[PATCH v2 08/25] powerpc/8xx: Map IMMR area with 512k page at a fixed address
scottwood at freescale.com
Sat Sep 26 03:09:06 AEST 2015
On Fri, 2015-09-25 at 14:46 +0000, David Laight wrote:
> From: Scott Wood
> > Sent: 24 September 2015 21:14
> > > Isn't this a more general problem?
> > >
> > > If there are multiple remap requests for the same physical page
> > > shouldn't the kernel be just increasing a reference count somewhere
> > > and returning address in the same virtual page?
> > > This should probably happen regardless of the address.
> > > I presume it must be done for cacheable mappings.
> > Why would you assume that?
> Because 'really horrid (tm)' things happen on some cache
> architectures if you map the same physical address to
> multiple virtual addresses.
PPC is not such an architecture.
More information about the Linuxppc-dev