diff mbox series

[v13,13/18] mm/swap: serialize memcg changes during pagevec_lru_move_fn

Message ID 1592555636-115095-14-git-send-email-alex.shi@linux.alibaba.com (mailing list archive)
State New, archived
Headers show
Series per memcg lru lock | expand

Commit Message

Alex Shi June 19, 2020, 8:33 a.m. UTC 
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 <hughd@google.com>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 mm/swap.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)
diff mbox series

Patch

diff --git a/mm/swap.c b/mm/swap.c
index 7ff9aa6a716a..cebb25ddeee7 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -203,7 +203,7 @@  int get_kernel_page(unsigned long start, int write, struct page **pages)
 EXPORT_SYMBOL_GPL(get_kernel_page);
 
 static void pagevec_lru_move_fn(struct pagevec *pvec,
-	void (*move_fn)(struct page *page, struct lruvec *lruvec))
+	void (*move_fn)(struct page *page, struct lruvec *lruvec), bool add)
 {
 	int i;
 	struct pglist_data *pgdat = NULL;
@@ -221,8 +221,15 @@  static void pagevec_lru_move_fn(struct pagevec *pvec,
 			spin_lock_irqsave(&pgdat->lru_lock, flags);
 		}
 
+		/* new page add to lru or page moving between lru */
+		if (!add && !TestClearPageLRU(page))
+			continue;
+
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		(*move_fn)(page, lruvec);
+
+		if (!add)
+			SetPageLRU(page);
 	}
 	if (pgdat)
 		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
@@ -259,7 +266,7 @@  void rotate_reclaimable_page(struct page *page)
 		local_lock_irqsave(&lru_rotate.lock, flags);
 		pvec = this_cpu_ptr(&lru_rotate.pvec);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, pagevec_move_tail_fn);
+			pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, false);
 		local_unlock_irqrestore(&lru_rotate.lock, flags);
 	}
 }
@@ -325,7 +332,7 @@  static void activate_page_drain(int cpu)
 	struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu);
 
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, __activate_page);
+		pagevec_lru_move_fn(pvec, __activate_page, false);
 }
 
 static bool need_activate_page_drain(int cpu)
@@ -343,7 +350,7 @@  void activate_page(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.activate_page);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, __activate_page);
+			pagevec_lru_move_fn(pvec, __activate_page, false);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -620,21 +627,21 @@  void lru_add_drain_cpu(int cpu)
 
 		/* No harm done if a racing interrupt already did this */
 		local_lock_irqsave(&lru_rotate.lock, flags);
-		pagevec_lru_move_fn(pvec, pagevec_move_tail_fn);
+		pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, false);
 		local_unlock_irqrestore(&lru_rotate.lock, flags);
 	}
 
 	pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu);
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
+		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, false);
 
 	pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu);
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, lru_deactivate_fn);
+		pagevec_lru_move_fn(pvec, lru_deactivate_fn, false);
 
 	pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu);
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
+		pagevec_lru_move_fn(pvec, lru_lazyfree_fn, false);
 
 	activate_page_drain(cpu);
 }
@@ -663,7 +670,7 @@  void deactivate_file_page(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
 
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
+			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, false);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -685,7 +692,7 @@  void deactivate_page(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, lru_deactivate_fn);
+			pagevec_lru_move_fn(pvec, lru_deactivate_fn, false);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -707,7 +714,7 @@  void mark_page_lazyfree(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
+			pagevec_lru_move_fn(pvec, lru_lazyfree_fn, false);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -975,7 +982,7 @@  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);
+	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, true);
 }
 
 /**