[PATCH 1/2] mm: free large amount of 0-order pages in workqueue

[Sasha Levin]

Freeing pages became a rather costly operation, specially when multiple debug
options are enabled. This causes hangs when an attempt to free a large amount
of 0-order is made. Two examples are vfree()ing large block of memory, and
punching a hole in a shmem filesystem.

To avoid that, move any free operations that involve batching pages into a
list to a workqueue handler where they could be freed later.

Signed-off-by: Sasha Levin <sasha.levin@xxxxxxxxxx>
---
 mm/page_alloc.c |   50 ++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 46 insertions(+), 4 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5bd9711..812ca75 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1586,10 +1586,11 @@ out:
 	local_irq_restore(flags);
 }
 
-/*
- * Free a list of 0-order pages
- */
-void free_hot_cold_page_list(struct list_head *list, bool cold)
+static LIST_HEAD(free_hot_page_list);
+static LIST_HEAD(free_cold_page_list);
+static DEFINE_SPINLOCK(free_page_lock);
+
+static void __free_hot_cold_page_list(struct list_head *list, bool cold)
 {
 	struct page *page, *next;
 
@@ -1599,6 +1600,47 @@ void free_hot_cold_page_list(struct list_head *list, bool cold)
 	}
 }
 
+static void free_page_lists_work(struct work_struct *work)
+{
+	LIST_HEAD(hot_pages);
+	LIST_HEAD(cold_pages);
+	unsigned long flags;
+
+	spin_lock_irqsave(&free_page_lock, flags);
+	list_cut_position(&hot_pages, &free_hot_page_list,
+					free_hot_page_list.prev);
+	list_cut_position(&cold_pages, &free_cold_page_list,
+					free_cold_page_list.prev);
+	spin_unlock_irqrestore(&free_page_lock, flags);
+
+	__free_hot_cold_page_list(&hot_pages, false);
+	__free_hot_cold_page_list(&cold_pages, true);
+}
+
+static DECLARE_WORK(free_page_work, free_page_lists_work);
+
+/*
+ * Free a list of 0-order pages
+ */
+void free_hot_cold_page_list(struct list_head *list, bool cold)
+{
+	unsigned long flags;
+
+	if (unlikely(!keventd_up())) {
+		__free_hot_cold_page_list(list, cold);
+		return;
+	}
+
+	spin_lock_irqsave(&free_page_lock, flags);
+	if(cold)
+		list_splice_tail(list, &free_cold_page_list);
+	else
+		list_splice_tail(list, &free_hot_page_list);
+	spin_unlock_irqrestore(&free_page_lock, flags);
+
+	schedule_work(&free_page_work);
+}
+
 /*
  * split_page takes a non-compound higher-order page, and splits it into
  * n (1<<order) sub-pages: page[0..n]
-- 
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/