diff mbox series

[v2,3/5] mm/memcontrol: Reorder memcg_stock_pcp members to avoid holes

Message ID 20230125073502.743446-4-leobras@redhat.com (mailing list archive)
State New
Headers show
Series Introduce memcg_stock_pcp remote draining | expand

Commit Message

Leonardo Bras Jan. 25, 2023, 7:35 a.m. UTC 
In 64-bit architectures, the current layout of memcg_stock_pcp should look
like this:

struct memcg_stock_pcp {
        spinlock_t                 stock_lock;           /*     0     4 */
        /* 4 bytes hole */
        struct mem_cgroup *        cached;               /*     8     8 */
        unsigned int               nr_pages;             /*    16     4 */
        /* 4 bytes hole */
	[...]
};

This happens because pointers will have 8 bytes (64-bit) and ints will have
4 bytes.

Those 2 holes are avoided if we reorder nr_pages and cached,
effectivelly putting nr_pages in the first hole, and saving 8 bytes.

Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
 mm/memcontrol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1d5c108413c83..373fa78c4d881 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2173,8 +2173,8 @@  void unlock_page_memcg(struct page *page)
 
 struct memcg_stock_pcp {
 	spinlock_t stock_lock; /* Protects the percpu struct */
-	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
+	struct mem_cgroup *cached; /* this never be root cgroup */
 
 #ifdef CONFIG_MEMCG_KMEM
 	struct obj_cgroup *cached_objcg;