK_RUNNING;
> > }
> 
> Indeed, and the patch looks quite simple now ;)
> 
> diff --git a/kernel/softirq.c b/kernel/softirq.c
> index 17caf4b63342d7839528f367b283a386413b0362..23c364485d03618773c385d943c0ef39f5931d09 100644
> --- a/kernel/softirq.c
> +++ b/kernel/softirq.c
> @@ -57,6 +57,11 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp
>  
>  DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
>  
> +static inline bool ksoftirqd_running(void)
> +{
> +	return __this_cpu_read(ksoftirqd)->state == TASK_RUNNING;
> +}
> +
>  const char * const softirq_to_name[NR_SOFTIRQS] = {
>  	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
>  	"TASKLET", "SCHED", "HRTIMER", "RCU"
> @@ -313,7 +318,7 @@ asmlinkage __visible void do_softirq(void)
>  
>  	pending = local_softirq_pending();
>  
> -	if (pending)
> +	if (pending && !ksoftirqd_running())
>  		do_softirq_own_stack();
>  
>  	local_irq_restore(flags);
> @@ -340,6 +345,9 @@ void irq_enter(void)
>  
>  static inline void invoke_softirq(void)
>  {
> +	if (ksoftirqd_running())
> +		return;
> +
>  	if (!force_irqthreads) {
>  #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
>  		/*

In this version of the path, the chunk affecting __local_bh_enable_ip()
has been removed.

I think it is beneficial, because it allows avoiding a
local_irq_save()/local_irq_restore() pairs per local_bh_enable under heavy load.

Cheers,

Paolo