Message-ID: <CAMZfGtVMMBEFQAS=ch9fJFhCk+gBGV_frXBFnJLZR2Q22U4q2g@mail.gmail.com>
Date:   Sat, 27 Mar 2021 14:54:12 +0800
From:   Muchun Song <songmuchun@...edance.com>
To:     Mike Kravetz <mike.kravetz@...cle.com>
Cc:     Linux Memory Management List <linux-mm@...ck.org>,
        LKML <linux-kernel@...r.kernel.org>,
        Roman Gushchin <guro@...com>, Michal Hocko <mhocko@...e.com>,
        Shakeel Butt <shakeelb@...gle.com>,
        Oscar Salvador <osalvador@...e.de>,
        David Hildenbrand <david@...hat.com>,
        David Rientjes <rientjes@...gle.com>,
        Miaohe Lin <linmiaohe@...wei.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Matthew Wilcox <willy@...radead.org>,
        HORIGUCHI NAOYA <naoya.horiguchi@....com>,
        "Aneesh Kumar K . V" <aneesh.kumar@...ux.ibm.com>,
        Waiman Long <longman@...hat.com>, Peter Xu <peterx@...hat.com>,
        Mina Almasry <almasrymina@...gle.com>,
        Hillf Danton <hdanton@...a.com>,
        Andrew Morton <akpm@...ux-foundation.org>
Subject: Re: [External] [PATCH 5/8] hugetlb: call update_and_free_page without hugetlb_lock

On Thu, Mar 25, 2021 at 8:29 AM Mike Kravetz <mike.kravetz@...cle.com> wrote:
>
> With the introduction of remove_hugetlb_page(), there is no need for
> update_and_free_page to hold the hugetlb lock.  Change all callers to
> drop the lock before calling.
>
> With additional code modifications, this will allow loops which decrease
> the huge page pool to drop the hugetlb_lock with each page to reduce
> long hold times.
>
> The ugly unlock/lock cycle in free_pool_huge_page will be removed in
> a subsequent patch which restructures free_pool_huge_page.
>
> Signed-off-by: Mike Kravetz <mike.kravetz@...cle.com>

Reviewed-by: Muchun Song <songmuchun@...edance.com>

Some nits below.

> ---
>  mm/hugetlb.c | 34 +++++++++++++++++++++++++++++-----
>  1 file changed, 29 insertions(+), 5 deletions(-)
>
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 3938ec086b5c..fae7f034d1eb 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1450,16 +1450,18 @@ static void __free_huge_page(struct page *page)
>
>         if (HPageTemporary(page)) {
>                 remove_hugetlb_page(h, page, false);
> +               spin_unlock(&hugetlb_lock);
>                 update_and_free_page(h, page);
>         } else if (h->surplus_huge_pages_node[nid]) {
>                 /* remove the page from active list */
>                 remove_hugetlb_page(h, page, true);
> +               spin_unlock(&hugetlb_lock);
>                 update_and_free_page(h, page);
>         } else {
>                 arch_clear_hugepage_flags(page);
>                 enqueue_huge_page(h, page);
> +               spin_unlock(&hugetlb_lock);
>         }
> -       spin_unlock(&hugetlb_lock);
>  }
>
>  /*
> @@ -1740,7 +1742,13 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
>                                 list_entry(h->hugepage_freelists[node].next,
>                                           struct page, lru);
>                         remove_hugetlb_page(h, page, acct_surplus);
> +                       /*
> +                        * unlock/lock around update_and_free_page is temporary
> +                        * and will be removed with subsequent patch.
> +                        */
> +                       spin_unlock(&hugetlb_lock);
>                         update_and_free_page(h, page);
> +                       spin_lock(&hugetlb_lock);
>                         ret = 1;
>                         break;
>                 }
> @@ -1809,8 +1817,9 @@ int dissolve_free_huge_page(struct page *page)
>                 }
>                 remove_hugetlb_page(h, page, false);
>                 h->max_huge_pages--;
> +               spin_unlock(&hugetlb_lock);
>                 update_and_free_page(h, head);
> -               rc = 0;
> +               return 0;
>         }
>  out:
>         spin_unlock(&hugetlb_lock);
> @@ -2563,22 +2572,37 @@ static void try_to_free_low(struct hstate *h, unsigned long count,
>                                                 nodemask_t *nodes_allowed)
>  {
>         int i;
> +       struct list_head page_list;

I prefer to use LIST_HEAD(page_list) directly.

> +       struct page *page, *next;
>
>         if (hstate_is_gigantic(h))
>                 return;
>
> +       /*
> +        * Collect pages to be freed on a list, and free after dropping lock
> +        */
> +       INIT_LIST_HEAD(&page_list);
>         for_each_node_mask(i, *nodes_allowed) {
> -               struct page *page, *next;
>                 struct list_head *freel = &h->hugepage_freelists[i];
>                 list_for_each_entry_safe(page, next, freel, lru) {
>                         if (count >= h->nr_huge_pages)
> -                               return;
> +                               goto out;
>                         if (PageHighMem(page))
>                                 continue;
>                         remove_hugetlb_page(h, page, false);
> -                       update_and_free_page(h, page);
> +                       INIT_LIST_HEAD(&page->lru);

As Michal pointed out that this is superfluous.

> +                       list_add(&page->lru, &page_list);
>                 }
>         }
> +
> +out:
> +       spin_unlock(&hugetlb_lock);
> +       list_for_each_entry_safe(page, next, &page_list, lru) {
> +               list_del(&page->lru);

It looks like list_del() is also superfluous. Should we remove it?

Thanks.

> +               update_and_free_page(h, page);
> +               cond_resched();
> +       }
> +       spin_lock(&hugetlb_lock);
>  }
>  #else
>  static inline void try_to_free_low(struct hstate *h, unsigned long count,
> --
> 2.30.2
>

Powered by blists - more mailing lists