mm: embed the memcg pointer directly into struct page
Memory cgroups used to have 5 per-page pointers. To allow users to
disable that amount of overhead during runtime, those pointers were
allocated in a separate array, with a translation layer between them and
struct page.
There is now only one page pointer remaining: the memcg pointer, that
indicates which cgroup the page is associated with when charged. The
complexity of runtime allocation and the runtime translation overhead is
no longer justified to save that *potential* 0.19% of memory. With
CONFIG_SLUB, page->mem_cgroup actually sits in the doubleword padding
after the page->private member and doesn't even increase struct page,
and then this patch actually saves space. Remaining users that care can
still compile their kernels without CONFIG_MEMCG.
text data bss dec hex filename
8828345 1725264 983040 11536649 b00909 vmlinux.old
8827425 1725264 966656 11519345 afc571 vmlinux.new
[mhocko@suse.cz: update Documentation/cgroups/memory.txt]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Konstantin Khlebnikov <koct9i@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index de01876..c4d08087 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -25,7 +25,6 @@
#include <linux/jump_label.h>
struct mem_cgroup;
-struct page_cgroup;
struct page;
struct mm_struct;
struct kmem_cache;
@@ -466,8 +465,6 @@
* memcg_kmem_uncharge_pages: uncharge pages from memcg
* @page: pointer to struct page being freed
* @order: allocation order.
- *
- * there is no need to specify memcg here, since it is embedded in page_cgroup
*/
static inline void
memcg_kmem_uncharge_pages(struct page *page, int order)
@@ -484,8 +481,7 @@
*
* Needs to be called after memcg_kmem_newpage_charge, regardless of success or
* failure of the allocation. if @page is NULL, this function will revert the
- * charges. Otherwise, it will commit the memcg given by @memcg to the
- * corresponding page_cgroup.
+ * charges. Otherwise, it will commit @page to @memcg.
*/
static inline void
memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 004e9d1..bf9f575 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -22,6 +22,7 @@
#define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
struct address_space;
+struct mem_cgroup;
#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \
@@ -167,6 +168,10 @@
struct page *first_page; /* Compound tail pages */
};
+#ifdef CONFIG_MEMCG
+ struct mem_cgroup *mem_cgroup;
+#endif
+
/*
* On machines where all RAM is mapped into kernel address space,
* we can simply calculate the virtual address. On machines with
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ffe66e3..3879d76 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -722,9 +722,6 @@
int nr_zones;
#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
struct page *node_mem_map;
-#ifdef CONFIG_MEMCG
- struct page_cgroup *node_page_cgroup;
-#endif
#endif
#ifndef CONFIG_NO_BOOTMEM
struct bootmem_data *bdata;
@@ -1078,7 +1075,6 @@
#define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK)
struct page;
-struct page_cgroup;
struct mem_section {
/*
* This is, logically, a pointer to an array of struct
@@ -1096,14 +1092,6 @@
/* See declaration of similar field in struct zone */
unsigned long *pageblock_flags;
-#ifdef CONFIG_MEMCG
- /*
- * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
- * section. (see memcontrol.h/page_cgroup.h about this.)
- */
- struct page_cgroup *page_cgroup;
- unsigned long pad;
-#endif
/*
* WARNING: mem_section must be a power-of-2 in size for the
* calculation and use of SECTION_ROOT_MASK to make sense.
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 1289be6..65be357 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -1,59 +1,6 @@
#ifndef __LINUX_PAGE_CGROUP_H
#define __LINUX_PAGE_CGROUP_H
-struct pglist_data;
-
-#ifdef CONFIG_MEMCG
-struct mem_cgroup;
-
-/*
- * Page Cgroup can be considered as an extended mem_map.
- * A page_cgroup page is associated with every page descriptor. The
- * page_cgroup helps us identify information about the cgroup
- * All page cgroups are allocated at boot or memory hotplug event,
- * then the page cgroup for pfn always exists.
- */
-struct page_cgroup {
- struct mem_cgroup *mem_cgroup;
-};
-
-extern void pgdat_page_cgroup_init(struct pglist_data *pgdat);
-
-#ifdef CONFIG_SPARSEMEM
-static inline void page_cgroup_init_flatmem(void)
-{
-}
-extern void page_cgroup_init(void);
-#else
-extern void page_cgroup_init_flatmem(void);
-static inline void page_cgroup_init(void)
-{
-}
-#endif
-
-struct page_cgroup *lookup_page_cgroup(struct page *page);
-
-#else /* !CONFIG_MEMCG */
-struct page_cgroup;
-
-static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-}
-
-static inline struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
- return NULL;
-}
-
-static inline void page_cgroup_init(void)
-{
-}
-
-static inline void page_cgroup_init_flatmem(void)
-{
-}
-#endif /* CONFIG_MEMCG */
-
#include <linux/swap.h>
#ifdef CONFIG_MEMCG_SWAP