Re: [PATCH v3 2/4] mm/gup: decrement head page once for group of subpages

[Joao Martins <joao.m.martins@oracle.com>]

On 2/10/21 9:02 PM, Jason Gunthorpe wrote:
> On Fri, Feb 05, 2021 at 08:41:25PM +0000, Joao Martins wrote:
>> Rather than decrementing the head page refcount one by one, we
>> walk the page array and checking which belong to the same
>> compound_head. Later on we decrement the calculated amount
>> of references in a single write to the head page. To that
>> end switch to for_each_compound_head() does most of the work.
>>
>> set_page_dirty() needs no adjustment as it's a nop for
>> non-dirty head pages and it doesn't operate on tail pages.
>>
>> This considerably improves unpinning of pages with THP and
>> hugetlbfs:
>>
>> - THP
>> gup_test -t -m 16384 -r 10 [-L|-a] -S -n 512 -w
>> PIN_LONGTERM_BENCHMARK (put values): ~87.6k us -> ~23.2k us
>>
>> - 16G with 1G huge page size
>> gup_test -f /mnt/huge/file -m 16384 -r 10 [-L|-a] -S -n 512 -w
>> PIN_LONGTERM_BENCHMARK: (put values): ~87.6k us -> ~27.5k us
>>
>> Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
>> Reviewed-by: John Hubbard <jhubbard@nvidia.com>
>> ---
>>  mm/gup.c | 29 +++++++++++------------------
>>  1 file changed, 11 insertions(+), 18 deletions(-)
> 
> Looks fine
> 
> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
> 
Thanks!

> I was wondering why this only touches the FOLL_PIN path, 

That's just because I was looking at pinning mostly.

> it would make
> sense to also use this same logic for release_pages()

Yeah, indeed -- any place tearing potentially consecutive sets of pages
are candidates.

> 
>         for (i = 0; i < nr; i++) {
>                 struct page *page = pages[i];
>                 page = compound_head(page);
>                 if (is_huge_zero_page(page))
>                         continue; 
> 
> Jason
>