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.)
meta data usage of this is no problem in FLATMEM/DISCONTIGMEM.
On SPARSEMEM, this makes mem_section[] size twice.

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.
(and uses xx kbytes for mem_section.)
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 <redacted>

 include/linux/memcontrol.h  |   11 -
 include/linux/mm_types.h    |    4 
 include/linux/mmzone.h      |    9 +
 include/linux/page_cgroup.h |   90 +++++++++++++++
 mm/Makefile                 |    2 
 mm/memcontrol.c             |  258 ++++++++++++--------------------------------
 mm/page_alloc.c             |   12 --
 mm/page_cgroup.c            |  253 +++++++++++++++++++++++++++++++++++++++++++
 8 files changed, 431 insertions(+), 208 deletions(-)

Index: mmotm-2.6.27-rc7+/mm/page_cgroup.c
===================================================================

--- /dev/null
+++ mmotm-2.6.27-rc7+/mm/page_cgroup.c

@@ -0,0 +1,253 @@
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/bootmem.h>
+#include <linux/bit_spinlock.h>
+#include <linux/page_cgroup.h>
+#include <linux/hash.h>
+#include <linux/memory.h>
+
+static void __meminit
+__init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
+{
+	pc->flags = 0;
+	pc->mem_cgroup = NULL;
+	pc->page = pfn_to_page(pfn);
+}
+static unsigned long total_usage = 0;
+
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+
+
+void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+{
+	pgdat->node_page_cgroup = NULL;
+}
+
+struct page_cgroup *lookup_page_cgroup(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long offset;
+	struct page_cgroup *base;
+
+	base = NODE_DATA(page_to_nid(nid))->node_page_cgroup;

@@ -812,49 +708,41 @@ __mem_cgroup_uncharge_common(struct page
 
 	if (mem_cgroup_subsys.disabled)
 		return;
+	/* check the condition we can know from page */
 
-	/*
-	 * Check if our page_cgroup is valid
-	 */
-	lock_page_cgroup(page);
-	pc = page_get_page_cgroup(page);
-	if (unlikely(!pc))
-		goto unlock;
-
-	VM_BUG_ON(pc->page != page);
+	pc = lookup_page_cgroup(page);
+	if (unlikely(!pc || !PageCgroupUsed(pc)))
+		return;
+	preempt_disable();
+	lock_page_cgroup(pc);
+	if (unlikely(page_mapped(page))) {
+		unlock_page_cgroup(pc);
+		preempt_enable();
+		return;
+	}