Linux-HyperV Archive on lore.kernel.org
 help / color / Atom feed
From: David Hildenbrand <david@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: 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>,
	David Hildenbrand <david@redhat.com>,
	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: [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 20:21:08 +0200
Message-ID: <20200928182110.7050-4-david@redhat.com> (raw)
In-Reply-To: <20200928182110.7050-1-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);
-- 
2.26.2


  parent 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 ` David Hildenbrand [this message]
2020-09-28 20:55   ` [PATCH v1 3/5] mm/page_alloc: always move pages to the tail of the freelist in unset_migratetype_isolate() Pankaj Gupta
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=20200928182110.7050-4-david@redhat.com \
    --to=david@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.h.duyck@linux.intel.com \
    --cc=cheloha@linux.ibm.com \
    --cc=dave.hansen@intel.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