From: David Hildenbrand <david@redhat.com>
To: Muchun Song <songmuchun@bytedance.com>, akpm@linux-foundation.org
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] mm/page_alloc: Do not isolate redundant pageblock
Date: Fri, 27 Nov 2020 17:54:45 +0100 [thread overview]
Message-ID: <54061152-2a1b-694f-8d45-d1333bc4a3fb@redhat.com> (raw)
In-Reply-To: <20201127141900.43348-1-songmuchun@bytedance.com>
On 27.11.20 15:19, Muchun Song wrote:
> Current pageblock isolation logic could isolate each pageblock individually
> since commit d9dddbf55667 ("mm/page_alloc: prevent merging between isolated
> and other pageblocks"). So we not need to concern about page allocator
> merges buddies from different pageblocks and changes MIGRATE_ISOLATE to
> some other migration type.
>
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
> mm/page_alloc.c | 26 ++++++++------------------
> 1 file changed, 8 insertions(+), 18 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index cefbef32bf4a..608a2c2b8ab7 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -8313,16 +8313,14 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page,
> }
>
> #ifdef CONFIG_CONTIG_ALLOC
> -static unsigned long pfn_max_align_down(unsigned long pfn)
> +static unsigned long pfn_align_down(unsigned long pfn)
> {
> - return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
> - pageblock_nr_pages) - 1);
> + return pfn & ~(pageblock_nr_pages - 1);
> }
>
> -static unsigned long pfn_max_align_up(unsigned long pfn)
> +static unsigned long pfn_align_up(unsigned long pfn)
> {
> - return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
> - pageblock_nr_pages));
> + return ALIGN(pfn, pageblock_nr_pages);
> }
>
> /* [start, end) must belong to a single zone. */
> @@ -8415,14 +8413,6 @@ int alloc_contig_range(unsigned long start, unsigned long end,
> INIT_LIST_HEAD(&cc.migratepages);
>
> /*
> - * What we do here is we mark all pageblocks in range as
> - * MIGRATE_ISOLATE. Because pageblock and max order pages may
> - * have different sizes, and due to the way page allocator
> - * work, we align the range to biggest of the two pages so
> - * that page allocator won't try to merge buddies from
> - * different pageblocks and change MIGRATE_ISOLATE to some
> - * other migration type.
> - *
> * Once the pageblocks are marked as MIGRATE_ISOLATE, we
> * migrate the pages from an unaligned range (ie. pages that
> * we are interested in). This will put all the pages in
> @@ -8438,8 +8428,8 @@ int alloc_contig_range(unsigned long start, unsigned long end,
> * put back to page allocator so that buddy can use them.
> */
>
> - ret = start_isolate_page_range(pfn_max_align_down(start),
> - pfn_max_align_up(end), migratetype, 0);
> + ret = start_isolate_page_range(pfn_align_down(start), pfn_align_up(end),
> + migratetype, 0);
> if (ret)
> return ret;
>
> @@ -8522,8 +8512,8 @@ int alloc_contig_range(unsigned long start, unsigned long end,
> free_contig_range(end, outer_end - end);
>
> done:
> - undo_isolate_page_range(pfn_max_align_down(start),
> - pfn_max_align_up(end), migratetype);
> + undo_isolate_page_range(pfn_align_down(start), pfn_align_up(end),
> + migratetype);
> return ret;
> }
> EXPORT_SYMBOL(alloc_contig_range);
>
Last time I checked, set_migratetype_isolate()->has_unmovable_pages()
was not prepared for that in case of !CMA and !ZONE_MOVABLE.
Assume you have an unmovable MAX_ORDER - 1 page that spans two
pageblocks (e.g., x86-64). Assume you try to isolate the second
pageblock. IIRC, you would answer "yes", as the refcount of all involved
pages is 0.
How did you test this works as expected?
--
Thanks,
David / dhildenb
next prev parent reply other threads:[~2020-11-27 16:54 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-27 14:19 [PATCH] mm/page_alloc: Do not isolate redundant pageblock Muchun Song
2020-11-27 15:17 ` Vlastimil Babka
2020-11-27 15:43 ` [External] " Muchun Song
2020-11-27 16:54 ` David Hildenbrand [this message]
2020-11-27 16:56 ` 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=54061152-2a1b-694f-8d45-d1333bc4a3fb@redhat.com \
--to=david@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=songmuchun@bytedance.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).