Received-SPF: pass (google.com: domain of linux-kernel+bounces-43367-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Precedence: bulk
MIME-Version: 1.0
References: <20240129054551.57728-1-ioworker0@gmail.com>
In-Reply-To: <20240129054551.57728-1-ioworker0@gmail.com>
From: Yang Shi <shy828301@gmail.com>
Date: Mon, 29 Jan 2024 10:53:07 -0800
Message-ID: <CAHbLzkqrTPZD_Fz_a5LYa49Tum_Za=J9dX_SRyTr=kVZA26RAg@mail.gmail.com>
Subject: Re: [PATCH 1/1] mm/khugepaged: bypassing unnecessary scans with
 MMF_DISABLE_THP check
To: Lance Yang <ioworker0@gmail.com>
Cc: akpm@linux-foundation.org, mhocko@suse.com, zokeefe@google.com, 
	david@redhat.com, songmuchun@bytedance.com, peterx@redhat.com, 
	minchan@kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Sun, Jan 28, 2024 at 9:46=E2=80=AFPM Lance Yang <ioworker0@gmail.com> wr=
ote:
>
> khugepaged scans the entire address space in the
> background for each given mm, looking for
> opportunities to merge sequences of basic pages
> into huge pages. However, when an mm is inserted
> to the mm_slots list, and the MMF_DISABLE_THP flag
> is set later, this scanning process becomes
> unnecessary for that mm and can be skipped to avoid
> redundant operations, especially in scenarios with
> a large address space.
>
> This commit introduces a check before each scanning
> process to test the MMF_DISABLE_THP flag for the
> given mm; if the flag is set, the scanning process
> is bypassed, thereby improving the efficiency of
> khugepaged.
>
> Signed-off-by: Lance Yang <ioworker0@gmail.com>
> ---
>  mm/khugepaged.c | 18 ++++++++++++------
>  1 file changed, 12 insertions(+), 6 deletions(-)
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 2b219acb528e..d6a700834edc 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -410,6 +410,12 @@ static inline int hpage_collapse_test_exit(struct mm=
_struct *mm)
>         return atomic_read(&mm->mm_users) =3D=3D 0;
>  }
>
> +static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *=
mm)
> +{
> +       return hpage_collapse_test_exit(mm) ||
> +              test_bit(MMF_DISABLE_THP, &mm->flags);
> +}
> +
>  void __khugepaged_enter(struct mm_struct *mm)
>  {
>         struct khugepaged_mm_slot *mm_slot;
> @@ -1422,7 +1428,7 @@ static void collect_mm_slot(struct khugepaged_mm_sl=
ot *mm_slot)
>
>         lockdep_assert_held(&khugepaged_mm_lock);
>
> -       if (hpage_collapse_test_exit(mm)) {
> +       if (hpage_collapse_test_exit_or_disable(mm)) {
>                 /* free mm_slot */
>                 hash_del(&slot->hash);
>                 list_del(&slot->mm_node);
> @@ -2360,7 +2366,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigne=
d int pages, int *result,
>                 goto breakouterloop_mmap_lock;
>
>         progress++;
> -       if (unlikely(hpage_collapse_test_exit(mm)))
> +       if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
>                 goto breakouterloop;
>
>         vma_iter_init(&vmi, mm, khugepaged_scan.address);
> @@ -2368,7 +2374,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigne=
d int pages, int *result,
>                 unsigned long hstart, hend;
>
>                 cond_resched();
> -               if (unlikely(hpage_collapse_test_exit(mm))) {
> +               if (unlikely(hpage_collapse_test_exit_or_disable(mm))) {

The later thp_vma_allowable_order() does check whether MMF_DISABLE_THP
is set or not. And the hugepage_vma_revalidate() after re-acquiring
mmap_lock does the same check too. The checking in khugepaged should
be already serialized with prctl, which takes mmap_lock in write.

>                         progress++;
>                         break;
>                 }
> @@ -2390,7 +2396,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigne=
d int pages, int *result,
>                         bool mmap_locked =3D true;
>
>                         cond_resched();
> -                       if (unlikely(hpage_collapse_test_exit(mm)))
> +                       if (unlikely(hpage_collapse_test_exit_or_disable(=
mm)))
>                                 goto breakouterloop;
>
>                         VM_BUG_ON(khugepaged_scan.address < hstart ||
> @@ -2408,7 +2414,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigne=
d int pages, int *result,
>                                 fput(file);
>                                 if (*result =3D=3D SCAN_PTE_MAPPED_HUGEPA=
GE) {
>                                         mmap_read_lock(mm);
> -                                       if (hpage_collapse_test_exit(mm))
> +                                       if (hpage_collapse_test_exit_or_d=
isable(mm))
>                                                 goto breakouterloop;
>                                         *result =3D collapse_pte_mapped_t=
hp(mm,
>                                                 khugepaged_scan.address, =
false);
> @@ -2450,7 +2456,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigne=
d int pages, int *result,
>          * Release the current mm_slot if this mm is about to die, or
>          * if we scanned all vmas of this mm.
>          */
> -       if (hpage_collapse_test_exit(mm) || !vma) {
> +       if (hpage_collapse_test_exit_or_disable(mm) || !vma) {
>                 /*
>                  * Make sure that if mm_users is reaching zero while
>                  * khugepaged runs here, khugepaged_exit will find
> --
> 2.33.1
>