memcg: allocate all page_cgroup at boot
Allocate all page_cgroup at boot and remove page_cgroup poitner from
struct page. This patch adds an interface as
struct page_cgroup *lookup_page_cgroup(struct page*)
All FLATMEM/DISCONTIGMEM/SPARSEMEM and MEMORY_HOTPLUG is supported.
Remove page_cgroup pointer reduces the amount of memory by
- 4 bytes per PAGE_SIZE.
- 8 bytes per PAGE_SIZE
if memory controller is disabled. (even if configured.)
On usual 8GB x86-32 server, this saves 8MB of NORMAL_ZONE memory.
On my x86-64 server with 48GB of memory, this saves 96MB of memory.
I think this reduction makes sense.
By pre-allocation, kmalloc/kfree in charge/uncharge are removed.
This means
- we're not necessary to be afraid of kmalloc faiulre.
(this can happen because of gfp_mask type.)
- we can avoid calling kmalloc/kfree.
- we can avoid allocating tons of small objects which can be fragmented.
- we can know what amount of memory will be used for this extra-lru handling.
I added printk message as
"allocated %ld bytes of page_cgroup"
"please try cgroup_disable=memory option if you don't want"
maybe enough informative for users.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f2fc44e..d0a240f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -44,7 +44,7 @@
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
#include <linux/page-isolation.h>
-#include <linux/memcontrol.h>
+#include <linux/page_cgroup.h>
#include <linux/debugobjects.h>
#include <asm/tlbflush.h>
@@ -223,17 +223,12 @@
static void bad_page(struct page *page)
{
- void *pc = page_get_page_cgroup(page);
-
printk(KERN_EMERG "Bad page state in process '%s'\n" KERN_EMERG
"page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
current->comm, page, (int)(2*sizeof(unsigned long)),
(unsigned long)page->flags, page->mapping,
page_mapcount(page), page_count(page));
- if (pc) {
- printk(KERN_EMERG "cgroup:%p\n", pc);
- page_reset_bad_cgroup(page);
- }
+
printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
KERN_EMERG "Backtrace:\n");
dump_stack();
@@ -457,7 +452,6 @@
free_page_mlock(page);
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
- (page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
(page->flags & PAGE_FLAGS_CHECK_AT_FREE)))
bad_page(page);
@@ -603,7 +597,6 @@
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
- (page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
(page->flags & PAGE_FLAGS_CHECK_AT_PREP)))
bad_page(page);
@@ -3438,6 +3431,7 @@
pgdat->nr_zones = 0;
init_waitqueue_head(&pgdat->kswapd_wait);
pgdat->kswapd_max_order = 0;
+ pgdat_page_cgroup_init(pgdat);
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;