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>

4 files changed, 117 insertions, 16 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ee1b2fcb4410..1fbe14d39521 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -27,9 +27,6 @@ struct mm_struct;
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
-#define page_reset_bad_cgroup(page)     ((page)->page_cgroup = 0)
-
-extern struct page_cgroup *page_get_page_cgroup(struct page *page);
 extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
                                 gfp_t gfp_mask);
 extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
@@ -72,16 +69,8 @@ extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
 extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
                                         int priority, enum lru_list lru);
 
-#else /* CONFIG_CGROUP_MEM_RES_CTLR */
-static inline void page_reset_bad_cgroup(struct page *page)
-{
-}
-
-static inline struct page_cgroup *page_get_page_cgroup(struct page *page)
-{
-        return NULL;
-}
 
+#else /* CONFIG_CGROUP_MEM_RES_CTLR */
 static inline int mem_cgroup_charge(struct page *page,
                                         struct mm_struct *mm, gfp_t gfp_mask)
 {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 9d49fa36bbef..fe825471d5aa 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -94,9 +94,6 @@ struct page {
         void *virtual;                  /* Kernel virtual address (NULL if
                                            not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-        unsigned long page_cgroup;
-#endif
 };
 
 /*
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index da2d053a95f1..35a7b5e19465 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -601,8 +601,11 @@ typedef struct pglist_data {
         struct zone node_zones[MAX_NR_ZONES];
         struct zonelist node_zonelists[MAX_ZONELISTS];
         int nr_zones;
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
+#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
         struct page *node_mem_map;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+        struct page_cgroup *node_page_cgroup;
+#endif
 #endif
         struct bootmem_data *bdata;
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -931,6 +934,7 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 #endif
 
 struct page;
+struct page_cgroup;
 struct mem_section {
         /*
          * This is, logically, a pointer to an array of struct
@@ -948,6 +952,14 @@ struct mem_section {
 
         /* See declaration of similar field in struct zone */
         unsigned long *pageblock_flags;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+        /*
+         * 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
 };
 
 #ifdef CONFIG_SPARSEMEM_EXTREME
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
new file mode 100644
index 000000000000..0fd39f2231ec
--- /dev/null
+++ b/include/linux/page_cgroup.h
@@ -0,0 +1,103 @@
+#ifndef __LINUX_PAGE_CGROUP_H
+#define __LINUX_PAGE_CGROUP_H
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#include <linux/bit_spinlock.h>
+/*
+ * 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 {
+        unsigned long flags;
+        struct mem_cgroup *mem_cgroup;
+        struct page *page;
+        struct list_head lru;           /* per cgroup LRU list */
+};
+
+void __init pgdat_page_cgroup_init(struct pglist_data *pgdat);
+void __init page_cgroup_init(void);
+struct page_cgroup *lookup_page_cgroup(struct page *page);
+
+enum {
+        /* flags for mem_cgroup */
+        PCG_LOCK,  /* page cgroup is locked */
+        PCG_CACHE, /* charged as cache */
+        PCG_USED, /* this object is in use. */
+        /* flags for LRU placement */
+        PCG_ACTIVE, /* page is active in this cgroup */
+        PCG_FILE, /* page is file system backed */
+        PCG_UNEVICTABLE, /* page is unevictableable */
+};
+
+#define TESTPCGFLAG(uname, lname)                       \
+static inline int PageCgroup##uname(struct page_cgroup *pc)     \
+        { return test_bit(PCG_##lname, &pc->flags); }
+
+#define SETPCGFLAG(uname, lname)                        \
+static inline void SetPageCgroup##uname(struct page_cgroup *pc)\
+        { set_bit(PCG_##lname, &pc->flags);  }
+
+#define CLEARPCGFLAG(uname, lname)                      \
+static inline void ClearPageCgroup##uname(struct page_cgroup *pc)       \
+        { clear_bit(PCG_##lname, &pc->flags);  }
+
+/* Cache flag is set only once (at allocation) */
+TESTPCGFLAG(Cache, CACHE)
+
+TESTPCGFLAG(Used, USED)
+CLEARPCGFLAG(Used, USED)
+
+/* LRU management flags (from global-lru definition) */
+TESTPCGFLAG(File, FILE)
+SETPCGFLAG(File, FILE)
+CLEARPCGFLAG(File, FILE)
+
+TESTPCGFLAG(Active, ACTIVE)
+SETPCGFLAG(Active, ACTIVE)
+CLEARPCGFLAG(Active, ACTIVE)
+
+TESTPCGFLAG(Unevictable, UNEVICTABLE)
+SETPCGFLAG(Unevictable, UNEVICTABLE)
+CLEARPCGFLAG(Unevictable, UNEVICTABLE)
+
+static inline int page_cgroup_nid(struct page_cgroup *pc)
+{
+        return page_to_nid(pc->page);
+}
+
+static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc)
+{
+        return page_zonenum(pc->page);
+}
+
+static inline void lock_page_cgroup(struct page_cgroup *pc)
+{
+        bit_spin_lock(PCG_LOCK, &pc->flags);
+}
+
+static inline int trylock_page_cgroup(struct page_cgroup *pc)
+{
+        return bit_spin_trylock(PCG_LOCK, &pc->flags);
+}
+
+static inline void unlock_page_cgroup(struct page_cgroup *pc)
+{
+        bit_spin_unlock(PCG_LOCK, &pc->flags);
+}
+
+#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+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;
+}
+#endif
+#endif