[RFC v2 PATCH] mm/hotplug: enable memory hotplug for non-lru movable pages

[Yisheng Xie]

We had considered all of the non-lru pages as unmovable before
commit bda807d44454 ("mm: migrate: support non-lru movable page
migration"). But now some of non-lru pages like zsmalloc,
virtio-balloon pages also become movable. So we can offline such
blocks by using non-lru page migration.

This patch straightforwardly add non-lru migration code, which
means adding non-lru related code to the functions which scan
over pfn and collect pages to be migrated and isolate them before
migration.

Signed-off-by: Yisheng Xie <xieyisheng1@xxxxxxxxxx>
---
v2
 make a minor change about lock_page logic in function scan_movable_pages.

 mm/memory_hotplug.c | 36 +++++++++++++++++++++++++-----------
 mm/page_alloc.c     |  8 ++++++--
 2 files changed, 31 insertions(+), 13 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e43142c1..5559175 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1510,10 +1510,10 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 }
 
 /*
- * Scan pfn range [start,end) to find movable/migratable pages (LRU pages
- * and hugepages). We scan pfn because it's much easier than scanning over
- * linked list. This function returns the pfn of the first found movable
- * page if it's found, otherwise 0.
+ * Scan pfn range [start,end) to find movable/migratable pages (LRU pages,
+ * non-lru movable pages and hugepages). We scan pfn because it's much
+ * easier than scanning over linked list. This function returns the pfn
+ * of the first found movable page if it's found, otherwise 0.
  */
 static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 {
@@ -1531,6 +1531,16 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 					pfn = round_up(pfn + 1,
 						1 << compound_order(page)) - 1;
 			}
+			/*
+			 * check __PageMovable in lock_page to avoid miss some
+			 * non-lru movable pages at race condition.
+			 */
+			lock_page(page);
+			if (__PageMovable(page)) {
+				unlock_page(page);
+				return pfn;
+			}
+			unlock_page(page);
 		}
 	}
 	return 0;
@@ -1600,21 +1610,25 @@ static struct page *new_node_page(struct page *page, unsigned long private,
 		if (!get_page_unless_zero(page))
 			continue;
 		/*
-		 * We can skip free pages. And we can only deal with pages on
-		 * LRU.
+		 * We can skip free pages. And we can deal with pages on
+		 * LRU and non-lru movable pages.
 		 */
-		ret = isolate_lru_page(page);
+		if (PageLRU(page))
+			ret = isolate_lru_page(page);
+		else
+			ret = !isolate_movable_page(page, ISOLATE_UNEVICTABLE);
 		if (!ret) { /* Success */
 			put_page(page);
 			list_add_tail(&page->lru, &source);
 			move_pages--;
-			inc_node_page_state(page, NR_ISOLATED_ANON +
-					    page_is_file_cache(page));
+			if (!__PageMovable(page))
+				inc_node_page_state(page, NR_ISOLATED_ANON +
+						    page_is_file_cache(page));
 
 		} else {
 #ifdef CONFIG_DEBUG_VM
-			pr_alert("removing pfn %lx from LRU failed\n", pfn);
-			dump_page(page, "failed to remove from LRU");
+			pr_alert("failed to isolate pfn %lx\n", pfn);
+			dump_page(page, "isolation failed");
 #endif
 			put_page(page);
 			/* Because we don't have big zone->lock. we should
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d604d25..52d3067 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7055,8 +7055,9 @@ void *__init alloc_large_system_hash(const char *tablename,
  * If @count is not zero, it is okay to include less @count unmovable pages
  *
  * PageLRU check without isolation or lru_lock could race so that
- * MIGRATE_MOVABLE block might include unmovable pages. It means you can't
- * expect this function should be exact.
+ * 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.
  */
 bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 			 bool skip_hwpoisoned_pages)
@@ -7112,6 +7113,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		if (skip_hwpoisoned_pages && PageHWPoison(page))
 			continue;
 
+		if (__PageMovable(page))
+			continue;
+
 		if (!PageLRU(page))
 			found++;
 		/*
-- 
1.7.12.4