vmscan.c

	 */
	if (scan_global_lru(sc))
		mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
				global_page_state(NR_ANON_PAGES)) * 100) /
					vm_total_pages;
	else
		mapped_ratio = mem_cgroup_calc_mapped_ratio(sc->mem_cgroup);

	/*
	 * Now decide how much we really want to unmap some pages.  The
	 * mapped ratio is downgraded - just because there's a lot of
	 * mapped memory doesn't necessarily mean that page reclaim
	 * isn't succeeding.
	 *
	 * The distress ratio is important - we don't want to start
	 * going oom.
	 *
	 * A 100% value of vm_swappiness overrides this algorithm
	 * altogether.
	 */
	swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;

	/*
	 * If there's huge imbalance between active and inactive
	 * (think active 100 times larger than inactive) we should
	 * become more permissive, or the system will take too much
	 * cpu before it start swapping during memory pressure.
	 * Distress is about avoiding early-oom, this is about
	 * making swappiness graceful despite setting it to low
	 * values.
	 *
	 * Avoid div by zero with nr_inactive+1, and max resulting
	 * value is vm_total_pages.
	 */
	if (scan_global_lru(sc)) {
		imbalance  = zone_page_state(zone, NR_ACTIVE);
		imbalance /= zone_page_state(zone, NR_INACTIVE) + 1;
	} else
		imbalance = mem_cgroup_reclaim_imbalance(sc->mem_cgroup);

	/*
	 * Reduce the effect of imbalance if swappiness is low,
	 * this means for a swappiness very low, the imbalance
	 * must be much higher than 100 for this logic to make
	 * the difference.
	 *
	 * Max temporary value is vm_total_pages*100.
	 */
	imbalance *= (vm_swappiness + 1);
	imbalance /= 100;

	/*
	 * If not much of the ram is mapped, makes the imbalance
	 * less relevant, it's high priority we refill the inactive
	 * list with mapped pages only in presence of high ratio of
	 * mapped pages.
	 *
	 * Max temporary value is vm_total_pages*100.
	 */
	imbalance *= mapped_ratio;
	imbalance /= 100;

	/* apply imbalance feedback to swap_tendency */
	swap_tendency += imbalance;

	/*
	 * Now use this metric to decide whether to start moving mapped
	 * memory onto the inactive list.
	 */
	if (swap_tendency >= 100)
		reclaim_mapped = 1;

	return reclaim_mapped;
}

/*
 * This moves pages from the active list to the inactive list.
 *
 * We move them the other way if the page is referenced by one or more
 * processes, from rmap.
 *
 * If the pages are mostly unmapped, the processing is fast and it is
 * appropriate to hold zone->lru_lock across the whole operation.  But if
 * the pages are mapped, the processing is slow (page_referenced()) so we
 * should drop zone->lru_lock around each page.  It's impossible to balance
 * this, so instead we remove the pages from the LRU while processing them.
 * It is safe to rely on PG_active against the non-LRU pages in here because
 * nobody will play with that bit on a non-LRU page.
 *
 * The downside is that we have to touch page->_count against each page.
 * But we had to alter page->flags anyway.
 */


static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
				struct scan_control *sc, int priority)
{
	unsigned long pgmoved;
	int pgdeactivate = 0;
	unsigned long pgscanned;
	LIST_HEAD(l_hold);	/* The pages which were snipped off */
	LIST_HEAD(l_inactive);	/* Pages to go onto the inactive_list */
	LIST_HEAD(l_active);	/* Pages to go onto the active_list */
	struct page *page;
	struct pagevec pvec;
	int reclaim_mapped = 0;

	if (sc->may_swap)
		reclaim_mapped = calc_reclaim_mapped(sc, zone, priority);

	lru_add_drain();
	spin_lock_irq(&zone->lru_lock);
	pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
					ISOLATE_ACTIVE, zone,
					sc->mem_cgroup, 1);
	/*
	 * zone->pages_scanned is used for detect zone's oom
	 * mem_cgroup remembers nr_scan by itself.
	 */
	if (scan_global_lru(sc))
		zone->pages_scanned += pgscanned;

	__mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
	spin_unlock_irq(&zone->lru_lock);

	while (!list_empty(&l_hold)) {
		cond_resched();
		page = lru_to_page(&l_hold);
		list_del(&page->lru);
		if (page_mapped(page)) {
			if (!reclaim_mapped ||
			    (total_swap_pages == 0 && PageAnon(page)) ||
			    page_referenced(page, 0, sc->mem_cgroup)) {
				list_add(&page->lru, &l_active);
				continue;
			}
		}
		list_add(&page->lru, &l_inactive);
	}

	pagevec_init(&pvec, 1);
	pgmoved = 0;
	spin_lock_irq(&zone->lru_lock);
	while (!list_empty(&l_inactive)) {
		page = lru_to_page(&l_inactive);
		prefetchw_prev_lru_page(page, &l_inactive, flags);
		VM_BUG_ON(PageLRU(page));
		SetPageLRU(page);
		VM_BUG_ON(!PageActive(page));
		ClearPageActive(page);

		list_move(&page->lru, &zone->inactive_list);
		mem_cgroup_move_lists(page, false);
		pgmoved++;
		if (!pagevec_add(&pvec, page)) {
			__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
			spin_unlock_irq(&zone->lru_lock);
			pgdeactivate += pgmoved;
			pgmoved = 0;
			if (buffer_heads_over_limit)
				pagevec_strip(&pvec);
			__pagevec_release(&pvec);
			spin_lock_irq(&zone->lru_lock);
		}
	}
	__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
	pgdeactivate += pgmoved;
	if (buffer_heads_over_limit) {
		spin_unlock_irq(&zone->lru_lock);
		pagevec_strip(&pvec);
		spin_lock_irq(&zone->lru_lock);
	}

	pgmoved = 0;
	while (!list_empty(&l_active)) {
		page = lru_to_page(&l_active);
		prefetchw_prev_lru_page(page, &l_active, flags);
		VM_BUG_ON(PageLRU(page));
		SetPageLRU(page);
		VM_BUG_ON(!PageActive(page));

		list_move(&page->lru, &zone->active_list);
		mem_cgroup_move_lists(page, true);
		pgmoved++;
		if (!pagevec_add(&pvec, page)) {
			__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
			pgmoved = 0;
			spin_unlock_irq(&zone->lru_lock);
			__pagevec_release(&pvec);
			spin_lock_irq(&zone->lru_lock);
		}
	}
	__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);

	__count_zone_vm_events(PGREFILL, zone, pgscanned);
	__count_vm_events(PGDEACTIVATE, pgdeactivate);
	spin_unlock_irq(&zone->lru_lock);

	pagevec_release(&pvec);
}

/*
 * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
 */
static unsigned long shrink_zone(int priority, struct zone *zone,
				struct scan_control *sc)
{
	unsigned long nr_active;
	unsigned long nr_inactive;
	unsigned long nr_to_scan;
	unsigned long nr_reclaimed = 0;

	if (scan_global_lru(sc)) {
		/*
		 * Add one to nr_to_scan just to make sure that the kernel
		 * will slowly sift through the active list.
		 */
		zone->nr_scan_active +=
			(zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
		nr_active = zone->nr_scan_active;
		zone->nr_scan_inactive +=
			(zone_page_state(zone, NR_INACTIVE) >> priority) + 1;
		nr_inactive = zone->nr_scan_inactive;
		if (nr_inactive >= sc->swap_cluster_max)
			zone->nr_scan_inactive = 0;
		else
			nr_inactive = 0;

		if (nr_active >= sc->swap_cluster_max)
			zone->nr_scan_active = 0;
		else
			nr_active = 0;
	} else {
		/*
		 * This reclaim occurs not because zone memory shortage but
		 * because memory controller hits its limit.
		 * Then, don't modify zone reclaim related data.
		 */
		nr_active = mem_cgroup_calc_reclaim_active(sc->mem_cgroup,
					zone, priority);

		nr_inactive = mem_cgroup_calc_reclaim_inactive(sc->mem_cgroup,
					zone, priority);
	}


	while (nr_active || nr_inactive) {
		if (nr_active) {
			nr_to_scan = min(nr_active,
					(unsigned long)sc->swap_cluster_max);
			nr_active -= nr_to_scan;
			shrink_active_list(nr_to_scan, zone, sc, priority);
		}

		if (nr_inactive) {
			nr_to_scan = min(nr_inactive,
					(unsigned long)sc->swap_cluster_max);
			nr_inactive -= nr_to_scan;
			nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
								sc);
		}
	}

	throttle_vm_writeout(sc->gfp_mask);
	return nr_reclaimed;
}

/*
 * This is the direct reclaim path, for page-allocating processes.  We only
 * try to reclaim pages from zones which will satisfy the caller's allocation
 * request.
 *
 * We reclaim from a zone even if that zone is over pages_high.  Because:
 * a) The caller may be trying to free *extra* pages to satisfy a higher-order
 *    allocation or
 * b) The zones may be over pages_high but they must go *over* pages_high to
 *    satisfy the `incremental min' zone defense algorithm.
 *
 * Returns the number of reclaimed pages.
 *
 * If a zone is deemed to be full of pinned pages then just give it a light
 * scan then give up on it.
 */
static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
					struct scan_control *sc)
{
	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
	unsigned long nr_reclaimed = 0;
	struct zoneref *z;
	struct zone *zone;

	sc->all_unreclaimable = 1;
	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
		if (!populated_zone(zone))
			continue;
		/*
		 * Take care memory controller reclaiming has small influence
		 * to global LRU.
		 */
		if (scan_global_lru(sc)) {
			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
				continue;
			note_zone_scanning_priority(zone, priority);

			if (zone_is_all_unreclaimable(zone) &&
						priority != DEF_PRIORITY)
				continue;	/* Let kswapd poll it */
			sc->all_unreclaimable = 0;
		} else {
			/*
			 * Ignore cpuset limitation here. We just want to reduce
			 * # of used pages by us regardless of memory shortage.
			 */
			sc->all_unreclaimable = 0;
			mem_cgroup_note_reclaim_priority(sc->mem_cgroup,
							priority);
		}

		nr_reclaimed += shrink_zone(priority, zone, sc);
	}

	return nr_reclaimed;
}
 
/*
 * This is the main entry point to direct page reclaim.
 *
 * If a full scan of the inactive list fails to free enough memory then we
 * are "out of memory" and something needs to be killed.
 *
 * If the caller is !__GFP_FS then the probability of a failure is reasonably
 * high - the zone may be full of dirty or under-writeback pages, which this
 * caller can't do much about.  We kick pdflush and take explicit naps in the
 * hope that some of these pages can be written.  But if the allocating task
 * holds filesystem locks which prevent writeout this might not work, and the
 * allocation attempt will fail.
 *
 * returns:	0, if no pages reclaimed
 * 		else, the number of pages reclaimed
 */
static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
					struct scan_control *sc)
{
	int priority;
	unsigned long ret = 0;
	unsigned long total_scanned = 0;
	unsigned long nr_reclaimed = 0;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	unsigned long lru_pages = 0;
	struct zoneref *z;
	struct zone *zone;
	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);

	delayacct_freepages_start();

	if (scan_global_lru(sc))
		count_vm_event(ALLOCSTALL);
	/*
	 * mem_cgroup will not do shrink_slab.
	 */
	if (scan_global_lru(sc)) {
		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {

			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
				continue;

			lru_pages += zone_page_state(zone, NR_ACTIVE)
					+ zone_page_state(zone, NR_INACTIVE);
		}
	}

	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
		sc->nr_scanned = 0;
		if (!priority)
			disable_swap_token();
		nr_reclaimed += shrink_zones(priority, zonelist, sc);
		/*
		 * Don't shrink slabs when reclaiming memory from
		 * over limit cgroups
		 */
		if (scan_global_lru(sc)) {
			shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
			if (reclaim_state) {
				nr_reclaimed += reclaim_state->reclaimed_slab;
				reclaim_state->reclaimed_slab = 0;
			}
		}
		total_scanned += sc->nr_scanned;
		if (nr_reclaimed >= sc->swap_cluster_max) {
			ret = nr_reclaimed;
			goto out;
		}

		/*
		 * Try to write back as many pages as we just scanned.  This
		 * tends to cause slow streaming writers to write data to the
		 * disk smoothly, at the dirtying rate, which is nice.   But
		 * that's undesirable in laptop mode, where we *want* lumpy
		 * writeout.  So in laptop mode, write out the whole world.
		 */
		if (total_scanned > sc->swap_cluster_max +
					sc->swap_cluster_max / 2) {
			wakeup_pdflush(laptop_mode ? 0 : total_scanned);
			sc->may_writepage = 1;
		}

		/* Take a nap, wait for some writeback to complete */
		if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
			congestion_wait(WRITE, HZ/10);
	}
	/* top priority shrink_caches still had more to do? don't OOM, then */
	if (!sc->all_unreclaimable && scan_global_lru(sc))
		ret = nr_reclaimed;
out:
	/*
	 * Now that we've scanned all the zones at this priority level, note
	 * that level within the zone so that the next thread which performs
	 * scanning of this zone will immediately start out at this priority
	 * level.  This affects only the decision whether or not to bring
	 * mapped pages onto the inactive list.
	 */
	if (priority < 0)
		priority = 0;

	if (scan_global_lru(sc)) {
		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {

			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
				continue;

			zone->prev_priority = priority;
		}
	} else
		mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);

	delayacct_freepages_end();

	return ret;
}

unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
								gfp_t gfp_mask)
{
	struct scan_control sc = {
		.gfp_mask = gfp_mask,
		.may_writepage = !laptop_mode,
		.swap_cluster_max = SWAP_CLUSTER_MAX,
		.may_swap = 1,
		.swappiness = vm_swappiness,
		.order = order,
		.mem_cgroup = NULL,
		.isolate_pages = isolate_pages_global,
	};

	return do_try_to_free_pages(zonelist, &sc);
}

#ifdef CONFIG_CGROUP_MEM_RES_CTLR

unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
						gfp_t gfp_mask)
{
	struct scan_control sc = {
		.may_writepage = !laptop_mode,
		.may_swap = 1,
		.swap_cluster_max = SWAP_CLUSTER_MAX,
		.swappiness = vm_swappiness,
		.order = 0,
		.mem_cgroup = mem_cont,
		.isolate_pages = mem_cgroup_isolate_pages,
	};
	struct zonelist *zonelist;

	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
	zonelist = NODE_DATA(numa_node_id())->node_zonelists;
	return do_try_to_free_pages(zonelist, &sc);
}
#endif

/*
 * For kswapd, balance_pgdat() will work across all this node's zones until
 * they are all at pages_high.
 *
 * Returns the number of pages which were actually freed.
 *
 * There is special handling here for zones which are full of pinned pages.
 * This can happen if the pages are all mlocked, or if they are all used by
 * device drivers (say, ZONE_DMA).  Or if they are all in use by hugetlb.
 * What we do is to detect the case where all pages in the zone have been
 * scanned twice and there has been zero successful reclaim.  Mark the zone as
 * dead and from now on, only perform a short scan.  Basically we're polling
 * the zone for when the problem goes away.
 *
 * kswapd scans the zones in the highmem->normal->dma direction.  It skips
 * zones which have free_pages > pages_high, but once a zone is found to have
 * free_pages <= pages_high, we scan that zone and the lower zones regardless
 * of the number of free pages in the lower zones.  This interoperates with
 * the page allocator fallback scheme to ensure that aging of pages is balanced
 * across the zones.
 */
static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
{
	int all_zones_ok;
	int priority;
	int i;
	unsigned long total_scanned;
	unsigned long nr_reclaimed;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_swap = 1,
		.swap_cluster_max = SWAP_CLUSTER_MAX,
		.swappiness = vm_swappiness,
		.order = order,
		.mem_cgroup = NULL,
		.isolate_pages = isolate_pages_global,
	};
	/*
	 * temp_priority is used to remember the scanning priority at which
	 * this zone was successfully refilled to free_pages == pages_high.
	 */
	int temp_priority[MAX_NR_ZONES];

loop_again:
	total_scanned = 0;
	nr_reclaimed = 0;
	sc.may_writepage = !laptop_mode;
	count_vm_event(PAGEOUTRUN);

	for (i = 0; i < pgdat->nr_zones; i++)
		temp_priority[i] = DEF_PRIORITY;

	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
		unsigned long lru_pages = 0;

		/* The swap token gets in the way of swapout... */
		if (!priority)
			disable_swap_token();

		all_zones_ok = 1;

		/*
		 * Scan in the highmem->dma direction for the highest
		 * zone which needs scanning
		 */
		for (i = pgdat->nr_zones - 1; i >= 0; i--) {
			struct zone *zone = pgdat->node_zones + i;

			if (!populated_zone(zone))
				continue;

			if (zone_is_all_unreclaimable(zone) &&
			    priority != DEF_PRIORITY)
				continue;

			if (!zone_watermark_ok(zone, order, zone->pages_high,
					       0, 0)) {
				end_zone = i;
				break;
			}
		}
		if (i < 0)
			goto out;

		for (i = 0; i <= end_zone; i++) {
			struct zone *zone = pgdat->node_zones + i;

			lru_pages += zone_page_state(zone, NR_ACTIVE)
					+ zone_page_state(zone, NR_INACTIVE);
		}

		/*
		 * Now scan the zone in the dma->highmem direction, stopping
		 * at the last zone which needs scanning.
		 *
		 * We do this because the page allocator works in the opposite
		 * direction.  This prevents the page allocator from allocating
		 * pages behind kswapd's direction of progress, which would
		 * cause too much scanning of the lower zones.
		 */
		for (i = 0; i <= end_zone; i++) {
			struct zone *zone = pgdat->node_zones + i;
			int nr_slab;

			if (!populated_zone(zone))
				continue;

			if (zone_is_all_unreclaimable(zone) &&
					priority != DEF_PRIORITY)
				continue;

			if (!zone_watermark_ok(zone, order, zone->pages_high,
					       end_zone, 0))
				all_zones_ok = 0;
			temp_priority[i] = priority;
			sc.nr_scanned = 0;
			note_zone_scanning_priority(zone, priority);
			/*
			 * We put equal pressure on every zone, unless one
			 * zone has way too many pages free already.
			 */
			if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
						end_zone, 0))
				nr_reclaimed += shrink_zone(priority, zone, &sc);
			reclaim_state->reclaimed_slab = 0;
			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
						lru_pages);
			nr_reclaimed += reclaim_state->reclaimed_slab;
			total_scanned += sc.nr_scanned;
			if (zone_is_all_unreclaimable(zone))
				continue;
			if (nr_slab == 0 && zone->pages_scanned >=
				(zone_page_state(zone, NR_ACTIVE)
				+ zone_page_state(zone, NR_INACTIVE)) * 6)
					zone_set_flag(zone,
						      ZONE_ALL_UNRECLAIMABLE);
			/*
			 * If we've done a decent amount of scanning and
			 * the reclaim ratio is low, start doing writepage
			 * even in laptop mode
			 */
			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
			    total_scanned > nr_reclaimed + nr_reclaimed / 2)
				sc.may_writepage = 1;
		}
		if (all_zones_ok)
			break;		/* kswapd: all done */
		/*
		 * OK, kswapd is getting into trouble.  Take a nap, then take
		 * another pass across the zones.
		 */
		if (total_scanned && priority < DEF_PRIORITY - 2)
			congestion_wait(WRITE, HZ/10);

		/*
		 * We do this so kswapd doesn't build up large priorities for
		 * example when it is freeing in parallel with allocators. It
		 * matches the direct reclaim path behaviour in terms of impact
		 * on zone->*_priority.
		 */
		if (nr_reclaimed >= SWAP_CLUSTER_MAX)
			break;
	}
out:
	/*
	 * Note within each zone the priority level at which this zone was
	 * brought into a happy state.  So that the next thread which scans this
	 * zone will start out at that priority level.
	 */
	for (i = 0; i < pgdat->nr_zones; i++) {
		struct zone *zone = pgdat->node_zones + i;

		zone->prev_priority = temp_priority[i];
	}
	if (!all_zones_ok) {
		cond_resched();

		try_to_freeze();

		goto loop_again;
	}

	return nr_reclaimed;
}

/*
 * The background pageout daemon, started as a kernel thread
 * from the init process. 
 *
 * This basically trickles out pages so that we have _some_
 * free memory available even if there is no other activity
 * that frees anything up. This is needed for things like routing
 * etc, where we otherwise might have all activity going on in
 * asynchronous contexts that cannot page things out.
 *
 * If there are applications that are active memory-allocators
 * (most normal use), this basically shouldn't matter.
 */
static int kswapd(void *p)
{
	unsigned long order;
	pg_data_t *pgdat = (pg_data_t*)p;
	struct task_struct *tsk = current;
	DEFINE_WAIT(wait);
	struct reclaim_state reclaim_state = {
		.reclaimed_slab = 0,
	};
	node_to_cpumask_ptr(cpumask, pgdat->node_id);

	if (!cpus_empty(*cpumask))
		set_cpus_allowed_ptr(tsk, cpumask);
	current->reclaim_state = &reclaim_state;

	/*
	 * Tell the memory management that we're a "memory allocator",
	 * and that if we need more memory we should get access to it
	 * regardless (see "__alloc_pages()"). "kswapd" should
	 * never get caught in the normal page freeing logic.
	 *
	 * (Kswapd normally doesn't need memory anyway, but sometimes
	 * you need a small amount of memory in order to be able to
	 * page out something else, and this flag essentially protects
	 * us from recursively trying to free more memory as we're
	 * trying to free the first piece of memory in the first place).
	 */
	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
	set_freezable();

	order = 0;
	for ( ; ; ) {
		unsigned long new_order;

		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
		new_order = pgdat->kswapd_max_order;
		pgdat->kswapd_max_order = 0;
		if (order < new_order) {
			/*
			 * Don't sleep if someone wants a larger 'order'
			 * allocation
			 */
			order = new_order;
		} else {
			if (!freezing(current))
				schedule();

			order = pgdat->kswapd_max_order;
		}
		finish_wait(&pgdat->kswapd_wait, &wait);

		if (!try_to_freeze()) {
			/* We can speed up thawing tasks if we don't call
			 * balance_pgdat after returning from the refrigerator
			 */
			balance_pgdat(pgdat, order);
		}
	}
	return 0;
}

/*
 * A zone is low on free memory, so wake its kswapd task to service it.
 */
void wakeup_kswapd(struct zone *zone, int order)
{
	pg_data_t *pgdat;

	if (!populated_zone(zone))
		return;

	pgdat = zone->zone_pgdat;
	if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
		return;
	if (pgdat->kswapd_max_order < order)
		pgdat->kswapd_max_order = order;
	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
		return;
	if (!waitqueue_active(&pgdat->kswapd_wait))
		return;
	wake_up_interruptible(&pgdat->kswapd_wait);
}

#ifdef CONFIG_PM
/*
 * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
 * from LRU lists system-wide, for given pass and priority, and returns the
 * number of reclaimed pages
 *
 * For pass > 3 we also try to shrink the LRU lists that contain a few pages
 */
static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
				      int pass, struct scan_control *sc)
{
	struct zone *zone;
	unsigned long nr_to_scan, ret = 0;

	for_each_zone(zone) {

		if (!populated_zone(zone))
			continue;

		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
			continue;

		/* For pass = 0 we don't shrink the active list */
		if (pass > 0) {
			zone->nr_scan_active +=
				(zone_page_state(zone, NR_ACTIVE) >> prio) + 1;
			if (zone->nr_scan_active >= nr_pages || pass > 3) {
				zone->nr_scan_active = 0;
				nr_to_scan = min(nr_pages,
					zone_page_state(zone, NR_ACTIVE));
				shrink_active_list(nr_to_scan, zone, sc, prio);
			}
		}

		zone->nr_scan_inactive +=
			(zone_page_state(zone, NR_INACTIVE) >> prio) + 1;
		if (zone->nr_scan_inactive >= nr_pages || pass > 3) {
			zone->nr_scan_inactive = 0;
			nr_to_scan = min(nr_pages,
				zone_page_state(zone, NR_INACTIVE));
			ret += shrink_inactive_list(nr_to_scan, zone, sc);
			if (ret >= nr_pages)
				return ret;
		}
	}

	return ret;
}

static unsigned long count_lru_pages(void)
{
	return global_page_state(NR_ACTIVE) + global_page_state(NR_INACTIVE);
}

/*
 * Try to free `nr_pages' of memory, system-wide, and return the number of
 * freed pages.
 *
 * Rather than trying to age LRUs the aim is to preserve the overall
 * LRU order by reclaiming preferentially
 * inactive > active > active referenced > active mapped
 */
unsigned long shrink_all_memory(unsigned long nr_pages)
{
	unsigned long lru_pages, nr_slab;
	unsigned long ret = 0;
	int pass;
	struct reclaim_state reclaim_state;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_swap = 0,
		.swap_cluster_max = nr_pages,
		.may_writepage = 1,
		.swappiness = vm_swappiness,
		.isolate_pages = isolate_pages_global,
	};

	current->reclaim_state = &reclaim_state;

	lru_pages = count_lru_pages();
	nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
	/* If slab caches are huge, it's better to hit them first */
	while (nr_slab >= lru_pages) {
		reclaim_state.reclaimed_slab = 0;
		shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
		if (!reclaim_state.reclaimed_slab)
			break;

		ret += reclaim_state.reclaimed_slab;
		if (ret >= nr_pages)
			goto out;

		nr_slab -= reclaim_state.reclaimed_slab;
	}

	/*
	 * We try to shrink LRUs in 5 passes:
	 * 0 = Reclaim from inactive_list only
	 * 1 = Reclaim from active list but don't reclaim mapped
	 * 2 = 2nd pass of type 1
	 * 3 = Reclaim mapped (normal reclaim)
	 * 4 = 2nd pass of type 3
	 */
	for (pass = 0; pass < 5; pass++) {
		int prio;

		/* Force reclaiming mapped pages in the passes #3 and #4 */
		if (pass > 2) {
			sc.may_swap = 1;
			sc.swappiness = 100;
		}

		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
			unsigned long nr_to_scan = nr_pages - ret;

			sc.nr_scanned = 0;
			ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
			if (ret >= nr_pages)
				goto out;

			reclaim_state.reclaimed_slab = 0;
			shrink_slab(sc.nr_scanned, sc.gfp_mask,
					count_lru_pages());
			ret += reclaim_state.reclaimed_slab;
			if (ret >= nr_pages)
				goto out;

			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
				congestion_wait(WRITE, HZ / 10);
		}
	}

	/*
	 * If ret = 0, we could not shrink LRUs, but there may be something
	 * in slab caches
	 */
	if (!ret) {
		do {
			reclaim_state.reclaimed_slab = 0;
			shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages());
			ret += reclaim_state.reclaimed_slab;
		} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
	}

out:
	current->reclaim_state = NULL;

	return ret;
}
#endif

/* It's optimal to keep kswapds on the same CPUs as their memory, but
   not required for correctness.  So if the last cpu in a node goes
   away, we get changed to run anywhere: as the first one comes back,
   restore their cpu bindings. */
static int __devinit cpu_callback(struct notifier_block *nfb,
				  unsigned long action, void *hcpu)
{
	int nid;

	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
		for_each_node_state(nid, N_HIGH_MEMORY) {
			pg_data_t *pgdat = NODE_DATA(nid);
			node_to_cpumask_ptr(mask, pgdat->node_id);

			if (any_online_cpu(*mask) < nr_cpu_ids)
				/* One of our CPUs online: restore mask */
				set_cpus_allowed_ptr(pgdat->kswapd, mask);
		}
	}
	return NOTIFY_OK;
}

/*
 * This kswapd start function will be called by init and node-hot-add.
 * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
 */
int kswapd_run(int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);
	int ret = 0;

	if (pgdat->kswapd)
		return 0;

	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
	if (IS_ERR(pgdat->kswapd)) {
		/* failure at boot is fatal */
		BUG_ON(system_state == SYSTEM_BOOTING);
		printk("Failed to start kswapd on node %d\n",nid);
		ret = -1;
	}
	return ret;
}

static int __init kswapd_init(void)
{
	int nid;

	swap_setup();
	for_each_node_state(nid, N_HIGH_MEMORY)
 		kswapd_run(nid);
	hotcpu_notifier(cpu_callback, 0);
	return 0;
}

module_init(kswapd_init)

#ifdef CONFIG_NUMA
/*
 * Zone reclaim mode
 *
 * If non-zero call zone_reclaim when the number of free pages falls below
 * the watermarks.
 */
int zone_reclaim_mode __read_mostly;

#define RECLAIM_OFF 0
#define RECLAIM_ZONE (1<<0)	/* Run shrink_cache on the zone */
#define RECLAIM_WRITE (1<<1)	/* Writeout pages during reclaim */
#define RECLAIM_SWAP (1<<2)	/* Swap pages out during reclaim */

/*
 * Priority for ZONE_RECLAIM. This determines the fraction of pages
 * of a node considered for each zone_reclaim. 4 scans 1/16th of
 * a zone.
 */
#define ZONE_RECLAIM_PRIORITY 4

/*
 * Percentage of pages in a zone that must be unmapped for zone_reclaim to
 * occur.
 */
int sysctl_min_unmapped_ratio = 1;

/*
 * If the number of slab pages in a zone grows beyond this percentage then