1 files changed, 22 insertions, 0 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e29a6ba050c8..f6005b7c3446 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1063,6 +1063,15 @@ static bool bulkfree_pcp_prepare(struct page *page)
 }
 #endif /* CONFIG_DEBUG_VM */
 
+static inline void prefetch_buddy(struct page *page)
+{
+        unsigned long pfn = page_to_pfn(page);
+        unsigned long buddy_pfn = __find_buddy_pfn(pfn, 0);
+        struct page *buddy = page + (buddy_pfn - pfn);
+
+        prefetch(buddy);
+}
+
 /*
  * Frees a number of pages from the PCP lists
  * Assumes all pages on list are in same zone, and of same order.
@@ -1079,6 +1088,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 {
         int migratetype = 0;
         int batch_free = 0;
+        int prefetch_nr = 0;
         bool isolated_pageblocks;
         struct page *page, *tmp;
         LIST_HEAD(head);
@@ -1114,6 +1124,18 @@ static void free_pcppages_bulk(struct zone *zone, int count,
                                 continue;
 
                         list_add_tail(&page->lru, &head);
+
+                        /*
+                         * We are going to put the page back to the global
+                         * pool, prefetch its buddy to speed up later access
+                         * under zone->lock. It is believed the overhead of
+                         * an additional test and calculating buddy_pfn here
+                         * can be offset by reduced memory latency later. To
+                         * avoid excessive prefetching due to large count, only
+                         * prefetch buddy for the first pcp->batch nr of pages.
+                         */
+                        if (prefetch_nr++ < pcp->batch)
+                                prefetch_buddy(page);
                 } while (--count && --batch_free && !list_empty(list));
         }