Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 494 insertions, 399 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 00fafda76b..df2c442f1c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -54,6 +54,7 @@
 #include <linux/khugepaged.h>
 #include <linux/delayacct.h>
 #include <linux/cacheinfo.h>
+#include <linux/pgalloc_tag.h>
 #include <asm/div64.h>
 #include "internal.h"
 #include "shuffle.h"
@@ -206,24 +207,6 @@ EXPORT_SYMBOL(node_states);
 
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
 
-/*
- * A cached value of the page's pageblock's migratetype, used when the page is
- * put on a pcplist. Used to avoid the pageblock migratetype lookup when
- * freeing from pcplists in most cases, at the cost of possibly becoming stale.
- * Also the migratetype set in the page does not necessarily match the pcplist
- * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any
- * other index - this ensures that it will be put on the correct CMA freelist.
- */
-static inline int get_pcppage_migratetype(struct page *page)
-{
-	return page->index;
-}
-
-static inline void set_pcppage_migratetype(struct page *page, int migratetype)
-{
-	page->index = migratetype;
-}
-
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 unsigned int pageblock_order __read_mostly;
 #endif
@@ -332,7 +315,7 @@ static inline bool deferred_pages_enabled(void)
 static bool __ref
 _deferred_grow_zone(struct zone *zone, unsigned int order)
 {
-       return deferred_grow_zone(zone, order);
+	return deferred_grow_zone(zone, order);
 }
 #else
 static inline bool deferred_pages_enabled(void)
@@ -525,7 +508,7 @@ static inline unsigned int order_to_pindex(int migratetype, int order)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	if (order > PAGE_ALLOC_COSTLY_ORDER) {
-		VM_BUG_ON(order != pageblock_order);
+		VM_BUG_ON(order != HPAGE_PMD_ORDER);
 
 		movable = migratetype == MIGRATE_MOVABLE;
 
@@ -544,7 +527,7 @@ static inline int pindex_to_order(unsigned int pindex)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	if (pindex >= NR_LOWORDER_PCP_LISTS)
-		order = pageblock_order;
+		order = HPAGE_PMD_ORDER;
 #else
 	VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER);
 #endif
@@ -557,20 +540,12 @@ static inline bool pcp_allowed_order(unsigned int order)
 	if (order <= PAGE_ALLOC_COSTLY_ORDER)
 		return true;
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (order == pageblock_order)
+	if (order == HPAGE_PMD_ORDER)
 		return true;
 #endif
 	return false;
 }
 
-static inline void free_the_page(struct page *page, unsigned int order)
-{
-	if (pcp_allowed_order(order))		/* Via pcp? */
-		free_unref_page(page, order);
-	else
-		__free_pages_ok(page, order, FPI_NONE);
-}
-
 /*
  * Higher-order pages are called "compound pages".  They are structured thusly:
  *
@@ -595,20 +570,6 @@ void prep_compound_page(struct page *page, unsigned int order)
 	prep_compound_head(page, order);
 }
 
-void destroy_large_folio(struct folio *folio)
-{
-	if (folio_test_hugetlb(folio)) {
-		free_huge_folio(folio);
-		return;
-	}
-
-	if (folio_test_large_rmappable(folio))
-		folio_undo_large_rmappable(folio);
-
-	mem_cgroup_uncharge(folio);
-	free_the_page(&folio->page, folio_order(folio));
-}
-
 static inline void set_buddy_order(struct page *page, unsigned int order)
 {
 	set_page_private(page, order);
@@ -639,12 +600,14 @@ compaction_capture(struct capture_control *capc, struct page *page,
 		return false;
 
 	/*
-	 * Do not let lower order allocations pollute a movable pageblock.
+	 * Do not let lower order allocations pollute a movable pageblock
+	 * unless compaction is also requesting movable pages.
 	 * This might let an unmovable request use a reclaimable pageblock
 	 * and vice-versa but no more than normal fallback logic which can
 	 * have trouble finding a high-order free page.
 	 */
-	if (order < pageblock_order && migratetype == MIGRATE_MOVABLE)
+	if (order < pageblock_order && migratetype == MIGRATE_MOVABLE &&
+	    capc->cc->migratetype != MIGRATE_MOVABLE)
 		return false;
 
 	capc->page = page;
@@ -665,23 +628,33 @@ compaction_capture(struct capture_control *capc, struct page *page,
 }
 #endif /* CONFIG_COMPACTION */
 
-/* Used for pages not on another list */
-static inline void add_to_free_list(struct page *page, struct zone *zone,
-				    unsigned int order, int migratetype)
+static inline void account_freepages(struct zone *zone, int nr_pages,
+				     int migratetype)
 {
-	struct free_area *area = &zone->free_area[order];
+	if (is_migrate_isolate(migratetype))
+		return;
 
-	list_add(&page->buddy_list, &area->free_list[migratetype]);
-	area->nr_free++;
+	__mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages);
+
+	if (is_migrate_cma(migratetype))
+		__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages);
 }
 
 /* Used for pages not on another list */
-static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
-					 unsigned int order, int migratetype)
+static inline void __add_to_free_list(struct page *page, struct zone *zone,
+				      unsigned int order, int migratetype,
+				      bool tail)
 {
 	struct free_area *area = &zone->free_area[order];
 
-	list_add_tail(&page->buddy_list, &area->free_list[migratetype]);
+	VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype,
+		     "page type is %lu, passed migratetype is %d (nr=%d)\n",
+		     get_pageblock_migratetype(page), migratetype, 1 << order);
+
+	if (tail)
+		list_add_tail(&page->buddy_list, &area->free_list[migratetype]);
+	else
+		list_add(&page->buddy_list, &area->free_list[migratetype]);
 	area->nr_free++;
 }
 
@@ -691,16 +664,28 @@ static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
  * allocation again (e.g., optimization for memory onlining).
  */
 static inline void move_to_free_list(struct page *page, struct zone *zone,
-				     unsigned int order, int migratetype)
+				     unsigned int order, int old_mt, int new_mt)
 {
 	struct free_area *area = &zone->free_area[order];
 
-	list_move_tail(&page->buddy_list, &area->free_list[migratetype]);
+	/* Free page moving can fail, so it happens before the type update */
+	VM_WARN_ONCE(get_pageblock_migratetype(page) != old_mt,
+		     "page type is %lu, passed migratetype is %d (nr=%d)\n",
+		     get_pageblock_migratetype(page), old_mt, 1 << order);
+
+	list_move_tail(&page->buddy_list, &area->free_list[new_mt]);
+
+	account_freepages(zone, -(1 << order), old_mt);
+	account_freepages(zone, 1 << order, new_mt);
 }
 
-static inline void del_page_from_free_list(struct page *page, struct zone *zone,
-					   unsigned int order)
+static inline void __del_page_from_free_list(struct page *page, struct zone *zone,
+					     unsigned int order, int migratetype)
 {
+        VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype,
+		     "page type is %lu, passed migratetype is %d (nr=%d)\n",
+		     get_pageblock_migratetype(page), migratetype, 1 << order);
+
 	/* clear reported state and update reported page count */
 	if (page_reported(page))
 		__ClearPageReported(page);
@@ -711,6 +696,13 @@ static inline void del_page_from_free_list(struct page *page, struct zone *zone,
 	zone->free_area[order].nr_free--;
 }
 
+static inline void del_page_from_free_list(struct page *page, struct zone *zone,
+					   unsigned int order, int migratetype)
+{
+	__del_page_from_free_list(page, zone, order, migratetype);
+	account_freepages(zone, -(1 << order), migratetype);
+}
+
 static inline struct page *get_page_from_free_area(struct free_area *area,
 					    int migratetype)
 {
@@ -782,16 +774,16 @@ static inline void __free_one_page(struct page *page,
 	VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
 
 	VM_BUG_ON(migratetype == -1);
-	if (likely(!is_migrate_isolate(migratetype)))
-		__mod_zone_freepage_state(zone, 1 << order, migratetype);
-
 	VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
+	account_freepages(zone, 1 << order, migratetype);
+
 	while (order < MAX_PAGE_ORDER) {
+		int buddy_mt = migratetype;
+
 		if (compaction_capture(capc, page, order, migratetype)) {
-			__mod_zone_freepage_state(zone, -(1 << order),
-								migratetype);
+			account_freepages(zone, -(1 << order), migratetype);
 			return;
 		}
 
@@ -806,11 +798,11 @@ static inline void __free_one_page(struct page *page,
 			 * pageblock isolation could cause incorrect freepage or CMA
 			 * accounting or HIGHATOMIC accounting.
 			 */
-			int buddy_mt = get_pfnblock_migratetype(buddy, buddy_pfn);
+			buddy_mt = get_pfnblock_migratetype(buddy, buddy_pfn);
 
-			if (migratetype != buddy_mt
-					&& (!migratetype_is_mergeable(migratetype) ||
-						!migratetype_is_mergeable(buddy_mt)))
+			if (migratetype != buddy_mt &&
+			    (!migratetype_is_mergeable(migratetype) ||
+			     !migratetype_is_mergeable(buddy_mt)))
 				goto done_merging;
 		}
 
@@ -819,9 +811,19 @@ static inline void __free_one_page(struct page *page,
 		 * merge with it and move up one order.
 		 */
 		if (page_is_guard(buddy))
-			clear_page_guard(zone, buddy, order, migratetype);
+			clear_page_guard(zone, buddy, order);
 		else
-			del_page_from_free_list(buddy, zone, order);
+			__del_page_from_free_list(buddy, zone, order, buddy_mt);
+
+		if (unlikely(buddy_mt != migratetype)) {
+			/*
+			 * Match buddy type. This ensures that an
+			 * expand() down the line puts the sub-blocks
+			 * on the right freelists.
+			 */
+			set_pageblock_migratetype(buddy, migratetype);
+		}
+
 		combined_pfn = buddy_pfn & pfn;
 		page = page + (combined_pfn - pfn);
 		pfn = combined_pfn;
@@ -838,74 +840,13 @@ done_merging:
 	else
 		to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);
 
-	if (to_tail)
-		add_to_free_list_tail(page, zone, order, migratetype);
-	else
-		add_to_free_list(page, zone, order, migratetype);
+	__add_to_free_list(page, zone, order, migratetype, to_tail);
 
 	/* Notify page reporting subsystem of freed page */
 	if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY))
 		page_reporting_notify_free(order);
 }
 
-/**
- * split_free_page() -- split a free page at split_pfn_offset
- * @free_page:		the original free page
- * @order:		the order of the page
- * @split_pfn_offset:	split offset within the page
- *
- * Return -ENOENT if the free page is changed, otherwise 0
- *
- * It is used when the free page crosses two pageblocks with different migratetypes
- * at split_pfn_offset within the page. The split free page will be put into
- * separate migratetype lists afterwards. Otherwise, the function achieves
- * nothing.
- */
-int split_free_page(struct page *free_page,
-			unsigned int order, unsigned long split_pfn_offset)
-{
-	struct zone *zone = page_zone(free_page);
-	unsigned long free_page_pfn = page_to_pfn(free_page);
-	unsigned long pfn;
-	unsigned long flags;
-	int free_page_order;
-	int mt;
-	int ret = 0;
-
-	if (split_pfn_offset == 0)
-		return ret;
-
-	spin_lock_irqsave(&zone->lock, flags);
-
-	if (!PageBuddy(free_page) || buddy_order(free_page) != order) {
-		ret = -ENOENT;
-		goto out;
-	}
-
-	mt = get_pfnblock_migratetype(free_page, free_page_pfn);
-	if (likely(!is_migrate_isolate(mt)))
-		__mod_zone_freepage_state(zone, -(1UL << order), mt);
-
-	del_page_from_free_list(free_page, zone, order);
-	for (pfn = free_page_pfn;
-	     pfn < free_page_pfn + (1UL << order);) {
-		int mt = get_pfnblock_migratetype(pfn_to_page(pfn), pfn);
-
-		free_page_order = min_t(unsigned int,
-					pfn ? __ffs(pfn) : order,
-					__fls(split_pfn_offset));
-		__free_one_page(pfn_to_page(pfn), pfn, zone, free_page_order,
-				mt, FPI_NONE);
-		pfn += 1UL << free_page_order;
-		split_pfn_offset -= (1UL << free_page_order);
-		/* we have done the first part, now switch to second part */
-		if (split_pfn_offset == 0)
-			split_pfn_offset = (1UL << order) - (pfn - free_page_pfn);
-	}
-out:
-	spin_unlock_irqrestore(&zone->lock, flags);
-	return ret;
-}
 /*
  * A bad page could be due to a number of fields. Instead of multiple branches,
  * try and check multiple fields with one check. The caller must do a detailed
@@ -1001,6 +942,10 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page)
 			bad_page(page, "nonzero entire_mapcount");
 			goto out;
 		}
+		if (unlikely(folio_large_mapcount(folio))) {
+			bad_page(page, "nonzero large_mapcount");
+			goto out;
+		}
 		if (unlikely(atomic_read(&folio->_nr_pages_mapped))) {
 			bad_page(page, "nonzero nr_pages_mapped");
 			goto out;
@@ -1011,10 +956,11 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page)
 		}
 		break;
 	case 2:
-		/*
-		 * the second tail page: ->mapping is
-		 * deferred_list.next -- ignore value.
-		 */
+		/* the second tail page: deferred_list overlaps ->mapping */
+		if (unlikely(!list_empty(&folio->_deferred_list))) {
+			bad_page(page, "on deferred list");
+			goto out;
+		}
 		break;
 	default:
 		if (page->mapping != TAIL_MAPPING) {
@@ -1106,6 +1052,7 @@ __always_inline bool free_pages_prepare(struct page *page,
 		/* Do not let hwpoison pages hit pcplists/buddy */
 		reset_page_owner(page, order);
 		page_table_check_free(page, order);
+		pgalloc_tag_sub(page, 1 << order);
 		return false;
 	}
 
@@ -1145,6 +1092,7 @@ __always_inline bool free_pages_prepare(struct page *page,
 	page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	reset_page_owner(page, order);
 	page_table_check_free(page, order);
+	pgalloc_tag_sub(page, 1 << order);
 
 	if (!PageHighMem(page)) {
 		debug_check_no_locks_freed(page_address(page),
@@ -1196,7 +1144,6 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 {
 	unsigned long flags;
 	unsigned int order;
-	bool isolated_pageblocks;
 	struct page *page;
 
 	/*
@@ -1209,7 +1156,6 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	pindex = pindex - 1;
 
 	spin_lock_irqsave(&zone->lock, flags);
-	isolated_pageblocks = has_isolate_pageblock(zone);
 
 	while (count > 0) {
 		struct list_head *list;
@@ -1225,23 +1171,19 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 		order = pindex_to_order(pindex);
 		nr_pages = 1 << order;
 		do {
+			unsigned long pfn;
 			int mt;
 
 			page = list_last_entry(list, struct page, pcp_list);
-			mt = get_pcppage_migratetype(page);
+			pfn = page_to_pfn(page);
+			mt = get_pfnblock_migratetype(page, pfn);
 
 			/* must delete to avoid corrupting pcp list */
 			list_del(&page->pcp_list);
 			count -= nr_pages;
 			pcp->count -= nr_pages;
 
-			/* MIGRATE_ISOLATE page should not go to pcplists */
-			VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
-			/* Pageblock could have been isolated meanwhile */
-			if (unlikely(isolated_pageblocks))
-				mt = get_pageblock_migratetype(page);
-
-			__free_one_page(page, page_to_pfn(page), zone, order, mt, FPI_NONE);
+			__free_one_page(page, pfn, zone, order, mt, FPI_NONE);
 			trace_mm_page_pcpu_drain(page, order, mt);
 		} while (count > 0 && !list_empty(list));
 	}
@@ -1249,18 +1191,15 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
 
-static void free_one_page(struct zone *zone,
-				struct page *page, unsigned long pfn,
-				unsigned int order,
-				int migratetype, fpi_t fpi_flags)
+static void free_one_page(struct zone *zone, struct page *page,
+			  unsigned long pfn, unsigned int order,
+			  fpi_t fpi_flags)
 {
 	unsigned long flags;
+	int migratetype;
 
 	spin_lock_irqsave(&zone->lock, flags);
-	if (unlikely(has_isolate_pageblock(zone) ||
-		is_migrate_isolate(migratetype))) {
-		migratetype = get_pfnblock_migratetype(page, pfn);
-	}
+	migratetype = get_pfnblock_migratetype(page, pfn);
 	__free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
@@ -1268,21 +1207,13 @@ static void free_one_page(struct zone *zone,
 static void __free_pages_ok(struct page *page, unsigned int order,
 			    fpi_t fpi_flags)
 {
-	int migratetype;
 	unsigned long pfn = page_to_pfn(page);
 	struct zone *zone = page_zone(page);
 
 	if (!free_pages_prepare(page, order))
 		return;
 
-	/*
-	 * Calling get_pfnblock_migratetype() without spin_lock_irqsave() here
-	 * is used to avoid calling get_pfnblock_migratetype() under the lock.
-	 * This will reduce the lock holding time.
-	 */
-	migratetype = get_pfnblock_migratetype(page, pfn);
-
-	free_one_page(zone, page, pfn, order, migratetype, fpi_flags);
+	free_one_page(zone, page, pfn, order, fpi_flags);
 
 	__count_vm_events(PGFREE, 1 << order);
 }
@@ -1393,6 +1324,7 @@ static inline void expand(struct zone *zone, struct page *page,
 	int low, int high, int migratetype)
 {
 	unsigned long size = 1 << high;
+	unsigned long nr_added = 0;
 
 	while (high > low) {
 		high--;
@@ -1405,12 +1337,14 @@ static inline void expand(struct zone *zone, struct page *page,
 		 * Corresponding page table entries will not be touched,
 		 * pages will stay not present in virtual address space
 		 */
-		if (set_page_guard(zone, &page[size], high, migratetype))
+		if (set_page_guard(zone, &page[size], high))
 			continue;
 
-		add_to_free_list(&page[size], zone, high, migratetype);
+		__add_to_free_list(&page[size], zone, high, migratetype, false);
 		set_buddy_order(&page[size], high);
+		nr_added += size;
 	}
+	account_freepages(zone, nr_added, migratetype);
 }
 
 static void check_new_page_bad(struct page *page)
@@ -1538,6 +1472,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 
 	set_page_owner(page, order, gfp_flags);
 	page_table_check_alloc(page, order);
+	pgalloc_tag_add(page, current, 1 << order);
 }
 
 static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
@@ -1578,9 +1513,8 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		page = get_page_from_free_area(area, migratetype);
 		if (!page)
 			continue;
-		del_page_from_free_list(page, zone, current_order);
+		del_page_from_free_list(page, zone, current_order, migratetype);
 		expand(zone, page, order, current_order, migratetype);
-		set_pcppage_migratetype(page, migratetype);
 		trace_mm_page_alloc_zone_locked(page, order, migratetype,
 				pcp_allowed_order(order) &&
 				migratetype < MIGRATE_PCPTYPES);
@@ -1597,7 +1531,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
  *
  * The other migratetypes do not have fallbacks.
  */
-static int fallbacks[MIGRATE_TYPES][MIGRATE_PCPTYPES - 1] = {
+static int fallbacks[MIGRATE_PCPTYPES][MIGRATE_PCPTYPES - 1] = {
 	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE   },
 	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE },
 	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE   },
@@ -1615,30 +1549,23 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
 #endif
 
 /*
- * Move the free pages in a range to the freelist tail of the requested type.
- * Note that start_page and end_pages are not aligned on a pageblock
- * boundary. If alignment is required, use move_freepages_block()
+ * Change the type of a block and move all its free pages to that
+ * type's freelist.
  */
-static int move_freepages(struct zone *zone,
-			  unsigned long start_pfn, unsigned long end_pfn,
-			  int migratetype, int *num_movable)
+static int __move_freepages_block(struct zone *zone, unsigned long start_pfn,
+				  int old_mt, int new_mt)
 {
 	struct page *page;
-	unsigned long pfn;
+	unsigned long pfn, end_pfn;
 	unsigned int order;
 	int pages_moved = 0;
 
-	for (pfn = start_pfn; pfn <= end_pfn;) {
+	VM_WARN_ON(start_pfn & (pageblock_nr_pages - 1));
+	end_pfn = pageblock_end_pfn(start_pfn);
+
+	for (pfn = start_pfn; pfn < end_pfn;) {
 		page = pfn_to_page(pfn);
 		if (!PageBuddy(page)) {
-			/*
-			 * We assume that pages that could be isolated for
-			 * migration are movable. But we don't actually try
-			 * isolating, as that would be expensive.
-			 */
-			if (num_movable &&
-					(PageLRU(page) || __PageMovable(page)))
-				(*num_movable)++;
 			pfn++;
 			continue;
 		}
@@ -1648,36 +1575,187 @@ static int move_freepages(struct zone *zone,
 		VM_BUG_ON_PAGE(page_zone(page) != zone, page);
 
 		order = buddy_order(page);
-		move_to_free_list(page, zone, order, migratetype);
+
+		move_to_free_list(page, zone, order, old_mt, new_mt);
+
 		pfn += 1 << order;
 		pages_moved += 1 << order;
 	}
 
+	set_pageblock_migratetype(pfn_to_page(start_pfn), new_mt);
+
 	return pages_moved;
 }
 
-int move_freepages_block(struct zone *zone, struct page *page,
-				int migratetype, int *num_movable)
+static bool prep_move_freepages_block(struct zone *zone, struct page *page,
+				      unsigned long *start_pfn,
+				      int *num_free, int *num_movable)
 {
-	unsigned long start_pfn, end_pfn, pfn;
+	unsigned long pfn, start, end;
+
+	pfn = page_to_pfn(page);
+	start = pageblock_start_pfn(pfn);
+	end = pageblock_end_pfn(pfn);
 
-	if (num_movable)
+	/*
+	 * The caller only has the lock for @zone, don't touch ranges
+	 * that straddle into other zones. While we could move part of
+	 * the range that's inside the zone, this call is usually
+	 * accompanied by other operations such as migratetype updates
+	 * which also should be locked.
+	 */
+	if (!zone_spans_pfn(zone, start))
+		return false;
+	if (!zone_spans_pfn(zone, end - 1))
+		return false;
+
+	*start_pfn = start;
+
+	if (num_free) {
+		*num_free = 0;
 		*num_movable = 0;
+		for (pfn = start; pfn < end;) {
+			page = pfn_to_page(pfn);
+			if (PageBuddy(page)) {
+				int nr = 1 << buddy_order(page);
 
-	pfn = page_to_pfn(page);
-	start_pfn = pageblock_start_pfn(pfn);
-	end_pfn = pageblock_end_pfn(pfn) - 1;
+				*num_free += nr;
+				pfn += nr;
+				continue;
+			}
+			/*
+			 * We assume that pages that could be isolated for
+			 * migration are movable. But we don't actually try
+			 * isolating, as that would be expensive.
+			 */
+			if (PageLRU(page) || __PageMovable(page))
+				(*num_movable)++;
+			pfn++;
+		}
+	}
 
-	/* Do not cross zone boundaries */
-	if (!zone_spans_pfn(zone, start_pfn))
-		start_pfn = pfn;
-	if (!zone_spans_pfn(zone, end_pfn))
-		return 0;
+	return true;
+}
+
+static int move_freepages_block(struct zone *zone, struct page *page,
+				int old_mt, int new_mt)
+{
+	unsigned long start_pfn;
 
-	return move_freepages(zone, start_pfn, end_pfn, migratetype,
-								num_movable);
+	if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL))
+		return -1;
+
+	return __move_freepages_block(zone, start_pfn, old_mt, new_mt);
 }
 
+#ifdef CONFIG_MEMORY_ISOLATION
+/* Look for a buddy that straddles start_pfn */
+static unsigned long find_large_buddy(unsigned long start_pfn)
+{
+	int order = 0;
+	struct page *page;
+	unsigned long pfn = start_pfn;
+
+	while (!PageBuddy(page = pfn_to_page(pfn))) {
+		/* Nothing found */
+		if (++order > MAX_PAGE_ORDER)
+			return start_pfn;
+		pfn &= ~0UL << order;
+	}
+
+	/*
+	 * Found a preceding buddy, but does it straddle?
+	 */
+	if (pfn + (1 << buddy_order(page)) > start_pfn)
+		return pfn;
+
+	/* Nothing found */
+	return start_pfn;
+}
+
+/* Split a multi-block free page into its individual pageblocks */
+static void split_large_buddy(struct zone *zone, struct page *page,
+			      unsigned long pfn, int order)
+{
+	unsigned long end_pfn = pfn + (1 << order);
+
+	VM_WARN_ON_ONCE(order <= pageblock_order);
+	VM_WARN_ON_ONCE(pfn & (pageblock_nr_pages - 1));
+
+	/* Caller removed page from freelist, buddy info cleared! */
+	VM_WARN_ON_ONCE(PageBuddy(page));
+
+	while (pfn != end_pfn) {
+		int mt = get_pfnblock_migratetype(page, pfn);
+
+		__free_one_page(page, pfn, zone, pageblock_order, mt, FPI_NONE);
+		pfn += pageblock_nr_pages;
+		page = pfn_to_page(pfn);
+	}
+}
+
+/**
+ * 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
+ *
+ * This is similar to move_freepages_block(), but handles the special
+ * case encountered in page isolation, where the block of interest
+ * might be part of a larger buddy spanning multiple pageblocks.
+ *
+ * Unlike the regular page allocator path, which moves pages while
+ * stealing buddies off the freelist, page isolation is interested in
+ * arbitrary pfn ranges that may have overlapping buddies on both ends.
+ *
+ * This function handles that. Straddling buddies are split into
+ * individual pageblocks. Only the block of interest is moved.
+ *
+ * Returns %true if pages could be moved, %false otherwise.
+ */
+bool move_freepages_block_isolate(struct zone *zone, struct page *page,
+				  int migratetype)
+{
+	unsigned long start_pfn, pfn;
+
+	if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL))
+		return false;
+
+	/* No splits needed if buddies can't span multiple blocks */
+	if (pageblock_order == MAX_PAGE_ORDER)
+		goto move;
+
+	/* We're a tail block in a larger buddy */
+	pfn = find_large_buddy(start_pfn);
+	if (pfn != start_pfn) {
+		struct page *buddy = pfn_to_page(pfn);
+		int order = buddy_order(buddy);
+
+		del_page_from_free_list(buddy, zone, order,
+					get_pfnblock_migratetype(buddy, pfn));
+		set_pageblock_migratetype(page, migratetype);
+		split_large_buddy(zone, buddy, pfn, order);
+		return true;
+	}
+
+	/* We're the starting block of a larger buddy */
+	if (PageBuddy(page) && buddy_order(page) > pageblock_order) {
+		int order = buddy_order(page);
+
+		del_page_from_free_list(page, zone, order,
+					get_pfnblock_migratetype(page, pfn));
+		set_pageblock_migratetype(page, migratetype);
+		split_large_buddy(zone, page, pfn, order);
+		return true;
+	}
+move:
+	__move_freepages_block(zone, start_pfn,
+			       get_pfnblock_migratetype(page, start_pfn),
+			       migratetype);
+	return true;
+}
+#endif /* CONFIG_MEMORY_ISOLATION */
+
 static void change_pageblock_range(struct page *pageblock_page,
 					int start_order, int migratetype)
 {
@@ -1760,33 +1838,37 @@ static inline bool boost_watermark(struct zone *zone)
 }
 
 /*
- * This function implements actual steal behaviour. If order is large enough,
- * we can steal whole pageblock. If not, we first move freepages in this
- * pageblock to our migratetype and determine how many already-allocated pages
- * are there in the pageblock with a compatible migratetype. If at least half
- * of pages are free or compatible, we can change migratetype of the pageblock
- * itself, so pages freed in the future will be put on the correct free list.
+ * This function implements actual steal behaviour. If order is large enough, we
+ * can claim the whole pageblock for the requested migratetype. If not, we check
+ * the pageblock for constituent pages; if at least half of the pages are free
+ * or compatible, we can still claim the whole block, so pages freed in the
+ * future will be put on the correct free list. Otherwise, we isolate exactly
+ * the order we need from the fallback block and leave its migratetype alone.
  */
-static void steal_suitable_fallback(struct zone *zone, struct page *page,
-		unsigned int alloc_flags, int start_type, bool whole_block)
+static struct page *
+steal_suitable_fallback(struct zone *zone, struct page *page,
+			int current_order, int order, int start_type,
+			unsigned int alloc_flags, bool whole_block)
 {
-	unsigned int current_order = buddy_order(page);
 	int free_pages, movable_pages, alike_pages;
-	int old_block_type;
+	unsigned long start_pfn;
+	int block_type;
 
-	old_block_type = get_pageblock_migratetype(page);
+	block_type = get_pageblock_migratetype(page);
 
 	/*
 	 * This can happen due to races and we want to prevent broken
 	 * highatomic accounting.
 	 */
-	if (is_migrate_highatomic(old_block_type))
+	if (is_migrate_highatomic(block_type))
 		goto single_page;
 
 	/* Take ownership for orders >= pageblock_order */
 	if (current_order >= pageblock_order) {
+		del_page_from_free_list(page, zone, current_order, block_type);
 		change_pageblock_range(page, current_order, start_type);
-		goto single_page;
+		expand(zone, page, order, current_order, start_type);
+		return page;
 	}
 
 	/*
@@ -1801,10 +1883,9 @@ 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);
 	/* moving whole block can fail due to zone boundary conditions */
-	if (!free_pages)
+	if (!prep_move_freepages_block(zone, page, &start_pfn, &free_pages,
+				       &movable_pages))
 		goto single_page;
 
 	/*
@@ -1822,7 +1903,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page,
 		 * vice versa, be conservative since we can't distinguish the
 		 * exact migratetype of non-movable pages.
 		 */
-		if (old_block_type == MIGRATE_MOVABLE)
+		if (block_type == MIGRATE_MOVABLE)
 			alike_pages = pageblock_nr_pages
 						- (free_pages + movable_pages);
 		else
@@ -1833,13 +1914,15 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page,
 	 * compatible migratability as our allocation, claim the whole block.
 	 */
 	if (free_pages + alike_pages >= (1 << (pageblock_order-1)) ||
-			page_group_by_mobility_disabled)
-		set_pageblock_migratetype(page, start_type);
-
-	return;
+			page_group_by_mobility_disabled) {
+		__move_freepages_block(zone, start_pfn, block_type, start_type);
+		return __rmqueue_smallest(zone, order, start_type);
+	}
 
 single_page:
-	move_to_free_list(page, zone, current_order, start_type);
+	del_page_from_free_list(page, zone, current_order, block_type);
+	expand(zone, page, order, current_order, block_type);
+	return page;
 }
 
 /*
@@ -1877,10 +1960,12 @@ int find_suitable_fallback(struct free_area *area, unsigned int order,
 }
 
 /*
- * Reserve a pageblock for exclusive use of high-order atomic allocations if
- * there are no empty page blocks that contain a page with a suitable order
+ * Reserve the pageblock(s) surrounding an allocation request for
+ * exclusive use of high-order atomic allocations if there are no
+ * empty page blocks that contain a page with a suitable order
  */
-static void reserve_highatomic_pageblock(struct page *page, struct zone *zone)
+static void reserve_highatomic_pageblock(struct page *page, int order,
+					 struct zone *zone)
 {
 	int mt;
 	unsigned long max_managed, flags;
@@ -1906,10 +1991,16 @@ static void reserve_highatomic_pageblock(struct page *page, struct zone *zone)
 	/* Yoink! */
 	mt = get_pageblock_migratetype(page);
 	/* Only reserve normal pageblocks (i.e., they can merge with others) */
-	if (migratetype_is_mergeable(mt)) {
+	if (!migratetype_is_mergeable(mt))
+		goto out_unlock;
+
+	if (order < pageblock_order) {
+		if (move_freepages_block(zone, page, mt, MIGRATE_HIGHATOMIC) == -1)
+			goto out_unlock;
 		zone->nr_reserved_highatomic += pageblock_nr_pages;
-		set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC);
-		move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL);
+	} else {
+		change_pageblock_range(page, order, MIGRATE_HIGHATOMIC);
+		zone->nr_reserved_highatomic += 1 << order;
 	}
 
 out_unlock:
@@ -1922,7 +2013,7 @@ out_unlock:
  * intense memory pressure but failed atomic allocations should be easier
  * to recover from than an OOM.
  *
- * If @force is true, try to unreserve a pageblock even though highatomic
+ * If @force is true, try to unreserve pageblocks even though highatomic
  * pageblock is exhausted.
  */
 static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
@@ -1934,7 +2025,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
 	struct zone *zone;
 	struct page *page;
 	int order;
-	bool ret;
+	int ret;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx,
 								ac->nodemask) {
@@ -1949,11 +2040,13 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
 		spin_lock_irqsave(&zone->lock, flags);
 		for (order = 0; order < NR_PAGE_ORDERS; order++) {
 			struct free_area *area = &(zone->free_area[order]);
+			int mt;
 
 			page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC);
 			if (!page)
 				continue;
 
+			mt = get_pageblock_migratetype(page);
 			/*
 			 * In page freeing path, migratetype change is racy so
 			 * we can counter several free pages in a pageblock
@@ -1961,7 +2054,8 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
 			 * from highatomic to ac->migratetype. So we should
 			 * adjust the count once.
 			 */
-			if (is_migrate_highatomic_page(page)) {
+			if (is_migrate_highatomic(mt)) {
+				unsigned long size;
 				/*
 				 * It should never happen but changes to
 				 * locking could inadvertently allow a per-cpu
@@ -1969,9 +2063,9 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
 				 * while unreserving so be safe and watch for
 				 * underflows.
 				 */
-				zone->nr_reserved_highatomic -= min(
-						pageblock_nr_pages,
-						zone->nr_reserved_highatomic);
+				size = max(pageblock_nr_pages, 1UL << order);
+				size = min(size, zone->nr_reserved_highatomic);
+				zone->nr_reserved_highatomic -= size;
 			}
 
 			/*
@@ -1983,10 +2077,22 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
 			 * of pageblocks that cannot be completely freed
 			 * may increase.
 			 */
-			set_pageblock_migratetype(page, ac->migratetype);
-			ret = move_freepages_block(zone, page, ac->migratetype,
-									NULL);
-			if (ret) {
+			if (order < pageblock_order)
+				ret = move_freepages_block(zone, page, mt,
+							   ac->migratetype);
+			else {
+				move_to_free_list(page, zone, order, mt,
+						  ac->migratetype);
+				change_pageblock_range(page, order,
+						       ac->migratetype);
+				ret = 1;
+			}
+			/*
+			 * Reserving the block(s) already succeeded,
+			 * so this should not fail on zone boundaries.
+			 */
+			WARN_ON_ONCE(ret == -1);
+			if (ret > 0) {
 				spin_unlock_irqrestore(&zone->lock, flags);
 				return ret;
 			}
@@ -2007,7 +2113,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
  * deviation from the rest of this file, to make the for loop
  * condition simpler.
  */
-static __always_inline bool
+static __always_inline struct page *
 __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
 						unsigned int alloc_flags)
 {
@@ -2054,7 +2160,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
 		goto do_steal;
 	}
 
-	return false;
+	return NULL;
 
 find_smallest:
 	for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) {
@@ -2074,14 +2180,14 @@ find_smallest:
 do_steal:
 	page = get_page_from_free_area(area, fallback_mt);
 
-	steal_suitable_fallback(zone, page, alloc_flags, start_migratetype,
-								can_steal);
+	/* take off list, maybe claim block, expand remainder */
+	page = steal_suitable_fallback(zone, page, current_order, order,
+				       start_migratetype, alloc_flags, can_steal);
 
 	trace_mm_page_alloc_extfrag(page, order, current_order,
 		start_migratetype, fallback_mt);
 
-	return true;
-
+	return page;
 }
 
 /*
@@ -2108,15 +2214,15 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
 				return page;
 		}
 	}
-retry:
+
 	page = __rmqueue_smallest(zone, order, migratetype);
 	if (unlikely(!page)) {
 		if (alloc_flags & ALLOC_CMA)
 			page = __rmqueue_cma_fallback(zone, order);
 
-		if (!page && __rmqueue_fallback(zone, order, migratetype,
-								alloc_flags))
-			goto retry;
+		if (!page)
+			page = __rmqueue_fallback(zone, order, migratetype,
+						  alloc_flags);
 	}
 	return page;
 }
@@ -2151,12 +2257,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		 * pages are ordered properly.
 		 */
 		list_add_tail(&page->pcp_list, list);
-		if (is_migrate_cma(get_pcppage_migratetype(page)))
-			__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
-					      -(1 << order));
 	}
-
-	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
 	spin_unlock_irqrestore(&zone->lock, flags);
 
 	return i;
@@ -2221,14 +2322,21 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
  */
 static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
-	struct per_cpu_pages *pcp;
+	struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
+	int count;
 
-	pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
-	if (pcp->count) {
+	do {
 		spin_lock(&pcp->lock);
-		free_pcppages_bulk(zone, pcp->count, pcp, 0);
+		count = pcp->count;
+		if (count) {
+			int to_drain = min(count,
+				pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
+
+			free_pcppages_bulk(zone, to_drain, pcp, 0);
+			count -= to_drain;
+		}
 		spin_unlock(&pcp->lock);
-	}
+	} while (count);
 }
 
 /*
@@ -2344,19 +2452,6 @@ void drain_all_pages(struct zone *zone)
 	__drain_all_pages(zone, false);
 }
 
-static bool free_unref_page_prepare(struct page *page, unsigned long pfn,
-							unsigned int order)
-{
-	int migratetype;
-
-	if (!free_pages_prepare(page, order))
-		return false;
-
-	migratetype = get_pfnblock_migratetype(page, pfn);
-	set_pcppage_migratetype(page, migratetype);
-	return true;
-}
-
 static int nr_pcp_free(struct per_cpu_pages *pcp, int batch, int high, bool free_high)
 {
 	int min_nr_free, max_nr_free;
@@ -2487,9 +2582,14 @@ void free_unref_page(struct page *page, unsigned int order)
 	struct per_cpu_pages *pcp;
 	struct zone *zone;
 	unsigned long pfn = page_to_pfn(page);
-	int migratetype, pcpmigratetype;
+	int migratetype;
 
-	if (!free_unref_page_prepare(page, pfn, order))
+	if (!pcp_allowed_order(order)) {
+		__free_pages_ok(page, order, FPI_NONE);
+		return;
+	}
+
+	if (!free_pages_prepare(page, order))
 		return;
 
 	/*
@@ -2499,23 +2599,23 @@ void free_unref_page(struct page *page, unsigned int order)
 	 * get those areas back if necessary. Otherwise, we may have to free
 	 * excessively into the page allocator
 	 */
-	migratetype = pcpmigratetype = get_pcppage_migratetype(page);
+	migratetype = get_pfnblock_migratetype(page, pfn);
 	if (unlikely(migratetype >= MIGRATE_PCPTYPES)) {
 		if (unlikely(is_migrate_isolate(migratetype))) {
-			free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE);
+			free_one_page(page_zone(page), page, pfn, order, FPI_NONE);
 			return;
 		}
-		pcpmigratetype = MIGRATE_MOVABLE;
+		migratetype = MIGRATE_MOVABLE;
 	}
 
 	zone = page_zone(page);
 	pcp_trylock_prepare(UP_flags);
 	pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 	if (pcp) {
-		free_unref_page_commit(zone, pcp, page, pcpmigratetype, order);
+		free_unref_page_commit(zone, pcp, page, migratetype, order);
 		pcp_spin_unlock(pcp);
 	} else {
-		free_one_page(zone, page, pfn, order, migratetype, FPI_NONE);
+		free_one_page(zone, page, pfn, order, FPI_NONE);
 	}
 	pcp_trylock_finish(UP_flags);
 }
@@ -2528,7 +2628,7 @@ void free_unref_folios(struct folio_batch *folios)
 	unsigned long __maybe_unused UP_flags;
 	struct per_cpu_pages *pcp = NULL;
 	struct zone *locked_zone = NULL;
-	int i, j, migratetype;
+	int i, j;
 
 	/* Prepare folios for freeing */
 	for (i = 0, j = 0; i < folios->nr; i++) {
@@ -2538,18 +2638,15 @@ void free_unref_folios(struct folio_batch *folios)
 
 		if (order > 0 && folio_test_large_rmappable(folio))
 			folio_undo_large_rmappable(folio);
-		if (!free_unref_page_prepare(&folio->page, pfn, order))
+		if (!free_pages_prepare(&folio->page, order))
 			continue;
-
 		/*
-		 * Free isolated folios and orders not handled on the PCP
-		 * directly to the allocator, see comment in free_unref_page.
+		 * Free orders not handled on the PCP directly to the
+		 * allocator.
 		 */
-		migratetype = get_pcppage_migratetype(&folio->page);
-		if (!pcp_allowed_order(order) ||
-		    is_migrate_isolate(migratetype)) {
-			free_one_page(folio_zone(folio), &folio->page, pfn,
-					order, migratetype, FPI_NONE);
+		if (!pcp_allowed_order(order)) {
+			free_one_page(folio_zone(folio), &folio->page,
+				      pfn, order, FPI_NONE);
 			continue;
 		}
 		folio->private = (void *)(unsigned long)order;
@@ -2562,16 +2659,31 @@ void free_unref_folios(struct folio_batch *folios)
 	for (i = 0; i < folios->nr; i++) {
 		struct folio *folio = folios->folios[i];
 		struct zone *zone = folio_zone(folio);
+		unsigned long pfn = folio_pfn(folio);
 		unsigned int order = (unsigned long)folio->private;
+		int migratetype;
 
 		folio->private = NULL;
-		migratetype = get_pcppage_migratetype(&folio->page);
+		migratetype = get_pfnblock_migratetype(&folio->page, pfn);
 
 		/* Different zone requires a different pcp lock */
-		if (zone != locked_zone) {
+		if (zone != locked_zone ||
+		    is_migrate_isolate(migratetype)) {
 			if (pcp) {
 				pcp_spin_unlock(pcp);
 				pcp_trylock_finish(UP_flags);
+				locked_zone = NULL;
+				pcp = NULL;
+			}
+
+			/*
+			 * Free isolated pages directly to the
+			 * allocator, see comment in free_unref_page.
+			 */
+			if (is_migrate_isolate(migratetype)) {
+				free_one_page(zone, &folio->page, pfn,
+					      order, FPI_NONE);
+				continue;
 			}
 
 			/*
@@ -2582,10 +2694,8 @@ void free_unref_folios(struct folio_batch *folios)
 			pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 			if (unlikely(!pcp)) {
 				pcp_trylock_finish(UP_flags);
-				free_one_page(zone, &folio->page,
-						folio_pfn(folio), order,
-						migratetype, FPI_NONE);
-				locked_zone = NULL;
+				free_one_page(zone, &folio->page, pfn,
+					      order, FPI_NONE);
 				continue;
 			}
 			locked_zone = zone;
@@ -2628,6 +2738,7 @@ void split_page(struct page *page, unsigned int order)
 	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
 	split_page_owner(page, order, 0);
+	pgalloc_tag_split(page, 1 << order);
 	split_page_memcg(page, order, 0);
 }
 EXPORT_SYMBOL_GPL(split_page);
@@ -2648,11 +2759,9 @@ int __isolate_free_page(struct page *page, unsigned int order)
 		watermark = zone->_watermark[WMARK_MIN] + (1UL << order);
 		if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
 			return 0;
-
-		__mod_zone_freepage_state(zone, -(1UL << order), mt);
 	}
 
-	del_page_from_free_list(page, zone, order);
+	del_page_from_free_list(page, zone, order, mt);
 
 	/*
 	 * Set the pageblock if the isolated page is at least half of a
@@ -2667,8 +2776,8 @@ int __isolate_free_page(struct page *page, unsigned int order)
 			 * with others)
 			 */
 			if (migratetype_is_mergeable(mt))
-				set_pageblock_migratetype(page,
-							  MIGRATE_MOVABLE);
+				move_freepages_block(zone, page, mt,
+						     MIGRATE_MOVABLE);
 		}
 	}
 
@@ -2752,8 +2861,6 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
 				return NULL;
 			}
 		}
-		__mod_zone_freepage_state(zone, -(1 << order),
-					  get_pcppage_migratetype(page));
 		spin_unlock_irqrestore(&zone->lock, flags);
 	} while (check_new_pages(page, order));
 
@@ -3326,7 +3433,7 @@ try_this_zone:
 			 * if the pageblock should be reserved for the future
 			 */
 			if (unlikely(alloc_flags & ALLOC_HIGHATOMIC))
-				reserve_highatomic_pageblock(page, zone);
+				reserve_highatomic_pageblock(page, order, zone);
 
 			return page;
 		} else {
@@ -4389,7 +4496,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
  *
  * Returns the number of pages on the list or array.
  */
-unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
+unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 			nodemask_t *nodemask, int nr_pages,
 			struct list_head *page_list,
 			struct page **page_array)
@@ -4525,7 +4632,7 @@ failed_irq:
 	pcp_trylock_finish(UP_flags);
 
 failed:
-	page = __alloc_pages(gfp, 0, preferred_nid, nodemask);
+	page = __alloc_pages_noprof(gfp, 0, preferred_nid, nodemask);
 	if (page) {
 		if (page_list)
 			list_add(&page->lru, page_list);
@@ -4536,13 +4643,13 @@ failed:
 
 	goto out;
 }
-EXPORT_SYMBOL_GPL(__alloc_pages_bulk);
+EXPORT_SYMBOL_GPL(alloc_pages_bulk_noprof);
 
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */
-struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
-							nodemask_t *nodemask)
+struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order,
+				      int preferred_nid, nodemask_t *nodemask)
 {
 	struct page *page;
 	unsigned int alloc_flags = ALLOC_WMARK_LOW;
@@ -4604,38 +4711,38 @@ out:
 
 	return page;
 }
-EXPORT_SYMBOL(__alloc_pages);
+EXPORT_SYMBOL(__alloc_pages_noprof);
 
-struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
+struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid,
 		nodemask_t *nodemask)
 {
-	struct page *page = __alloc_pages(gfp | __GFP_COMP, order,
+	struct page *page = __alloc_pages_noprof(gfp | __GFP_COMP, order,
 					preferred_nid, nodemask);
 	return page_rmappable_folio(page);
 }
-EXPORT_SYMBOL(__folio_alloc);
+EXPORT_SYMBOL(__folio_alloc_noprof);
 
 /*
  * Common helper functions. Never use with __GFP_HIGHMEM because the returned
  * address cannot represent highmem pages. Use alloc_pages and then kmap if
  * you need to access high mem.
  */
-unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
+unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order)
 {
 	struct page *page;
 
-	page = alloc_pages(gfp_mask & ~__GFP_HIGHMEM, order);
+	page = alloc_pages_noprof(gfp_mask & ~__GFP_HIGHMEM, order);
 	if (!page)
 		return 0;
 	return (unsigned long) page_address(page);
 }
-EXPORT_SYMBOL(__get_free_pages);
+EXPORT_SYMBOL(get_free_pages_noprof);
 
-unsigned long get_zeroed_page(gfp_t gfp_mask)
+unsigned long get_zeroed_page_noprof(gfp_t gfp_mask)
 {
-	return __get_free_page(gfp_mask | __GFP_ZERO);
+	return get_free_pages_noprof(gfp_mask | __GFP_ZERO, 0);
 }
-EXPORT_SYMBOL(get_zeroed_page);
+EXPORT_SYMBOL(get_zeroed_page_noprof);
 
 /**
  * __free_pages - Free pages allocated with alloc_pages().
@@ -4661,12 +4768,15 @@ void __free_pages(struct page *page, unsigned int order)
 {
 	/* get PageHead before we drop reference */
 	int head = PageHead(page);
+	struct alloc_tag *tag = pgalloc_tag_get(page);
 
 	if (put_page_testzero(page))
-		free_the_page(page, order);
-	else if (!head)
+		free_unref_page(page, order);
+	else if (!head) {
+		pgalloc_tag_sub_pages(tag, (1 << order) - 1);
 		while (order-- > 0)
-			free_the_page(page + (1 << order), order);
+			free_unref_page(page + (1 << order), order);
+	}
 }
 EXPORT_SYMBOL(__free_pages);
 
@@ -4727,7 +4837,7 @@ void __page_frag_cache_drain(struct page *page, unsigned int count)
 	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
 
 	if (page_ref_sub_and_test(page, count))
-		free_the_page(page, compound_order(page));
+		free_unref_page(page, compound_order(page));
 }
 EXPORT_SYMBOL(__page_frag_cache_drain);
 
@@ -4768,7 +4878,7 @@ refill:
 			goto refill;
 
 		if (unlikely(nc->pfmemalloc)) {
-			free_the_page(page, compound_order(page));
+			free_unref_page(page, compound_order(page));
 			goto refill;
 		}
 
@@ -4812,7 +4922,7 @@ void page_frag_free(void *addr)
 	struct page *page = virt_to_head_page(addr);
 
 	if (unlikely(put_page_testzero(page)))
-		free_the_page(page, compound_order(page));
+		free_unref_page(page, compound_order(page));
 }
 EXPORT_SYMBOL(page_frag_free);
 
@@ -4825,6 +4935,7 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order,
 		struct page *last = page + nr;
 
 		split_page_owner(page, order, 0);
+		pgalloc_tag_split(page, 1 << order);
 		split_page_memcg(page, order, 0);
 		while (page < --last)
 			set_page_refcounted(last);
@@ -4851,7 +4962,7 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order,
  *
  * Return: pointer to the allocated area or %NULL in case of error.
  */
-void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
+void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask)
 {
 	unsigned int order = get_order(size);
 	unsigned long addr;
@@ -4859,10 +4970,10 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
 	if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM)))
 		gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM);
 
-	addr = __get_free_pages(gfp_mask, order);
+	addr = get_free_pages_noprof(gfp_mask, order);
 	return make_alloc_exact(addr, order, size);
 }
-EXPORT_SYMBOL(alloc_pages_exact);
+EXPORT_SYMBOL(alloc_pages_exact_noprof);
 
 /**
  * alloc_pages_exact_nid - allocate an exact number of physically-contiguous
@@ -4876,7 +4987,7 @@ EXPORT_SYMBOL(alloc_pages_exact);
  *
  * Return: pointer to the allocated area or %NULL in case of error.
  */
-void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
+void * __meminit alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask)
 {
 	unsigned int order = get_order(size);
 	struct page *p;
@@ -4884,7 +4995,7 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
 	if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM)))
 		gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM);
 
-	p = alloc_pages_node(nid, gfp_mask, order);
+	p = alloc_pages_node_noprof(nid, gfp_mask, order);
 	if (!p)
 		return NULL;
 	return make_alloc_exact((unsigned long)page_address(p), order, size);
@@ -5185,37 +5296,13 @@ static void setup_min_slab_ratio(void);
 
 static void build_zonelists(pg_data_t *pgdat)
 {
-	int node, local_node;
 	struct zoneref *zonerefs;
 	int nr_zones;
 
-	local_node = pgdat->node_id;
-
 	zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
 	nr_zones = build_zonerefs_node(pgdat, zonerefs);
 	zonerefs += nr_zones;
 
-	/*
-	 * Now we build the zonelist so that it contains the zones
-	 * of all the other nodes.
-	 * We don't want to pressure a particular node, so when
-	 * building the zones for node N, we make sure that the
-	 * zones coming right after the local ones are those from
-	 * node N+1 (modulo N)
-	 */
-	for (node = local_node + 1; node < MAX_NUMNODES; node++) {
-		if (!node_online(node))
-			continue;
-		nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
-		zonerefs += nr_zones;
-	}
-	for (node = 0; node < local_node; node++) {
-		if (!node_online(node))
-			continue;
-		nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
-		zonerefs += nr_zones;
-	}
-
 	zonerefs->zone = NULL;
 	zonerefs->zone_idx = 0;
 }
@@ -5722,6 +5809,23 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
 	return pages;
 }
 
+void free_reserved_page(struct page *page)
+{
+	if (mem_alloc_profiling_enabled()) {
+		union codetag_ref *ref = get_page_tag_ref(page);
+
+		if (ref) {
+			set_codetag_empty(ref);
+			put_page_tag_ref(ref);
+		}
+	}
+	ClearPageReserved(page);
+	init_page_count(page);
+	__free_page(page);
+	adjust_managed_page_count(page, 1);
+}
+EXPORT_SYMBOL(free_reserved_page);
+
 static int page_alloc_cpu_dead(unsigned int cpu)
 {
 	struct zone *zone;
@@ -5832,10 +5936,11 @@ static void setup_per_zone_lowmem_reserve(void)
 
 			for (j = i + 1; j < MAX_NR_ZONES; j++) {
 				struct zone *upper_zone = &pgdat->node_zones[j];
+				bool empty = !zone_managed_pages(upper_zone);
 
 				managed_pages += zone_managed_pages(upper_zone);
 
-				if (clear)
+				if (clear || empty)
 					zone->lowmem_reserve[j] = 0;
 				else
 					zone->lowmem_reserve[j] = managed_pages / ratio;
@@ -6216,7 +6321,6 @@ static struct ctl_table page_alloc_sysctl_table[] = {
 		.extra2		= SYSCTL_ONE_HUNDRED,
 	},
 #endif
-	{}
 };
 
 void __init page_alloc_sysctl_init(void)
@@ -6256,6 +6360,7 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 	struct migration_target_control mtc = {
 		.nid = zone_to_nid(cc->zone),
 		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+		.reason = MR_CONTIG_RANGE,
 	};
 	struct page *page;
 	unsigned long total_mapped = 0;
@@ -6288,8 +6393,12 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 
 		if (trace_mm_alloc_contig_migrate_range_info_enabled()) {
 			total_reclaimed += nr_reclaimed;
-			list_for_each_entry(page, &cc->migratepages, lru)
-				total_mapped += page_mapcount(page);
+			list_for_each_entry(page, &cc->migratepages, lru) {
+				struct folio *folio = page_folio(page);
+
+				total_mapped += folio_mapped(folio) *
+						folio_nr_pages(folio);
+			}
 		}
 
 		ret = migrate_pages(&cc->migratepages, alloc_migration_target,
@@ -6341,11 +6450,10 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
  * pages which PFN is in [start, end) are allocated for the caller and
  * need to be freed with free_contig_range().
  */
-int alloc_contig_range(unsigned long start, unsigned long end,
+int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 		       unsigned migratetype, gfp_t gfp_mask)
 {
 	unsigned long outer_start, outer_end;
-	int order;
 	int ret = 0;
 
 	struct compact_control cc = {
@@ -6418,29 +6526,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 * We don't have to hold zone->lock here because the pages are
 	 * isolated thus they won't get removed from buddy.
 	 */
-
-	order = 0;
-	outer_start = start;
-	while (!PageBuddy(pfn_to_page(outer_start))) {
-		if (++order > MAX_PAGE_ORDER) {
-			outer_start = start;
-			break;
-		}
-		outer_start &= ~0UL << order;
-	}
-
-	if (outer_start != start) {
-		order = buddy_order(pfn_to_page(outer_start));
-
-		/*
-		 * outer_start page could be small order buddy page and
-		 * it doesn't include start page. Adjust outer_start
-		 * in this case to report failed page properly
-		 * on tracepoint in test_pages_isolated()
-		 */
-		if (outer_start + (1UL << order) <= start)
-			outer_start = start;
-	}
+	outer_start = find_large_buddy(start);
 
 	/* Make sure the range is really isolated. */
 	if (test_pages_isolated(outer_start, end, 0)) {
@@ -6465,15 +6551,15 @@ done:
 	undo_isolate_page_range(start, end, migratetype);
 	return ret;
 }
-EXPORT_SYMBOL(alloc_contig_range);
+EXPORT_SYMBOL(alloc_contig_range_noprof);
 
 static int __alloc_contig_pages(unsigned long start_pfn,
 				unsigned long nr_pages, gfp_t gfp_mask)
 {
 	unsigned long end_pfn = start_pfn + nr_pages;
 
-	return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE,
-				  gfp_mask);
+	return alloc_contig_range_noprof(start_pfn, end_pfn, MIGRATE_MOVABLE,
+				   gfp_mask);
 }
 
 static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn,
@@ -6528,8 +6614,8 @@ static bool zone_spans_last_pfn(const struct zone *zone,
  *
  * Return: pointer to contiguous pages on success, or NULL if not successful.
  */
-struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask,
-				int nid, nodemask_t *nodemask)
+struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask,
+				 int nid, nodemask_t *nodemask)
 {
 	unsigned long ret, pfn, flags;
 	struct zonelist *zonelist;
@@ -6660,8 +6746,9 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 
 		BUG_ON(page_count(page));
 		BUG_ON(!PageBuddy(page));
+		VM_WARN_ON(get_pageblock_migratetype(page) != MIGRATE_ISOLATE);
 		order = buddy_order(page);
-		del_page_from_free_list(page, zone, order);
+		del_page_from_free_list(page, zone, order, MIGRATE_ISOLATE);
 		pfn += (1 << order);
 	}
 	spin_unlock_irqrestore(&zone->lock, flags);
@@ -6671,16 +6758,16 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 /*
  * This function returns a stable result only if called under zone lock.
  */
-bool is_free_buddy_page(struct page *page)
+bool is_free_buddy_page(const struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
 	unsigned int order;
 
 	for (order = 0; order < NR_PAGE_ORDERS; order++) {
-		struct page *page_head = page - (pfn & ((1 << order) - 1));
+		const struct page *head = page - (pfn & ((1 << order) - 1));
 
-		if (PageBuddy(page_head) &&
-		    buddy_order_unsafe(page_head) >= order)
+		if (PageBuddy(head) &&
+		    buddy_order_unsafe(head) >= order)
 			break;
 	}
 
@@ -6689,6 +6776,14 @@ bool is_free_buddy_page(struct page *page)
 EXPORT_SYMBOL(is_free_buddy_page);
 
 #ifdef CONFIG_MEMORY_FAILURE
+static inline void add_to_free_list(struct page *page, struct zone *zone,
+				    unsigned int order, int migratetype,
+				    bool tail)
+{
+	__add_to_free_list(page, zone, order, migratetype, tail);
+	account_freepages(zone, 1 << order, migratetype);
+}
+
 /*
  * Break down a higher-order page in sub-pages, and keep our target out of
  * buddy allocator.
@@ -6711,10 +6806,10 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page,
 			current_buddy = page + size;
 		}
 
-		if (set_page_guard(zone, current_buddy, high, migratetype))
+		if (set_page_guard(zone, current_buddy, high))
 			continue;
 
-		add_to_free_list(current_buddy, zone, high, migratetype);
+		add_to_free_list(current_buddy, zone, high, migratetype, false);
 		set_buddy_order(current_buddy, high);
 	}
 }
@@ -6740,12 +6835,11 @@ bool take_page_off_buddy(struct page *page)
 			int migratetype = get_pfnblock_migratetype(page_head,
 								   pfn_head);
 
-			del_page_from_free_list(page_head, zone, page_order);
+			del_page_from_free_list(page_head, zone, page_order,
+						migratetype);
 			break_down_buddy_pages(zone, page_head, page, 0,
 						page_order, migratetype);
 			SetPageHWPoisonTakenOff(page);
-			if (!is_migrate_isolate(migratetype))
-				__mod_zone_freepage_state(zone, -1, migratetype);
 			ret = true;
 			break;
 		}
@@ -6762,13 +6856,14 @@ bool take_page_off_buddy(struct page *page)
 bool put_page_back_buddy(struct page *page)
 {
 	struct zone *zone = page_zone(page);
-	unsigned long pfn = page_to_pfn(page);
 	unsigned long flags;
-	int migratetype = get_pfnblock_migratetype(page, pfn);
 	bool ret = false;
 
 	spin_lock_irqsave(&zone->lock, flags);
 	if (put_page_testzero(page)) {
+		unsigned long pfn = page_to_pfn(page);
+		int migratetype = get_pfnblock_migratetype(page, pfn);
+
 		ClearPageHWPoisonTakenOff(page);
 		__free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE);
 		if (TestClearPageHWPoison(page)) {
@@ -6852,7 +6947,7 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	list_del(&page->lru);
 	last = list_empty(&zone->unaccepted_pages);
 
-	__mod_zone_freepage_state(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
+	account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
 	__mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
@@ -6904,7 +6999,7 @@ static bool __free_unaccepted(struct page *page)
 	spin_lock_irqsave(&zone->lock, flags);
 	first = list_empty(&zone->unaccepted_pages);
 	list_add_tail(&page->lru, &zone->unaccepted_pages);
-	__mod_zone_freepage_state(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
+	account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
 	__mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES);
 	spin_unlock_irqrestore(&zone->lock, flags);