Received-SPF: pass (google.com: domain of linux-kernel+bounces-198586-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Precedence: bulk
MIME-Version: 1.0
References: <20240603033118.76457-1-ioworker0@gmail.com>
In-Reply-To: <20240603033118.76457-1-ioworker0@gmail.com>
From: Barry Song <21cnbao@gmail.com>
Date: Mon, 3 Jun 2024 16:14:39 +1200
Message-ID: <CAGsJ_4wxPk+bk9UM+PvA3x=LJG+mWmTD3e2HSEsS83X3vMWTJQ@mail.gmail.com>
Subject: Re: [PATCH 1/1] mm/mlock: implement folio_mlock_step() using folio_pte_batch()
To: Lance Yang <ioworker0@gmail.com>
Cc: akpm@linux-foundation.org, ryan.roberts@arm.com, david@redhat.com, 
	baolin.wang@linux.alibaba.com, ziy@nvidia.com, fengwei.yin@intel.com, 
	ying.huang@intel.com, libang.li@antgroup.com, linux-mm@kvack.org, 
	linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Mon, Jun 3, 2024 at 3:31=E2=80=AFPM Lance Yang <ioworker0@gmail.com> wro=
te:
>
> Let's make folio_mlock_step() simply a wrapper around folio_pte_batch(),
> which will greatly reduce the cost of ptep_get() when scanning a range of
> contptes.
>
> Signed-off-by: Lance Yang <ioworker0@gmail.com>
> ---
>  mm/mlock.c | 23 ++++++-----------------
>  1 file changed, 6 insertions(+), 17 deletions(-)
>
> diff --git a/mm/mlock.c b/mm/mlock.c
> index 30b51cdea89d..1ae6232d38cf 100644
> --- a/mm/mlock.c
> +++ b/mm/mlock.c
> @@ -307,26 +307,15 @@ void munlock_folio(struct folio *folio)
>  static inline unsigned int folio_mlock_step(struct folio *folio,
>                 pte_t *pte, unsigned long addr, unsigned long end)
>  {
> -       unsigned int count, i, nr =3D folio_nr_pages(folio);
> -       unsigned long pfn =3D folio_pfn(folio);
> -       pte_t ptent =3D ptep_get(pte);
> -
> -       if (!folio_test_large(folio))
> +       if (likely(!folio_test_large(folio)))
>                 return 1;
>
> -       count =3D pfn + nr - pte_pfn(ptent);
> -       count =3D min_t(unsigned int, count, (end - addr) >> PAGE_SHIFT);
> -
> -       for (i =3D 0; i < count; i++, pte++) {
> -               pte_t entry =3D ptep_get(pte);
> -
> -               if (!pte_present(entry))
> -                       break;
> -               if (pte_pfn(entry) - pfn >=3D nr)
> -                       break;
> -       }
> +       const fpb_t fpb_flags =3D FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRT=
Y;
> +       int max_nr =3D (end - addr) / PAGE_SIZE;
> +       pte_t ptent =3D ptep_get(pte);
>
> -       return i;
> +       return folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags=
, NULL,
> +                              NULL, NULL);
>  }

what about a minimum change as below?
index 30b51cdea89d..e8b98f84fbd2 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -307,26 +307,15 @@ void munlock_folio(struct folio *folio)
 static inline unsigned int folio_mlock_step(struct folio *folio,
                pte_t *pte, unsigned long addr, unsigned long end)
 {
-       unsigned int count, i, nr =3D folio_nr_pages(folio);
-       unsigned long pfn =3D folio_pfn(folio);
+       unsigned int count =3D (end - addr) >> PAGE_SHIFT;
        pte_t ptent =3D ptep_get(pte);
+       const fpb_t fpb_flags =3D FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;

        if (!folio_test_large(folio))
                return 1;

-       count =3D pfn + nr - pte_pfn(ptent);
-       count =3D min_t(unsigned int, count, (end - addr) >> PAGE_SHIFT);
-
-       for (i =3D 0; i < count; i++, pte++) {
-               pte_t entry =3D ptep_get(pte);
-
-               if (!pte_present(entry))
-                       break;
-               if (pte_pfn(entry) - pfn >=3D nr)
-                       break;
-       }
-
-       return i;
+       return folio_pte_batch(folio, addr, pte, ptent, count, fpb_flags, N=
ULL,
+                              NULL, NULL);
 }


>
>  static inline bool allow_mlock_munlock(struct folio *folio,
> --
> 2.33.1
>