1 files changed, 139 insertions, 167 deletions

diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 47fbc1696466..f72b6cd38b95 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -21,9 +21,9 @@
  * consequently belong to a single zone.
  *
  * PageLRU check without isolation or lru_lock could race so that
- * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
- * check without lock_page also may miss some movable non-lru pages at
- * race condition. So you can't expect this function should be exact.
+ * MIGRATE_MOVABLE block might include unmovable pages. Similarly, pages
+ * with movable_ops can only be identified some time after they were
+ * allocated. So you can't expect this function should be exact.
  *
  * Returns a page without holding a reference. If the caller wants to
  * dereference that page (e.g., dumping), it has to make sure that it
@@ -31,7 +31,7 @@
  *
  */
 static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long end_pfn,
-				int migratetype, int flags)
+				enum pb_isolate_mode mode)
 {
 	struct page *page = pfn_to_page(start_pfn);
 	struct zone *zone = page_zone(page);
@@ -46,7 +46,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
 		 * isolate CMA pageblocks even when they are not movable in fact
 		 * so consider them movable here.
 		 */
-		if (is_migrate_cma(migratetype))
+		if (mode == PB_ISOLATE_MODE_CMA_ALLOC)
 			return NULL;
 
 		return page;
@@ -79,17 +79,24 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
 		 * handle each tail page individually in migration.
 		 */
 		if (PageHuge(page) || PageTransCompound(page)) {
-			struct page *head = compound_head(page);
+			struct folio *folio = page_folio(page);
 			unsigned int skip_pages;
 
 			if (PageHuge(page)) {
-				if (!hugepage_migration_supported(page_hstate(head)))
+				struct hstate *h;
+
+				/*
+				 * The huge page may be freed so can not
+				 * use folio_hstate() directly.
+				 */
+				h = size_to_hstate(folio_size(folio));
+				if (h && !hugepage_migration_supported(h))
 					return page;
-			} else if (!PageLRU(head) && !__PageMovable(head)) {
+			} else if (!folio_test_lru(folio)) {
 				return page;
 			}
 
-			skip_pages = compound_nr(head) - (page - head);
+			skip_pages = folio_nr_pages(folio) - folio_page_idx(folio, page);
 			pfn += skip_pages - 1;
 			continue;
 		}
@@ -110,7 +117,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
 		 * The HWPoisoned page may be not in buddy system, and
 		 * page_count() is not 0.
 		 */
-		if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
+		if ((mode == PB_ISOLATE_MODE_MEM_OFFLINE) && PageHWPoison(page))
 			continue;
 
 		/*
@@ -123,10 +130,10 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
 		 * move these pages that still have a reference count > 0.
 		 * (false negatives in this function only)
 		 */
-		if ((flags & MEMORY_OFFLINE) && PageOffline(page))
+		if ((mode == PB_ISOLATE_MODE_MEM_OFFLINE) && PageOffline(page))
 			continue;
 
-		if (__PageMovable(page) || PageLRU(page))
+		if (PageLRU(page) || page_has_movable_ops(page))
 			continue;
 
 		/*
@@ -144,7 +151,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
  * present in [start_pfn, end_pfn). The pageblock must intersect with
  * [start_pfn, end_pfn).
  */
-static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags,
+static int set_migratetype_isolate(struct page *page, enum pb_isolate_mode mode,
 			unsigned long start_pfn, unsigned long end_pfn)
 {
 	struct zone *zone = page_zone(page);
@@ -152,6 +159,9 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	unsigned long flags;
 	unsigned long check_unmovable_start, check_unmovable_end;
 
+	if (PageUnaccepted(page))
+		accept_page(page);
+
 	spin_lock_irqsave(&zone->lock, flags);
 
 	/*
@@ -176,23 +186,19 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 				  end_pfn);
 
 	unmovable = has_unmovable_pages(check_unmovable_start, check_unmovable_end,
-			migratetype, isol_flags);
+			mode);
 	if (!unmovable) {
-		unsigned long nr_pages;
-		int mt = get_pageblock_migratetype(page);
-
-		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+		if (!pageblock_isolate_and_move_free_pages(zone, page)) {
+			spin_unlock_irqrestore(&zone->lock, flags);
+			return -EBUSY;
+		}
 		zone->nr_isolate_pageblock++;
-		nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE,
-									NULL);
-
-		__mod_zone_freepage_state(zone, -nr_pages, mt);
 		spin_unlock_irqrestore(&zone->lock, flags);
 		return 0;
 	}
 
 	spin_unlock_irqrestore(&zone->lock, flags);
-	if (isol_flags & REPORT_FAILURE) {
+	if (mode == PB_ISOLATE_MODE_MEM_OFFLINE) {
 		/*
 		 * printk() with zone->lock held will likely trigger a
 		 * lockdep splat, so defer it here.
@@ -203,10 +209,10 @@ 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, nr_pages;
+	unsigned long flags;
 	bool isolated_page = false;
 	unsigned int order;
 	struct page *buddy;
@@ -226,7 +232,7 @@ static void unset_migratetype_isolate(struct page *page, int migratetype)
 	 */
 	if (PageBuddy(page)) {
 		order = buddy_order(page);
-		if (order >= pageblock_order && order < MAX_ORDER - 1) {
+		if (order >= pageblock_order && order < MAX_PAGE_ORDER) {
 			buddy = find_buddy_page_pfn(page, page_to_pfn(page),
 						    order, NULL);
 			if (buddy && !is_migrate_isolate_page(buddy)) {
@@ -252,12 +258,15 @@ static void unset_migratetype_isolate(struct page *page, int migratetype)
 	 * allocation.
 	 */
 	if (!isolated_page) {
-		nr_pages = move_freepages_block(zone, page, migratetype, NULL);
-		__mod_zone_freepage_state(zone, nr_pages, migratetype);
+		/*
+		 * Isolating this block already succeeded, so this
+		 * should not fail on zone boundaries.
+		 */
+		WARN_ON_ONCE(!pageblock_unisolate_and_move_free_pages(zone, page));
+	} else {
+		clear_pageblock_isolate(page);
+		__putback_isolated_page(page, order, get_pageblock_migratetype(page));
 	}
-	set_pageblock_migratetype(page, migratetype);
-	if (isolated_page)
-		__putback_isolated_page(page, order, migratetype);
 	zone->nr_isolate_pageblock--;
 out:
 	spin_unlock_irqrestore(&zone->lock, flags);
@@ -283,18 +292,17 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * isolate_single_pageblock() -- tries to isolate a pageblock that might be
  * within a free or in-use page.
  * @boundary_pfn:		pageblock-aligned pfn that a page might cross
- * @flags:			isolation flags
- * @gfp_flags:			GFP flags used for migrating pages
+ * @mode:			isolation mode
  * @isolate_before:	isolate the pageblock before the boundary_pfn
  * @skip_isolation:	the flag to skip the pageblock isolation in second
  *			isolate_single_pageblock()
- * @migratetype:	migrate type to set in error recovery.
  *
- * Free and in-use pages can be as big as MAX_ORDER-1 and contain more than one
+ * Free and in-use pages can be as big as MAX_PAGE_ORDER and contain more than one
  * pageblock. When not all pageblocks within a page are isolated at the same
  * time, free page accounting can go wrong. For example, in the case of
- * MAX_ORDER-1 = pageblock_order + 1, a MAX_ORDER-1 page has two pagelbocks.
- * [         MAX_ORDER-1         ]
+ * MAX_PAGE_ORDER = pageblock_order + 1, a MAX_PAGE_ORDER page has two
+ * pagelbocks.
+ * [      MAX_PAGE_ORDER         ]
  * [  pageblock0  |  pageblock1  ]
  * When either pageblock is isolated, if it is a free page, the page is not
  * split into separate migratetype lists, which is supposed to; if it is an
@@ -302,9 +310,9 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * either. The function handles this by splitting the free page or migrating
  * the in-use page then splitting the free page.
  */
-static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
-			gfp_t gfp_flags, bool isolate_before, bool skip_isolation,
-			int migratetype)
+static int isolate_single_pageblock(unsigned long boundary_pfn,
+			enum pb_isolate_mode mode, bool isolate_before,
+			bool skip_isolation)
 {
 	unsigned long start_pfn;
 	unsigned long isolate_pageblock;
@@ -330,12 +338,11 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 				      zone->zone_start_pfn);
 
 	if (skip_isolation) {
-		int mt __maybe_unused = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
-
-		VM_BUG_ON(!is_migrate_isolate(mt));
+		VM_BUG_ON(!get_pageblock_isolate(pfn_to_page(isolate_pageblock)));
 	} else {
-		ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock), migratetype,
-				flags, isolate_pageblock, isolate_pageblock + pageblock_nr_pages);
+		ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock),
+				mode, isolate_pageblock,
+				isolate_pageblock + pageblock_nr_pages);
 
 		if (ret)
 			return ret;
@@ -366,108 +373,57 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 
 		VM_BUG_ON(!page);
 		pfn = page_to_pfn(page);
-		/*
-		 * start_pfn is MAX_ORDER_NR_PAGES aligned, if there is any
-		 * free pages in [start_pfn, boundary_pfn), its head page will
-		 * always be in the range.
-		 */
+
+		if (PageUnaccepted(page)) {
+			pfn += MAX_ORDER_NR_PAGES;
+			continue;
+		}
+
 		if (PageBuddy(page)) {
 			int order = buddy_order(page);
 
-			if (pfn + (1UL << order) > boundary_pfn) {
-				/* free page changed before split, check it again */
-				if (split_free_page(page, order, boundary_pfn - pfn))
-					continue;
-			}
+			/* pageblock_isolate_and_move_free_pages() handled this */
+			VM_WARN_ON_ONCE(pfn + (1 << order) > boundary_pfn);
 
 			pfn += 1UL << order;
 			continue;
 		}
+
 		/*
-		 * migrate compound pages then let the free page handling code
-		 * above do the rest. If migration is not possible, just fail.
+		 * If a compound page is straddling our block, attempt
+		 * to migrate it out of the way.
+		 *
+		 * We don't have to worry about this creating a large
+		 * free page that straddles into our block: gigantic
+		 * pages are freed as order-0 chunks, and LRU pages
+		 * (currently) do not exceed pageblock_order.
+		 *
+		 * The block of interest has already been marked
+		 * MIGRATE_ISOLATE above, so when migration is done it
+		 * will free its pages onto the correct freelists.
 		 */
 		if (PageCompound(page)) {
 			struct page *head = compound_head(page);
 			unsigned long head_pfn = page_to_pfn(head);
 			unsigned long nr_pages = compound_nr(head);
 
-			if (head_pfn + nr_pages <= boundary_pfn) {
+			if (head_pfn + nr_pages <= boundary_pfn ||
+			    PageHuge(page)) {
 				pfn = head_pfn + nr_pages;
 				continue;
 			}
-#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+
 			/*
-			 * hugetlb, lru compound (THP), and movable compound pages
-			 * can be migrated. Otherwise, fail the isolation.
+			 * These pages are movable too, but they're
+			 * not expected to exceed pageblock_order.
+			 *
+			 * Let us know when they do, so we can add
+			 * proper free and split handling for them.
 			 */
-			if (PageHuge(page) || PageLRU(page) || __PageMovable(page)) {
-				int order;
-				unsigned long outer_pfn;
-				int page_mt = get_pageblock_migratetype(page);
-				bool isolate_page = !is_migrate_isolate_page(page);
-				struct compact_control cc = {
-					.nr_migratepages = 0,
-					.order = -1,
-					.zone = page_zone(pfn_to_page(head_pfn)),
-					.mode = MIGRATE_SYNC,
-					.ignore_skip_hint = true,
-					.no_set_skip_hint = true,
-					.gfp_mask = gfp_flags,
-					.alloc_contig = true,
-				};
-				INIT_LIST_HEAD(&cc.migratepages);
+			VM_WARN_ON_ONCE_PAGE(PageLRU(page), page);
+			VM_WARN_ON_ONCE_PAGE(page_has_movable_ops(page), page);
 
-				/*
-				 * XXX: mark the page as MIGRATE_ISOLATE so that
-				 * no one else can grab the freed page after migration.
-				 * Ideally, the page should be freed as two separate
-				 * pages to be added into separate migratetype free
-				 * lists.
-				 */
-				if (isolate_page) {
-					ret = set_migratetype_isolate(page, page_mt,
-						flags, head_pfn, head_pfn + nr_pages);
-					if (ret)
-						goto failed;
-				}
-
-				ret = __alloc_contig_migrate_range(&cc, head_pfn,
-							head_pfn + nr_pages);
-
-				/*
-				 * restore the page's migratetype so that it can
-				 * be split into separate migratetype free lists
-				 * later.
-				 */
-				if (isolate_page)
-					unset_migratetype_isolate(page, page_mt);
-
-				if (ret)
-					goto failed;
-				/*
-				 * reset pfn to the head of the free page, so
-				 * that the free page handling code above can split
-				 * the free page to the right migratetype list.
-				 *
-				 * head_pfn is not used here as a hugetlb page order
-				 * can be bigger than MAX_ORDER-1, but after it is
-				 * freed, the free page order is not. Use pfn within
-				 * the range to find the head of the free page.
-				 */
-				order = 0;
-				outer_pfn = pfn;
-				while (!PageBuddy(pfn_to_page(outer_pfn))) {
-					/* stop if we cannot find the free page */
-					if (++order >= MAX_ORDER)
-						goto failed;
-					outer_pfn &= ~0UL << order;
-				}
-				pfn = outer_pfn;
-				continue;
-			} else
-#endif
-				goto failed;
+			goto failed;
 		}
 
 		pfn++;
@@ -476,25 +432,15 @@ 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;
 }
 
 /**
- * start_isolate_page_range() - make page-allocation-type of range of pages to
- * be MIGRATE_ISOLATE.
- * @start_pfn:		The lower PFN of the range to be isolated.
- * @end_pfn:		The upper PFN of the range to be isolated.
- * @migratetype:	Migrate type to set in error recovery.
- * @flags:		The following flags are allowed (they can be combined in
- *			a bit mask)
- *			MEMORY_OFFLINE - isolate to offline (!allocate) memory
- *					 e.g., skip over PageHWPoison() pages
- *					 and PageOffline() pages.
- *			REPORT_FAILURE - report details about the failure to
- *			isolate the range
- * @gfp_flags:		GFP flags used for migrating pages that sit across the
- *			range boundaries.
+ * start_isolate_page_range() - mark page range MIGRATE_ISOLATE
+ * @start_pfn:		The first PFN of the range to be isolated.
+ * @end_pfn:		The last PFN of the range to be isolated.
+ * @mode:		isolation mode
  *
  * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
  * the range will never be allocated. Any free pages and pages freed in the
@@ -527,7 +473,7 @@ failed:
  * Return: 0 on success and -EBUSY if any part of range cannot be isolated.
  */
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     int migratetype, int flags, gfp_t gfp_flags)
+			     enum pb_isolate_mode mode)
 {
 	unsigned long pfn;
 	struct page *page;
@@ -538,8 +484,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	bool skip_isolation = false;
 
 	/* isolate [isolate_start, isolate_start + pageblock_nr_pages) pageblock */
-	ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false,
-			skip_isolation, migratetype);
+	ret = isolate_single_pageblock(isolate_start, mode, false,
+			skip_isolation);
 	if (ret)
 		return ret;
 
@@ -547,10 +493,9 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 		skip_isolation = true;
 
 	/* isolate [isolate_end - pageblock_nr_pages, isolate_end) pageblock */
-	ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true,
-			skip_isolation, migratetype);
+	ret = isolate_single_pageblock(isolate_end, mode, true, skip_isolation);
 	if (ret) {
-		unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype);
+		unset_migratetype_isolate(pfn_to_page(isolate_start));
 		return ret;
 	}
 
@@ -559,23 +504,25 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	     pfn < isolate_end - pageblock_nr_pages;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
-		if (page && set_migratetype_isolate(page, migratetype, flags,
-					start_pfn, end_pfn)) {
-			undo_isolate_page_range(isolate_start, pfn, migratetype);
+		if (page && set_migratetype_isolate(page, mode, start_pfn,
+					end_pfn)) {
+			undo_isolate_page_range(isolate_start, pfn);
 			unset_migratetype_isolate(
-				pfn_to_page(isolate_end - pageblock_nr_pages),
-				migratetype);
+				pfn_to_page(isolate_end - pageblock_nr_pages));
 			return -EBUSY;
 		}
 	}
 	return 0;
 }
 
-/*
- * Make isolated pages available again.
+/**
+ * undo_isolate_page_range - undo effects of start_isolate_page_range()
+ * @start_pfn:		The first PFN of the isolated range
+ * @end_pfn:		The last PFN of the isolated range
+ *
+ * This finds and unsets every MIGRATE_ISOLATE page block in the given range
  */
-void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			    int migratetype)
+void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long pfn;
 	struct page *page;
@@ -588,7 +535,7 @@ 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);
 	}
 }
 /*
@@ -600,7 +547,7 @@ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  */
 static unsigned long
 __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
-				  int flags)
+				  enum pb_isolate_mode mode)
 {
 	struct page *page;
 
@@ -613,11 +560,12 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
 			 * simple way to verify that as VM_BUG_ON(), though.
 			 */
 			pfn += 1 << buddy_order(page);
-		else if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
+		else if ((mode == PB_ISOLATE_MODE_MEM_OFFLINE) &&
+			 PageHWPoison(page))
 			/* A HWPoisoned page cannot be also PageBuddy */
 			pfn++;
-		else if ((flags & MEMORY_OFFLINE) && PageOffline(page) &&
-			 !page_count(page))
+		else if ((mode == PB_ISOLATE_MODE_MEM_OFFLINE) &&
+			 PageOffline(page) && !page_count(page))
 			/*
 			 * The responsible driver agreed to skip PageOffline()
 			 * pages when offlining memory by dropping its
@@ -631,9 +579,23 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
 	return pfn;
 }
 
-/* Caller should ensure that requested range is in a single zone */
+/**
+ * test_pages_isolated - check if pageblocks in range are isolated
+ * @start_pfn:		The first PFN of the isolated range
+ * @end_pfn:		The first PFN *after* the isolated range
+ * @mode:		Testing mode
+ *
+ * This tests if all in the specified range are free.
+ *
+ * If %PB_ISOLATE_MODE_MEM_OFFLINE specified in @mode, it will consider
+ * poisoned and offlined pages free as well.
+ *
+ * Caller must ensure the requested range doesn't span zones.
+ *
+ * Returns 0 if true, -EBUSY if one or more pages are in use.
+ */
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
-			int isol_flags)
+			enum pb_isolate_mode mode)
 {
 	unsigned long pfn, flags;
 	struct page *page;
@@ -641,8 +603,18 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 	int ret;
 
 	/*
-	 * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages
-	 * are not aligned to pageblock_nr_pages.
+	 * Due to the deferred freeing of hugetlb folios, the hugepage folios may
+	 * not immediately release to the buddy system. This can cause PageBuddy()
+	 * to fail in __test_page_isolated_in_pageblock(). To ensure that the
+	 * hugetlb folios are properly released back to the buddy system, we
+	 * invoke the wait_for_freed_hugetlb_folios() function to wait for the
+	 * release to complete.
+	 */
+	wait_for_freed_hugetlb_folios();
+
+	/*
+	 * Note: pageblock_nr_pages != MAX_PAGE_ORDER. Then, chunks of free
+	 * pages are not aligned to pageblock_nr_pages.
 	 * Then we just check migratetype first.
 	 */
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
@@ -659,7 +631,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 	/* Check all pages are free or marked as ISOLATED */
 	zone = page_zone(page);
 	spin_lock_irqsave(&zone->lock, flags);
-	pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, isol_flags);
+	pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, mode);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
 	ret = pfn < end_pfn ? -EBUSY : 0;