TechPanelGM/kernel_xiaomi_sm8250
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

mm: remove unnecessary uses of lock_page_memcg()

Browse Source 
There are several users that nest lock_page_memcg() inside lock_page()
to prevent page->mem_cgroup from changing.  But the page lock prevents
pages from moving between cgroups, so that is unnecessary overhead.

Remove lock_page_memcg() in contexts with locked contexts and fix the
debug code in the page stat functions to be okay with the page lock.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Johannes Weiner
2016-03-15 14:57:25 -07:00
committed by Linus Torvalds
parent 62cccb8c8e
commit fdf1cdb91b
5 changed files with 8 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
include/linux/memcontrol.h
View File

@@ -28,6 +28,7 @@
#include <linux/eventfd.h>
#include <linux/mmzone.h>
#include <linux/writeback.h>
#include <linux/page-flags.h>
struct mem_cgroup;
struct page;
@@ -464,18 +465,19 @@ void unlock_page_memcg(struct page *page);
* @idx: page state item to account
* @val: number of pages (positive or negative)
*
* Callers must use lock_page_memcg() to prevent double accounting
* when the page is concurrently being moved to another memcg:
* The @page must be locked or the caller must use lock_page_memcg()
* to prevent double accounting when the page is concurrently being
* moved to another memcg:
*
* lock_page_memcg(page);
* lock_page(page) or lock_page_memcg(page)
* if (TestClearPageState(page))
* mem_cgroup_update_page_stat(page, state, -1);
* unlock_page_memcg(page);
* unlock_page(page) or unlock_page_memcg(page)
*/
static inline void mem_cgroup_update_page_stat(struct page *page,
enum mem_cgroup_stat_index idx, int val)
{
VM_BUG_ON(!rcu_read_lock_held());
VM_BUG_ON(!(rcu_read_lock_held() || PageLocked(page)));
if (page->mem_cgroup)
this_cpu_add(page->mem_cgroup->stat->count[idx], val);