Re: [PATCH, RFC] hacks to allow -rt to run kernbench on POWER

[Darren Hart <dvhltc@us.ibm.com>]

On Tue, 2007-10-30 at 07:07 +1100, Benjamin Herrenschmidt wrote: 
> On Mon, 2007-10-29 at 11:50 -0700, Paul E. McKenney wrote:
> > Hello!
> > 
> > A few random patches that permit POWER to pass kernbench on -rt.
> > Many of these have more focus on expediency than care for correctness,
> > so might best be thought of as workarounds than as complete solutions.
> > There are still issues not addressed by this patch, including:
> > 
> > o	kmem_cache_alloc() from non-preemptible context during
> > 	bootup (xics_startup() building the irq_radix_revmap()).
> > 
> > o	unmap_vmas() freeing pages with preemption disabled.
> > 	Might be able to address this by linking the pages together,
> > 	then freeing them en masse after preemption has been re-enabled,
> > 	but there is likely a better approach.
> > 
> > Thoughts?
> 
> I see a lot of case where you add preempt_disable/enable around areas
> that have the PTE lock held...
> 
> So in -rt, spin_lock doesn't disable preempt ? I'm a bit worried...

So as Paul mentioned, spin_lock is now a mutex.  There is a new
raw_spinlock however (simply change the way it is declared, calling
conventions are the same) which is used in a very few areas where a
traditional spin_lock is truly necessary.  This may or may not be one of
those times, but I wanted to point it out.

--Darren


> there are some strong requirements that anything within that lock is not
> preempted, so zap_pte_ranges() is the obvious ones but all of them would
> need to be addressed.
> 
> Ben.
> 
>