sparc-related comment, to Re: [PATCH V1 07/10] arch/kmap: Ensure kmap_prot visibility

Ira Weiny ira.weiny at intel.com
Sat May 2 01:35:52 AEST 2020


On Fri, May 01, 2020 at 01:44:46AM -0700, Christoph Hellwig wrote:
> > --- a/arch/sparc/mm/highmem.c
> > +++ b/arch/sparc/mm/highmem.c
> > @@ -33,6 +33,7 @@
> >  #include <asm/vaddrs.h>
> >  
> >  pgprot_t kmap_prot;
> > +EXPORT_SYMBOL(kmap_prot);
> 
> Btw, I don't see why sparc needs this as a variable, as there is just
> a single assignment to it.

Because sparc uses non-standard defines which I'm not familiar with.

        kmap_prot = __pgprot(SRMMU_ET_PTE | SRMMU_PRIV | SRMMU_CACHE);

SRMMU_ET_PTE and friends are defined in 

arch/sparc/include/asm/pgtsrmmu.h

Since I can't readily test sparc this was easier to put out than let 0-day
crank on the entire series checking if including that header in the common
header chain would be an issue.

> 
> If sparc is sorted out we can always make it a define, and use a define
> for kmap_prot that defaults to PAGE_KERNEL, avoiding a little
> more duplication.

Agreed.  But it seems easier as a follow up (for me with 0-day).  Perhaps
someone from sparc can weigh in on the specifics of those defines and why they
are different from the normal ones?  Or even provide a follow on patch?

Ira



More information about the Linuxppc-dev mailing list