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/1604566549-62481-11-git-send-email-alex.shi@linux.alibaba.comSigned-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: "Chen, Rong A" <rong.a.chen@intel.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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)));
 }
 

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);
 

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: