[PATCH v20 17/20] mm/swap.c: serialize memcg changes in pagevec_lru_move_fn

[Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>]

Hugh Dickins' found a memcg change bug on original version:
If we want to change the pgdat->lru_lock to memcg's lruvec lock, we have
to serialize mem_cgroup_move_account during pagevec_lru_move_fn. The
possible bad scenario would like:

	cpu 0					cpu 1
lruvec = mem_cgroup_page_lruvec()
					if (!isolate_lru_page())
						mem_cgroup_move_account

spin_lock_irqsave(&lruvec->lru_lock <== wrong lock.

So we need TestClearPageLRU to block isolate_lru_page(), that serializes
the memcg change. and then removing the PageLRU check in move_fn callee
as the consequence.

__pagevec_lru_add_fn() is different from the others, because the pages
it deals with are, by definition, not yet on the lru.  TestClearPageLRU
is not needed and would not work, so __pagevec_lru_add() goes its own
way.

Reported-by: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
Acked-by: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
---
 mm/swap.c | 44 +++++++++++++++++++++++++++++++++++---------
 1 file changed, 35 insertions(+), 9 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 8798bd899db0..9e30f096309b 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -222,8 +222,14 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 			spin_lock_irqsave(&pgdat->lru_lock, flags);
 		}
 
+		/* block memcg migration during page moving between lru */
+		if (!TestClearPageLRU(page))
+			continue;
+
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		(*move_fn)(page, lruvec);
+
+		SetPageLRU(page);
 	}
 	if (pgdat)
 		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
@@ -233,7 +239,7 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 
 static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && !PageUnevictable(page)) {
+	if (!PageUnevictable(page)) {
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		ClearPageActive(page);
 		add_page_to_lru_list_tail(page, lruvec, page_lru(page));
@@ -306,7 +312,7 @@ void lru_note_cost_page(struct page *page)
 
 static void __activate_page(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+	if (!PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
 		int nr_pages = thp_nr_pages(page);
 
@@ -362,7 +368,8 @@ static void activate_page(struct page *page)
 
 	page = compound_head(page);
 	spin_lock_irq(&pgdat->lru_lock);
-	__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
+	if (PageLRU(page))
+		__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
 	spin_unlock_irq(&pgdat->lru_lock);
 }
 #endif
@@ -519,9 +526,6 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 	bool active;
 	int nr_pages = thp_nr_pages(page);
 
-	if (!PageLRU(page))
-		return;
-
 	if (PageUnevictable(page))
 		return;
 
@@ -562,7 +566,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 
 static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+	if (PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
 		int nr_pages = thp_nr_pages(page);
 
@@ -579,7 +583,7 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
 
 static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
+	if (PageAnon(page) && PageSwapBacked(page) &&
 	    !PageSwapCache(page) && !PageUnevictable(page)) {
 		bool active = PageActive(page);
 		int nr_pages = thp_nr_pages(page);
@@ -1018,7 +1022,29 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
  */
 void __pagevec_lru_add(struct pagevec *pvec)
 {
-	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn);
+	int i;
+	struct pglist_data *pgdat = NULL;
+	struct lruvec *lruvec;
+	unsigned long flags = 0;
+
+	for (i = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+		struct pglist_data *pagepgdat = page_pgdat(page);
+
+		if (pagepgdat != pgdat) {
+			if (pgdat)
+				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+			pgdat = pagepgdat;
+			spin_lock_irqsave(&pgdat->lru_lock, flags);
+		}
+
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		__pagevec_lru_add_fn(page, lruvec);
+	}
+	if (pgdat)
+		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+	release_pages(pvec->pages, pvec->nr);
+	pagevec_reinit(pvec);
 }
 
 /**
-- 
1.8.3.1