mm/lru: move lock into lru_note_cost

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.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Alex Shi <[email protected]>
Acked-by: Hugh Dickins <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Alexander Duyck <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Andrey Ryabinin <[email protected]>
Cc: "Chen, Rong A" <[email protected]>
Cc: Daniel Jordan <[email protected]>
Cc: "Huang, Ying" <[email protected]>
Cc: Jann Horn <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Konstantin Khlebnikov <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mika Penttilä <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vladimir Davydov <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Wei Yang <[email protected]>
Cc: Yang Shi <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

3 files changed, 4 insertions, 5 deletions

diff --git a/mm/swap.c b/mm/swap.c
index b4ca5b965838..c3187d04f9b2 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 1c3df77972e8..f69601d39a6d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1971,19 +1971,17 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &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 25f75bbe80e0..94b512538d5a 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: