Re: [PATCH] ksoftirqd: Enable IRQs and call cond_resched() before poking RCU

[Thomas Gleixner <tglx@linutronix.de>]

On Tue, 20 Jan 2015, Paul E. McKenney wrote:
> On Tue, Jan 20, 2015 at 02:21:51PM +0100, Thomas Gleixner wrote:
> > The whole rcu_note_context_switch() in run_ksoftirqd() is silly.
> > 
> >     cond_resched()
> > 	__preempt_count_add(PREEMPT_ACTIVE);
> > 
> > 	__schedule();
> > 	     preempt_disable();
> > 	     rcu_note_context_switch();
> > 	     ....
> > 
> > 	__preempt_count_sub(PREEMPT_ACTIVE);
> 
> I agree that if should_resched() returns true as assumed above, then there
> is no point to invoking rcu_note_context_switch().  However, the case that
> this code applies to is when should_resched() returns false, but RCU is
> waiting for a quiescent state from the current CPU.  In that case,
> cond_resched() won't do anything for RCU, and we do need the
> rcu_note_context_switch().

So this should be:

   if (!cond_resched())
      rcu_note_context_switch();

Hmm?
 
> Of course, it would be better to avoid the extra RCU work in the common
> case where cond_resched() does inovke the scheduler.  And that is the
> point of the following patch, which uses cond_resched_rcu_qs().
> However, this use of cond_resched_rcu_qs() doesn't work in older
> kernels.  So Calvin's patch is for backporting, and the follow-up
> patch for future kernels.

I see.

Thanks,

	tglx