Message-ID: <20250509200111.3372279-3-ziy@nvidia.com>
Date: Fri,  9 May 2025 16:01:09 -0400
From: Zi Yan <ziy@...dia.com>
To: David Hildenbrand <david@...hat.com>,
	Oscar Salvador <osalvador@...e.de>,
	Johannes Weiner <hannes@...xchg.org>,
	linux-mm@...ck.org
Cc: Andrew Morton <akpm@...ux-foundation.org>,
	Vlastimil Babka <vbabka@...e.cz>,
	Baolin Wang <baolin.wang@...ux.alibaba.com>,
	"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
	Mel Gorman <mgorman@...hsingularity.net>,
	Suren Baghdasaryan <surenb@...gle.com>,
	Michal Hocko <mhocko@...e.com>,
	Brendan Jackman <jackmanb@...gle.com>,
	Richard Chang <richardycc@...gle.com>,
	linux-kernel@...r.kernel.org,
	Zi Yan <ziy@...dia.com>
Subject: [PATCH v4 2/4] mm/page_isolation: remove migratetype from move_freepages_block_isolate()

Since migratetype is no longer overwritten during pageblock isolation,
moving pageblocks to and from MIGRATE_ISOLATE no longer needs migratetype.

Add MIGRATETYPE_NO_ISO_MASK to allow read before-isolation migratetype
when a pageblock is isolated. It is used by move_freepages_block_isolate().

Add pageblock_isolate_and_move_free_pages() and
pageblock_unisolate_and_move_free_pages() to be explicit about the page
isolation operations. Both share the common code in
__move_freepages_block_isolate(), which is renamed from
move_freepages_block_isolate().

Make set_pageblock_migratetype() only accept non MIGRATE_ISOLATE types,
so that one should use set_pageblock_isolate() to isolate pageblocks.

Two consequential changes:
1. move pageblock migratetype code out of __move_freepages_block().
2. in online_pages() from mm/memory_hotplug.c, move_pfn_range_to_zone() is
   called with MIGRATE_MOVABLE instead of MIGRATE_ISOLATE and all affected
   pageblocks are isolated afterwards. Otherwise, all online pageblocks
   will have non-determined migratetype.

Signed-off-by: Zi Yan <ziy@...dia.com>
---
 include/linux/mmzone.h         |  4 +-
 include/linux/page-isolation.h |  5 ++-
 mm/memory_hotplug.c            |  7 +++-
 mm/page_alloc.c                | 73 +++++++++++++++++++++++++---------
 mm/page_isolation.c            | 27 ++++++++-----
 5 files changed, 82 insertions(+), 34 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7ef01fe148ce..f66895456974 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -107,8 +107,10 @@ static inline bool migratetype_is_mergeable(int mt)
 extern int page_group_by_mobility_disabled;
 
 #ifdef CONFIG_MEMORY_ISOLATION
-#define MIGRATETYPE_MASK ((BIT(PB_migratetype_bits) - 1) | PB_migrate_isolate_bit)
+#define MIGRATETYPE_NO_ISO_MASK (BIT(PB_migratetype_bits) - 1)
+#define MIGRATETYPE_MASK (MIGRATETYPE_NO_ISO_MASK | PB_migrate_isolate_bit)
 #else
+#define MIGRATETYPE_NO_ISO_MASK MIGRATETYPE_MASK
 #define MIGRATETYPE_MASK (BIT(PB_migratetype_bits) - 1)
 #endif
 
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 898bb788243b..b0a2af0a5357 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -26,9 +26,10 @@ static inline bool is_migrate_isolate(int migratetype)
 #define REPORT_FAILURE	0x2
 
 void set_pageblock_migratetype(struct page *page, int migratetype);
+void set_pageblock_isolate(struct page *page);
 
-bool move_freepages_block_isolate(struct zone *zone, struct page *page,
-				  int migratetype);
+bool pageblock_isolate_and_move_free_pages(struct zone *zone, struct page *page);
+bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *page);
 
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			     int migratetype, int flags);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b1caedbade5b..c86c47bba019 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1178,6 +1178,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 	const int nid = zone_to_nid(zone);
 	int ret;
 	struct memory_notify arg;
+	unsigned long isol_pfn;
 
 	/*
 	 * {on,off}lining is constrained to full memory sections (or more
@@ -1192,7 +1193,11 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 
 
 	/* associate pfn range with the zone */
-	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE);
+	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_MOVABLE);
+	for (isol_pfn = pfn;
+	     isol_pfn < pfn + nr_pages;
+	     isol_pfn += pageblock_nr_pages)
+		set_pageblock_isolate(pfn_to_page(isol_pfn));
 
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 04e301fb4879..cfd37b2d992e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -454,11 +454,9 @@ void set_pageblock_migratetype(struct page *page, int migratetype)
 		migratetype = MIGRATE_UNMOVABLE;
 
 #ifdef CONFIG_MEMORY_ISOLATION
-	if (migratetype == MIGRATE_ISOLATE) {
-		set_pfnblock_flags_mask(page, PB_migrate_isolate_bit,
-				page_to_pfn(page), PB_migrate_isolate_bit);
-		return;
-	}
+	VM_WARN(migratetype == MIGRATE_ISOLATE,
+			"Use set_pageblock_isolate() for pageblock isolation");
+	return;
 #endif
 	set_pfnblock_flags_mask(page, (unsigned long)migratetype,
 				page_to_pfn(page), MIGRATETYPE_MASK);
@@ -1819,8 +1817,8 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
 #endif
 
 /*
- * Change the type of a block and move all its free pages to that
- * type's freelist.
+ * Move all free pages of a block to new type's freelist. Caller needs to
+ * change the block type.
  */
 static int __move_freepages_block(struct zone *zone, unsigned long start_pfn,
 				  int old_mt, int new_mt)
@@ -1852,8 +1850,6 @@ static int __move_freepages_block(struct zone *zone, unsigned long start_pfn,
 		pages_moved += 1 << order;
 	}
 
-	set_pageblock_migratetype(pfn_to_page(start_pfn), new_mt);
-
 	return pages_moved;
 }
 
@@ -1911,11 +1907,16 @@ static int move_freepages_block(struct zone *zone, struct page *page,
 				int old_mt, int new_mt)
 {
 	unsigned long start_pfn;
+	int res;
 
 	if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL))
 		return -1;
 
-	return __move_freepages_block(zone, start_pfn, old_mt, new_mt);
+	res = __move_freepages_block(zone, start_pfn, old_mt, new_mt);
+	set_pageblock_migratetype(pfn_to_page(start_pfn), new_mt);
+
+	return res;
+
 }
 
 #ifdef CONFIG_MEMORY_ISOLATION
@@ -1943,11 +1944,17 @@ static unsigned long find_large_buddy(unsigned long start_pfn)
 	return start_pfn;
 }
 
+static inline void toggle_pageblock_isolate(struct page *page, bool isolate)
+{
+	set_pfnblock_flags_mask(page, (isolate << PB_migrate_isolate),
+			page_to_pfn(page), PB_migrate_isolate_bit);
+}
+
 /**
- * move_freepages_block_isolate - move free pages in block for page isolation
+ * __move_freepages_block_isolate - move free pages in block for page isolation
  * @zone: the zone
  * @page: the pageblock page
- * @migratetype: migratetype to set on the pageblock
+ * @isolate: to isolate the given pageblock or unisolate it
  *
  * This is similar to move_freepages_block(), but handles the special
  * case encountered in page isolation, where the block of interest
@@ -1962,10 +1969,15 @@ static unsigned long find_large_buddy(unsigned long start_pfn)
  *
  * Returns %true if pages could be moved, %false otherwise.
  */
-bool move_freepages_block_isolate(struct zone *zone, struct page *page,
-				  int migratetype)
+static bool __move_freepages_block_isolate(struct zone *zone,
+		struct page *page, bool isolate)
 {
 	unsigned long start_pfn, pfn;
+	int from_mt;
+	int to_mt;
+
+	if (isolate == (get_pageblock_migratetype(page) == MIGRATE_ISOLATE))
+		return false;
 
 	if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL))
 		return false;
@@ -1982,7 +1994,7 @@ bool move_freepages_block_isolate(struct zone *zone, struct page *page,
 
 		del_page_from_free_list(buddy, zone, order,
 					get_pfnblock_migratetype(buddy, pfn));
-		set_pageblock_migratetype(page, migratetype);
+		toggle_pageblock_isolate(page, isolate);
 		split_large_buddy(zone, buddy, pfn, order, FPI_NONE);
 		return true;
 	}
@@ -1993,16 +2005,38 @@ bool move_freepages_block_isolate(struct zone *zone, struct page *page,
 
 		del_page_from_free_list(page, zone, order,
 					get_pfnblock_migratetype(page, pfn));
-		set_pageblock_migratetype(page, migratetype);
+		toggle_pageblock_isolate(page, isolate);
 		split_large_buddy(zone, page, pfn, order, FPI_NONE);
 		return true;
 	}
 move:
-	__move_freepages_block(zone, start_pfn,
-			       get_pfnblock_migratetype(page, start_pfn),
-			       migratetype);
+	/* use MIGRATETYPE_NO_ISO_MASK to get the non-isolate migratetype */
+	if (isolate) {
+		from_mt = get_pfnblock_flags_mask(page, page_to_pfn(page),
+				MIGRATETYPE_NO_ISO_MASK);
+		to_mt = MIGRATE_ISOLATE;
+	} else {
+		from_mt = MIGRATE_ISOLATE;
+		to_mt = get_pfnblock_flags_mask(page, page_to_pfn(page),
+				MIGRATETYPE_NO_ISO_MASK);
+	}
+
+	__move_freepages_block(zone, start_pfn, from_mt, to_mt);
+	toggle_pageblock_isolate(pfn_to_page(start_pfn), isolate);
+
 	return true;
 }
+
+bool pageblock_isolate_and_move_free_pages(struct zone *zone, struct page *page)
+{
+	return __move_freepages_block_isolate(zone, page, true);
+}
+
+bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *page)
+{
+	return __move_freepages_block_isolate(zone, page, false);
+}
+
 #endif /* CONFIG_MEMORY_ISOLATION */
 
 static void change_pageblock_range(struct page *pageblock_page,
@@ -2194,6 +2228,7 @@ try_to_claim_block(struct zone *zone, struct page *page,
 	if (free_pages + alike_pages >= (1 << (pageblock_order-1)) ||
 			page_group_by_mobility_disabled) {
 		__move_freepages_block(zone, start_pfn, block_type, start_type);
+		set_pageblock_migratetype(pfn_to_page(start_pfn), start_type);
 		return __rmqueue_smallest(zone, order, start_type);
 	}
 
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 751e21f6d85e..4571940f14db 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -25,6 +25,12 @@ static inline void clear_pageblock_isolate(struct page *page)
 	set_pfnblock_flags_mask(page, 0, page_to_pfn(page),
 			PB_migrate_isolate_bit);
 }
+void set_pageblock_isolate(struct page *page)
+{
+	set_pfnblock_flags_mask(page, PB_migrate_isolate_bit,
+			page_to_pfn(page),
+			PB_migrate_isolate_bit);
+}
 
 /*
  * This function checks whether the range [start_pfn, end_pfn) includes
@@ -199,7 +205,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	unmovable = has_unmovable_pages(check_unmovable_start, check_unmovable_end,
 			migratetype, isol_flags);
 	if (!unmovable) {
-		if (!move_freepages_block_isolate(zone, page, MIGRATE_ISOLATE)) {
+		if (!pageblock_isolate_and_move_free_pages(zone, page)) {
 			spin_unlock_irqrestore(&zone->lock, flags);
 			return -EBUSY;
 		}
@@ -220,7 +226,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	return -EBUSY;
 }
 
-static void unset_migratetype_isolate(struct page *page, int migratetype)
+static void unset_migratetype_isolate(struct page *page)
 {
 	struct zone *zone;
 	unsigned long flags;
@@ -273,10 +279,10 @@ static void unset_migratetype_isolate(struct page *page, int migratetype)
 		 * Isolating this block already succeeded, so this
 		 * should not fail on zone boundaries.
 		 */
-		WARN_ON_ONCE(!move_freepages_block_isolate(zone, page, migratetype));
+		WARN_ON_ONCE(!pageblock_unisolate_and_move_free_pages(zone, page));
 	} else {
-		set_pageblock_migratetype(page, migratetype);
-		__putback_isolated_page(page, order, migratetype);
+		clear_pageblock_isolate(page);
+		__putback_isolated_page(page, order, get_pageblock_migratetype(page));
 	}
 	zone->nr_isolate_pageblock--;
 out:
@@ -394,7 +400,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 		if (PageBuddy(page)) {
 			int order = buddy_order(page);
 
-			/* move_freepages_block_isolate() handled this */
+			/* pageblock_isolate_and_move_free_pages() handled this */
 			VM_WARN_ON_ONCE(pfn + (1 << order) > boundary_pfn);
 
 			pfn += 1UL << order;
@@ -444,7 +450,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 failed:
 	/* restore the original migratetype */
 	if (!skip_isolation)
-		unset_migratetype_isolate(pfn_to_page(isolate_pageblock), migratetype);
+		unset_migratetype_isolate(pfn_to_page(isolate_pageblock));
 	return -EBUSY;
 }
 
@@ -515,7 +521,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	ret = isolate_single_pageblock(isolate_end, flags, true,
 			skip_isolation, migratetype);
 	if (ret) {
-		unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype);
+		unset_migratetype_isolate(pfn_to_page(isolate_start));
 		return ret;
 	}
 
@@ -528,8 +534,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 					start_pfn, end_pfn)) {
 			undo_isolate_page_range(isolate_start, pfn, migratetype);
 			unset_migratetype_isolate(
-				pfn_to_page(isolate_end - pageblock_nr_pages),
-				migratetype);
+				pfn_to_page(isolate_end - pageblock_nr_pages));
 			return -EBUSY;
 		}
 	}
@@ -559,7 +564,7 @@ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 		page = __first_valid_page(pfn, pageblock_nr_pages);
 		if (!page || !is_migrate_isolate_page(page))
 			continue;
-		unset_migratetype_isolate(page, migratetype);
+		unset_migratetype_isolate(page);
 	}
 }
 /*
-- 
2.47.2

Powered by blists - more mailing lists