[PATCH] mm/swap.c: optimizing __pagevec_lru_add lru_lock

[Alex Shi]

The current relock logical will change lru_lock when if found a new
lruvec, so if 2 memcgs are reading file or alloc page equally, they
could hold the lru_lock alternately.

This patch will record the needed lru_lock and only hold them once in
above scenario. That could reduce the lock contention.

Suggested-by: Konstantin Khlebnikov <koct9i@xxxxxxxxx>
Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
---
 mm/swap.c | 42 +++++++++++++++++++++++++++++++++++-------
 1 file changed, 35 insertions(+), 7 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 2ac78e8fab71..dba3f0aba2a0 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -958,24 +958,52 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
 	trace_mm_lru_insertion(page, lru);
 }
 
+struct add_lruvecs {
+	struct list_head lists[PAGEVEC_SIZE];
+	struct lruvec *vecs[PAGEVEC_SIZE];
+};
+
 /*
  * Add the passed pages to the LRU, then drop the caller's refcount
  * on them.  Reinitialises the caller's pagevec.
  */
 void __pagevec_lru_add(struct pagevec *pvec)
 {
-	int i;
+	int i, j, total;
 	struct lruvec *lruvec = NULL;
 	unsigned long flags = 0;
+	struct page *page;
+	struct add_lruvecs lruvecs;
+
+	for (i = total = 0; i < pagevec_count(pvec); i++) {
+		page = pvec->pages[i];
+		lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+		lruvecs.vecs[i] = NULL;
+
+		/* Try to find a same lruvec */
+		for (j = 0; j < total; j++)
+			if (lruvec == lruvecs.vecs[j])
+				break;
+		/* A new lruvec */
+		if (j == total) {
+			INIT_LIST_HEAD(&lruvecs.lists[total]);
+			lruvecs.vecs[total] = lruvec;
+			total++;
+		}
 
-	for (i = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
+		list_add(&page->lru, &lruvecs.lists[j]);
+	}
 
-		lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
-		__pagevec_lru_add_fn(page, lruvec);
+	for (i = 0; i < total; i++) {
+		spin_lock_irqsave(&lruvecs.vecs[i]->lru_lock, flags);
+		while (!list_empty(&lruvecs.lists[i])) {
+			page = lru_to_page(&lruvecs.lists[i]);
+			list_del(&page->lru);
+			__pagevec_lru_add_fn(page, lruvecs.vecs[i]);
+		}
+		spin_unlock_irqrestore(&lruvecs.vecs[i]->lru_lock, flags);
 	}
-	if (lruvec)
-		unlock_page_lruvec_irqrestore(lruvec, flags);
+
 	release_pages(pvec->pages, pvec->nr);
 	pagevec_reinit(pvec);
 }
-- 
1.8.3.1