Received-SPF: pass (google.com: domain of linux-kernel+bounces-168400-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Precedence: bulk
MIME-Version: 1.0
References: <20240503005023.174597-1-21cnbao@gmail.com> <20240503005023.174597-7-21cnbao@gmail.com>
 <0b4d4d4b-91d8-4fd5-af4e-aebe9ee08b89@arm.com>
In-Reply-To: <0b4d4d4b-91d8-4fd5-af4e-aebe9ee08b89@arm.com>
From: Barry Song <21cnbao@gmail.com>
Date: Sat, 4 May 2024 07:23:35 +0800
Message-ID: <CAGsJ_4wm6v+xgh4jQ+u2-EzOXCLsz6L6nRJi_=FfWuGDUjxRYg@mail.gmail.com>
Subject: Re: [PATCH v3 6/6] mm: swap: entirely map large folios found in swapcache
To: Ryan Roberts <ryan.roberts@arm.com>
Cc: akpm@linux-foundation.org, linux-mm@kvack.org, 
	baolin.wang@linux.alibaba.com, chrisl@kernel.org, david@redhat.com, 
	hanchuanhua@oppo.com, hannes@cmpxchg.org, hughd@google.com, 
	kasong@tencent.com, linux-kernel@vger.kernel.org, surenb@google.com, 
	v-songbaohua@oppo.com, willy@infradead.org, xiang@kernel.org, 
	ying.huang@intel.com, yosryahmed@google.com, yuzhao@google.com, 
	ziy@nvidia.com
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Fri, May 3, 2024 at 6:50=E2=80=AFPM Ryan Roberts <ryan.roberts@arm.com> =
wrote:
>
> On 03/05/2024 01:50, Barry Song wrote:
> > From: Chuanhua Han <hanchuanhua@oppo.com>
> >
> > When a large folio is found in the swapcache, the current implementatio=
n
> > requires calling do_swap_page() nr_pages times, resulting in nr_pages
> > page faults. This patch opts to map the entire large folio at once to
> > minimize page faults. Additionally, redundant checks and early exits
> > for ARM64 MTE restoring are removed.
> >
> > Signed-off-by: Chuanhua Han <hanchuanhua@oppo.com>
> > Co-developed-by: Barry Song <v-songbaohua@oppo.com>
> > Signed-off-by: Barry Song <v-songbaohua@oppo.com>
>
> With the suggested changes below:
>
> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
>
> > ---
> >  mm/memory.c | 60 ++++++++++++++++++++++++++++++++++++++++++-----------
> >  1 file changed, 48 insertions(+), 12 deletions(-)
> >
> > diff --git a/mm/memory.c b/mm/memory.c
> > index 22e7c33cc747..940fdbe69fa1 100644
> > --- a/mm/memory.c
> > +++ b/mm/memory.c
> > @@ -3968,6 +3968,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> >       pte_t pte;
> >       vm_fault_t ret =3D 0;
> >       void *shadow =3D NULL;
> > +     int nr_pages =3D 1;
> > +     unsigned long page_idx =3D 0;
> > +     unsigned long address =3D vmf->address;
> > +     pte_t *ptep;
>
> nit: Personally I'd prefer all these to get initialised just before the "=
if
> (folio_test_large()..." block below. That way it is clear they are fresh =
(incase
> any logic between here and there makes an adjustment) and its clear that =
they
> are only to be used after that block (the compiler will warn if using an
> uninitialized value).

right. I agree this will make the code more readable.

>
> >
> >       if (!pte_unmap_same(vmf))
> >               goto out;
> > @@ -4166,6 +4170,36 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> >               goto out_nomap;
> >       }
> >
> > +     ptep =3D vmf->pte;
> > +     if (folio_test_large(folio) && folio_test_swapcache(folio)) {
> > +             int nr =3D folio_nr_pages(folio);
> > +             unsigned long idx =3D folio_page_idx(folio, page);
> > +             unsigned long folio_start =3D vmf->address - idx * PAGE_S=
IZE;
> > +             unsigned long folio_end =3D folio_start + nr * PAGE_SIZE;
> > +             pte_t *folio_ptep;
> > +             pte_t folio_pte;
> > +
> > +             if (unlikely(folio_start < max(vmf->address & PMD_MASK, v=
ma->vm_start)))
> > +                     goto check_folio;
> > +             if (unlikely(folio_end > pmd_addr_end(vmf->address, vma->=
vm_end)))
> > +                     goto check_folio;
> > +
> > +             folio_ptep =3D vmf->pte - idx;
> > +             folio_pte =3D ptep_get(folio_ptep);
> > +             if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pt=
e, -idx)) ||
> > +                 swap_pte_batch(folio_ptep, nr, folio_pte) !=3D nr)
> > +                     goto check_folio;
> > +
> > +             page_idx =3D idx;
> > +             address =3D folio_start;
> > +             ptep =3D folio_ptep;
> > +             nr_pages =3D nr;
> > +             entry =3D folio->swap;
> > +             page =3D &folio->page;
> > +     }
> > +
> > +check_folio:
>
> Is this still the correct label name, given the checks are now above the =
new
> block? Perhaps "one_page" or something like that?

not quite sure about this, as the code after one_page can be multiple_pages=
.
On the other hand, it seems we are really checking folio after "check_folio=
"
:-)


BUG_ON(!folio_test_anon(folio) && folio_test_mappedtodisk(folio));
BUG_ON(folio_test_anon(folio) && PageAnonExclusive(page));

/*
* Check under PT lock (to protect against concurrent fork() sharing
* the swap entry concurrently) for certainly exclusive pages.
*/
if (!folio_test_ksm(folio)) {


>
> > +
> >       /*
> >        * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swa=
p pte
> >        * must never point at an anonymous page in the swapcache that is
> > @@ -4225,12 +4259,13 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> >        * We're already holding a reference on the page but haven't mapp=
ed it
> >        * yet.
> >        */
> > -     swap_free_nr(entry, 1);
> > +     swap_free_nr(entry, nr_pages);
> >       if (should_try_to_free_swap(folio, vma, vmf->flags))
> >               folio_free_swap(folio);
> >
> > -     inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
> > -     dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
> > +     folio_ref_add(folio, nr_pages - 1);
> > +     add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
> > +     add_mm_counter(vma->vm_mm, MM_SWAPENTS, -nr_pages);
> >       pte =3D mk_pte(page, vma->vm_page_prot);
> >
> >       /*
> > @@ -4240,34 +4275,35 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> >        * exclusivity.
> >        */
> >       if (!folio_test_ksm(folio) &&
> > -         (exclusive || folio_ref_count(folio) =3D=3D 1)) {
> > +         (exclusive || (folio_ref_count(folio) =3D=3D nr_pages &&
> > +                        folio_nr_pages(folio) =3D=3D nr_pages))) {
>
> I think in practice there is no change here? If nr_pages > 1 then the fol=
io is
> in the swapcache, so there is an extra ref on it? I agree with the change=
 for
> robustness sake. Just checking my understanding.

This is the code showing we are reusing/(mkwrite) a folio either
1. we meet a small folio and we are the only one hitting the small folio
2. we meet a large folio and we are the only one hitting the large folio

any corner cases besides the above two seems difficult. for example,

while we hit a large folio in swapcache but if we can't entirely map it
(nr_pages=3D=3D1) due to partial unmap, we will have folio_ref_count(folio)
=3D=3D nr_pages =3D=3D 1, in this case, lacking  folio_nr_pages(folio) =3D=
=3D nr_pages
might lead to mkwrite() on a single pte within a partially unmapped large
folio. not quite sure this is wrong, but seems buggy and arduous.

>
> >               if (vmf->flags & FAULT_FLAG_WRITE) {
> >                       pte =3D maybe_mkwrite(pte_mkdirty(pte), vma);
> >                       vmf->flags &=3D ~FAULT_FLAG_WRITE;
> >               }
> >               rmap_flags |=3D RMAP_EXCLUSIVE;
> >       }
> > -     flush_icache_page(vma, page);
> > +     flush_icache_pages(vma, page, nr_pages);
> >       if (pte_swp_soft_dirty(vmf->orig_pte))
> >               pte =3D pte_mksoft_dirty(pte);
> >       if (pte_swp_uffd_wp(vmf->orig_pte))
> >               pte =3D pte_mkuffd_wp(pte);
> > -     vmf->orig_pte =3D pte;
> > +     vmf->orig_pte =3D pte_advance_pfn(pte, page_idx);
> >
> >       /* ksm created a completely new copy */
> >       if (unlikely(folio !=3D swapcache && swapcache)) {
> > -             folio_add_new_anon_rmap(folio, vma, vmf->address);
> > +             folio_add_new_anon_rmap(folio, vma, address);
> >               folio_add_lru_vma(folio, vma);
> >       } else {
> > -             folio_add_anon_rmap_pte(folio, page, vma, vmf->address,
> > +             folio_add_anon_rmap_ptes(folio, page, nr_pages, vma, addr=
ess,
> >                                       rmap_flags);
> >       }
> >
> >       VM_BUG_ON(!folio_test_anon(folio) ||
> >                       (pte_write(pte) && !PageAnonExclusive(page)));
> > -     set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
> > -     arch_do_swap_page_nr(vma->vm_mm, vma, vmf->address,
> > -                     pte, vmf->orig_pte, 1);
> > +     set_ptes(vma->vm_mm, address, ptep, pte, nr_pages);
> > +     arch_do_swap_page_nr(vma->vm_mm, vma, address,
> > +                     pte, pte, nr_pages);
> >
> >       folio_unlock(folio);
> >       if (folio !=3D swapcache && swapcache) {
> > @@ -4291,7 +4327,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> >       }
> >
> >       /* No need to invalidate - it was non-present before */
> > -     update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
> > +     update_mmu_cache_range(vmf, vma, address, ptep, nr_pages);
> >  unlock:
> >       if (vmf->pte)
> >               pte_unmap_unlock(vmf->pte, vmf->ptl);
>

Thanks
Barry