[PATCH 2/8] thp, mm: avoid PageUnevictable on active/inactive lru lists

[Kirill A. Shutemov]

From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>

active/inactive lru lists can contain unevicable pages (i.e. ramfs pages
that have been placed on the LRU lists when first allocated), but these
pages must not have PageUnevictable set - otherwise shrink_[in]active_list
goes crazy:

kernel BUG at /home/space/kas/git/public/linux-next/mm/vmscan.c:1122!

1090 static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
1091                 struct lruvec *lruvec, struct list_head *dst,
1092                 unsigned long *nr_scanned, struct scan_control *sc,
1093                 isolate_mode_t mode, enum lru_list lru)
1094 {
...
1108                 switch (__isolate_lru_page(page, mode)) {
1109                 case 0:
...
1116                 case -EBUSY:
...
1121                 default:
1122                         BUG();
1123                 }
1124         }
...
1130 }

__isolate_lru_page() returns EINVAL for PageUnevictable(page).

For lru_add_page_tail(), it means we should not set PageUnevictable()
for tail pages unless we're sure that it will go to LRU_UNEVICTABLE.
Let's just copy PG_active and PG_unevictable from head page in
__split_huge_page_refcount(), it will simplify lru_add_page_tail().

This will fix one more bug in lru_add_page_tail():
if page_evictable(page_tail) is false and PageLRU(page) is true, page_tail
will go to the same lru as page, but nobody cares to sync page_tail
active/inactive state with page. So we can end up with inactive page on
active lru.
The patch will fix it as well since we copy PG_active from head page.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Acked-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
---
 mm/huge_memory.c |  4 +++-
 mm/swap.c        | 20 ++------------------
 2 files changed, 5 insertions(+), 19 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 243e710..a92012a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1620,7 +1620,9 @@ static void __split_huge_page_refcount(struct page *page,
 				     ((1L << PG_referenced) |
 				      (1L << PG_swapbacked) |
 				      (1L << PG_mlocked) |
-				      (1L << PG_uptodate)));
+				      (1L << PG_uptodate) |
+				      (1L << PG_active) |
+				      (1L << PG_unevictable)));
 		page_tail->flags |= (1L << PG_dirty);
 
 		/* clear PageTail before overwriting first_page */
diff --git a/mm/swap.c b/mm/swap.c
index 4a1d0d2..7bd8910 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -774,8 +774,6 @@ EXPORT_SYMBOL(__pagevec_release);
 void lru_add_page_tail(struct page *page, struct page *page_tail,
 		       struct lruvec *lruvec, struct list_head *list)
 {
-	int uninitialized_var(active);
-	enum lru_list lru;
 	const int file = 0;
 
 	VM_BUG_ON(!PageHead(page));
@@ -787,20 +785,6 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 	if (!list)
 		SetPageLRU(page_tail);
 
-	if (page_evictable(page_tail)) {
-		if (PageActive(page)) {
-			SetPageActive(page_tail);
-			active = 1;
-			lru = LRU_ACTIVE_ANON;
-		} else {
-			active = 0;
-			lru = LRU_INACTIVE_ANON;
-		}
-	} else {
-		SetPageUnevictable(page_tail);
-		lru = LRU_UNEVICTABLE;
-	}
-
 	if (likely(PageLRU(page)))
 		list_add_tail(&page_tail->lru, &page->lru);
 	else if (list) {
@@ -816,13 +800,13 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 		 * Use the standard add function to put page_tail on the list,
 		 * but then correct its position so they all end up in order.
 		 */
-		add_page_to_lru_list(page_tail, lruvec, lru);
+		add_page_to_lru_list(page_tail, lruvec, page_lru(page_tail));
 		list_head = page_tail->lru.prev;
 		list_move_tail(&page_tail->lru, list_head);
 	}
 
 	if (!PageUnevictable(page))
-		update_page_reclaim_stat(lruvec, file, active);
+		update_page_reclaim_stat(lruvec, file, PageActive(page_tail));
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-- 
1.8.3.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/