PL310 errata workarounds

[Russell King - ARM Linux]

On Mon, Mar 17, 2014 at 05:09:46PM -0400, Nicolas Pitre wrote:
> L2 is normally a per cluster resource.  It is flushed by the last man 
> standing when no other CPUs might contend for the L2 controller.  And if 
> the outer cache is shared by multiple clusters then some additional 
> handling (such as "last cluster standing") would need to be implemented.
> 
> Clearly this outer_cache_flush() call is just a hint if someone were to 
> copy that file to write their own backend.  If it is causing problems 
> then it should just be removed altogether.  No platforms with MCPM that 
> I know of have an actual outer cache at the moment.  And certainly not 
> the platform where dcscb.c is used.

This sounds to me like an invitation to kill it :)  Killing it off
would be good, though maybe a comment should be left behind at this
site?

As you're the most familiar with this code, I'd prefer to commit a
patch from you rather than just deleting the reference myself.

Thanks.

-- 
FTTC broadband for 0.8mile line: now at 9.7Mbps down 460kbps up... slowly
improving, and getting towards what was expected from it.