Received-SPF: pass (google.com: domain of linux-kernel+bounces-75203-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
Precedence: bulk
MIME-Version: 1.0
References: <20240221085036.105621-1-21cnbao@gmail.com>
In-Reply-To: <20240221085036.105621-1-21cnbao@gmail.com>
From: Vishal Moola <vishal.moola@gmail.com>
Date: Wed, 21 Feb 2024 09:35:31 -0800
Message-ID: <CAOzc2pwZO4xg8TBvt2dpPNT8TeHDnWod6iJh-LJ50hfTn4ua3A@mail.gmail.com>
Subject: Re: [PATCH] madvise:madvise_cold_or_pageout_pte_range(): allow split
 while folio_estimated_sharers = 0
To: Barry Song <21cnbao@gmail.com>
Cc: akpm@linux-foundation.org, linux-mm@kvack.org, 
	linux-kernel@vger.kernel.org, Barry Song <v-songbaohua@oppo.com>, 
	Yin Fengwei <fengwei.yin@intel.com>, Yu Zhao <yuzhao@google.com>, 
	Ryan Roberts <ryan.roberts@arm.com>, David Hildenbrand <david@redhat.com>, 
	Kefeng Wang <wangkefeng.wang@huawei.com>, Matthew Wilcox <willy@infradead.org>, 
	Minchan Kim <minchan@kernel.org>, Yang Shi <shy828301@gmail.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Wed, Feb 21, 2024 at 12:50=E2=80=AFAM Barry Song <21cnbao@gmail.com> wro=
te:
>
> From: Barry Song <v-songbaohua@oppo.com>
>
> The purpose is stopping splitting large folios whose mapcount are 2 or
> above. Folios whose estimated_shares =3D 0 should be still perfect and
> even better candidates than estimated_shares =3D 1.
>
> Consider a pte-mapped large folio with 16 subpages, if we unmap 1-15,
> the current code will split folios and reclaim them while madvise goes
> on this folio; but if we unmap subpage 0, we will keep this folio and
> break. This is weird.
> For pmd-mapped large folios, we can still use "=3D 1" as the condition
> as anyway we have the entire map for it. So this patch doesn't change
> the condition for pmd-mapped large folios.
> This also explains why we had been using "=3D 1" for both pmd-mapped and
> pte-mapped large folios before commit 07e8c82b5eff ("madvise: convert
> madvise_cold_or_pageout_pte_range() to use folios"), because in the
> past, we used the mapcount of the specific subpage, since the subpage
> had pte present, its mapcount wouldn't be 0.
> The problem can be quite easily reproduced by writing a small program,
> unmapping the first subpage of a pte-mapped large folio vs. unmapping
> anyone other than the first subpage.
>
> Fixes: 2f406263e3e9 ("madvise:madvise_cold_or_pageout_pte_range(): don't =
use mapcount() against large folio for sharing check")
> Cc: Yin Fengwei <fengwei.yin@intel.com>
> Cc: Yu Zhao <yuzhao@google.com>
> Cc: Ryan Roberts <ryan.roberts@arm.com>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Minchan Kim <minchan@kernel.org>
> Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
> Cc: Yang Shi <shy828301@gmail.com>
> Signed-off-by: Barry Song <v-songbaohua@oppo.com>

Reviewed-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>

> ---
>  mm/madvise.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/mm/madvise.c b/mm/madvise.c
> index cfa5e7288261..abde3edb04f0 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -453,7 +453,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *p=
md,
>                 if (folio_test_large(folio)) {
>                         int err;
>
> -                       if (folio_estimated_sharers(folio) !=3D 1)
> +                       if (folio_estimated_sharers(folio) > 1)
>                                 break;
>                         if (pageout_anon_only_filter && !folio_test_anon(=
folio))
>                                 break;
> --
> 2.34.1
>