memcontrol.c

最新最稳定的Linux内存管理模块源代码

					unsigned long *scanned, int order,
					int mode, struct zone *z,
					struct mem_cgroup *mem_cont,
					int active, int file)
{
	unsigned long nr_taken = 0;
	struct page *page;
	unsigned long scan;
	LIST_HEAD(pc_list);
	struct list_head *src;
	struct page_cgroup *pc, *tmp;
	int nid = z->zone_pgdat->node_id;
	int zid = zone_idx(z);
	struct mem_cgroup_per_zone *mz;
	int lru = LRU_FILE * !!file + !!active;

	BUG_ON(!mem_cont);
	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
	src = &mz->lists[lru];

	scan = 0;
	list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
		if (scan >= nr_to_scan)
			break;

		page = pc->page;
		if (unlikely(!PageCgroupUsed(pc)))
			continue;
		if (unlikely(!PageLRU(page)))
			continue;

		scan++;
		if (__isolate_lru_page(page, mode, file) == 0) {
			list_move(&page->lru, dst);
			nr_taken++;
		}
	}

	*scanned = scan;
	return nr_taken;
}

#define mem_cgroup_from_res_counter(counter, member)	\
	container_of(counter, struct mem_cgroup, member)

/*
 * This routine finds the DFS walk successor. This routine should be
 * called with hierarchy_mutex held
 */
static struct mem_cgroup *
__mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
{
	struct cgroup *cgroup, *curr_cgroup, *root_cgroup;

	curr_cgroup = curr->css.cgroup;
	root_cgroup = root_mem->css.cgroup;

	if (!list_empty(&curr_cgroup->children)) {
		/*
		 * Walk down to children
		 */
		cgroup = list_entry(curr_cgroup->children.next,
						struct cgroup, sibling);
		curr = mem_cgroup_from_cont(cgroup);
		goto done;
	}

visit_parent:
	if (curr_cgroup == root_cgroup) {
		/* caller handles NULL case */
		curr = NULL;
		goto done;
	}

	/*
	 * Goto next sibling
	 */
	if (curr_cgroup->sibling.next != &curr_cgroup->parent->children) {
		cgroup = list_entry(curr_cgroup->sibling.next, struct cgroup,
						sibling);
		curr = mem_cgroup_from_cont(cgroup);
		goto done;
	}

	/*
	 * Go up to next parent and next parent's sibling if need be
	 */
	curr_cgroup = curr_cgroup->parent;
	goto visit_parent;

done:
	return curr;
}

/*
 * Visit the first child (need not be the first child as per the ordering
 * of the cgroup list, since we track last_scanned_child) of @mem and use
 * that to reclaim free pages from.
 */
static struct mem_cgroup *
mem_cgroup_get_next_node(struct mem_cgroup *root_mem)
{
	struct cgroup *cgroup;
	struct mem_cgroup *orig, *next;
	bool obsolete;

	/*
	 * Scan all children under the mem_cgroup mem
	 */
	mutex_lock(&mem_cgroup_subsys.hierarchy_mutex);

	orig = root_mem->last_scanned_child;
	obsolete = mem_cgroup_is_obsolete(orig);

	if (list_empty(&root_mem->css.cgroup->children)) {
		/*
		 * root_mem might have children before and last_scanned_child
		 * may point to one of them. We put it later.
		 */
		if (orig)
			VM_BUG_ON(!obsolete);
		next = NULL;
		goto done;
	}

	if (!orig || obsolete) {
		cgroup = list_first_entry(&root_mem->css.cgroup->children,
				struct cgroup, sibling);
		next = mem_cgroup_from_cont(cgroup);
	} else
		next = __mem_cgroup_get_next_node(orig, root_mem);

done:
	if (next)
		mem_cgroup_get(next);
	root_mem->last_scanned_child = next;
	if (orig)
		mem_cgroup_put(orig);
	mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex);
	return (next) ? next : root_mem;
}

static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
{
	if (do_swap_account) {
		if (res_counter_check_under_limit(&mem->res) &&
			res_counter_check_under_limit(&mem->memsw))
			return true;
	} else
		if (res_counter_check_under_limit(&mem->res))
			return true;
	return false;
}

static unsigned int get_swappiness(struct mem_cgroup *memcg)
{
	struct cgroup *cgrp = memcg->css.cgroup;
	unsigned int swappiness;

	/* root ? */
	if (cgrp->parent == NULL)
		return vm_swappiness;

	spin_lock(&memcg->reclaim_param_lock);
	swappiness = memcg->swappiness;
	spin_unlock(&memcg->reclaim_param_lock);

	return swappiness;
}

/*
 * Dance down the hierarchy if needed to reclaim memory. We remember the
 * last child we reclaimed from, so that we don't end up penalizing
 * one child extensively based on its position in the children list.
 *
 * root_mem is the original ancestor that we've been reclaim from.
 */
static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
						gfp_t gfp_mask, bool noswap)
{
	struct mem_cgroup *next_mem;
	int ret = 0;

	/*
	 * Reclaim unconditionally and don't check for return value.
	 * We need to reclaim in the current group and down the tree.
	 * One might think about checking for children before reclaiming,
	 * but there might be left over accounting, even after children
	 * have left.
	 */
	ret += try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap,
					   get_swappiness(root_mem));
	if (mem_cgroup_check_under_limit(root_mem))
		return 1;	/* indicate reclaim has succeeded */
	if (!root_mem->use_hierarchy)
		return ret;

	next_mem = mem_cgroup_get_next_node(root_mem);

	while (next_mem != root_mem) {
		if (mem_cgroup_is_obsolete(next_mem)) {
			next_mem = mem_cgroup_get_next_node(root_mem);
			continue;
		}
		ret += try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap,
						   get_swappiness(next_mem));
		if (mem_cgroup_check_under_limit(root_mem))
			return 1;	/* indicate reclaim has succeeded */
		next_mem = mem_cgroup_get_next_node(root_mem);
	}
	return ret;
}

bool mem_cgroup_oom_called(struct task_struct *task)
{
	bool ret = false;
	struct mem_cgroup *mem;
	struct mm_struct *mm;

	rcu_read_lock();
	mm = task->mm;
	if (!mm)
		mm = &init_mm;
	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
	if (mem && time_before(jiffies, mem->last_oom_jiffies + HZ/10))
		ret = true;
	rcu_read_unlock();
	return ret;
}
/*
 * Unlike exported interface, "oom" parameter is added. if oom==true,
 * oom-killer can be invoked.
 */
static int __mem_cgroup_try_charge(struct mm_struct *mm,
			gfp_t gfp_mask, struct mem_cgroup **memcg,
			bool oom)
{
	struct mem_cgroup *mem, *mem_over_limit;
	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
	struct res_counter *fail_res;

	if (unlikely(test_thread_flag(TIF_MEMDIE))) {
		/* Don't account this! */
		*memcg = NULL;
		return 0;
	}

	/*
	 * 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).
	 */
	mem = *memcg;
	if (likely(!mem)) {
		mem = try_get_mem_cgroup_from_mm(mm);
		*memcg = mem;
	} else {
		css_get(&mem->css);
	}
	if (unlikely(!mem))
		return 0;

	VM_BUG_ON(mem_cgroup_is_obsolete(mem));

	while (1) {
		int ret;
		bool noswap = false;

		ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res);
		if (likely(!ret)) {
			if (!do_swap_account)
				break;
			ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
							&fail_res);
			if (likely(!ret))
				break;
			/* mem+swap counter fails */
			res_counter_uncharge(&mem->res, PAGE_SIZE);
			noswap = true;
			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
									memsw);
		} else
			/* mem counter fails */
			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
									res);

		if (!(gfp_mask & __GFP_WAIT))
			goto nomem;

		ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
							noswap);
		if (ret)
			continue;

		/*
		 * try_to_free_mem_cgroup_pages() might not give us a full
		 * picture of reclaim. Some pages are reclaimed and might be
		 * moved to swap cache or just unmapped from the cgroup.
		 * Check the limit again to see if the reclaim reduced the
		 * current usage of the cgroup before giving up
		 *
		 */
		if (mem_cgroup_check_under_limit(mem_over_limit))
			continue;

		if (!nr_retries--) {
			if (oom) {
				mutex_lock(&memcg_tasklist);
				mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
				mutex_unlock(&memcg_tasklist);
				mem_over_limit->last_oom_jiffies = jiffies;
			}
			goto nomem;
		}
	}
	return 0;
nomem:
	css_put(&mem->css);
	return -ENOMEM;
}

static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
{
	struct mem_cgroup *mem;
	swp_entry_t ent;

	if (!PageSwapCache(page))
		return NULL;

	ent.val = page_private(page);
	mem = lookup_swap_cgroup(ent);
	if (!mem)
		return NULL;
	if (!css_tryget(&mem->css))
		return NULL;
	return mem;
}

/*
 * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be
 * USED state. If already USED, uncharge and return.
 */

static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
				     struct page_cgroup *pc,
				     enum charge_type ctype)
{
	/* try_charge() can return NULL to *memcg, taking care of it. */
	if (!mem)
		return;

	lock_page_cgroup(pc);
	if (unlikely(PageCgroupUsed(pc))) {
		unlock_page_cgroup(pc);
		res_counter_uncharge(&mem->res, PAGE_SIZE);
		if (do_swap_account)
			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
		css_put(&mem->css);
		return;
	}
	pc->mem_cgroup = mem;
	smp_wmb();
	pc->flags = pcg_default_flags[ctype];

	mem_cgroup_charge_statistics(mem, pc, true);

	unlock_page_cgroup(pc);
}

/**
 * mem_cgroup_move_account - move account of the page
 * @pc:	page_cgroup of the page.
 * @from: mem_cgroup which the page is moved from.
 * @to:	mem_cgroup which the page is moved to. @from != @to.
 *
 * The caller must confirm following.
 * - page is not on LRU (isolate_page() is useful.)
 *
 * returns 0 at success,
 * returns -EBUSY when lock is busy or "pc" is unstable.
 *
 * This function does "uncharge" from old cgroup but doesn't do "charge" to
 * new cgroup. It should be done by a caller.
 */

static int mem_cgroup_move_account(struct page_cgroup *pc,
	struct mem_cgroup *from, struct mem_cgroup *to)
{
	struct mem_cgroup_per_zone *from_mz, *to_mz;
	int nid, zid;
	int ret = -EBUSY;

	VM_BUG_ON(from == to);
	VM_BUG_ON(PageLRU(pc->page));

	nid = page_cgroup_nid(pc);
	zid = page_cgroup_zid(pc);
	from_mz =  mem_cgroup_zoneinfo(from, nid, zid);
	to_mz =  mem_cgroup_zoneinfo(to, nid, zid);

	if (!trylock_page_cgroup(pc))
		return ret;

	if (!PageCgroupUsed(pc))
		goto out;

	if (pc->mem_cgroup != from)
		goto out;

	res_counter_uncharge(&from->res, PAGE_SIZE);
	mem_cgroup_charge_statistics(from, pc, false);
	if (do_swap_account)
		res_counter_uncharge(&from->memsw, PAGE_SIZE);
	css_put(&from->css);

	css_get(&to->css);
	pc->mem_cgroup = to;
	mem_cgroup_charge_statistics(to, pc, true);
	ret = 0;
out:
	unlock_page_cgroup(pc);
	return ret;
}

/*
 * move charges to its parent.
 */

static int mem_cgroup_move_parent(struct page_cgroup *pc,
				  struct mem_cgroup *child,
				  gfp_t gfp_mask)
{
	struct page *page = pc->page;
	struct cgroup *cg = child->css.cgroup;
	struct cgroup *pcg = cg->parent;
	struct mem_cgroup *parent;
	int ret;

	/* Is ROOT ? */
	if (!pcg)
		return -EINVAL;


	parent = mem_cgroup_from_cont(pcg);


	ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false);
	if (ret || !parent)
		return ret;

	if (!get_page_unless_zero(page)) {
		ret = -EBUSY;
		goto uncharge;
	}

	ret = isolate_lru_page(page);

	if (ret)
		goto cancel;

	ret = mem_cgroup_move_account(pc, child, parent);

	putback_lru_page(page);
	if (!ret) {
		put_page(page);
		/* drop extra refcnt by try_charge() */
		css_put(&parent->css);
		return 0;
	}

cancel:
	put_page(page);
uncharge:
	/* drop extra refcnt by try_charge() */
	css_put(&parent->css);
	/* uncharge if move fails */
	res_counter_uncharge(&parent->res, PAGE_SIZE);
	if (do_swap_account)
		res_counter_uncharge(&parent->memsw, PAGE_SIZE);
	return ret;
}

/*
 * Charge the memory controller for page usage.
 * Return
 * 0 if the charge was successful
 * < 0 if the cgroup is over its limit
 */
static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
				gfp_t gfp_mask, enum charge_type ctype,
				struct mem_cgroup *memcg)
{
	struct mem_cgroup *mem;
	struct page_cgroup *pc;
	int ret;

	pc = lookup_page_cgroup(page);
	/* can happen at boot */
	if (unlikely(!pc))
		return 0;
	prefetchw(pc);

	mem = memcg;
	ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
	if (ret || !mem)
		return ret;

	__mem_cgroup_commit_charge(mem, pc, ctype);
	return 0;
}

int mem_cgroup_newpage_charge(struct page *page,
			      struct mm_struct *mm, gfp_t gfp_mask)
{
	if (mem_cgroup_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.
	 * But page->mapping may have out-of-use anon_vma pointer,
	 * detecit it by PageAnon() check. newly-mapped-anon's page->mapping
	 * is NULL.
  	 */
	if (page_mapped(page) || (page->mapping && !PageAnon(page)))
		return 0;
	if (unlikely(!mm))
		mm = &init_mm;
	return mem_cgroup_charge_common(page, mm, gfp_mask,
				MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
}

int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
				gfp_t gfp_mask)
{
	struct mem_cgroup *mem = NULL;
	int ret;

	if (mem_cgroup_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
	 * and call add_to_page_cache() with GFP_NOWAIT.
	 *
	 * For GFP_NOWAIT case, the page may be pre-charged before calling
	 * add_to_page_cache(). (See shmem.c) check it here and avoid to call
	 * charge twice. (It works but has to pay a bit larger cost.)
	 * And when the page is SwapCache, it should take swap information
	 * into account. This is under lock_page() now.
	 */
	if (!(gfp_mask & __GFP_WAIT)) {
		struct page_cgroup *pc;


		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(pc);
	}

	if (do_swap_account && PageSwapCache(page)) {
		mem = try_get_mem_cgroup_from_swapcache(page);
		if (mem)
			mm = NULL;
		  else
			mem = NULL;
		/* SwapCache may be still linked to LRU now. */
		mem_cgroup_lru_del_before_commit_swapcache(page);
	}

	if (unlikely(!mm && !mem))
		mm = &init_mm;

	if (page_is_file_cache(page))
		return mem_cgroup_charge_common(page, mm, gfp_mask,
				MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);