[PATCH V2 01/29] powerpc/mm: add _PAGE_HASHPTE similar to 4K hash

Aneesh Kumar K.V aneesh.kumar at linux.vnet.ibm.com
Sat Feb 13 16:08:32 AEDT 2016


Paul Mackerras <paulus at ozlabs.org> writes:

> On Mon, Feb 08, 2016 at 02:50:13PM +0530, Aneesh Kumar K.V wrote:
>> Not really needed. But this brings it back to as it was before
>
> If it's not really needed, what's the motivation for putting this
> patch in?  You need to explain where you are heading with this patch.

I explained this in the last review.

What confused me in the beginning was difference between 4k and 64k
page size. I was trying to find out whether we miss a hpte flush in any
scenario because of this. ie, a pte update on a linux pte, for which we
are doing a parallel hash pte insert. After looking at it closer my
understanding is this won't happen because pte update also look at
_PAGE_BUSY and we will wait for hash pte insert to finish before going
ahead with the pte update. But to avoid further confusion I was wondering
whether we should keep this closer to what we have with __hash_page_4k.
Hence the statement "Not really needed".

I will add more information in the commit message.


>
>> Check this
>> 41743a4e34f0777f51c1cf0675b91508ba143050
>
> The SHA1 is useful, but you need to be more explicit - something like
>
> "This partially reverts commit 41743a4e34f0 ("powerpc: Free a PTE bit
> on ppc64 with 64K pages", 2008-06-11)."
>

ok

-aneesh



More information about the Linuxppc-dev mailing list