Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1367077

[PATCH] Revert "mm/page_alloc: protect pcp->batch accesses with ACCESS_ONCE"

Show all headers | View raw

This reverts commit 998d39cb236fe464af86a3492a24d2f67ee1efc2.

When local irq is disabled, a percpu variable does not change, so we can
remove the access macros and let the compiler optimize the code safely.

Signed-off-by: He Kuang <hekuang@huawei.com>
---
 mm/page_alloc.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 59de90d..4575b82 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2015,11 +2015,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 {
 	unsigned long flags;
-	int to_drain, batch;
+	int to_drain;
 
 	local_irq_save(flags);
-	batch = READ_ONCE(pcp->batch);
-	to_drain = min(pcp->count, batch);
+	to_drain = min(pcp->count, pcp->batch);
 	if (to_drain > 0) {
 		free_pcppages_bulk(zone, to_drain, pcp);
 		pcp->count -= to_drain;
@@ -2217,9 +2216,8 @@ void free_hot_cold_page(struct page *page, bool cold)
 		list_add_tail(&page->lru, &pcp->lists[migratetype]);
 	pcp->count++;
 	if (pcp->count >= pcp->high) {
-		unsigned long batch = READ_ONCE(pcp->batch);
-		free_pcppages_bulk(zone, batch, pcp);
-		pcp->count -= batch;
+		free_pcppages_bulk(zone, pcp->batch, pcp);
+		pcp->count -= pcp->batch;
 	}
 
 out:
-- 
1.8.5.2

Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread

Thread

[PATCH] Revert "mm/page_alloc: protect pcp->batch accesses with ACCESS_ONCE" He Kuang <hekuang@huawei.com> - 2016-03-30 12:30 +0200
  Re: [PATCH] Revert "mm/page_alloc: protect pcp->batch accesses with  ACCESS_ONCE" Mel Gorman <mgorman@techsingularity.net> - 2016-03-30 12:40 +0200
    Re: [PATCH] Revert "mm/page_alloc: protect pcp->batch accesses with  ACCESS_ONCE" Hekuang <hekuang@huawei.com> - 2016-03-30 13:00 +0200
      Re: [PATCH] Revert "mm/page_alloc: protect pcp->batch accesses with  ACCESS_ONCE" Michal Hocko <mhocko@kernel.org> - 2016-03-30 13:20 +0200
        Re: [PATCH] Revert "mm/page_alloc: protect pcp->batch accesses with  ACCESS_ONCE" Hekuang <hekuang@huawei.com> - 2016-03-31 03:20 +0200
          Re: [PATCH] Revert "mm/page_alloc: protect pcp->batch accesses with  ACCESS_ONCE" Hekuang <hekuang@huawei.com> - 2016-03-31 03:50 +0200
          Re: [PATCH] Revert "mm/page_alloc: protect pcp->batch accesses with  ACCESS_ONCE" Zefan Li <lizefan@huawei.com> - 2016-03-31 03:50 +0200

csiph-web