Re: MI non-interlocked atomic ops?

[yamt%mwd.biglobe.ne.jp@localhost (YAMAMOTO Takashi)]

hi,

> David Young <dyoung%pobox.com@localhost> wrote:
>> <...>
>> 
>> which spends (on x86) a small but not immeasurable amount of time in
>> splx(s), so I was tempted to rewrite it like this:
>> 
>>         void
>>         mbstat_type_add(int type, int diff)
>>         {
>>                 struct mbstat_cpu *mb;
>> 
>>                 mb = percpu_getref(mbstat_percpu);
>>                 atomic_add_uint_ni(&mb->m_mtypes[type], diff);
>>                 percpu_putref(mbstat_percpu);
>>         }
>> 
>> There is no such routine as atomic_add_uint_ni(), though, and I don't
>> know if every NetBSD architecture can supply that routine.
> 
> Right, spl*()/splx() have a cost.  However, code like this (networking)
> should not be in the hard-interrupt handler.  As we move towards a wider
> use of software interrupts, SPL calls will disappear and kernel preemption
> provides the necessary protection (although software interrupts are not
> yet preemptable).

iirc kpreempt_disable() doesn't provide a protection from a softint.

YAMAMOTO Takashi

> 
> We have non-interlocked CAS operation - atomic_cas_*_ni().  This can be
> used to replicate all other operations.  I doubt there is much need to
> define them all due to the reason stated above.  CAS is enough for now.
> 
> -- 
> Mindaugas