memcontrol.c

	/*
	 * In typical case, batch->memcg == mem. This means we can
	 * merge a series of uncharges to an uncharge of res_counter.
	 * If not, we uncharge res_counter ony by one.
	 */
	if (batch->memcg != memcg)
		goto direct_uncharge;
	/* remember freed charge and uncharge it later */
	batch->nr_pages++;
	if (uncharge_memsw)
		batch->memsw_nr_pages++;
	return;
direct_uncharge:
	res_counter_uncharge(&memcg->res, nr_pages * PAGE_SIZE);
	if (uncharge_memsw)
		res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE);
	if (unlikely(batch->memcg != memcg))
		memcg_oom_recover(memcg);
	return;
}

/*
 * uncharge if !page_mapped(page)
 */
static struct mem_cgroup *
__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
{
	struct mem_cgroup *memcg = NULL;
	unsigned int nr_pages = 1;
	struct page_cgroup *pc;

	if (mem_cgroup_disabled())
		return NULL;

	if (PageSwapCache(page))
		return NULL;

	if (PageTransHuge(page)) {
		nr_pages <<= compound_order(page);
		VM_BUG_ON(!PageTransHuge(page));
	}
	/*
	 * Check if our page_cgroup is valid
	 */
	pc = lookup_page_cgroup(page);
	if (unlikely(!pc || !PageCgroupUsed(pc)))
		return NULL;

	lock_page_cgroup(pc);

	memcg = pc->mem_cgroup;

	if (!PageCgroupUsed(pc))
		goto unlock_out;

	switch (ctype) {
	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
	case MEM_CGROUP_CHARGE_TYPE_DROP:
		/* See mem_cgroup_prepare_migration() */
		if (page_mapped(page) || PageCgroupMigration(pc))
			goto unlock_out;
		break;
	case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
		if (!PageAnon(page)) {	/* Shared memory */
			if (page->mapping && !page_is_file_cache(page))
				goto unlock_out;
		} else if (page_mapped(page)) /* Anon */
				goto unlock_out;
		break;
	default:
		break;
	}

	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -nr_pages);

	ClearPageCgroupUsed(pc);
	/*
	 * pc->mem_cgroup is not cleared here. It will be accessed when it's
	 * freed from LRU. This is safe because uncharged page is expected not
	 * to be reused (freed soon). Exception is SwapCache, it's handled by
	 * special functions.
	 */

	unlock_page_cgroup(pc);
	/*
	 * even after unlock, we have memcg->res.usage here and this memcg
	 * will never be freed.
	 */
	memcg_check_events(memcg, page);
	if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) {
		mem_cgroup_swap_statistics(memcg, true);
		mem_cgroup_get(memcg);
	}
	if (!mem_cgroup_is_root(memcg))
		mem_cgroup_do_uncharge(memcg, nr_pages, ctype);

	return memcg;

unlock_out:
	unlock_page_cgroup(pc);
	return NULL;
}

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);
}

void mem_cgroup_uncharge_cache_page(struct page *page)
{
	VM_BUG_ON(page_mapped(page));
	VM_BUG_ON(page->mapping);
	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
}

/*
 * Batch_start/batch_end is called in unmap_page_range/invlidate/trucate.
 * In that cases, pages are freed continuously and we can expect pages
 * are in the same memcg. All these calls itself limits the number of
 * pages freed at once, then uncharge_start/end() is called properly.
 * This may be called prural(2) times in a context,
 */

void mem_cgroup_uncharge_start(void)
{
	current->memcg_batch.do_batch++;
	/* We can do nest. */
	if (current->memcg_batch.do_batch == 1) {
		current->memcg_batch.memcg = NULL;
		current->memcg_batch.nr_pages = 0;
		current->memcg_batch.memsw_nr_pages = 0;
	}
}

void mem_cgroup_uncharge_end(void)
{
	struct memcg_batch_info *batch = &current->memcg_batch;

	if (!batch->do_batch)
		return;

	batch->do_batch--;
	if (batch->do_batch) /* If stacked, do nothing. */
		return;

	if (!batch->memcg)
		return;
	/*
	 * This "batch->memcg" is valid without any css_get/put etc...
	 * bacause we hide charges behind us.
	 */
	if (batch->nr_pages)
		res_counter_uncharge(&batch->memcg->res,
				     batch->nr_pages * PAGE_SIZE);
	if (batch->memsw_nr_pages)
		res_counter_uncharge(&batch->memcg->memsw,
				     batch->memsw_nr_pages * PAGE_SIZE);
	memcg_oom_recover(batch->memcg);
	/* forget this pointer (for sanity check) */
	batch->memcg = NULL;
}

#ifdef CONFIG_SWAP
/*
 * called after __delete_from_swap_cache() and drop "page" account.
 * memcg information is recorded to swap_cgroup of "ent"
 */
void
mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
{
	struct mem_cgroup *memcg;
	int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT;

	if (!swapout) /* this was a swap cache but the swap is unused ! */
		ctype = MEM_CGROUP_CHARGE_TYPE_DROP;

	memcg = __mem_cgroup_uncharge_common(page, ctype);

	/*
	 * record memcg information,  if swapout && memcg != NULL,
	 * mem_cgroup_get() was called in uncharge().
	 */
	if (do_swap_account && swapout && memcg)
		swap_cgroup_record(ent, css_id(&memcg->css));
}
#endif

#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
/*
 * called from swap_entry_free(). remove record in swap_cgroup and
 * uncharge "memsw" account.
 */
void mem_cgroup_uncharge_swap(swp_entry_t ent)
{
	struct mem_cgroup *memcg;
	unsigned short id;

	if (!do_swap_account)
		return;

	id = swap_cgroup_record(ent, 0);
	rcu_read_lock();
	memcg = mem_cgroup_lookup(id);
	if (memcg) {
		/*
		 * We uncharge this because swap is freed.
		 * This memcg can be obsolete one. We avoid calling css_tryget
		 */
		if (!mem_cgroup_is_root(memcg))
			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
		mem_cgroup_swap_statistics(memcg, false);
		mem_cgroup_put(memcg);
	}
	rcu_read_unlock();
}

/**
 * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record.
 * @entry: swap entry to be moved
 * @from:  mem_cgroup which the entry is moved from
 * @to:  mem_cgroup which the entry is moved to
 * @need_fixup: whether we should fixup res_counters and refcounts.
 *
 * It succeeds only when the swap_cgroup's record for this entry is the same
 * as the mem_cgroup's id of @from.
 *
 * Returns 0 on success, -EINVAL on failure.
 *
 * The caller must have charged to @to, IOW, called res_counter_charge() about
 * both res and memsw, and called css_get().
 */
static int mem_cgroup_move_swap_account(swp_entry_t entry,
		struct mem_cgroup *from, struct mem_cgroup *to, bool need_fixup)
{
	unsigned short old_id, new_id;

	old_id = css_id(&from->css);
	new_id = css_id(&to->css);

	if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
		mem_cgroup_swap_statistics(from, false);
		mem_cgroup_swap_statistics(to, true);
		/*
		 * This function is only called from task migration context now.
		 * It postpones res_counter and refcount handling till the end
		 * of task migration(mem_cgroup_clear_mc()) for performance
		 * improvement. But we cannot postpone mem_cgroup_get(to)
		 * because if the process that has been moved to @to does
		 * swap-in, the refcount of @to might be decreased to 0.
		 */
		mem_cgroup_get(to);
		if (need_fixup) {
			if (!mem_cgroup_is_root(from))
				res_counter_uncharge(&from->memsw, PAGE_SIZE);
			mem_cgroup_put(from);
			/*
			 * we charged both to->res and to->memsw, so we should
			 * uncharge to->res.
			 */
			if (!mem_cgroup_is_root(to))
				res_counter_uncharge(&to->res, PAGE_SIZE);
		}
		return 0;
	}
	return -EINVAL;
}
#else
static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
		struct mem_cgroup *from, struct mem_cgroup *to, bool need_fixup)
{
	return -EINVAL;
}
#endif

/*
 * Before starting migration, account PAGE_SIZE to mem_cgroup that the old
 * page belongs to.
 */
int mem_cgroup_prepare_migration(struct page *page,
	struct page *newpage, struct mem_cgroup **ptr, gfp_t gfp_mask)
{
	struct mem_cgroup *memcg = NULL;
	struct page_cgroup *pc;
	enum charge_type ctype;
	int ret = 0;

	*ptr = NULL;

	VM_BUG_ON(PageTransHuge(page));
	if (mem_cgroup_disabled())
		return 0;

	pc = lookup_page_cgroup(page);
	lock_page_cgroup(pc);
	if (PageCgroupUsed(pc)) {
		memcg = pc->mem_cgroup;
		css_get(&memcg->css);
		/*
		 * At migrating an anonymous page, its mapcount goes down
		 * to 0 and uncharge() will be called. But, even if it's fully
		 * unmapped, migration may fail and this page has to be
		 * charged again. We set MIGRATION flag here and delay uncharge
		 * until end_migration() is called
		 *
		 * Corner Case Thinking
		 * A)
		 * When the old page was mapped as Anon and it's unmap-and-freed
		 * while migration was ongoing.
		 * If unmap finds the old page, uncharge() of it will be delayed
		 * until end_migration(). If unmap finds a new page, it's
		 * uncharged when it make mapcount to be 1->0. If unmap code
		 * finds swap_migration_entry, the new page will not be mapped
		 * and end_migration() will find it(mapcount==0).
		 *
		 * B)
		 * When the old page was mapped but migraion fails, the kernel
		 * remaps it. A charge for it is kept by MIGRATION flag even
		 * if mapcount goes down to 0. We can do remap successfully
		 * without charging it again.
		 *
		 * C)
		 * The "old" page is under lock_page() until the end of
		 * migration, so, the old page itself will not be swapped-out.
		 * If the new page is swapped out before end_migraton, our
		 * hook to usual swap-out path will catch the event.
		 */
		if (PageAnon(page))
			SetPageCgroupMigration(pc);
	}
	unlock_page_cgroup(pc);
	/*
	 * If the page is not charged at this point,
	 * we return here.
	 */
	if (!memcg)
		return 0;

	*ptr = memcg;
	ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, ptr, false);
	css_put(&memcg->css);/* drop extra refcnt */
	if (ret || *ptr == NULL) {
		if (PageAnon(page)) {
			lock_page_cgroup(pc);
			ClearPageCgroupMigration(pc);
			unlock_page_cgroup(pc);
			/*
			 * The old page may be fully unmapped while we kept it.
			 */
			mem_cgroup_uncharge_page(page);
		}
		return -ENOMEM;
	}
	/*
	 * We charge new page before it's used/mapped. So, even if unlock_page()
	 * is called before end_migration, we can catch all events on this new
	 * page. In the case new page is migrated but not remapped, new page's
	 * mapcount will be finally 0 and we call uncharge in end_migration().
	 */
	pc = lookup_page_cgroup(newpage);
	if (PageAnon(page))
		ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
	else if (page_is_file_cache(page))
		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
	else
		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
	__mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
	return ret;
}

/* remove redundant charge if migration failed*/
void mem_cgroup_end_migration(struct mem_cgroup *memcg,
	struct page *oldpage, struct page *newpage, bool migration_ok)
{
	struct page *used, *unused;
	struct page_cgroup *pc;

	if (!memcg)
		return;
	/* blocks rmdir() */
	cgroup_exclude_rmdir(&memcg->css);
	if (!migration_ok) {
		used = oldpage;
		unused = newpage;
	} else {
		used = newpage;
		unused = oldpage;
	}
	/*
	 * We disallowed uncharge of pages under migration because mapcount
	 * of the page goes down to zero, temporarly.
	 * Clear the flag and check the page should be charged.
	 */
	pc = lookup_page_cgroup(oldpage);
	lock_page_cgroup(pc);
	ClearPageCgroupMigration(pc);
	unlock_page_cgroup(pc);

	__mem_cgroup_uncharge_common(unused, MEM_CGROUP_CHARGE_TYPE_FORCE);

	/*
	 * If a page is a file cache, radix-tree replacement is very atomic
	 * and we can skip this check. When it was an Anon page, its mapcount
	 * goes down to 0. But because we added MIGRATION flage, it's not
	 * uncharged yet. There are several case but page->mapcount check
	 * and USED bit check in mem_cgroup_uncharge_page() will do enough
	 * check. (see prepare_charge() also)
	 */
	if (PageAnon(used))
		mem_cgroup_uncharge_page(used);
	/*
	 * At migration, we may charge account against cgroup which has no
	 * tasks.
	 * So, rmdir()->pre_destroy() can be called while we do this charge.
	 * In that case, we need to call pre_destroy() again. check it here.
	 */
	cgroup_release_and_wakeup_rmdir(&memcg->css);
}

#ifdef CONFIG_DEBUG_VM
static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
{
	struct page_cgroup *pc;

	pc = lookup_page_cgroup(page);
	if (likely(pc) && PageCgroupUsed(pc))
		return pc;
	return NULL;
}

bool mem_cgroup_bad_page_check(struct page *page)
{
	if (mem_cgroup_disabled())
		return false;

	return lookup_page_cgroup_used(page) != NULL;
}

void mem_cgroup_print_bad_page(struct page *page)
{
	struct page_cgroup *pc;

	pc = lookup_page_cgroup_used(page);
	if (pc) {
		int ret = -1;
		char *path;

		printk(KERN_ALERT "pc:%p pc->flags:%lx pc->mem_cgroup:%p",
		       pc, pc->flags, pc->mem_cgroup);

		path = kmalloc(PATH_MAX, GFP_KERNEL);
		if (path) {
			rcu_read_lock();
			ret = cgroup_path(pc->mem_cgroup->css.cgroup,
							path, PATH_MAX);
			rcu_read_unlock();
		}

		printk(KERN_CONT "(%s)\n",
				(ret < 0) ? "cannot get the path" : path);
		kfree(path);
	}
}
#endif

static DEFINE_MUTEX(set_limit_mutex);

static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
				unsigned long long val)
{
	int retry_count;
	u64 memswlimit, memlimit;
	int ret = 0;
	int children = mem_cgroup_count_children(memcg);
	u64 curusage, oldusage;
	int enlarge;

	/*
	 * For keeping hierarchical_reclaim simple, how long we should retry
	 * is depends on callers. We set our retry-count to be function
	 * of # of children which we should visit in this loop.
	 */
	retry_count = MEM_CGROUP_RECLAIM_RETRIES * children;

	oldusage = res_counter_read_u64(&memcg->res, RES_USAGE);

	enlarge = 0;
	while (retry_count) {
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}
		/*
		 * Rather than hide all in some function, I do this in
		 * open coded manner. You see what this really does.
		 * We have to guarantee memcg->res.limit < memcg->memsw.limit.
		 */
		mutex_lock(&set_limit_mutex);
		memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
		if (memswlimit < val) {
			ret = -EINVAL;
			mutex_unlock(&set_limit_mutex);
			break;
		}

		memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
		if (memlimit < val)
			enlarge = 1;

		ret = res_counter_set_limit(&memcg->res, val);
		if (!ret) {
			if (memswlimit == val)
				memcg->memsw_is_minimum = true;
			else
				memcg->memsw_is_minimum = false;
		}
		mutex_unlock(&set_limit_mutex);

		if (!ret)
			break;

		mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL,
						MEM_CGROUP_RECLAIM_SHRINK,
						NULL);
		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
		/* Usage is reduced ? */
  		if (curusage >= oldusage)
			retry_count--;
		else
			oldusage = curusage;
	}
	if (!ret && enlarge)
		memcg_oom_recover(memcg);

	return ret;
}

static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
					unsigned long long val)
{
	int retry_count;
	u64 memlimit, memswlimit, oldusage, curusage;
	int children = mem_cgroup_count_children(memcg);
	int ret = -EBUSY;
	int enlarge = 0;

	/* see mem_cgroup_resize_res_limit */
 	retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
	oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
	while (retry_count) {
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}
		/*
		 * Rather than hide all in some function, I do this in
		 * open coded manner. You see what this really does.
		 * We have to guarantee memcg->res.limit < memcg->memsw.limit.
		 */
		mutex_lock(&set_limit_mutex);
		memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
		if (memlimit > val) {
			ret = -EINVAL;
			mutex_unlock(&set_limit_mutex);
			break;
		}
		memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
		if (memswlimit < val)
			enlarge = 1;
		ret = res_counter_set_limit(&memcg->memsw, val);
		if (!ret) {
			if (memlimit == val)
				memcg->memsw_is_minimum = true;
			else
				memcg->memsw_is_minimum = false;
		}
		mutex_unlock(&set_limit_mutex);

		if (!ret)
			break;

		mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL,
						MEM_CGROUP_RECLAIM_NOSWAP |
						MEM_CGROUP_RECLAIM_SHRINK,
						NULL);
		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
		/* Usage is reduced ? */
		if (curusage >= oldusage)
			retry_count--;
		else
			oldusage = curusage;
	}
	if (!ret && enlarge)
		memcg_oom_recover(memcg);
	return ret;
}

unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
					    gfp_t gfp_mask,
					    unsigned long *total_scanned)
{
	unsigned long nr_reclaimed = 0;
	struct mem_cgroup_per_zone *mz, *next_mz = NULL;
	unsigned long reclaimed;
	int loop = 0;
	struct mem_cgroup_tree_per_zone *mctz;
	unsigned long long excess;
	unsigned long nr_scanned;

	if (order > 0)
		return 0;

	mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
	/*
	 * This loop can run a while, specially if mem_cgroup's continuously
	 * keep exceeding their soft limit and putting the system under
	 * pressure
	 */
	do {
		if (next_mz)
			mz = next_mz;
		else
			mz = mem_cgroup_largest_soft_limit_node(mctz);
		if (!mz)
			break;

		nr_scanned = 0;
		reclaimed = mem_cgroup_hierarchical_reclaim(mz->mem, zone,
						gfp_mask,
						MEM_CGROUP_RECLAIM_SOFT,
						&nr_scanned);
		nr_reclaimed += reclaimed;
		*total_scanned += nr_scanned;
		spin_lock(&mctz->lock);

		/*
		 * If we failed to reclaim anything from this memory cgroup
		 * it is time to move on to the next cgroup
		 */
		next_mz = NULL;
		if (!reclaimed) {
			do {
				/*
				 * Loop until we find yet another one.
				 *
				 * By the time we get the soft_limit lock
				 * again, someone might have aded the
				 * group back on the RB tree. Iterate to
				 * make sure we get a different mem.
				 * mem_cgroup_largest_soft_limit_node returns
				 * NULL if no other cgroup is present on
				 * the tree
				 */
				next_mz =
				__mem_cgroup_largest_soft_limit_node(mctz);
				if (next_mz == mz)
					css_put(&next_mz->mem->css);
				else /* next_mz == NULL or other memcg */
					break;
			} while (1);
		}
		__mem_cgroup_remove_exceeded(mz->mem, mz, mctz);
		excess = res_counter_soft_limit_excess(&mz->mem->res);
		/*
		 * One school of thought says that we should not add
		 * back the node to the tree if reclaim returns 0.
		 * But our reclaim could return 0, simply because due
		 * to priority we are exposing a smaller subset of
		 * memory to reclaim from. Consider this as a longer
		 * term TODO.
		 */
		/* If excess == 0, no tree ops */
		__mem_cgroup_insert_exceeded(mz->mem, mz, mctz, excess);
		spin_unlock(&mctz->lock);
		css_put(&mz->mem->css);
		loop++;
		/*
		 * Could not reclaim anything and there are no more
		 * mem cgroups to try or we seem to be looping without
		 * reclaiming anything.
		 */
		if (!nr_reclaimed &&
			(next_mz == NULL ||
			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
			break;
	} while (!nr_reclaimed);
	if (next_mz)
		css_put(&next_mz->mem->css);
	return nr_reclaimed;
}

/*
 * This routine traverse page_cgroup in given list and drop them all.
 * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
 */
static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
				int node, int zid, enum lru_list lru)
{
	struct zone *zone;
	struct mem_cgroup_per_zone *mz;
	struct page_cgroup *pc, *busy;
	unsigned long flags, loop;
	struct list_head *list;
	int ret = 0;

	zone = &NODE_DATA(node)->node_zones[zid];
	mz = mem_cgroup_zoneinfo(memcg, node, zid);
	list = &mz->lists[lru];

	loop = MEM_CGROUP_ZSTAT(mz, lru);
	/* give some margin against EBUSY etc...*/
	loop += 256;
	busy = NULL;
	while (loop--) {
		struct page *page;

		ret = 0;
		spin_lock_irqsave(&zone->lru_lock, flags);
		if (list_empty(list)) {
			spin_unlock_irqrestore(&zone->lru_lock, flags);
			break;
		}
		pc = list_entry(list->prev, struct page_cgroup, lru);
		if (busy == pc) {
			list_move(&pc->lru, list);
			busy = NULL;
			spin_unlock_irqrestore(&zone->lru_lock, flags);
			continue;
		}
		spin_unlock_irqrestore(&zone->lru_lock, flags);

		page = lookup_cgroup_page(pc);

		ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL);
		if (ret == -ENOMEM)
			break;

		if (ret == -EBUSY || ret == -EINVAL) {
			/* found lock contention or "pc" is obsolete. */
			busy = pc;
			cond_resched();
		} else
			busy = NULL;
	}

	if (!ret && !list_empty(list))
		return -EBUSY;
	return ret;
}

/*
 * make mem_cgroup's charge to be 0 if there is no task.
 * This enables deleting this mem_cgroup.
 */
static int mem_cgroup_force_empty(struct mem_cgroup *memcg, bool free_all)
{
	int ret;
	int node, zid, shrink;
	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
	struct cgroup *cgrp = memcg->css.cgroup;

	css_get(&memcg->css);

	shrink = 0;
	/* should free all ? */
	if (free_all)
		goto try_to_free;
move_account:
	do {
		ret = -EBUSY;
		if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
			goto out;
		ret = -EINTR;
		if (signal_pending(current))
			goto out;
		/* This is for making all *used* pages to be on LRU. */
		lru_add_drain_all();
		drain_all_stock_sync(memcg);
		ret = 0;
		mem_cgroup_start_move(memcg);
		for_each_node_state(node, N_HIGH_MEMORY) {
			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
				enum lru_list l;
				for_each_lru(l) {
					ret = mem_cgroup_force_empty_list(memcg,
							node, zid, l);
					if (ret)
						break;
				}
			}
			if (ret)
				break;
		}
		mem_cgroup_end_move(memcg);
		memcg_oom_recover(memcg);
		/* it seems parent cgroup doesn't have enough mem */
		if (ret == -ENOMEM)
			goto try_to_free;
		cond_resched();
	/* "ret" should also be checked to ensure all lists are empty. */
	} while (memcg->res.usage > 0 || ret);
out:
	css_put(&memcg->css);
	return ret;

try_to_free:
	/* returns EBUSY if there is a task or if we come here twice. */
	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) {
		ret = -EBUSY;
		goto out;
	}
	/* we call try-to-free pages for make this cgroup empty */
	lru_add_drain_all();
	/* try to free all pages in this cgroup */
	shrink = 1;
	while (nr_retries && memcg->res.usage > 0) {
		int progress;

		if (signal_pending(current)) {
			ret = -EINTR;
			goto out;
		}
		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL,
						false);
		if (!progress) {
			nr_retries--;
			/* maybe some writeback is necessary */
			congestion_wait(BLK_RW_ASYNC, HZ/10);
		}

	}
	lru_add_drain();
	/* try move_account...there may be some *locked* pages. */
	goto move_account;
}

int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
{
	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true);
}


static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft)
{
	return mem_cgroup_from_cont(cont)->use_hierarchy;
}

static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
					u64 val)
{
	int retval = 0;
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
	struct cgroup *parent = cont->parent;
	struct mem_cgroup *parent_memcg = NULL;

	if (parent)
		parent_memcg = mem_cgroup_from_cont(parent);

	cgroup_lock();
	/*
	 * If parent's use_hierarchy is set, we can't make any modifications
	 * in the child subtrees. If it is unset, then the change can
	 * occur, provided the current cgroup has no children.
	 *
	 * For the root cgroup, parent_mem is NULL, we allow value to be
	 * set if there are no children.
	 */
	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
				(val == 1 || val == 0)) {
		if (list_empty(&cont->children))
			memcg->use_hierarchy = val;
		else
			retval = -EBUSY;
	} else
		retval = -EINVAL;
	cgroup_unlock();

	return retval;
}


static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg,
					       enum mem_cgroup_stat_index idx)
{
	struct mem_cgroup *iter;
	long val = 0;

	/* Per-cpu values can be negative, use a signed accumulator */
	for_each_mem_cgroup_tree(iter, memcg)
		val += mem_cgroup_read_stat(iter, idx);

	if (val < 0) /* race ? */
		val = 0;
	return val;
}

static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
{
	u64 val;

	if (!mem_cgroup_is_root(memcg)) {
		val = 0;
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
		if (!memcg->kmem_independent_accounting)
			val = res_counter_read_u64(&memcg->kmem, RES_USAGE);
#endif
		if (!swap)
			val += res_counter_read_u64(&memcg->res, RES_USAGE);
		else
			val += res_counter_read_u64(&memcg->memsw, RES_USAGE);

		return val;
	}

	val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
	val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);

	if (swap)
		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAPOUT);

	return val << PAGE_SHIFT;
}

static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
	u64 val;
	int type, name;

	type = MEMFILE_TYPE(cft->private);
	name = MEMFILE_ATTR(cft->private);
	switch (type) {
	case _MEM:
		if (name == RES_USAGE)
			val = mem_cgroup_usage(memcg, false);
		else
			val = res_counter_read_u64(&memcg->res, name);
		break;
	case _MEMSWAP:
		if (name == RES_USAGE)
			val = mem_cgroup_usage(memcg, true);
		else
			val = res_counter_read_u64(&memcg->memsw, name);
		break;
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
	case _KMEM:
		val = res_counter_read_u64(&memcg->kmem, name);
		break;
#endif
	default:
		BUG();
		break;
	}
	return val;
}
/*
 * The user of this function is...
 * RES_LIMIT.
 */
static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
			    const char *buffer)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
	int type, name;
	unsigned long long val;
	int ret;

	type = MEMFILE_TYPE(cft->private);
	name = MEMFILE_ATTR(cft->private);
	switch (name) {
	case RES_LIMIT:
		if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */
			ret = -EINVAL;
			break;
		}
		/* This function does all necessary parse...reuse it */
		ret = res_counter_memparse_write_strategy(buffer, &val);
		if (ret)
			break;
		if (type == _MEM)
			ret = mem_cgroup_resize_limit(memcg, val);
		else
			ret = mem_cgroup_resize_memsw_limit(memcg, val);
		break;
	case RES_SOFT_LIMIT:
		ret = res_counter_memparse_write_strategy(buffer, &val);
		if (ret)
			break;
		/*
		 * For memsw, soft limits are hard to implement in terms
		 * of semantics, for now, we support soft limits for
		 * control without swap
		 */
		if (type == _MEM)
			ret = res_counter_set_soft_limit(&memcg->res, val);
		else