Linux-HyperV Archive on lore.kernel.org
 help / color / Atom feed
From: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
To: David Hildenbrand <david@redhat.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Linux MM <linux-mm@kvack.org>,
	linux-hyperv@vger.kernel.org, xen-devel@lists.xenproject.org,
	linux-acpi@vger.kernel.org,
	Andrew Morton <akpm@linux-foundation.org>,
	Oscar Salvador <osalvador@suse.de>,
	Alexander Duyck <alexander.h.duyck@linux.intel.com>,
	Mel Gorman <mgorman@techsingularity.net>,
	Michal Hocko <mhocko@kernel.org>,
	Dave Hansen <dave.hansen@intel.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	Wei Yang <richard.weiyang@linux.alibaba.com>,
	Mike Rapoport <rppt@kernel.org>,
	Scott Cheloha <cheloha@linux.ibm.com>,
	Michael Ellerman <mpe@ellerman.id.au>
Subject: Re: [PATCH v1 3/5] mm/page_alloc: always move pages to the tail of the freelist in unset_migratetype_isolate()
Date: Mon, 28 Sep 2020 22:55:19 +0200
Message-ID: <CAM9Jb+jYKPOcrDT7nfy=ZnSNGuTHE_M+AxG3G4kHcjT_UDnQ3w@mail.gmail.com> (raw)
In-Reply-To: <20200928182110.7050-4-david@redhat.com>

> Page isolation doesn't actually touch the pages, it simply isolates
> pageblocks and moves all free pages to the MIGRATE_ISOLATE freelist.
>
> We already place pages to the tail of the freelists when undoing
> isolation via __putback_isolated_page(), let's do it in any case
> (e.g., if order <= pageblock_order) and document the behavior.
>
> Add a "to_tail" parameter to move_freepages_block() but introduce a
> a new move_to_free_list_tail() - similar to add_to_free_list_tail().
>
> This change results in all pages getting onlined via online_pages() to
> be placed to the tail of the freelist.
>
> Reviewed-by: Oscar Salvador <osalvador@suse.de>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Dave Hansen <dave.hansen@intel.com>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
> Cc: Oscar Salvador <osalvador@suse.de>
> Cc: Mike Rapoport <rppt@kernel.org>
> Cc: Scott Cheloha <cheloha@linux.ibm.com>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---
>  include/linux/page-isolation.h |  4 ++--
>  mm/page_alloc.c                | 35 +++++++++++++++++++++++-----------
>  mm/page_isolation.c            | 12 +++++++++---
>  3 files changed, 35 insertions(+), 16 deletions(-)
>
> diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
> index 572458016331..3eca9b3c5305 100644
> --- a/include/linux/page-isolation.h
> +++ b/include/linux/page-isolation.h
> @@ -36,8 +36,8 @@ static inline bool is_migrate_isolate(int migratetype)
>  struct page *has_unmovable_pages(struct zone *zone, struct page *page,
>                                  int migratetype, int flags);
>  void set_pageblock_migratetype(struct page *page, int migratetype);
> -int move_freepages_block(struct zone *zone, struct page *page,
> -                               int migratetype, int *num_movable);
> +int move_freepages_block(struct zone *zone, struct page *page, int migratetype,
> +                        bool to_tail, int *num_movable);
>
>  /*
>   * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE.
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 9e3ed4a6f69a..d5a5f528b8ca 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -905,6 +905,15 @@ static inline void move_to_free_list(struct page *page, struct zone *zone,
>         list_move(&page->lru, &area->free_list[migratetype]);
>  }
>
> +/* Used for pages which are on another list */
> +static inline void move_to_free_list_tail(struct page *page, struct zone *zone,
> +                                         unsigned int order, int migratetype)
> +{
> +       struct free_area *area = &zone->free_area[order];
> +
> +       list_move_tail(&page->lru, &area->free_list[migratetype]);
> +}
> +
>  static inline void del_page_from_free_list(struct page *page, struct zone *zone,
>                                            unsigned int order)
>  {
> @@ -2338,9 +2347,9 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
>   * Note that start_page and end_pages are not aligned on a pageblock
>   * boundary. If alignment is required, use move_freepages_block()
>   */
> -static int move_freepages(struct zone *zone,
> -                         struct page *start_page, struct page *end_page,
> -                         int migratetype, int *num_movable)
> +static int move_freepages(struct zone *zone, struct page *start_page,
> +                         struct page *end_page, int migratetype,
> +                         bool to_tail, int *num_movable)
>  {
>         struct page *page;
>         unsigned int order;
> @@ -2371,7 +2380,10 @@ static int move_freepages(struct zone *zone,
>                 VM_BUG_ON_PAGE(page_zone(page) != zone, page);
>
>                 order = page_order(page);
> -               move_to_free_list(page, zone, order, migratetype);
> +               if (to_tail)
> +                       move_to_free_list_tail(page, zone, order, migratetype);
> +               else
> +                       move_to_free_list(page, zone, order, migratetype);
>                 page += 1 << order;
>                 pages_moved += 1 << order;
>         }
> @@ -2379,8 +2391,8 @@ static int move_freepages(struct zone *zone,
>         return pages_moved;
>  }
>
> -int move_freepages_block(struct zone *zone, struct page *page,
> -                               int migratetype, int *num_movable)
> +int move_freepages_block(struct zone *zone, struct page *page, int migratetype,
> +                        bool to_tail, int *num_movable)
>  {
>         unsigned long start_pfn, end_pfn;
>         struct page *start_page, *end_page;
> @@ -2401,7 +2413,7 @@ int move_freepages_block(struct zone *zone, struct page *page,
>                 return 0;
>
>         return move_freepages(zone, start_page, end_page, migratetype,
> -                                                               num_movable);
> +                             to_tail, num_movable);
>  }
>
>  static void change_pageblock_range(struct page *pageblock_page,
> @@ -2526,8 +2538,8 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page,
>         if (!whole_block)
>                 goto single_page;
>
> -       free_pages = move_freepages_block(zone, page, start_type,
> -                                               &movable_pages);
> +       free_pages = move_freepages_block(zone, page, start_type, false,
> +                                         &movable_pages);
>         /*
>          * Determine how many pages are compatible with our allocation.
>          * For movable allocation, it's the number of movable pages which
> @@ -2635,7 +2647,8 @@ static void reserve_highatomic_pageblock(struct page *page, struct zone *zone,
>             && !is_migrate_cma(mt)) {
>                 zone->nr_reserved_highatomic += pageblock_nr_pages;
>                 set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC);
> -               move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL);
> +               move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, false,
> +                                    NULL);
>         }
>
>  out_unlock:
> @@ -2711,7 +2724,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
>                          */
>                         set_pageblock_migratetype(page, ac->migratetype);
>                         ret = move_freepages_block(zone, page, ac->migratetype,
> -                                                                       NULL);
> +                                                  false, NULL);
>                         if (ret) {
>                                 spin_unlock_irqrestore(&zone->lock, flags);
>                                 return ret;
> diff --git a/mm/page_isolation.c b/mm/page_isolation.c
> index abfe26ad59fd..de44e1329706 100644
> --- a/mm/page_isolation.c
> +++ b/mm/page_isolation.c
> @@ -45,7 +45,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
>                 set_pageblock_migratetype(page, MIGRATE_ISOLATE);
>                 zone->nr_isolate_pageblock++;
>                 nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE,
> -                                                                       NULL);
> +                                               false, NULL);
>
>                 __mod_zone_freepage_state(zone, -nr_pages, mt);
>                 spin_unlock_irqrestore(&zone->lock, flags);
> @@ -83,7 +83,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
>          * Because freepage with more than pageblock_order on isolated
>          * pageblock is restricted to merge due to freepage counting problem,
>          * it is possible that there is free buddy page.
> -        * move_freepages_block() doesn't care of merge so we need other
> +        * move_freepages_block() don't care about merging, so we need another
>          * approach in order to merge them. Isolation and free will make
>          * these pages to be merged.
>          */
> @@ -106,9 +106,15 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
>          * If we isolate freepage with more than pageblock_order, there
>          * should be no freepage in the range, so we could avoid costly
>          * pageblock scanning for freepage moving.
> +        *
> +        * We didn't actually touch any of the isolated pages, so place them
> +        * to the tail of the freelist. This is an optimization for memory
> +        * onlining - just onlined memory won't immediately be considered for
> +        * allocation.
>          */
>         if (!isolated_page) {
> -               nr_pages = move_freepages_block(zone, page, migratetype, NULL);
> +               nr_pages = move_freepages_block(zone, page, migratetype, true,
> +                                               NULL);
>                 __mod_zone_freepage_state(zone, nr_pages, migratetype);
>         }
>         set_pageblock_migratetype(page, migratetype);

Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>

  reply index

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-28 18:21 [PATCH v1 0/5] mm: place pages to the freelist tail when onling and undoing isolation David Hildenbrand
2020-09-28 18:21 ` [PATCH v1 1/5] mm/page_alloc: convert "report" flag of __free_one_page() to a proper flag David Hildenbrand
2020-09-28 20:11   ` Pankaj Gupta
2020-09-29  8:58   ` Wei Yang
2020-10-02 13:17   ` Michal Hocko
2020-10-02 13:41   ` Matthew Wilcox
2020-10-02 14:48     ` David Hildenbrand
2020-10-02 14:57       ` David Hildenbrand
2020-09-28 18:21 ` [PATCH v1 2/5] mm/page_alloc: place pages to tail in __putback_isolated_page() David Hildenbrand
2020-09-28 20:38   ` Pankaj Gupta
2020-09-29  9:10   ` Wei Yang
2020-10-02 13:19   ` Michal Hocko
2020-09-28 18:21 ` [PATCH v1 3/5] mm/page_alloc: always move pages to the tail of the freelist in unset_migratetype_isolate() David Hildenbrand
2020-09-28 20:55   ` Pankaj Gupta [this message]
2020-09-29  9:18   ` Wei Yang
2020-09-29 10:12     ` David Hildenbrand
2020-09-30  7:48       ` Wei Yang
2020-10-02 13:24   ` Michal Hocko
2020-10-02 15:20     ` David Hildenbrand
2020-10-05  6:56       ` Michal Hocko
2020-10-05  8:20         ` Mel Gorman
2020-10-05  9:11           ` David Hildenbrand
2020-09-28 18:21 ` [PATCH v1 4/5] mm/page_alloc: place pages to tail in __free_pages_core() David Hildenbrand
2020-09-28 20:33   ` Pankaj Gupta
2020-09-29  9:36   ` Wei Yang
2020-09-29 10:14     ` David Hildenbrand
2020-10-02 13:41   ` Michal Hocko
2020-10-02 15:10     ` David Hildenbrand
2020-09-28 18:21 ` [PATCH v1 5/5] mm/memory_hotplug: update comment regarding zone shuffling David Hildenbrand
2020-09-29  9:40   ` Wei Yang
2020-10-02 13:41   ` Michal Hocko

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='CAM9Jb+jYKPOcrDT7nfy=ZnSNGuTHE_M+AxG3G4kHcjT_UDnQ3w@mail.gmail.com' \
    --to=pankaj.gupta.linux@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.h.duyck@linux.intel.com \
    --cc=cheloha@linux.ibm.com \
    --cc=dave.hansen@intel.com \
    --cc=david@redhat.com \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-hyperv@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@kernel.org \
    --cc=mpe@ellerman.id.au \
    --cc=osalvador@suse.de \
    --cc=richard.weiyang@linux.alibaba.com \
    --cc=rppt@kernel.org \
    --cc=vbabka@suse.cz \
    --cc=xen-devel@lists.xenproject.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

Linux-HyperV Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-hyperv/0 linux-hyperv/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-hyperv linux-hyperv/ https://lore.kernel.org/linux-hyperv \
		linux-hyperv@vger.kernel.org
	public-inbox-index linux-hyperv

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-hyperv


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git