From: Muchun Song <songmuchun@bytedance.com>
To: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Linux Memory Management List <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
Roman Gushchin <guro@fb.com>, Michal Hocko <mhocko@suse.com>,
Shakeel Butt <shakeelb@google.com>,
Oscar Salvador <osalvador@suse.de>,
David Hildenbrand <david@redhat.com>,
David Rientjes <rientjes@google.com>,
Miaohe Lin <linmiaohe@huawei.com>,
Peter Zijlstra <peterz@infradead.org>,
Matthew Wilcox <willy@infradead.org>,
HORIGUCHI NAOYA <naoya.horiguchi@nec.com>,
"Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>,
Waiman Long <longman@redhat.com>, Peter Xu <peterx@redhat.com>,
Mina Almasry <almasrymina@google.com>,
Hillf Danton <hdanton@sina.com>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [External] [PATCH 5/8] hugetlb: call update_and_free_page without hugetlb_lock
Date: Sat, 27 Mar 2021 14:54:12 +0800 [thread overview]
Message-ID: <CAMZfGtVMMBEFQAS=ch9fJFhCk+gBGV_frXBFnJLZR2Q22U4q2g@mail.gmail.com> (raw)
In-Reply-To: <20210325002835.216118-6-mike.kravetz@oracle.com>
On Thu, Mar 25, 2021 at 8:29 AM Mike Kravetz <mike.kravetz@oracle.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@oracle.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.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
>
next prev parent reply other threads:[~2021-03-27 6:54 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-25 0:28 [PATCH 0/8] make hugetlb put_page safe for all calling contexts Mike Kravetz
2021-03-25 0:28 ` [PATCH 1/8] mm: cma: introduce cma_release_nowait() Mike Kravetz
2021-03-25 9:39 ` Oscar Salvador
2021-03-25 9:45 ` Michal Hocko
2021-03-25 9:54 ` Oscar Salvador
2021-03-25 10:10 ` Michal Hocko
2021-03-25 10:11 ` Michal Hocko
2021-03-25 10:13 ` David Hildenbrand
2021-03-25 10:17 ` Oscar Salvador
2021-03-25 10:24 ` Michal Hocko
2021-03-25 9:56 ` David Hildenbrand
2021-03-25 10:22 ` Michal Hocko
2021-03-25 16:56 ` Mike Kravetz
2021-03-25 17:15 ` David Hildenbrand
2021-03-25 20:12 ` Minchan Kim
2021-03-25 23:19 ` Roman Gushchin
2021-03-25 23:49 ` Mike Kravetz
2021-03-26 21:32 ` Mike Kravetz
2021-03-29 7:46 ` Michal Hocko
2021-03-29 22:27 ` Mike Kravetz
2021-03-25 0:28 ` [PATCH 2/8] mm: hugetlb: don't drop hugetlb_lock around cma_release() call Mike Kravetz
2021-03-25 0:28 ` [PATCH 3/8] hugetlb: add per-hstate mutex to synchronize user adjustments Mike Kravetz
2021-03-25 10:47 ` Michal Hocko
2021-03-25 12:29 ` Oscar Salvador
2021-03-26 1:52 ` Miaohe Lin
2021-03-25 0:28 ` [PATCH 4/8] hugetlb: create remove_hugetlb_page() to separate functionality Mike Kravetz
2021-03-25 10:49 ` Michal Hocko
2021-03-26 2:10 ` Miaohe Lin
2021-03-26 19:57 ` Mike Kravetz
2021-03-27 1:40 ` Miaohe Lin
2021-03-27 6:36 ` [External] " Muchun Song
2021-03-25 0:28 ` [PATCH 5/8] hugetlb: call update_and_free_page without hugetlb_lock Mike Kravetz
2021-03-25 10:55 ` Michal Hocko
2021-03-25 17:12 ` Mike Kravetz
2021-03-25 19:39 ` Michal Hocko
2021-03-25 20:33 ` Mike Kravetz
2021-03-27 6:54 ` Muchun Song [this message]
2021-03-28 21:40 ` [External] " Mike Kravetz
2021-03-25 0:28 ` [PATCH 6/8] hugetlb: change free_pool_huge_page to remove_pool_huge_page Mike Kravetz
2021-03-25 11:06 ` Michal Hocko
2021-03-25 17:29 ` Mike Kravetz
2021-03-25 0:28 ` [PATCH 7/8] hugetlb: make free_huge_page irq safe Mike Kravetz
2021-03-25 11:21 ` Michal Hocko
2021-03-25 17:32 ` Mike Kravetz
2021-03-27 7:06 ` [External] " Muchun Song
2021-03-29 7:49 ` Michal Hocko
2021-03-29 22:44 ` Mike Kravetz
2021-03-25 0:28 ` [PATCH 8/8] hugetlb: add lockdep_assert_held() calls for hugetlb_lock Mike Kravetz
2021-03-25 11:22 ` Michal Hocko
2021-03-26 2:12 ` Miaohe Lin
2021-03-27 8:14 ` [External] " Muchun Song
2021-03-26 1:42 ` [PATCH 0/8] make hugetlb put_page safe for all calling contexts Miaohe Lin
2021-03-26 20:00 ` Mike Kravetz
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='CAMZfGtVMMBEFQAS=ch9fJFhCk+gBGV_frXBFnJLZR2Q22U4q2g@mail.gmail.com' \
--to=songmuchun@bytedance.com \
--cc=akpm@linux-foundation.org \
--cc=almasrymina@google.com \
--cc=aneesh.kumar@linux.ibm.com \
--cc=david@redhat.com \
--cc=guro@fb.com \
--cc=hdanton@sina.com \
--cc=linmiaohe@huawei.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=longman@redhat.com \
--cc=mhocko@suse.com \
--cc=mike.kravetz@oracle.com \
--cc=naoya.horiguchi@nec.com \
--cc=osalvador@suse.de \
--cc=peterx@redhat.com \
--cc=peterz@infradead.org \
--cc=rientjes@google.com \
--cc=shakeelb@google.com \
--cc=willy@infradead.org \
/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).