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>

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)
 {

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
 };
 
 /*

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

include/linux/page_cgroup.h

+#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

mm/Makefile

@@ -33,5 +33,4 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_SMP) += allocpercpu.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
-obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o
-
+obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o

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 inline int bad_range(struct zone *zone, struct page *page)
 
 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 @@ static inline int free_pages_check(struct page *page)
 	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 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 {
 	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 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 	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;

mm/page_cgroup.c

+#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;
+
+#if !defined(CONFIG_SPARSEMEM)
+
+
+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(page))->node_page_cgroup;
+	if (unlikely(!base))
+		return NULL;
+
+	offset = pfn - NODE_DATA(page_to_nid(page))->node_start_pfn;
+	return base + offset;
+}
+
+static int __init alloc_node_page_cgroup(int nid)
+{
+	struct page_cgroup *base, *pc;
+	unsigned long table_size;
+	unsigned long start_pfn, nr_pages, index;
+
+	start_pfn = NODE_DATA(nid)->node_start_pfn;
+	nr_pages = NODE_DATA(nid)->node_spanned_pages;
+
+	table_size = sizeof(struct page_cgroup) * nr_pages;
+
+	base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
+			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	if (!base)
+		return -ENOMEM;
+	for (index = 0; index < nr_pages; index++) {
+		pc = base + index;
+		__init_page_cgroup(pc, start_pfn + index);
+	}
+	NODE_DATA(nid)->node_page_cgroup = base;
+	total_usage += table_size;
+	return 0;
+}
+
+void __init page_cgroup_init(void)
+{
+
+	int nid, fail;
+
+	for_each_online_node(nid)  {
+		fail = alloc_node_page_cgroup(nid);
+		if (fail)
+			goto fail;
+	}
+	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
+	printk(KERN_INFO "please try cgroup_disable=memory option if you"
+	" don't want\n");
+	return;
+fail:
+	printk(KERN_CRIT "allocation of page_cgroup was failed.\n");
+	printk(KERN_CRIT "please try cgroup_disable=memory boot option\n");
+	panic("Out of memory");
+}
+
+#else /* CONFIG_FLAT_NODE_MEM_MAP */
+
+struct page_cgroup *lookup_page_cgroup(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	struct mem_section *section = __pfn_to_section(pfn);
+
+	return section->page_cgroup + pfn;
+}
+
+int __meminit init_section_page_cgroup(unsigned long pfn)
+{
+	struct mem_section *section;
+	struct page_cgroup *base, *pc;
+	unsigned long table_size;
+	int nid, index;
+
+	section = __pfn_to_section(pfn);
+
+	if (section->page_cgroup)
+		return 0;
+
+	nid = page_to_nid(pfn_to_page(pfn));
+
+	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
+	base = kmalloc_node(table_size, GFP_KERNEL, nid);
+	if (!base)
+		base = vmalloc_node(table_size, nid);
+
+	if (!base) {
+		printk(KERN_ERR "page cgroup allocation failure\n");
+		return -ENOMEM;
+	}
+
+	for (index = 0; index < PAGES_PER_SECTION; index++) {
+		pc = base + index;
+		__init_page_cgroup(pc, pfn + index);
+	}
+
+	section = __pfn_to_section(pfn);
+	section->page_cgroup = base - pfn;
+	total_usage += table_size;
+	return 0;
+}
+#ifdef CONFIG_MEMORY_HOTPLUG
+void __free_page_cgroup(unsigned long pfn)
+{
+	struct mem_section *ms;
+	struct page_cgroup *base;
+
+	ms = __pfn_to_section(pfn);
+	if (!ms || !ms->page_cgroup)
+		return;
+	base = ms->page_cgroup + pfn;
+	ms->page_cgroup = NULL;
+	if (is_vmalloc_addr(base))
+		vfree(base);
+	else
+		kfree(base);
+}
+
+int online_page_cgroup(unsigned long start_pfn,
+			unsigned long nr_pages,
+			int nid)
+{
+	unsigned long start, end, pfn;
+	int fail = 0;
+
+	start = start_pfn & (PAGES_PER_SECTION - 1);
+	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
+
+	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
+		if (!pfn_present(pfn))
+			continue;
+		fail = init_section_page_cgroup(pfn);
+	}
+	if (!fail)
+		return 0;
+
+	/* rollback */
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+		__free_page_cgroup(pfn);
+
+	return -ENOMEM;
+}
+
+int offline_page_cgroup(unsigned long start_pfn,
+		unsigned long nr_pages, int nid)
+{
+	unsigned long start, end, pfn;
+
+	start = start_pfn & (PAGES_PER_SECTION - 1);
+	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
+
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+		__free_page_cgroup(pfn);
+	return 0;
+
+}
+
+static int page_cgroup_callback(struct notifier_block *self,
+			       unsigned long action, void *arg)
+{
+	struct memory_notify *mn = arg;
+	int ret = 0;
+	switch (action) {
+	case MEM_GOING_ONLINE:
+		ret = online_page_cgroup(mn->start_pfn,
+				   mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_CANCEL_ONLINE:
+	case MEM_OFFLINE:
+		offline_page_cgroup(mn->start_pfn,
+				mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_GOING_OFFLINE:
+		break;
+	case MEM_ONLINE:
+	case MEM_CANCEL_OFFLINE:
+		break;
+	}
+	ret = notifier_from_errno(ret);
+	return ret;
+}
+
+#endif
+
+void __init page_cgroup_init(void)
+{
+	unsigned long pfn;
+	int fail = 0;
+
+	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
+		if (!pfn_present(pfn))
+			continue;
+		fail = init_section_page_cgroup(pfn);
+	}
+	if (fail) {
+		printk(KERN_CRIT "try cgroup_disable=memory boot option\n");
+		panic("Out of memory");
+	} else {
+		hotplug_memory_notifier(page_cgroup_callback, 0);
+	}
+	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
+	printk(KERN_INFO "please try cgroup_disable=memory option if you don't"
+	" want\n");
+}
+
+void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+{
+	return;
+}
+
+#endif