From: Miaohe Lin <linmiaohe@huawei.com>
To: Yang Shi <shy828301@gmail.com>
Cc: <linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>,
<david@redhat.com>, <aarcange@redhat.com>, <hughd@google.com>,
<kirill.shutemov@linux.intel.com>, <akpm@linux-foundation.org>
Subject: Re: [PATCH] mm: thp: don't have to lock page anymore when splitting PMD
Date: Fri, 4 Mar 2022 10:25:34 +0800 [thread overview]
Message-ID: <78dab4e0-1d68-c54b-2463-c0a5420b07d9@huawei.com> (raw)
In-Reply-To: <20220303222014.517033-1-shy828301@gmail.com>
On 2022/3/4 6:20, Yang Shi wrote:
> The commit c444eb564fb1 ("mm: thp: make the THP mapcount atomic against
> __split_huge_pmd_locked()") locked the page for PMD split to make
> mapcount stable for reuse_swap_page(), then commit 1c2f67308af4 ("mm:
> thp: fix MADV_REMOVE deadlock on shmem THP") reduce the scope to
> anonymous page only.
>
> However COW has not used mapcount to determine if the page is shared or
> not anymore due to the COW fixes [1] from David Hildenbrand and the
> reuse_swap_page() was removed as well. So PMD split doesn't have to
> lock the page anymore. This patch basically reverted the above two
> commits.
>
Sounds reasonable. Since mapcount is not used to determine if we need to COW
the page, PMD split doesn't have to lock the page anymore.
> [1] https://lore.kernel.org/linux-mm/20220131162940.210846-1-david@redhat.com/
>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Andrea Arcangeli <aarcange@redhat.com>
> Cc: Hugh Dickins <hughd@google.com>
> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
> Signed-off-by: Yang Shi <shy828301@gmail.com>
> ---
> mm/huge_memory.c | 44 +++++---------------------------------------
> 1 file changed, 5 insertions(+), 39 deletions(-)
>
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index b49e1a11df2e..daaa698bd273 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2134,8 +2134,6 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
> {
> spinlock_t *ptl;
> struct mmu_notifier_range range;
> - bool do_unlock_folio = false;
> - pmd_t _pmd;
>
> mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
> address & HPAGE_PMD_MASK,
> @@ -2148,48 +2146,16 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
> * pmd against. Otherwise we can end up replacing wrong folio.
> */
> VM_BUG_ON(freeze && !folio);
> - if (folio) {
> - VM_WARN_ON_ONCE(!folio_test_locked(folio));
> - if (folio != page_folio(pmd_page(*pmd)))
> - goto out;
> - }
> + if (folio && folio != page_folio(pmd_page(*pmd)))
> + goto out;
>
> -repeat:
> - if (pmd_trans_huge(*pmd)) {
> - if (!folio) {
> - folio = page_folio(pmd_page(*pmd));
> - /*
> - * An anonymous page must be locked, to ensure that a
> - * concurrent reuse_swap_page() sees stable mapcount;
> - * but reuse_swap_page() is not used on shmem or file,
> - * and page lock must not be taken when zap_pmd_range()
> - * calls __split_huge_pmd() while i_mmap_lock is held.
> - */
> - if (folio_test_anon(folio)) {
> - if (unlikely(!folio_trylock(folio))) {
> - folio_get(folio);
> - _pmd = *pmd;
> - spin_unlock(ptl);
> - folio_lock(folio);
> - spin_lock(ptl);
> - if (unlikely(!pmd_same(*pmd, _pmd))) {
> - folio_unlock(folio);
> - folio_put(folio);
> - folio = NULL;
> - goto repeat;
> - }
> - folio_put(folio);
> - }
> - do_unlock_folio = true;
> - }
> - }
> - } else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
> + if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
> goto out;
> +
> __split_huge_pmd_locked(vma, pmd, range.start, freeze);
IUUC, here should be something like below:
if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd))
__split_huge_pmd_locked(vma, pmd, range.start, freeze);
i.e. the pmd_trans_huge case is missing in the above change. Or am I miss something ?
Thanks for the patch. This really simplify the code and avoid the unneeded overhead.
> out:
> spin_unlock(ptl);
> - if (do_unlock_folio)
> - folio_unlock(folio);
> +
> /*
> * No need to double call mmu_notifier->invalidate_range() callback.
> * They are 3 cases to consider inside __split_huge_pmd_locked():
>
next prev parent reply other threads:[~2022-03-04 2:25 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-03 22:20 [PATCH] mm: thp: don't have to lock page anymore when splitting PMD Yang Shi
2022-03-04 2:25 ` Miaohe Lin [this message]
2022-03-04 3:12 ` Yang Shi
[not found] ` <CADFyXm6W9CVkO4XPYep-tHg55c8m8NES783kcVYrdjSMbzYoDA@mail.gmail.com>
2022-03-04 18:30 ` Yang Shi
2022-03-04 18:50 ` David Hildenbrand
2022-03-04 19:01 ` Yang Shi
2022-03-07 2:07 ` Andrew Morton
2022-03-07 8:24 ` David Hildenbrand
2022-03-07 23:43 ` Andrew Morton
2022-03-08 0:03 ` Yang Shi
2022-03-08 0:50 ` Andrew Morton
2022-03-08 0:59 ` Yang Shi
2022-03-08 2:36 ` Hugh Dickins
2022-03-08 3:12 ` Yang Shi
2022-03-08 8:53 ` David Hildenbrand
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=78dab4e0-1d68-c54b-2463-c0a5420b07d9@huawei.com \
--to=linmiaohe@huawei.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=david@redhat.com \
--cc=hughd@google.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=shy828301@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).