Re: [PATCH v5 13/14] mm: memory: support clearing page-extents

[Ankur Arora <ankur.a.arora@oracle.com>]

David Hildenbrand <david@redhat.com> writes:

> On 10.07.25 02:59, Ankur Arora wrote:
>> folio_zero_user() is constrained to clear in a page-at-a-time
>> fashion because it supports CONFIG_HIGHMEM which means that kernel
>> mappings for pages in a folio are not guaranteed to be contiguous.
>> We don't have this problem when running under configurations with
>> CONFIG_CLEAR_PAGE_EXTENT (implies !CONFIG_HIGHMEM), so zero in
>> longer page-extents.
>> This is expected to be faster because the processor can now optimize
>> the clearing based on the knowledge of the extent.
>>
>
> I'm curious: how did we end up "page extent" terminology? :)

After trying all the others! I tried multi-page and contig_clear_pages
and finally decided to go with page-extent since clear_pages()
essentially takes a page-extent as an argument.

> "CONFIG_CLEAR_CONTIG_PAGES" or sth. like that would be a bit clearer (pun
> intended), at least to me.

Oddly enough I tried CONFIG_CONTIG_CLEAR_PAGES and
CONFIG_CLEAR_PAGES_CONTIG but those read a little awkwardly.

CONFIG_CLEAR_CONTIG_PAGES reads better. Should have tried moving the
CONTIG to the middle as well :D.

> We use "CONTIG" pages already in different MM context.
>
> "page extent" reminds of "page_ext", which is "page extension" ...

Yeah I see that in the Kconfig now. Will switch to this one.

Thanks

--
ankur