Re: [PATCH] In-kernel module loader 3/7

[Robert Love]

On Wed, 2002-09-18 at 19:07, Roman Zippel wrote:

> On Wed, 18 Sep 2002, Rusty Russell wrote:
> 
> > +/* Stopping interrupts faster than atomics on many archs (and more
> > +   easily optimized if they're not) */
> > +static inline void bigref_inc(struct bigref *ref)
> > +{
> > +	unsigned long flags;
> > +	struct bigref_percpu *cpu;
> > +
> > +	local_irq_save(flags);
> > +	cpu = &ref->ref[smp_processor_id()];
> > +	if (likely(!cpu->slow_mode))
> > +		cpu->counter++;
> 
> Did you benchmark this? On most UP machines an inc/dec should be cheaper
> than irq enable/disable.

Yah.  I would think due to pipeline effects, disabling interrupts would
never be faster than an atomic inc/dec, assuming the architecture has
normal locking.

	Robert Love