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 the ClearPageLRU to block isolate_lru_page(), then serialize
the memcg change here.

Reported-by: Hugh Dickins <hu...@google.com>
Signed-off-by: Alex Shi <alex....@linux.alibaba.com>
Cc: Andrew Morton <a...@linux-foundation.org>
Cc: linux...@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 mm/swap.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/mm/swap.c b/mm/swap.c
index 5092fe9c8c47..8488b9b25730 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -221,8 +221,14 @@ 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);
@@ -976,7 +982,29 @@ 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

Reply via email to