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>

1 files changed, 80 insertions, 167 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 031682e7ef0c..d4a92b63e98e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -33,11 +33,11 @@
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
 #include <linux/mm_inline.h>
+#include <linux/page_cgroup.h>
 
 #include <asm/uaccess.h>
 
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
-static struct kmem_cache *page_cgroup_cache __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 
 /*
@@ -135,79 +135,6 @@ struct mem_cgroup {
 };
 static struct mem_cgroup init_mem_cgroup;
 
-/*
- * We use the lower bit of the page->page_cgroup pointer as a bit spin
- * lock.  We need to ensure that page->page_cgroup is at least two
- * byte aligned (based on comments from Nick Piggin).  But since
- * bit_spin_lock doesn't actually set that lock bit in a non-debug
- * uniprocessor kernel, we should avoid setting it here too.
- */
-#define PAGE_CGROUP_LOCK_BIT 	0x0
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-#define PAGE_CGROUP_LOCK 	(1 << PAGE_CGROUP_LOCK_BIT)
-#else
-#define PAGE_CGROUP_LOCK	0x0
-#endif
-
-/*
- * A page_cgroup page is associated with every page descriptor. The
- * page_cgroup helps us identify information about the cgroup
- */
-struct page_cgroup {
-	struct list_head lru;		/* per cgroup LRU list */
-	struct page *page;
-	struct mem_cgroup *mem_cgroup;
-	unsigned long flags;
-};
-
-enum {
-	/* flags for mem_cgroup */
-	PCG_CACHE, /* charged as cache */
-	/* 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)
-
-/* 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 int page_cgroup_nid(struct page_cgroup *pc)
-{
-	return page_to_nid(pc->page);
-}
-
-static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
-{
-	return page_zonenum(pc->page);
-}
-
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
 	MEM_CGROUP_CHARGE_TYPE_MAPPED,
@@ -216,12 +143,18 @@ enum charge_type {
 	NR_CHARGE_TYPE,
 };
 
+/* only for here (for easy reading.) */
+#define PCGF_CACHE	(1UL << PCG_CACHE)
+#define PCGF_USED	(1UL << PCG_USED)
+#define PCGF_ACTIVE	(1UL << PCG_ACTIVE)
+#define PCGF_LOCK	(1UL << PCG_LOCK)
+#define PCGF_FILE	(1UL << PCG_FILE)
 static const unsigned long
 pcg_default_flags[NR_CHARGE_TYPE] = {
-	((1 << PCG_CACHE) | (1 << PCG_FILE)),
-	((1 << PCG_ACTIVE)),
-	((1 << PCG_ACTIVE) | (1 << PCG_CACHE)),
-	0,
+	PCGF_CACHE | PCGF_FILE | PCGF_USED | PCGF_LOCK, /* File Cache */
+	PCGF_ACTIVE | PCGF_USED | PCGF_LOCK, /* Anon */
+	PCGF_ACTIVE | PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
+	0, /* FORCE */
 };
 
 /*
@@ -303,37 +236,6 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 				struct mem_cgroup, css);
 }
 
-static inline int page_cgroup_locked(struct page *page)
-{
-	return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
-{
-	VM_BUG_ON(!page_cgroup_locked(page));
-	page->page_cgroup = ((unsigned long)pc | PAGE_CGROUP_LOCK);
-}
-
-struct page_cgroup *page_get_page_cgroup(struct page *page)
-{
-	return (struct page_cgroup *) (page->page_cgroup & ~PAGE_CGROUP_LOCK);
-}
-
-static void lock_page_cgroup(struct page *page)
-{
-	bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static int try_lock_page_cgroup(struct page *page)
-{
-	return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void unlock_page_cgroup(struct page *page)
-{
-	bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
 static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 			struct page_cgroup *pc)
 {
@@ -436,17 +338,16 @@ void mem_cgroup_move_lists(struct page *page, enum lru_list lru)
 	 * safely get to page_cgroup without it, so just try_lock it:
 	 * mem_cgroup_isolate_pages allows for page left on wrong list.
 	 */
-	if (!try_lock_page_cgroup(page))
+	pc = lookup_page_cgroup(page);
+	if (!trylock_page_cgroup(pc))
 		return;
-
-	pc = page_get_page_cgroup(page);
-	if (pc) {
+	if (pc && PageCgroupUsed(pc)) {
 		mz = page_cgroup_zoneinfo(pc);
 		spin_lock_irqsave(&mz->lru_lock, flags);
 		__mem_cgroup_move_lists(pc, lru);
 		spin_unlock_irqrestore(&mz->lru_lock, flags);
 	}
-	unlock_page_cgroup(page);
+	unlock_page_cgroup(pc);
 }
 
 /*
@@ -533,6 +434,8 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
 		if (scan >= nr_to_scan)
 			break;
+		if (unlikely(!PageCgroupUsed(pc)))
+			continue;
 		page = pc->page;
 
 		if (unlikely(!PageLRU(page)))
@@ -576,26 +479,27 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 {
 	struct mem_cgroup *mem;
 	struct page_cgroup *pc;
-	unsigned long flags;
 	unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
 	struct mem_cgroup_per_zone *mz;
+	unsigned long flags;
 
-	pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask);
-	if (unlikely(pc == NULL))
-		goto err;
-
+	pc = lookup_page_cgroup(page);
+	/* can happen at boot */
+	if (unlikely(!pc))
+		return 0;
+	prefetchw(pc);
 	/*
 	 * We always charge the cgroup the mm_struct belongs to.
 	 * The mm_struct's mem_cgroup changes on task migration if the
 	 * thread group leader migrates. It's possible that mm is not
 	 * set, if so charge the init_mm (happens for pagecache usage).
 	 */
+
 	if (likely(!memcg)) {
 		rcu_read_lock();
 		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
 		if (unlikely(!mem)) {
 			rcu_read_unlock();
-			kmem_cache_free(page_cgroup_cache, pc);
 			return 0;
 		}
 		/*
@@ -631,36 +535,33 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 		}
 	}
 
+
+	lock_page_cgroup(pc);
+	if (unlikely(PageCgroupUsed(pc))) {
+		unlock_page_cgroup(pc);
+		res_counter_uncharge(&mem->res, PAGE_SIZE);
+		css_put(&mem->css);
+
+		goto done;
+	}
 	pc->mem_cgroup = mem;
-	pc->page = page;
 	/*
 	 * If a page is accounted as a page cache, insert to inactive list.
 	 * If anon, insert to active list.
 	 */
 	pc->flags = pcg_default_flags[ctype];
 
-	lock_page_cgroup(page);
-	if (unlikely(page_get_page_cgroup(page))) {
-		unlock_page_cgroup(page);
-		res_counter_uncharge(&mem->res, PAGE_SIZE);
-		css_put(&mem->css);
-		kmem_cache_free(page_cgroup_cache, pc);
-		goto done;
-	}
-	page_assign_page_cgroup(page, pc);
-
 	mz = page_cgroup_zoneinfo(pc);
+
 	spin_lock_irqsave(&mz->lru_lock, flags);
 	__mem_cgroup_add_list(mz, pc);
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
+	unlock_page_cgroup(pc);
 
-	unlock_page_cgroup(page);
 done:
 	return 0;
 out:
 	css_put(&mem->css);
-	kmem_cache_free(page_cgroup_cache, pc);
-err:
 	return -ENOMEM;
 }
 
@@ -668,7 +569,8 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 {
 	if (mem_cgroup_subsys.disabled)
 		return 0;
-
+	if (PageCompound(page))
+		return 0;
 	/*
 	 * If already mapped, we don't have to account.
 	 * If page cache, page->mapping has address_space.
@@ -689,7 +591,8 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 {
 	if (mem_cgroup_subsys.disabled)
 		return 0;
-
+	if (PageCompound(page))
+		return 0;
 	/*
 	 * Corner case handling. This is called from add_to_page_cache()
 	 * in usual. But some FS (shmem) precharges this page before calling it
@@ -702,15 +605,16 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 	if (!(gfp_mask & __GFP_WAIT)) {
 		struct page_cgroup *pc;
 
-		lock_page_cgroup(page);
-		pc = page_get_page_cgroup(page);
-		if (pc) {
-			VM_BUG_ON(pc->page != page);
-			VM_BUG_ON(!pc->mem_cgroup);
-			unlock_page_cgroup(page);
+
+		pc = lookup_page_cgroup(page);
+		if (!pc)
+			return 0;
+		lock_page_cgroup(pc);
+		if (PageCgroupUsed(pc)) {
+			unlock_page_cgroup(pc);
 			return 0;
 		}
-		unlock_page_cgroup(page);
+		unlock_page_cgroup(pc);
 	}
 
 	if (unlikely(!mm))
@@ -741,37 +645,39 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	/*
 	 * 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;
 
-	if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
-	    && ((PageCgroupCache(pc) || page_mapped(page))))
-		goto unlock;
+	lock_page_cgroup(pc);
+	if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED && page_mapped(page))
+	     || !PageCgroupUsed(pc)) {
+		/* This happens at race in zap_pte_range() and do_swap_page()*/
+		unlock_page_cgroup(pc);
+		return;
+	}
+	ClearPageCgroupUsed(pc);
+	mem = pc->mem_cgroup;
 
 	mz = page_cgroup_zoneinfo(pc);
 	spin_lock_irqsave(&mz->lru_lock, flags);
 	__mem_cgroup_remove_list(mz, pc);
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
+	unlock_page_cgroup(pc);
 
-	page_assign_page_cgroup(page, NULL);
-	unlock_page_cgroup(page);
-
-	mem = pc->mem_cgroup;
 	res_counter_uncharge(&mem->res, PAGE_SIZE);
 	css_put(&mem->css);
 
-	kmem_cache_free(page_cgroup_cache, pc);
 	return;
-unlock:
-	unlock_page_cgroup(page);
 }
 
 void mem_cgroup_uncharge_page(struct page *page)
 {
+	/* early check. */
+	if (page_mapped(page))
+		return;
+	if (page->mapping && !PageAnon(page))
+		return;
 	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
 }
 
@@ -795,9 +701,9 @@ int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
 	if (mem_cgroup_subsys.disabled)
 		return 0;
 
-	lock_page_cgroup(page);
-	pc = page_get_page_cgroup(page);
-	if (pc) {
+	pc = lookup_page_cgroup(page);
+	lock_page_cgroup(pc);
+	if (PageCgroupUsed(pc)) {
 		mem = pc->mem_cgroup;
 		css_get(&mem->css);
 		if (PageCgroupCache(pc)) {
@@ -807,7 +713,7 @@ int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
 				ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
 		}
 	}
-	unlock_page_cgroup(page);
+	unlock_page_cgroup(pc);
 	if (mem) {
 		ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL,
 			ctype, mem);
@@ -832,7 +738,7 @@ void mem_cgroup_end_migration(struct page *newpage)
 	 */
 	if (!newpage->mapping)
 		__mem_cgroup_uncharge_common(newpage,
-					 MEM_CGROUP_CHARGE_TYPE_FORCE);
+				MEM_CGROUP_CHARGE_TYPE_FORCE);
 	else if (PageAnon(newpage))
 		mem_cgroup_uncharge_page(newpage);
 }
@@ -918,6 +824,8 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
 	while (!list_empty(list)) {
 		pc = list_entry(list->prev, struct page_cgroup, lru);
 		page = pc->page;
+		if (!PageCgroupUsed(pc))
+			break;
 		get_page(page);
 		spin_unlock_irqrestore(&mz->lru_lock, flags);
 		/*
@@ -932,8 +840,10 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
 				count = FORCE_UNCHARGE_BATCH;
 				cond_resched();
 			}
-		} else
-			cond_resched();
+		} else {
+			spin_lock_irqsave(&mz->lru_lock, flags);
+			break;
+		}
 		spin_lock_irqsave(&mz->lru_lock, flags);
 	}
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
@@ -957,6 +867,8 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem)
 	while (mem->res.usage > 0) {
 		if (atomic_read(&mem->css.cgroup->count) > 0)
 			goto out;
+		/* This is for making all *used* pages to be on LRU. */
+		lru_add_drain_all();
 		for_each_node_state(node, N_POSSIBLE)
 			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 				struct mem_cgroup_per_zone *mz;
@@ -965,6 +877,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem)
 				for_each_lru(l)
 					mem_cgroup_force_empty_list(mem, mz, l);
 			}
+		cond_resched();
 	}
 	ret = 0;
 out:
@@ -1175,8 +1088,8 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	int node;
 
 	if (unlikely((cont->parent) == NULL)) {
+		page_cgroup_init();
 		mem = &init_mem_cgroup;
-		page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
 	} else {
 		mem = mem_cgroup_alloc();
 		if (!mem)