Re: [PATCH 33/36] autonuma: powerpc port

[Andrea Arcangeli]

Hi Benjamin,

On Thu, Aug 23, 2012 at 03:11:00PM +1000, Benjamin Herrenschmidt wrote:
> Basically PROT_NONE turns into _PAGE_PRESENT without _PAGE_USER for us.

Maybe the simplest is to implement pte_numa as !_PAGE_USER too. No
need to clear the _PAGE_PRESENT bit and to alter pte_present() if
clearing _PAGE_USER already achieves it.

It should be trivial to add the vma parameter to pte_numa(pte, vma) so
you can implement pte_numa by checking the vma->vm_page_prot in the
inline pte_numa function, to be able to tell if it's a real prot none
(in which case pte_numa return false) or if it's the NUMA hinting page
fault. In the latter case pte_numa will return true.

> However, the embedded ppc situation is more interesting... and it looks
> like it is indeed broken, meaning that a user can coerce the kernel into
> accessing PROT_NONE on its behalf with copy_from_user & co (though read
> only really).
> 
> Looks like the SW TLB handlers used on embedded should also check
> whether the address is a user or kernel address, and enforce _PAGE_USER
> in the former case. They might have done in the past, it's possible that
> it's code we lost, but as it is, it's broken.
> 
> The case of HW loaded TLB embedded will need a different definition of
> PAGE_NONE as well I suspect. Kumar, can you have a look ?

Even if we can't track copy-user accesses with the NUMA
hinting page faults, AUTONUMA should still work fairly well. The
flakey PROTNONE on embedded, is more a problem in itself than it would
be for pte_numa on embedded.

OTOH AutoNUMA working on embedded isn't important so it may be just
better to disable it until !_PAGE_USER is reliable.

> I wasn't especially thinking of ppc32... there's also hash64-4k or
> embedded 64... Also pgtable.h is common, so all those added uses of
> _PAGE_NUMA_PTE to static inline functions are going to break the build
> unless _PAGE_NUMA_PTE is #defined to 0 when not used (we do that for a
> bunch of bits in pte-common.h already).

It'd be actually worse if it would build ;). But I guess using
_PAGE_USER to implement pte_numa will solve the problem for 4k page
size too.

We can discuss this during kernel summit ;).

Thanks a lot!
Andrea
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/