vmscan.c

			break;
		default:
			/* Look ma, no brain */
			BUG();
		}
		nr[lru] = scan;
	}
}

/*
 * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
 */
static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
	unsigned long nr[NR_LRU_LISTS];
	unsigned long targets[NR_LRU_LISTS];
	unsigned long nr_to_scan;
	enum lru_list lru;
	unsigned long nr_reclaimed = 0;
	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
	struct blk_plug plug;
	bool scan_adjusted = false;

	get_scan_count(lruvec, sc, nr);

	/* Record the original scan target for proportional adjustments later */
	memcpy(targets, nr, sizeof(nr));

	blk_start_plug(&plug);
	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
					nr[LRU_INACTIVE_FILE]) {
		unsigned long nr_anon, nr_file, percentage;
		unsigned long nr_scanned;

		for_each_evictable_lru(lru) {
			if (nr[lru]) {
				nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX);
				nr[lru] -= nr_to_scan;

				nr_reclaimed += shrink_list(lru, nr_to_scan,
							    lruvec, sc);
			}
		}

		if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
			continue;

		/*
		 * For global direct reclaim, reclaim only the number of pages
		 * requested. Less care is taken to scan proportionally as it
		 * is more important to minimise direct reclaim stall latency
		 * than it is to properly age the LRU lists.
		 */
		if (global_reclaim(sc) && !current_is_kswapd())
			break;

		/*
		 * For kswapd and memcg, reclaim at least the number of pages
		 * requested. Ensure that the anon and file LRUs shrink
		 * proportionally what was requested by get_scan_count(). We
		 * stop reclaiming one LRU and reduce the amount scanning
		 * proportional to the original scan target.
		 */
		nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
		nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];

		if (nr_file > nr_anon) {
			unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
						targets[LRU_ACTIVE_ANON] + 1;
			lru = LRU_BASE;
			percentage = nr_anon * 100 / scan_target;
		} else {
			unsigned long scan_target = targets[LRU_INACTIVE_FILE] +
						targets[LRU_ACTIVE_FILE] + 1;
			lru = LRU_FILE;
			percentage = nr_file * 100 / scan_target;
		}

		/* Stop scanning the smaller of the LRU */
		nr[lru] = 0;
		nr[lru + LRU_ACTIVE] = 0;

		/*
		 * Recalculate the other LRU scan count based on its original
		 * scan target and the percentage scanning already complete
		 */
		lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE;
		nr_scanned = targets[lru] - nr[lru];
		nr[lru] = targets[lru] * (100 - percentage) / 100;
		nr[lru] -= min(nr[lru], nr_scanned);

		lru += LRU_ACTIVE;
		nr_scanned = targets[lru] - nr[lru];
		nr[lru] = targets[lru] * (100 - percentage) / 100;
		nr[lru] -= min(nr[lru], nr_scanned);

		scan_adjusted = true;
	}
	blk_finish_plug(&plug);
	sc->nr_reclaimed += nr_reclaimed;

	/*
	 * Even if we did not try to evict anon pages at all, we want to
	 * rebalance the anon lru active/inactive ratio.
	 */
	if (inactive_anon_is_low(lruvec))
		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
				   sc, LRU_ACTIVE_ANON);

	throttle_vm_writeout(sc->gfp_mask);
}

/* Use reclaim/compaction for costly allocs or under memory pressure */
static bool in_reclaim_compaction(struct scan_control *sc)
{
	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
			 sc->priority < DEF_PRIORITY - 2))
		return true;

	return false;
}

/*
 * Reclaim/compaction is used for high-order allocation requests. It reclaims
 * order-0 pages before compacting the zone. should_continue_reclaim() returns
 * true if more pages should be reclaimed such that when the page allocator
 * calls try_to_compact_zone() that it will have enough free pages to succeed.
 * It will give up earlier than that if there is difficulty reclaiming pages.
 */
static inline bool should_continue_reclaim(struct zone *zone,
					unsigned long nr_reclaimed,
					unsigned long nr_scanned,
					struct scan_control *sc)
{
	unsigned long pages_for_compaction;
	unsigned long inactive_lru_pages;

	/* If not in reclaim/compaction mode, stop */
	if (!in_reclaim_compaction(sc))
		return false;

	/* Consider stopping depending on scan and reclaim activity */
	if (sc->gfp_mask & __GFP_REPEAT) {
		/*
		 * For __GFP_REPEAT allocations, stop reclaiming if the
		 * full LRU list has been scanned and we are still failing
		 * to reclaim pages. This full LRU scan is potentially
		 * expensive but a __GFP_REPEAT caller really wants to succeed
		 */
		if (!nr_reclaimed && !nr_scanned)
			return false;
	} else {
		/*
		 * For non-__GFP_REPEAT allocations which can presumably
		 * fail without consequence, stop if we failed to reclaim
		 * any pages from the last SWAP_CLUSTER_MAX number of
		 * pages that were scanned. This will return to the
		 * caller faster at the risk reclaim/compaction and
		 * the resulting allocation attempt fails
		 */
		if (!nr_reclaimed)
			return false;
	}

	/*
	 * If we have not reclaimed enough pages for compaction and the
	 * inactive lists are large enough, continue reclaiming
	 */
	pages_for_compaction = (2UL << sc->order);
	inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE);
	if (get_nr_swap_pages() > 0)
		inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON);
	if (sc->nr_reclaimed < pages_for_compaction &&
			inactive_lru_pages > pages_for_compaction)
		return true;

	/* If compaction would go ahead or the allocation would succeed, stop */
	switch (compaction_suitable(zone, sc->order)) {
	case COMPACT_PARTIAL:
	case COMPACT_CONTINUE:
		return false;
	default:
		return true;
	}
}

static void shrink_zone(struct zone *zone, struct scan_control *sc)
{
	unsigned long nr_reclaimed, nr_scanned;

	do {
		struct mem_cgroup *root = sc->target_mem_cgroup;
		struct mem_cgroup_reclaim_cookie reclaim = {
			.zone = zone,
			.priority = sc->priority,
		};
		struct mem_cgroup *memcg;

		nr_reclaimed = sc->nr_reclaimed;
		nr_scanned = sc->nr_scanned;

		memcg = mem_cgroup_iter(root, NULL, &reclaim);
		do {
			struct lruvec *lruvec;

			lruvec = mem_cgroup_zone_lruvec(zone, memcg);

			shrink_lruvec(lruvec, sc);

			/*
			 * Direct reclaim and kswapd have to scan all memory
			 * cgroups to fulfill the overall scan target for the
			 * zone.
			 *
			 * Limit reclaim, on the other hand, only cares about
			 * nr_to_reclaim pages to be reclaimed and it will
			 * retry with decreasing priority if one round over the
			 * whole hierarchy is not sufficient.
			 */
			if (!global_reclaim(sc) &&
					sc->nr_reclaimed >= sc->nr_to_reclaim) {
				mem_cgroup_iter_break(root, memcg);
				break;
			}
			memcg = mem_cgroup_iter(root, memcg, &reclaim);
		} while (memcg);

		vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
			   sc->nr_scanned - nr_scanned,
			   sc->nr_reclaimed - nr_reclaimed);

	} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
					 sc->nr_scanned - nr_scanned, sc));
}

/* Returns true if compaction should go ahead for a high-order request */
static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
{
	unsigned long balance_gap, watermark;
	bool watermark_ok;

	/* Do not consider compaction for orders reclaim is meant to satisfy */
	if (sc->order <= PAGE_ALLOC_COSTLY_ORDER)
		return false;

	/*
	 * Compaction takes time to run and there are potentially other
	 * callers using the pages just freed. Continue reclaiming until
	 * there is a buffer of free pages available to give compaction
	 * a reasonable chance of completing and allocating the page
	 */
	balance_gap = min(low_wmark_pages(zone),
		(zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
			KSWAPD_ZONE_BALANCE_GAP_RATIO);
	watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order);
	watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0);

	/*
	 * If compaction is deferred, reclaim up to a point where
	 * compaction will have a chance of success when re-enabled
	 */
	if (compaction_deferred(zone, sc->order))
		return watermark_ok;

	/* If compaction is not ready to start, keep reclaiming */
	if (!compaction_suitable(zone, sc->order))
		return false;

	return watermark_ok;
}

/*
 * 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 high_wmark_pages(zone).
 * Because:
 * a) The caller may be trying to free *extra* pages to satisfy a higher-order
 *    allocation or
 * b) The target zone may be at high_wmark_pages(zone) but the lower zones
 *    must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
 *    zone defense algorithm.
 *
 * If a zone is deemed to be full of pinned pages then just give it a light
 * scan then give up on it.
 *
 * This function returns true if a zone is being reclaimed for a costly
 * high-order allocation and compaction is ready to begin. This indicates to
 * the caller that it should consider retrying the allocation instead of
 * further reclaim.
 */
static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
{
	struct zoneref *z;
	struct zone *zone;
	unsigned long nr_soft_reclaimed;
	unsigned long nr_soft_scanned;
	bool aborted_reclaim = false;

	/*
	 * If the number of buffer_heads in the machine exceeds the maximum
	 * allowed level, force direct reclaim to scan the highmem zone as
	 * highmem pages could be pinning lowmem pages storing buffer_heads
	 */
	if (buffer_heads_over_limit)
		sc->gfp_mask |= __GFP_HIGHMEM;

	for_each_zone_zonelist_nodemask(zone, z, zonelist,
					gfp_zone(sc->gfp_mask), sc->nodemask) {
		if (!populated_zone(zone))
			continue;
		/*
		 * Take care memory controller reclaiming has small influence
		 * to global LRU.
		 */
		if (global_reclaim(sc)) {
			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
				continue;
			if (sc->priority != DEF_PRIORITY &&
			    !zone_reclaimable(zone))
				continue;	/* Let kswapd poll it */
			if (IS_ENABLED(CONFIG_COMPACTION)) {
				/*
				 * If we already have plenty of memory free for
				 * compaction in this zone, don't free any more.
				 * Even though compaction is invoked for any
				 * non-zero order, only frequent costly order
				 * reclamation is disruptive enough to become a
				 * noticeable problem, like transparent huge
				 * page allocations.
				 */
				if (compaction_ready(zone, sc)) {
					aborted_reclaim = true;
					continue;
				}
			}
			/*
			 * This steals pages from memory cgroups over softlimit
			 * and returns the number of reclaimed pages and
			 * scanned pages. This works for global memory pressure
			 * and balancing, not for a memcg's limit.
			 */
			nr_soft_scanned = 0;
			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
						sc->order, sc->gfp_mask,
						&nr_soft_scanned);
			sc->nr_reclaimed += nr_soft_reclaimed;
			sc->nr_scanned += nr_soft_scanned;
			/* need some check for avoid more shrink_zone() */
		}

		shrink_zone(zone, sc);
	}

	return aborted_reclaim;
}

/* All zones in zonelist are unreclaimable? */
static bool all_unreclaimable(struct zonelist *zonelist,
		struct scan_control *sc)
{
	struct zoneref *z;
	struct zone *zone;

	for_each_zone_zonelist_nodemask(zone, z, zonelist,
			gfp_zone(sc->gfp_mask), sc->nodemask) {
		if (!populated_zone(zone))
			continue;
		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
			continue;
		if (zone_reclaimable(zone))
			return false;
	}

	return true;
}

/*
 * 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 the writeback threads 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,
					struct shrink_control *shrink)
{
	unsigned long total_scanned = 0;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	struct zoneref *z;
	struct zone *zone;
	unsigned long writeback_threshold;
	bool aborted_reclaim;

	delayacct_freepages_start();

	if (global_reclaim(sc))
		count_vm_event(ALLOCSTALL);

	do {
		vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
				sc->priority);
		sc->nr_scanned = 0;
		aborted_reclaim = shrink_zones(zonelist, sc);

		/*
		 * Don't shrink slabs when reclaiming memory from over limit
		 * cgroups but do shrink slab at least once when aborting
		 * reclaim for compaction to avoid unevenly scanning file/anon
		 * LRU pages over slab pages.
		 */
		if (global_reclaim(sc)) {
			unsigned long lru_pages = 0;

			nodes_clear(shrink->nodes_to_scan);
			for_each_zone_zonelist(zone, z, zonelist,
					gfp_zone(sc->gfp_mask)) {
				if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
					continue;

				lru_pages += zone_reclaimable_pages(zone);
				node_set(zone_to_nid(zone),
					 shrink->nodes_to_scan);
			}

			shrink_slab(shrink, sc->nr_scanned, lru_pages);
			if (reclaim_state) {
				sc->nr_reclaimed += reclaim_state->reclaimed_slab;
				reclaim_state->reclaimed_slab = 0;
			}
		}
		total_scanned += sc->nr_scanned;
		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
			goto out;

		/*
		 * If we're getting trouble reclaiming, start doing
		 * writepage even in laptop mode.
		 */
		if (sc->priority < DEF_PRIORITY - 2)
			sc->may_writepage = 1;

		/*
		 * 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.
		 */
		writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
		if (total_scanned > writeback_threshold) {
			wakeup_flusher_threads(laptop_mode ? 0 : total_scanned,
						WB_REASON_TRY_TO_FREE_PAGES);
			sc->may_writepage = 1;
		}
	} while (--sc->priority >= 0 && !aborted_reclaim);

out:
	delayacct_freepages_end();

	if (sc->nr_reclaimed)
		return sc->nr_reclaimed;

	/*
	 * As hibernation is going on, kswapd is freezed so that it can't mark
	 * the zone into all_unreclaimable. Thus bypassing all_unreclaimable
	 * check.
	 */
	if (oom_killer_disabled)
		return 0;

	/* Aborted reclaim to try compaction? don't OOM, then */
	if (aborted_reclaim)
		return 1;

	/* top priority shrink_zones still had more to do? don't OOM, then */
	if (global_reclaim(sc) && !all_unreclaimable(zonelist, sc))
		return 1;

	return 0;
}

static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
{
	struct zone *zone;
	unsigned long pfmemalloc_reserve = 0;
	unsigned long free_pages = 0;
	int i;
	bool wmark_ok;

	for (i = 0; i <= ZONE_NORMAL; i++) {
		zone = &pgdat->node_zones[i];
		pfmemalloc_reserve += min_wmark_pages(zone);
		free_pages += zone_page_state(zone, NR_FREE_PAGES);
	}

	wmark_ok = free_pages > pfmemalloc_reserve / 2;

	/* kswapd must be awake if processes are being throttled */
	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
		pgdat->classzone_idx = min(pgdat->classzone_idx,
						(enum zone_type)ZONE_NORMAL);
		wake_up_interruptible(&pgdat->kswapd_wait);
	}

	return wmark_ok;
}

/*
 * Throttle direct reclaimers if backing storage is backed by the network
 * and the PFMEMALLOC reserve for the preferred node is getting dangerously
 * depleted. kswapd will continue to make progress and wake the processes
 * when the low watermark is reached.
 *
 * Returns true if a fatal signal was delivered during throttling. If this
 * happens, the page allocator should not consider triggering the OOM killer.
 */
static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
					nodemask_t *nodemask)
{
	struct zone *zone;
	int high_zoneidx = gfp_zone(gfp_mask);
	pg_data_t *pgdat;

	/*
	 * Kernel threads should not be throttled as they may be indirectly
	 * responsible for cleaning pages necessary for reclaim to make forward
	 * progress. kjournald for example may enter direct reclaim while
	 * committing a transaction where throttling it could forcing other
	 * processes to block on log_wait_commit().
	 */
	if (current->flags & PF_KTHREAD)
		goto out;

	/*
	 * If a fatal signal is pending, this process should not throttle.
	 * It should return quickly so it can exit and free its memory
	 */
	if (fatal_signal_pending(current))
		goto out;

	/* Check if the pfmemalloc reserves are ok */
	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
	pgdat = zone->zone_pgdat;
	if (pfmemalloc_watermark_ok(pgdat))
		goto out;

	/* Account for the throttling */
	count_vm_event(PGSCAN_DIRECT_THROTTLE);

	/*
	 * If the caller cannot enter the filesystem, it's possible that it
	 * is due to the caller holding an FS lock or performing a journal
	 * transaction in the case of a filesystem like ext[3|4]. In this case,
	 * it is not safe to block on pfmemalloc_wait as kswapd could be
	 * blocked waiting on the same lock. Instead, throttle for up to a
	 * second before continuing.
	 */
	if (!(gfp_mask & __GFP_FS)) {
		wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
			pfmemalloc_watermark_ok(pgdat), HZ);

		goto check_pending;
	}

	/* Throttle until kswapd wakes the process */
	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
		pfmemalloc_watermark_ok(pgdat));

check_pending:
	if (fatal_signal_pending(current))
		return true;

out:
	return false;
}

unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
				gfp_t gfp_mask, nodemask_t *nodemask)
{
	unsigned long nr_reclaimed;
	struct scan_control sc = {
		.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
		.may_writepage = !laptop_mode,
		.nr_to_reclaim = SWAP_CLUSTER_MAX,
		.may_unmap = 1,
		.may_swap = 1,
		.order = order,
		.priority = DEF_PRIORITY,
		.target_mem_cgroup = NULL,
		.nodemask = nodemask,
	};
	struct shrink_control shrink = {
		.gfp_mask = sc.gfp_mask,
	};

	/*
	 * Do not enter reclaim if fatal signal was delivered while throttled.
	 * 1 is returned so that the page allocator does not OOM kill at this
	 * point.
	 */
	if (throttle_direct_reclaim(gfp_mask, zonelist, nodemask))
		return 1;

	trace_mm_vmscan_direct_reclaim_begin(order,
				sc.may_writepage,
				gfp_mask);

	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);

	trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);

	return nr_reclaimed;
}

#ifdef CONFIG_MEMCG

unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
						gfp_t gfp_mask, bool noswap,
						struct zone *zone,
						unsigned long *nr_scanned)
{
	struct scan_control sc = {
		.nr_scanned = 0,
		.nr_to_reclaim = SWAP_CLUSTER_MAX,
		.may_writepage = !laptop_mode,
		.may_unmap = 1,
		.may_swap = !noswap,
		.order = 0,
		.priority = 0,
		.target_mem_cgroup = memcg,
	};
	struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);

	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);

	trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
						      sc.may_writepage,
						      sc.gfp_mask);

	/*
	 * NOTE: Although we can get the priority field, using it
	 * here is not a good idea, since it limits the pages we can scan.
	 * if we don't reclaim here, the shrink_zone from balance_pgdat
	 * will pick up pages from other mem cgroup's as well. We hack
	 * the priority and make it zero.
	 */
	shrink_lruvec(lruvec, &sc);

	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);

	*nr_scanned = sc.nr_scanned;
	return sc.nr_reclaimed;
}

unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
					   gfp_t gfp_mask,
					   bool noswap)
{
	struct zonelist *zonelist;
	unsigned long nr_reclaimed;
	int nid;
	struct scan_control sc = {
		.may_writepage = !laptop_mode,
		.may_unmap = 1,
		.may_swap = !noswap,
		.nr_to_reclaim = SWAP_CLUSTER_MAX,
		.order = 0,
		.priority = DEF_PRIORITY,
		.target_mem_cgroup = memcg,
		.nodemask = NULL, /* we don't care the placement */
		.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
	};
	struct shrink_control shrink = {
		.gfp_mask = sc.gfp_mask,
	};

	/*
	 * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
	 * take care of from where we get pages. So the node where we start the
	 * scan does not need to be the current node.
	 */
	nid = mem_cgroup_select_victim_node(memcg);

	zonelist = NODE_DATA(nid)->node_zonelists;

	trace_mm_vmscan_memcg_reclaim_begin(0,
					    sc.may_writepage,
					    sc.gfp_mask);

	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);

	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);

	return nr_reclaimed;
}
#endif

static void age_active_anon(struct zone *zone, struct scan_control *sc)
{
	struct mem_cgroup *memcg;

	if (!total_swap_pages)
		return;

	memcg = mem_cgroup_iter(NULL, NULL, NULL);
	do {
		struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);

		if (inactive_anon_is_low(lruvec))
			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
					   sc, LRU_ACTIVE_ANON);

		memcg = mem_cgroup_iter(NULL, memcg, NULL);
	} while (memcg);
}

static bool zone_balanced(struct zone *zone, int order,
			  unsigned long balance_gap, int classzone_idx)
{
	if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone) +
				    balance_gap, classzone_idx, 0))
		return false;

	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
	    !compaction_suitable(zone, order))
		return false;

	return true;
}

/*
 * pgdat_balanced() is used when checking if a node is balanced.
 *
 * For order-0, all zones must be balanced!
 *
 * For high-order allocations only zones that meet watermarks and are in a
 * zone allowed by the callers classzone_idx are added to balanced_pages. The
 * total of balanced pages must be at least 25% of the zones allowed by
 * classzone_idx for the node to be considered balanced. Forcing all zones to
 * be balanced for high orders can cause excessive reclaim when there are
 * imbalanced zones.
 * The choice of 25% is due to
 *   o a 16M DMA zone that is balanced will not balance a zone on any
 *     reasonable sized machine
 *   o On all other machines, the top zone must be at least a reasonable
 *     percentage of the middle zones. For example, on 32-bit x86, highmem
 *     would need to be at least 256M for it to be balance a whole node.
 *     Similarly, on x86-64 the Normal zone would need to be at least 1G
 *     to balance a node on its own. These seemed like reasonable ratios.
 */
static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
{
	unsigned long managed_pages = 0;
	unsigned long balanced_pages = 0;
	int i;

	/* Check the watermark levels */
	for (i = 0; i <= classzone_idx; i++) {
		struct zone *zone = pgdat->node_zones + i;

		if (!populated_zone(zone))
			continue;

		managed_pages += zone->managed_pages;

		/*
		 * A special case here:
		 *
		 * balance_pgdat() skips over all_unreclaimable after
		 * DEF_PRIORITY. Effectively, it considers them balanced so
		 * they must be considered balanced here as well!
		 */
		if (!zone_reclaimable(zone)) {
			balanced_pages += zone->managed_pages;
			continue;
		}

		if (zone_balanced(zone, order, 0, i))
			balanced_pages += zone->managed_pages;
		else if (!order)
			return false;
	}

	if (order)
		return balanced_pages >= (managed_pages >> 2);
	else
		return true;
}

/*
 * Prepare kswapd for sleeping. This verifies that there are no processes
 * waiting in throttle_direct_reclaim() and that watermarks have been met.
 *
 * Returns true if kswapd is ready to sleep
 */
static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
					int classzone_idx)
{
	/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
	if (remaining)
		return false;

	/*
	 * There is a potential race between when kswapd checks its watermarks
	 * and a process gets throttled. There is also a potential race if
	 * processes get throttled, kswapd wakes, a large process exits therby
	 * balancing the zones that causes kswapd to miss a wakeup. If kswapd
	 * is going to sleep, no process should be sleeping on pfmemalloc_wait
	 * so wake them now if necessary. If necessary, processes will wake
	 * kswapd and get throttled again
	 */
	if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
		wake_up(&pgdat->pfmemalloc_wait);
		return false;
	}

	return pgdat_balanced(pgdat, order, classzone_idx);
}

/*
 * kswapd shrinks the zone by the number of pages required to reach
 * the high watermark.
 *
 * Returns true if kswapd scanned at least the requested number of pages to
 * reclaim or if the lack of progress was due to pages under writeback.
 * This is used to determine if the scanning priority needs to be raised.
 */
static bool kswapd_shrink_zone(struct zone *zone,
			       int classzone_idx,
			       struct scan_control *sc,
			       unsigned long lru_pages,
			       unsigned long *nr_attempted)
{
	int testorder = sc->order;
	unsigned long balance_gap;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	struct shrink_control shrink = {
		.gfp_mask = sc->gfp_mask,
	};
	bool lowmem_pressure;

	/* Reclaim above the high watermark. */
	sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone));

	/*
	 * Kswapd reclaims only single pages with compaction enabled. Trying
	 * too hard to reclaim until contiguous free pages have become
	 * available can hurt performance by evicting too much useful data
	 * from memory. Do not reclaim more than needed for compaction.
	 */
	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
			compaction_suitable(zone, sc->order) !=
				COMPACT_SKIPPED)
		testorder = 0;

	/*
	 * We put equal pressure on every zone, unless one zone has way too
	 * many pages free already. The "too many pages" is defined as the
	 * high wmark plus a "gap" where the gap is either the low
	 * watermark or 1% of the zone, whichever is smaller.
	 */
	balance_gap = min(low_wmark_pages(zone),
		(zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
		KSWAPD_ZONE_BALANCE_GAP_RATIO);

	/*
	 * If there is no low memory pressure or the zone is balanced then no
	 * reclaim is necessary
	 */
	lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone));
	if (!lowmem_pressure && zone_balanced(zone, testorder,
						balance_gap, classzone_idx))
		return true;

	shrink_zone(zone, sc);
	nodes_clear(shrink.nodes_to_scan);
	node_set(zone_to_nid(zone), shrink.nodes_to_scan);

	reclaim_state->reclaimed_slab = 0;
	shrink_slab(&shrink, sc->nr_scanned, lru_pages);
	sc->nr_reclaimed += reclaim_state->reclaimed_slab;

	/* Account for the number of pages attempted to reclaim */
	*nr_attempted += sc->nr_to_reclaim;

	zone_clear_flag(zone, ZONE_WRITEBACK);

	/*
	 * If a zone reaches its high watermark, consider it to be no longer
	 * congested. It's possible there are dirty pages backed by congested
	 * BDIs but as pressure is relieved, speculatively avoid congestion
	 * waits.
	 */
	if (zone_reclaimable(zone) &&
	    zone_balanced(zone, testorder, 0, classzone_idx)) {
		zone_clear_flag(zone, ZONE_CONGESTED);
		zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
	}

	return sc->nr_scanned >= sc->nr_to_reclaim;
}

/*
 * For kswapd, balance_pgdat() will work across all this node's zones until
 * they are all at high_wmark_pages(zone).
 *
 * Returns the final order kswapd was reclaiming at
 *
 * 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 > high_wmark_pages(zone), but once a zone is
 * found to have free_pages <= high_wmark_pages(zone), 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 *classzone_idx)
{
	int i;
	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
	unsigned long nr_soft_reclaimed;
	unsigned long nr_soft_scanned;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.priority = DEF_PRIORITY,
		.may_unmap = 1,
		.may_swap = 1,
		.may_writepage = !laptop_mode,
		.order = order,
		.target_mem_cgroup = NULL,
	};
	count_vm_event(PAGEOUTRUN);

	do {
		unsigned long lru_pages = 0;
		unsigned long nr_attempted = 0;
		bool raise_priority = true;
		bool pgdat_needs_compaction = (order > 0);

		sc.nr_reclaimed = 0;

		/*
		 * 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 (sc.priority != DEF_PRIORITY &&
			    !zone_reclaimable(zone))
				continue;

			/*
			 * Do some background aging of the anon list, to give
			 * pages a chance to be referenced before reclaiming.
			 */
			age_active_anon(zone, &sc);

			/*
			 * If the number of buffer_heads in the machine
			 * exceeds the maximum allowed level and this node
			 * has a highmem zone, force kswapd to reclaim from
			 * it to relieve lowmem pressure.
			 */
			if (buffer_heads_over_limit && is_highmem_idx(i)) {
				end_zone = i;
				break;
			}

			if (!zone_balanced(zone, order, 0, 0)) {
				end_zone = i;
				break;
			} else {
				/*