Received-SPF: pass (google.com: domain of linux-kernel+bounces-101580-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Precedence: bulk
MIME-Version: 1.0
References: <20240311150058.1122862-1-ryan.roberts@arm.com>
 <20240311150058.1122862-7-ryan.roberts@arm.com> <CAGsJ_4wpjqRsn7ouO=Ut9oMBLSh803=XuSPX6gJ5nQ3jyqh3hQ@mail.gmail.com>
 <a75ec640-d025-45ee-b74d-305aaa3cc1ce@arm.com>
In-Reply-To: <a75ec640-d025-45ee-b74d-305aaa3cc1ce@arm.com>
From: Lance Yang <ioworker0@gmail.com>
Date: Wed, 13 Mar 2024 22:02:51 +0800
Message-ID: <CAK1f24k1AuHDdrLFNLvwdoOy=xJTVkVdfY4+SN+KW5-EiMSa9Q@mail.gmail.com>
Subject: Re: [PATCH v4 6/6] mm: madvise: Avoid split during MADV_PAGEOUT and MADV_COLD
To: Ryan Roberts <ryan.roberts@arm.com>
Cc: Barry Song <21cnbao@gmail.com>, Andrew Morton <akpm@linux-foundation.org>, 
	David Hildenbrand <david@redhat.com>, Matthew Wilcox <willy@infradead.org>, 
	Huang Ying <ying.huang@intel.com>, Gao Xiang <xiang@kernel.org>, Yu Zhao <yuzhao@google.com>, 
	Yang Shi <shy828301@gmail.com>, Michal Hocko <mhocko@suse.com>, 
	Kefeng Wang <wangkefeng.wang@huawei.com>, Chris Li <chrisl@kernel.org>, linux-mm@kvack.org, 
	linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Wed, Mar 13, 2024 at 5:03=E2=80=AFPM Ryan Roberts <ryan.roberts@arm.com>=
 wrote:
>
> On 13/03/2024 07:19, Barry Song wrote:
> > On Tue, Mar 12, 2024 at 4:01=E2=80=AFAM Ryan Roberts <ryan.roberts@arm.=
com> wrote:
> >>
> >> Rework madvise_cold_or_pageout_pte_range() to avoid splitting any larg=
e
> >> folio that is fully and contiguously mapped in the pageout/cold vm
> >> range. This change means that large folios will be maintained all the
> >> way to swap storage. This both improves performance during swap-out, b=
y
> >> eliding the cost of splitting the folio, and sets us up nicely for
> >> maintaining the large folio when it is swapped back in (to be covered =
in
> >> a separate series).
> >>
> >> Folios that are not fully mapped in the target range are still split,
> >> but note that behavior is changed so that if the split fails for any
> >> reason (folio locked, shared, etc) we now leave it as is and move to t=
he
> >> next pte in the range and continue work on the proceeding folios.
> >> Previously any failure of this sort would cause the entire operation t=
o
> >> give up and no folios mapped at higher addresses were paged out or mad=
e
> >> cold. Given large folios are becoming more common, this old behavior
> >> would have likely lead to wasted opportunities.
> >>
> >> While we are at it, change the code that clears young from the ptes to
> >> use ptep_test_and_clear_young(), which is more efficent than
> >> get_and_clear/modify/set, especially for contpte mappings on arm64,
> >> where the old approach would require unfolding/refolding and the new
> >> approach can be done in place.
> >>
> >> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> >
> > This looks so much better than our initial RFC.
> > Thank you for your excellent work!
>
> Thanks - its a team effort - I had your PoC and David's previous batching=
 work
> to use as a template.
>
> >
> >> ---
> >>  mm/madvise.c | 89 ++++++++++++++++++++++++++++++---------------------=
-
> >>  1 file changed, 51 insertions(+), 38 deletions(-)
> >>
> >> diff --git a/mm/madvise.c b/mm/madvise.c
> >> index 547dcd1f7a39..56c7ba7bd558 100644
> >> --- a/mm/madvise.c
> >> +++ b/mm/madvise.c
> >> @@ -336,6 +336,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t=
 *pmd,
> >>         LIST_HEAD(folio_list);
> >>         bool pageout_anon_only_filter;
> >>         unsigned int batch_count =3D 0;
> >> +       int nr;
> >>
> >>         if (fatal_signal_pending(current))
> >>                 return -EINTR;
> >> @@ -423,7 +424,8 @@ static int madvise_cold_or_pageout_pte_range(pmd_t=
 *pmd,
> >>                 return 0;
> >>         flush_tlb_batched_pending(mm);
> >>         arch_enter_lazy_mmu_mode();
> >> -       for (; addr < end; pte++, addr +=3D PAGE_SIZE) {
> >> +       for (; addr < end; pte +=3D nr, addr +=3D nr * PAGE_SIZE) {
> >> +               nr =3D 1;
> >>                 ptent =3D ptep_get(pte);
> >>
> >>                 if (++batch_count =3D=3D SWAP_CLUSTER_MAX) {
> >> @@ -447,55 +449,66 @@ static int madvise_cold_or_pageout_pte_range(pmd=
_t *pmd,
> >>                         continue;
> >>
> >>                 /*
> >> -                * Creating a THP page is expensive so split it only i=
f we
> >> -                * are sure it's worth. Split it if we are only owner.
> >> +                * If we encounter a large folio, only split it if it =
is not
> >> +                * fully mapped within the range we are operating on. =
Otherwise
> >> +                * leave it as is so that it can be swapped out whole.=
 If we
> >> +                * fail to split a folio, leave it in place and advanc=
e to the
> >> +                * next pte in the range.
> >>                  */
> >>                 if (folio_test_large(folio)) {
> >> -                       int err;
> >> -
> >> -                       if (folio_estimated_sharers(folio) > 1)
> >> -                               break;
> >> -                       if (pageout_anon_only_filter && !folio_test_an=
on(folio))
> >> -                               break;
> >> -                       if (!folio_trylock(folio))
> >> -                               break;
> >> -                       folio_get(folio);
> >> -                       arch_leave_lazy_mmu_mode();
> >> -                       pte_unmap_unlock(start_pte, ptl);
> >> -                       start_pte =3D NULL;
> >> -                       err =3D split_folio(folio);
> >> -                       folio_unlock(folio);
> >> -                       folio_put(folio);
> >> -                       if (err)
> >> -                               break;
> >> -                       start_pte =3D pte =3D
> >> -                               pte_offset_map_lock(mm, pmd, addr, &pt=
l);
> >> -                       if (!start_pte)
> >> -                               break;
> >> -                       arch_enter_lazy_mmu_mode();
> >> -                       pte--;
> >> -                       addr -=3D PAGE_SIZE;
> >> -                       continue;
> >> +                       const fpb_t fpb_flags =3D FPB_IGNORE_DIRTY |
> >> +                                               FPB_IGNORE_SOFT_DIRTY;
> >> +                       int max_nr =3D (end - addr) / PAGE_SIZE;
> >> +
> >> +                       nr =3D folio_pte_batch(folio, addr, pte, ptent=
, max_nr,
> >> +                                            fpb_flags, NULL);
> >
> > I wonder if we have a quick way to avoid folio_pte_batch() if users
> > are doing madvise() on a portion of a large folio.
>
> Good idea. Something like this?:
>
>         if (pte_pfn(pte) =3D=3D folio_pfn(folio)
>                 nr =3D folio_pte_batch(folio, addr, pte, ptent, max_nr,
>                                      fpb_flags, NULL);
>
> If we are not mapping the first page of the folio, then it can't be a ful=
l
> mapping, so no need to call folio_pte_batch(). Just split it.

                 if (folio_test_large(folio)) {
[...]
                       nr =3D folio_pte_batch(folio, addr, pte, ptent, max_=
nr,
                                            fpb_flags, NULL);
+                       if (folio_estimated_sharers(folio) > 1)
+                               continue;

Could we use folio_estimated_sharers as an early exit point here?

                       if (nr < folio_nr_pages(folio)) {
                               int err;

-                               if (folio_estimated_sharers(folio) > 1)
-                                       continue;
[...]

>
> >
> >> +
> >> +                       if (nr < folio_nr_pages(folio)) {
> >> +                               int err;
> >> +
> >> +                               if (folio_estimated_sharers(folio) > 1=
)
> >> +                                       continue;
> >> +                               if (pageout_anon_only_filter && !folio=
_test_anon(folio))
> >> +                                       continue;
> >> +                               if (!folio_trylock(folio))
> >> +                                       continue;
> >> +                               folio_get(folio);
> >> +                               arch_leave_lazy_mmu_mode();
> >> +                               pte_unmap_unlock(start_pte, ptl);
> >> +                               start_pte =3D NULL;
> >> +                               err =3D split_folio(folio);
> >> +                               folio_unlock(folio);
> >> +                               folio_put(folio);
> >> +                               if (err)
> >> +                                       continue;
> >> +                               start_pte =3D pte =3D
> >> +                                       pte_offset_map_lock(mm, pmd, a=
ddr, &ptl);
> >> +                               if (!start_pte)
> >> +                                       break;
> >> +                               arch_enter_lazy_mmu_mode();
> >> +                               nr =3D 0;
> >> +                               continue;
> >> +                       }
> >>                 }
> >>
> >>                 /*
> >>                  * Do not interfere with other mappings of this folio =
and
> >> -                * non-LRU folio.
> >> +                * non-LRU folio. If we have a large folio at this poi=
nt, we
> >> +                * know it is fully mapped so if its mapcount is the s=
ame as its
> >> +                * number of pages, it must be exclusive.
> >>                  */
> >> -               if (!folio_test_lru(folio) || folio_mapcount(folio) !=
=3D 1)
> >> +               if (!folio_test_lru(folio) ||
> >> +                   folio_mapcount(folio) !=3D folio_nr_pages(folio))
> >>                         continue;
> >
> > This looks so perfect and is exactly what I wanted to achieve.
> >
> >>
> >>                 if (pageout_anon_only_filter && !folio_test_anon(folio=
))
> >>                         continue;
> >>
> >> -               VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
> >> -
> >> -               if (!pageout && pte_young(ptent)) {
> >> -                       ptent =3D ptep_get_and_clear_full(mm, addr, pt=
e,
> >> -                                                       tlb->fullmm);
> >> -                       ptent =3D pte_mkold(ptent);
> >> -                       set_pte_at(mm, addr, pte, ptent);
> >> -                       tlb_remove_tlb_entry(tlb, pte, addr);
> >> +               if (!pageout) {
> >> +                       for (; nr !=3D 0; nr--, pte++, addr +=3D PAGE_=
SIZE) {
> >> +                               if (ptep_test_and_clear_young(vma, add=
r, pte))
> >> +                                       tlb_remove_tlb_entry(tlb, pte,=
 addr);

IIRC, some of the architecture(ex, PPC) don't update TLB with set_pte_at an=
d
tlb_remove_tlb_entry. So, didn't we consider remapping the PTE with old aft=
er
pte clearing?

Thanks,
Lance


> >> +                       }
> >
> > This looks so smart. if it is not pageout, we have increased pte
> > and addr here; so nr is 0 and we don't need to increase again in
> > for (; addr < end; pte +=3D nr, addr +=3D nr * PAGE_SIZE)
> >
> > otherwise, nr won't be 0. so we will increase addr and
> > pte by nr.
>
> Indeed. I'm hoping that Lance is able to follow a similar pattern for
> madvise_free_pte_range().
>
>
> >
> >
> >>                 }
> >>
> >>                 /*
> >> --
> >> 2.25.1
> >>
> >
> > Overall, LGTM,
> >
> > Reviewed-by: Barry Song <v-songbaohua@oppo.com>
>
> Thanks!
>
>