[PATCH v10 2/5] mm: page_isolation: check specified range for unmovable pages

[Zi Yan]

From: Zi Yan <ziy@xxxxxxxxxx>

Enable set_migratetype_isolate() to check specified sub-range for
unmovable pages during isolation. Page isolation is done
at MAX_ORDER_NR_PAEGS granularity, but not all pages within that
granularity are intended to be isolated. For example,
alloc_contig_range(), which uses page isolation, allows ranges without
alignment. This commit makes unmovable page check only look for
interesting pages, so that page isolation can succeed for any
non-overlapping ranges.

Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>
---
 mm/page_alloc.c     | 16 ++--------
 mm/page_isolation.c | 78 ++++++++++++++++++++++++++++++++-------------
 2 files changed, 57 insertions(+), 37 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index dafef8099acd..cacb2a16145e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8873,16 +8873,6 @@ void *__init alloc_large_system_hash(const char *tablename,
 }
 
 #ifdef CONFIG_CONTIG_ALLOC
-static unsigned long pfn_max_align_down(unsigned long pfn)
-{
-	return ALIGN_DOWN(pfn, MAX_ORDER_NR_PAGES);
-}
-
-static unsigned long pfn_max_align_up(unsigned long pfn)
-{
-	return ALIGN(pfn, MAX_ORDER_NR_PAGES);
-}
-
 #if defined(CONFIG_DYNAMIC_DEBUG) || \
 	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 /* Usage: See admin-guide/dynamic-debug-howto.rst */
@@ -9027,8 +9017,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 * put back to page allocator so that buddy can use them.
 	 */
 
-	ret = start_isolate_page_range(pfn_max_align_down(start),
-				       pfn_max_align_up(end), migratetype, 0);
+	ret = start_isolate_page_range(start, end, migratetype, 0);
 	if (ret)
 		return ret;
 
@@ -9109,8 +9098,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		free_contig_range(end, outer_end - end);
 
 done:
-	undo_isolate_page_range(pfn_max_align_down(start),
-				pfn_max_align_up(end), migratetype);
+	undo_isolate_page_range(start, end, migratetype);
 	return ret;
 }
 EXPORT_SYMBOL(alloc_contig_range);
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index df49f86a6ed1..b8f96ed49d8b 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -16,7 +16,9 @@
 #include <trace/events/page_isolation.h>
 
 /*
- * This function checks whether pageblock includes unmovable pages or not.
+ * This function checks whether the range [start_pfn, end_pfn) includes
+ * unmovable pages or not. The range must fall into a single pageblock and
+ * 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
@@ -28,12 +30,14 @@
  * cannot get removed (e.g., via memory unplug) concurrently.
  *
  */
-static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
-				 int migratetype, int flags)
+static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long end_pfn,
+				int migratetype, int flags)
 {
-	unsigned long iter = 0;
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long offset = pfn % pageblock_nr_pages;
+	unsigned long pfn = start_pfn;
+	struct page *page = pfn_to_page(pfn);
+
+	VM_BUG_ON(ALIGN_DOWN(start_pfn, pageblock_nr_pages) !=
+		  ALIGN_DOWN(end_pfn - 1, pageblock_nr_pages));
 
 	if (is_migrate_cma_page(page)) {
 		/*
@@ -47,8 +51,11 @@ static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 		return page;
 	}
 
-	for (; iter < pageblock_nr_pages - offset; iter++) {
-		page = pfn_to_page(pfn + iter);
+	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+		struct zone *zone;
+
+		page = pfn_to_page(pfn);
+		zone = page_zone(page);
 
 		/*
 		 * Both, bootmem allocations and memory holes are marked
@@ -85,7 +92,7 @@ static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 			}
 
 			skip_pages = compound_nr(head) - (page - head);
-			iter += skip_pages - 1;
+			pfn += skip_pages - 1;
 			continue;
 		}
 
@@ -97,7 +104,7 @@ static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 		 */
 		if (!page_ref_count(page)) {
 			if (PageBuddy(page))
-				iter += (1 << buddy_order(page)) - 1;
+				pfn += (1 << buddy_order(page)) - 1;
 			continue;
 		}
 
@@ -134,11 +141,18 @@ static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 	return NULL;
 }
 
-static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
+/*
+ * This function set pageblock migratetype to isolate if no unmovable page is
+ * 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,
+			unsigned long start_pfn, unsigned long end_pfn)
 {
 	struct zone *zone = page_zone(page);
 	struct page *unmovable;
 	unsigned long flags;
+	unsigned long check_unmovable_start, check_unmovable_end;
 
 	spin_lock_irqsave(&zone->lock, flags);
 
@@ -155,8 +169,16 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	/*
 	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
 	 * We just check MOVABLE pages.
+	 *
+	 * Pass the intersection of [start_pfn, end_pfn) and the page's pageblock
+	 * to avoid redundant checks.
 	 */
-	unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags);
+	check_unmovable_start = max(page_to_pfn(page), start_pfn);
+	check_unmovable_end = min(ALIGN(page_to_pfn(page) + 1, pageblock_nr_pages),
+				  end_pfn);
+
+	unmovable = has_unmovable_pages(check_unmovable_start, check_unmovable_end,
+			migratetype, isol_flags);
 	if (!unmovable) {
 		unsigned long nr_pages;
 		int mt = get_pageblock_migratetype(page);
@@ -259,12 +281,21 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
 	return NULL;
 }
 
+static unsigned long pfn_max_align_down(unsigned long pfn)
+{
+	return ALIGN_DOWN(pfn, MAX_ORDER_NR_PAGES);
+}
+
+static unsigned long pfn_max_align_up(unsigned long pfn)
+{
+	return ALIGN(pfn, MAX_ORDER_NR_PAGES);
+}
+
 /**
  * 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.
- *			start_pfn/end_pfn must be aligned to pageblock_order.
  * @migratetype:	Migrate type to set in error recovery.
  * @flags:		The following flags are allowed (they can be combined in
  *			a bit mask)
@@ -306,15 +337,16 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	unsigned long pfn;
 	struct page *page;
 
-	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
-	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
+	unsigned long isolate_start = pfn_max_align_down(start_pfn);
+	unsigned long isolate_end = pfn_max_align_up(end_pfn);
 
-	for (pfn = start_pfn;
-	     pfn < end_pfn;
+	for (pfn = isolate_start;
+	     pfn < isolate_end;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
-		if (page && set_migratetype_isolate(page, migratetype, flags)) {
-			undo_isolate_page_range(start_pfn, pfn, migratetype);
+		if (page && set_migratetype_isolate(page, migratetype, flags,
+					start_pfn, end_pfn)) {
+			undo_isolate_page_range(isolate_start, pfn, migratetype);
 			return -EBUSY;
 		}
 	}
@@ -329,12 +361,12 @@ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 {
 	unsigned long pfn;
 	struct page *page;
+	unsigned long isolate_start = pfn_max_align_down(start_pfn);
+	unsigned long isolate_end = pfn_max_align_up(end_pfn);
 
-	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
-	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
 
-	for (pfn = start_pfn;
-	     pfn < end_pfn;
+	for (pfn = isolate_start;
+	     pfn < isolate_end;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
 		if (!page || !is_migrate_isolate_page(page))
-- 
2.35.1