[PATCH v20 11/20] mm/lru: move lock into lru_note_cost

[Alex Shi]

We have to move lru_lock into lru_note_cost, since it cycle up on memcg
tree, for future per lruvec lru_lock replace. It's a bit ugly and may
cost a bit more locking, but benefit from multiple memcg locking could
cover the lost.

Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
Acked-by: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
---
 mm/swap.c       | 3 +++
 mm/vmscan.c     | 4 +---
 mm/workingset.c | 2 --
 3 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 31fc3ebc1079..8798bd899db0 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -268,7 +268,9 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 {
 	do {
 		unsigned long lrusize;
+		struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
+		spin_lock_irq(&pgdat->lru_lock);
 		/* Record cost event */
 		if (file)
 			lruvec->file_cost += nr_pages;
@@ -292,6 +294,7 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 			lruvec->file_cost /= 2;
 			lruvec->anon_cost /= 2;
 		}
+		spin_unlock_irq(&pgdat->lru_lock);
 	} while ((lruvec = parent_lruvec(lruvec)));
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6c6965cbbdef..42bac12aacb4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1973,19 +1973,17 @@ static int current_may_throttle(void)
 				&stat, false);
 
 	spin_lock_irq(&pgdat->lru_lock);
-
 	move_pages_to_lru(lruvec, &page_list);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-	lru_note_cost(lruvec, file, stat.nr_pageout);
 	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, nr_reclaimed);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
 	__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
-
 	spin_unlock_irq(&pgdat->lru_lock);
 
+	lru_note_cost(lruvec, file, stat.nr_pageout);
 	mem_cgroup_uncharge_list(&page_list);
 	free_unref_page_list(&page_list);
 
diff --git a/mm/workingset.c b/mm/workingset.c
index 975a4d2dd02e..d8d2fdf70c24 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -381,9 +381,7 @@ void workingset_refault(struct page *page, void *shadow)
 	if (workingset) {
 		SetPageWorkingset(page);
 		/* XXX: Move to lru_cache_add() when it supports new vs putback */
-		spin_lock_irq(&page_pgdat(page)->lru_lock);
 		lru_note_cost_page(page);
-		spin_unlock_irq(&page_pgdat(page)->lru_lock);
 		inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file);
 	}
 out:
-- 
1.8.3.1