On Tue, Jul 07, 2009 at 05:23:18PM +0200, Eric Dumazet wrote:
quoted text
> Mathieu Desnoyers a écrit :
> 
> > But read_lock + smp_mb__after_lock + read_unlock is not well suited for
> > powerpc, arm, mips and probably others where there is an explicit memory
> > barrier at the end of the read lock primitive.
> > 
> > One thing that would be efficient for all architectures is to create a
> > locking primitive that contains the smp_mb, e.g.:
> > 
> > read_lock_smp_mb()
> > 
> > which would act as a read_lock which does a full smp_mb after the lock
> > is taken.
> > 
> > The naming may be a bit odd, better ideas are welcome.
> 
> I see your point now, thanks for your patience.
> 
> Jiri, I think your first patch can be applied (including the full smp_mb()),
>  then we will optimize both for x86 and other arches, when all 
> arch maintainers have a chance to change
> "read_lock();smp_mb()" to a faster "read_lock_mb()" or something :)
>

great, I saw you Signed-off the 1/2 part.. could I leave it,
or do I need to resend as a single patch?

jirka
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html