Revert "include/linux/mm_inline.h: fold __update_lru_size() into its sole caller"

[thirdparty/linux.git] / mm / vmscan.c

// SPDX-License-Identifier: GPL-2.0
/*
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Swap reorganised 29.12.95, Stephen Tweedie.
 *  kswapd added: 7.1.96  sct
 *  Removed kswapd_ctl limits, and swap out as many pages as needed
 *  to bring the system back to freepages.high: 2.4.97, Rik van Riel.
 *  Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
 *  Multiqueue VM started 5.8.00, Rik van Riel.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/vmpressure.h>
#include <linux/vmstat.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>	/* for buffer_heads_over_limit */
#include <linux/mm_inline.h>
#include <linux/backing-dev.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/compaction.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/memcontrol.h>
#include <linux/migrate.h>
#include <linux/delayacct.h>
#include <linux/sysctl.h>
#include <linux/oom.h>
#include <linux/pagevec.h>
#include <linux/prefetch.h>
#include <linux/printk.h>
#include <linux/dax.h>
#include <linux/psi.h>

#include <asm/tlbflush.h>
#include <asm/div64.h>

#include <linux/swapops.h>
#include <linux/balloon_compaction.h>
#include <linux/sched/sysctl.h>

#include "internal.h"
#include "swap.h"

#define CREATE_TRACE_POINTS
#include <trace/events/vmscan.h>

struct scan_control {
	/* How many pages shrink_list() should reclaim */
	unsigned long nr_to_reclaim;

	/*
	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
	 * are scanned.
	 */
	nodemask_t	*nodemask;

	/*
	 * The memory cgroup that hit its limit and as a result is the
	 * primary target of this reclaim invocation.
	 */
	struct mem_cgroup *target_mem_cgroup;

	/*
	 * Scan pressure balancing between anon and file LRUs
	 */
	unsigned long	anon_cost;
	unsigned long	file_cost;

	/* Can active pages be deactivated as part of reclaim? */
#define DEACTIVATE_ANON 1
#define DEACTIVATE_FILE 2
	unsigned int may_deactivate:2;
	unsigned int force_deactivate:1;
	unsigned int skipped_deactivate:1;

	/* Writepage batching in laptop mode; RECLAIM_WRITE */
	unsigned int may_writepage:1;

	/* Can mapped pages be reclaimed? */
	unsigned int may_unmap:1;

	/* Can pages be swapped as part of reclaim? */
	unsigned int may_swap:1;

	/* Proactive reclaim invoked by userspace through memory.reclaim */
	unsigned int proactive:1;

	/*
	 * Cgroup memory below memory.low is protected as long as we
	 * don't threaten to OOM. If any cgroup is reclaimed at
	 * reduced force or passed over entirely due to its memory.low
	 * setting (memcg_low_skipped), and nothing is reclaimed as a
	 * result, then go back for one more cycle that reclaims the protected
	 * memory (memcg_low_reclaim) to avert OOM.
	 */
	unsigned int memcg_low_reclaim:1;
	unsigned int memcg_low_skipped:1;

	unsigned int hibernation_mode:1;

	/* One of the zones is ready for compaction */
	unsigned int compaction_ready:1;

	/* There is easily reclaimable cold cache in the current node */
	unsigned int cache_trim_mode:1;

	/* The file pages on the current node are dangerously low */
	unsigned int file_is_tiny:1;

	/* Always discard instead of demoting to lower tier memory */
	unsigned int no_demotion:1;

	/* Allocation order */
	s8 order;

	/* Scan (total_size >> priority) pages at once */
	s8 priority;

	/* The highest zone to isolate pages for reclaim from */
	s8 reclaim_idx;

	/* This context's GFP mask */
	gfp_t gfp_mask;

	/* Incremented by the number of inactive pages that were scanned */
	unsigned long nr_scanned;

	/* Number of pages freed so far during a call to shrink_zones() */
	unsigned long nr_reclaimed;

	struct {
		unsigned int dirty;
		unsigned int unqueued_dirty;
		unsigned int congested;
		unsigned int writeback;
		unsigned int immediate;
		unsigned int file_taken;
		unsigned int taken;
	} nr;

	/* for recording the reclaimed slab by now */
	struct reclaim_state reclaim_state;
};

#ifdef ARCH_HAS_PREFETCHW
#define prefetchw_prev_lru_folio(_folio, _base, _field)			\
	do {								\
		if ((_folio)->lru.prev != _base) {			\
			struct folio *prev;				\
									\
			prev = lru_to_folio(&(_folio->lru));		\
			prefetchw(&prev->_field);			\
		}							\
	} while (0)
#else
#define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0)
#endif

/*
 * From 0 .. 200.  Higher means more swappy.
 */
int vm_swappiness = 60;

static void set_task_reclaim_state(struct task_struct *task,
				   struct reclaim_state *rs)
{
	/* Check for an overwrite */
	WARN_ON_ONCE(rs && task->reclaim_state);

	/* Check for the nulling of an already-nulled member */
	WARN_ON_ONCE(!rs && !task->reclaim_state);

	task->reclaim_state = rs;
}

LIST_HEAD(shrinker_list);
DECLARE_RWSEM(shrinker_rwsem);

#ifdef CONFIG_MEMCG
static int shrinker_nr_max;

/* The shrinker_info is expanded in a batch of BITS_PER_LONG */
static inline int shrinker_map_size(int nr_items)
{
	return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long));
}

static inline int shrinker_defer_size(int nr_items)
{
	return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t));
}

static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
						     int nid)
{
	return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info,
					 lockdep_is_held(&shrinker_rwsem));
}

static int expand_one_shrinker_info(struct mem_cgroup *memcg,
				    int map_size, int defer_size,
				    int old_map_size, int old_defer_size)
{
	struct shrinker_info *new, *old;
	struct mem_cgroup_per_node *pn;
	int nid;
	int size = map_size + defer_size;

	for_each_node(nid) {
		pn = memcg->nodeinfo[nid];
		old = shrinker_info_protected(memcg, nid);
		/* Not yet online memcg */
		if (!old)
			return 0;

		new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
		if (!new)
			return -ENOMEM;

		new->nr_deferred = (atomic_long_t *)(new + 1);
		new->map = (void *)new->nr_deferred + defer_size;

		/* map: set all old bits, clear all new bits */
		memset(new->map, (int)0xff, old_map_size);
		memset((void *)new->map + old_map_size, 0, map_size - old_map_size);
		/* nr_deferred: copy old values, clear all new values */
		memcpy(new->nr_deferred, old->nr_deferred, old_defer_size);
		memset((void *)new->nr_deferred + old_defer_size, 0,
		       defer_size - old_defer_size);

		rcu_assign_pointer(pn->shrinker_info, new);
		kvfree_rcu(old, rcu);
	}

	return 0;
}

void free_shrinker_info(struct mem_cgroup *memcg)
{
	struct mem_cgroup_per_node *pn;
	struct shrinker_info *info;
	int nid;

	for_each_node(nid) {
		pn = memcg->nodeinfo[nid];
		info = rcu_dereference_protected(pn->shrinker_info, true);
		kvfree(info);
		rcu_assign_pointer(pn->shrinker_info, NULL);
	}
}

int alloc_shrinker_info(struct mem_cgroup *memcg)
{
	struct shrinker_info *info;
	int nid, size, ret = 0;
	int map_size, defer_size = 0;

	down_write(&shrinker_rwsem);
	map_size = shrinker_map_size(shrinker_nr_max);
	defer_size = shrinker_defer_size(shrinker_nr_max);
	size = map_size + defer_size;
	for_each_node(nid) {
		info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid);
		if (!info) {
			free_shrinker_info(memcg);
			ret = -ENOMEM;
			break;
		}
		info->nr_deferred = (atomic_long_t *)(info + 1);
		info->map = (void *)info->nr_deferred + defer_size;
		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info);
	}
	up_write(&shrinker_rwsem);

	return ret;
}

static inline bool need_expand(int nr_max)
{
	return round_up(nr_max, BITS_PER_LONG) >
	       round_up(shrinker_nr_max, BITS_PER_LONG);
}

static int expand_shrinker_info(int new_id)
{
	int ret = 0;
	int new_nr_max = new_id + 1;
	int map_size, defer_size = 0;
	int old_map_size, old_defer_size = 0;
	struct mem_cgroup *memcg;

	if (!need_expand(new_nr_max))
		goto out;

	if (!root_mem_cgroup)
		goto out;

	lockdep_assert_held(&shrinker_rwsem);

	map_size = shrinker_map_size(new_nr_max);
	defer_size = shrinker_defer_size(new_nr_max);
	old_map_size = shrinker_map_size(shrinker_nr_max);
	old_defer_size = shrinker_defer_size(shrinker_nr_max);

	memcg = mem_cgroup_iter(NULL, NULL, NULL);
	do {
		ret = expand_one_shrinker_info(memcg, map_size, defer_size,
					       old_map_size, old_defer_size);
		if (ret) {
			mem_cgroup_iter_break(NULL, memcg);
			goto out;
		}
	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
out:
	if (!ret)
		shrinker_nr_max = new_nr_max;

	return ret;
}

void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
{
	if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) {
		struct shrinker_info *info;

		rcu_read_lock();
		info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info);
		/* Pairs with smp mb in shrink_slab() */
		smp_mb__before_atomic();
		set_bit(shrinker_id, info->map);
		rcu_read_unlock();
	}
}

static DEFINE_IDR(shrinker_idr);

static int prealloc_memcg_shrinker(struct shrinker *shrinker)
{
	int id, ret = -ENOMEM;

	if (mem_cgroup_disabled())
		return -ENOSYS;

	down_write(&shrinker_rwsem);
	/* This may call shrinker, so it must use down_read_trylock() */
	id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL);
	if (id < 0)
		goto unlock;

	if (id >= shrinker_nr_max) {
		if (expand_shrinker_info(id)) {
			idr_remove(&shrinker_idr, id);
			goto unlock;
		}
	}
	shrinker->id = id;
	ret = 0;
unlock:
	up_write(&shrinker_rwsem);
	return ret;
}

static void unregister_memcg_shrinker(struct shrinker *shrinker)
{
	int id = shrinker->id;

	BUG_ON(id < 0);

	lockdep_assert_held(&shrinker_rwsem);

	idr_remove(&shrinker_idr, id);
}

static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker,
				   struct mem_cgroup *memcg)
{
	struct shrinker_info *info;

	info = shrinker_info_protected(memcg, nid);
	return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0);
}

static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
				  struct mem_cgroup *memcg)
{
	struct shrinker_info *info;

	info = shrinker_info_protected(memcg, nid);
	return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]);
}

void reparent_shrinker_deferred(struct mem_cgroup *memcg)
{
	int i, nid;
	long nr;
	struct mem_cgroup *parent;
	struct shrinker_info *child_info, *parent_info;

	parent = parent_mem_cgroup(memcg);
	if (!parent)
		parent = root_mem_cgroup;

	/* Prevent from concurrent shrinker_info expand */
	down_read(&shrinker_rwsem);
	for_each_node(nid) {
		child_info = shrinker_info_protected(memcg, nid);
		parent_info = shrinker_info_protected(parent, nid);
		for (i = 0; i < shrinker_nr_max; i++) {
			nr = atomic_long_read(&child_info->nr_deferred[i]);
			atomic_long_add(nr, &parent_info->nr_deferred[i]);
		}
	}
	up_read(&shrinker_rwsem);
}

static bool cgroup_reclaim(struct scan_control *sc)
{
	return sc->target_mem_cgroup;
}

/**
 * writeback_throttling_sane - is the usual dirty throttling mechanism available?
 * @sc: scan_control in question
 *
 * The normal page dirty throttling mechanism in balance_dirty_pages() is
 * completely broken with the legacy memcg and direct stalling in
 * shrink_page_list() is used for throttling instead, which lacks all the
 * niceties such as fairness, adaptive pausing, bandwidth proportional
 * allocation and configurability.
 *
 * This function tests whether the vmscan currently in progress can assume
 * that the normal dirty throttling mechanism is operational.
 */
static bool writeback_throttling_sane(struct scan_control *sc)
{
	if (!cgroup_reclaim(sc))
		return true;
#ifdef CONFIG_CGROUP_WRITEBACK
	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return true;
#endif
	return false;
}
#else
static int prealloc_memcg_shrinker(struct shrinker *shrinker)
{
	return -ENOSYS;
}

static void unregister_memcg_shrinker(struct shrinker *shrinker)
{
}

static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker,
				   struct mem_cgroup *memcg)
{
	return 0;
}

static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
				  struct mem_cgroup *memcg)
{
	return 0;
}

static bool cgroup_reclaim(struct scan_control *sc)
{
	return false;
}

static bool writeback_throttling_sane(struct scan_control *sc)
{
	return true;
}
#endif

static long xchg_nr_deferred(struct shrinker *shrinker,
			     struct shrink_control *sc)
{
	int nid = sc->nid;

	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
		nid = 0;

	if (sc->memcg &&
	    (shrinker->flags & SHRINKER_MEMCG_AWARE))
		return xchg_nr_deferred_memcg(nid, shrinker,
					      sc->memcg);

	return atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
}


static long add_nr_deferred(long nr, struct shrinker *shrinker,
			    struct shrink_control *sc)
{
	int nid = sc->nid;

	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
		nid = 0;

	if (sc->memcg &&
	    (shrinker->flags & SHRINKER_MEMCG_AWARE))
		return add_nr_deferred_memcg(nr, nid, shrinker,
					     sc->memcg);

	return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]);
}

static bool can_demote(int nid, struct scan_control *sc)
{
	if (!numa_demotion_enabled)
		return false;
	if (sc && sc->no_demotion)
		return false;
	if (next_demotion_node(nid) == NUMA_NO_NODE)
		return false;

	return true;
}

static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
					  int nid,
					  struct scan_control *sc)
{
	if (memcg == NULL) {
		/*
		 * For non-memcg reclaim, is there
		 * space in any swap device?
		 */
		if (get_nr_swap_pages() > 0)
			return true;
	} else {
		/* Is the memcg below its swap limit? */
		if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
			return true;
	}

	/*
	 * The page can not be swapped.
	 *
	 * Can it be reclaimed from this node via demotion?
	 */
	return can_demote(nid, sc);
}

/*
 * This misses isolated pages which are not accounted for to save counters.
 * As the data only determines if reclaim or compaction continues, it is
 * not expected that isolated pages will be a dominating factor.
 */
unsigned long zone_reclaimable_pages(struct zone *zone)
{
	unsigned long nr;

	nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
		zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
	if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL))
		nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
			zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);

	return nr;
}

/**
 * lruvec_lru_size -  Returns the number of pages on the given LRU list.
 * @lruvec: lru vector
 * @lru: lru to use
 * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list)
 */
static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru,
				     int zone_idx)
{
	unsigned long size = 0;
	int zid;

	for (zid = 0; zid <= zone_idx; zid++) {
		struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];

		if (!managed_zone(zone))
			continue;

		if (!mem_cgroup_disabled())
			size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
		else
			size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru);
	}
	return size;
}

/*
 * Add a shrinker callback to be called from the vm.
 */
static int __prealloc_shrinker(struct shrinker *shrinker)
{
	unsigned int size;
	int err;

	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
		err = prealloc_memcg_shrinker(shrinker);
		if (err != -ENOSYS)
			return err;

		shrinker->flags &= ~SHRINKER_MEMCG_AWARE;
	}

	size = sizeof(*shrinker->nr_deferred);
	if (shrinker->flags & SHRINKER_NUMA_AWARE)
		size *= nr_node_ids;

	shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
	if (!shrinker->nr_deferred)
		return -ENOMEM;

	return 0;
}

#ifdef CONFIG_SHRINKER_DEBUG
int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
	va_list ap;
	int err;

	va_start(ap, fmt);
	shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
	va_end(ap);
	if (!shrinker->name)
		return -ENOMEM;

	err = __prealloc_shrinker(shrinker);
	if (err) {
		kfree_const(shrinker->name);
		shrinker->name = NULL;
	}

	return err;
}
#else
int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
	return __prealloc_shrinker(shrinker);
}
#endif

void free_prealloced_shrinker(struct shrinker *shrinker)
{
#ifdef CONFIG_SHRINKER_DEBUG
	kfree_const(shrinker->name);
	shrinker->name = NULL;
#endif
	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
		down_write(&shrinker_rwsem);
		unregister_memcg_shrinker(shrinker);
		up_write(&shrinker_rwsem);
		return;
	}

	kfree(shrinker->nr_deferred);
	shrinker->nr_deferred = NULL;
}

void register_shrinker_prepared(struct shrinker *shrinker)
{
	down_write(&shrinker_rwsem);
	list_add_tail(&shrinker->list, &shrinker_list);
	shrinker->flags |= SHRINKER_REGISTERED;
	shrinker_debugfs_add(shrinker);
	up_write(&shrinker_rwsem);
}

static int __register_shrinker(struct shrinker *shrinker)
{
	int err = __prealloc_shrinker(shrinker);

	if (err)
		return err;
	register_shrinker_prepared(shrinker);
	return 0;
}

#ifdef CONFIG_SHRINKER_DEBUG
int register_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
	va_list ap;
	int err;

	va_start(ap, fmt);
	shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
	va_end(ap);
	if (!shrinker->name)
		return -ENOMEM;

	err = __register_shrinker(shrinker);
	if (err) {
		kfree_const(shrinker->name);
		shrinker->name = NULL;
	}
	return err;
}
#else
int register_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
	return __register_shrinker(shrinker);
}
#endif
EXPORT_SYMBOL(register_shrinker);

/*
 * Remove one
 */
void unregister_shrinker(struct shrinker *shrinker)
{
	if (!(shrinker->flags & SHRINKER_REGISTERED))
		return;

	down_write(&shrinker_rwsem);
	list_del(&shrinker->list);
	shrinker->flags &= ~SHRINKER_REGISTERED;
	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
		unregister_memcg_shrinker(shrinker);
	shrinker_debugfs_remove(shrinker);
	up_write(&shrinker_rwsem);

	kfree(shrinker->nr_deferred);
	shrinker->nr_deferred = NULL;
}
EXPORT_SYMBOL(unregister_shrinker);

/**
 * synchronize_shrinkers - Wait for all running shrinkers to complete.
 *
 * This is equivalent to calling unregister_shrink() and register_shrinker(),
 * but atomically and with less overhead. This is useful to guarantee that all
 * shrinker invocations have seen an update, before freeing memory, similar to
 * rcu.
 */
void synchronize_shrinkers(void)
{
	down_write(&shrinker_rwsem);
	up_write(&shrinker_rwsem);
}
EXPORT_SYMBOL(synchronize_shrinkers);

#define SHRINK_BATCH 128

static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
				    struct shrinker *shrinker, int priority)
{
	unsigned long freed = 0;
	unsigned long long delta;
	long total_scan;
	long freeable;
	long nr;
	long new_nr;
	long batch_size = shrinker->batch ? shrinker->batch
					  : SHRINK_BATCH;
	long scanned = 0, next_deferred;

	freeable = shrinker->count_objects(shrinker, shrinkctl);
	if (freeable == 0 || freeable == SHRINK_EMPTY)
		return freeable;

	/*
	 * copy the current shrinker scan count into a local variable
	 * and zero it so that other concurrent shrinker invocations
	 * don't also do this scanning work.
	 */
	nr = xchg_nr_deferred(shrinker, shrinkctl);

	if (shrinker->seeks) {
		delta = freeable >> priority;
		delta *= 4;
		do_div(delta, shrinker->seeks);
	} else {
		/*
		 * These objects don't require any IO to create. Trim
		 * them aggressively under memory pressure to keep
		 * them from causing refetches in the IO caches.
		 */
		delta = freeable / 2;
	}

	total_scan = nr >> priority;
	total_scan += delta;
	total_scan = min(total_scan, (2 * freeable));

	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
				   freeable, delta, total_scan, priority);

	/*
	 * Normally, we should not scan less than batch_size objects in one
	 * pass to avoid too frequent shrinker calls, but if the slab has less
	 * than batch_size objects in total and we are really tight on memory,
	 * we will try to reclaim all available objects, otherwise we can end
	 * up failing allocations although there are plenty of reclaimable
	 * objects spread over several slabs with usage less than the
	 * batch_size.
	 *
	 * We detect the "tight on memory" situations by looking at the total
	 * number of objects we want to scan (total_scan). If it is greater
	 * than the total number of objects on slab (freeable), we must be
	 * scanning at high prio and therefore should try to reclaim as much as
	 * possible.
	 */
	while (total_scan >= batch_size ||
	       total_scan >= freeable) {
		unsigned long ret;
		unsigned long nr_to_scan = min(batch_size, total_scan);

		shrinkctl->nr_to_scan = nr_to_scan;
		shrinkctl->nr_scanned = nr_to_scan;
		ret = shrinker->scan_objects(shrinker, shrinkctl);
		if (ret == SHRINK_STOP)
			break;
		freed += ret;

		count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned);
		total_scan -= shrinkctl->nr_scanned;
		scanned += shrinkctl->nr_scanned;

		cond_resched();
	}

	/*
	 * The deferred work is increased by any new work (delta) that wasn't
	 * done, decreased by old deferred work that was done now.
	 *
	 * And it is capped to two times of the freeable items.
	 */
	next_deferred = max_t(long, (nr + delta - scanned), 0);
	next_deferred = min(next_deferred, (2 * freeable));

	/*
	 * move the unused scan count back into the shrinker in a
	 * manner that handles concurrent updates.
	 */
	new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl);

	trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan);
	return freed;
}

#ifdef CONFIG_MEMCG
static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
			struct mem_cgroup *memcg, int priority)
{
	struct shrinker_info *info;
	unsigned long ret, freed = 0;
	int i;

	if (!mem_cgroup_online(memcg))
		return 0;

	if (!down_read_trylock(&shrinker_rwsem))
		return 0;

	info = shrinker_info_protected(memcg, nid);
	if (unlikely(!info))
		goto unlock;

	for_each_set_bit(i, info->map, shrinker_nr_max) {
		struct shrink_control sc = {
			.gfp_mask = gfp_mask,
			.nid = nid,
			.memcg = memcg,
		};
		struct shrinker *shrinker;

		shrinker = idr_find(&shrinker_idr, i);
		if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) {
			if (!shrinker)
				clear_bit(i, info->map);
			continue;
		}

		/* Call non-slab shrinkers even though kmem is disabled */
		if (!memcg_kmem_enabled() &&
		    !(shrinker->flags & SHRINKER_NONSLAB))
			continue;

		ret = do_shrink_slab(&sc, shrinker, priority);
		if (ret == SHRINK_EMPTY) {
			clear_bit(i, info->map);
			/*
			 * After the shrinker reported that it had no objects to
			 * free, but before we cleared the corresponding bit in
			 * the memcg shrinker map, a new object might have been
			 * added. To make sure, we have the bit set in this
			 * case, we invoke the shrinker one more time and reset
			 * the bit if it reports that it is not empty anymore.
			 * The memory barrier here pairs with the barrier in
			 * set_shrinker_bit():
			 *
			 * list_lru_add()     shrink_slab_memcg()
			 *   list_add_tail()    clear_bit()
			 *   <MB>               <MB>
			 *   set_bit()          do_shrink_slab()
			 */
			smp_mb__after_atomic();
			ret = do_shrink_slab(&sc, shrinker, priority);
			if (ret == SHRINK_EMPTY)
				ret = 0;
			else
				set_shrinker_bit(memcg, nid, i);
		}
		freed += ret;

		if (rwsem_is_contended(&shrinker_rwsem)) {
			freed = freed ? : 1;
			break;
		}
	}
unlock:
	up_read(&shrinker_rwsem);
	return freed;
}
#else /* CONFIG_MEMCG */
static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
			struct mem_cgroup *memcg, int priority)
{
	return 0;
}
#endif /* CONFIG_MEMCG */

/**
 * shrink_slab - shrink slab caches
 * @gfp_mask: allocation context
 * @nid: node whose slab caches to target
 * @memcg: memory cgroup whose slab caches to target
 * @priority: the reclaim priority
 *
 * Call the shrink functions to age shrinkable caches.
 *
 * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set,
 * unaware shrinkers will receive a node id of 0 instead.
 *
 * @memcg specifies the memory cgroup to target. Unaware shrinkers
 * are called only if it is the root cgroup.
 *
 * @priority is sc->priority, we take the number of objects and >> by priority
 * in order to get the scan target.
 *
 * Returns the number of reclaimed slab objects.
 */
static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
				 struct mem_cgroup *memcg,
				 int priority)
{
	unsigned long ret, freed = 0;
	struct shrinker *shrinker;

	/*
	 * The root memcg might be allocated even though memcg is disabled
	 * via "cgroup_disable=memory" boot parameter.  This could make
	 * mem_cgroup_is_root() return false, then just run memcg slab
	 * shrink, but skip global shrink.  This may result in premature
	 * oom.
	 */
	if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
		return shrink_slab_memcg(gfp_mask, nid, memcg, priority);

	if (!down_read_trylock(&shrinker_rwsem))
		goto out;

	list_for_each_entry(shrinker, &shrinker_list, list) {
		struct shrink_control sc = {
			.gfp_mask = gfp_mask,
			.nid = nid,
			.memcg = memcg,
		};

		ret = do_shrink_slab(&sc, shrinker, priority);
		if (ret == SHRINK_EMPTY)
			ret = 0;
		freed += ret;
		/*
		 * Bail out if someone want to register a new shrinker to
		 * prevent the registration from being stalled for long periods
		 * by parallel ongoing shrinking.
		 */
		if (rwsem_is_contended(&shrinker_rwsem)) {
			freed = freed ? : 1;
			break;
		}
	}

	up_read(&shrinker_rwsem);
out:
	cond_resched();
	return freed;
}

static void drop_slab_node(int nid)
{
	unsigned long freed;
	int shift = 0;

	do {
		struct mem_cgroup *memcg = NULL;

		if (fatal_signal_pending(current))
			return;

		freed = 0;
		memcg = mem_cgroup_iter(NULL, NULL, NULL);
		do {
			freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
		} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
	} while ((freed >> shift++) > 1);
}

void drop_slab(void)
{
	int nid;

	for_each_online_node(nid)
		drop_slab_node(nid);
}

static inline int is_page_cache_freeable(struct folio *folio)
{
	/*
	 * A freeable page cache page is referenced only by the caller
	 * that isolated the page, the page cache and optional buffer
	 * heads at page->private.
	 */
	return folio_ref_count(folio) - folio_test_private(folio) ==
		1 + folio_nr_pages(folio);
}

/*
 * We detected a synchronous write error writing a folio out.  Probably
 * -ENOSPC.  We need to propagate that into the address_space for a subsequent
 * fsync(), msync() or close().
 *
 * The tricky part is that after writepage we cannot touch the mapping: nothing
 * prevents it from being freed up.  But we have a ref on the folio and once
 * that folio is locked, the mapping is pinned.
 *
 * We're allowed to run sleeping folio_lock() here because we know the caller has
 * __GFP_FS.
 */
static void handle_write_error(struct address_space *mapping,
				struct folio *folio, int error)
{
	folio_lock(folio);
	if (folio_mapping(folio) == mapping)
		mapping_set_error(mapping, error);
	folio_unlock(folio);
}

static bool skip_throttle_noprogress(pg_data_t *pgdat)
{
	int reclaimable = 0, write_pending = 0;
	int i;

	/*
	 * If kswapd is disabled, reschedule if necessary but do not
	 * throttle as the system is likely near OOM.
	 */
	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
		return true;

	/*
	 * If there are a lot of dirty/writeback pages then do not
	 * throttle as throttling will occur when the pages cycle
	 * towards the end of the LRU if still under writeback.
	 */
	for (i = 0; i < MAX_NR_ZONES; i++) {
		struct zone *zone = pgdat->node_zones + i;

		if (!managed_zone(zone))
			continue;

		reclaimable += zone_reclaimable_pages(zone);
		write_pending += zone_page_state_snapshot(zone,
						  NR_ZONE_WRITE_PENDING);
	}
	if (2 * write_pending <= reclaimable)
		return true;

	return false;
}

void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
{
	wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason];
	long timeout, ret;
	DEFINE_WAIT(wait);

	/*
	 * Do not throttle IO workers, kthreads other than kswapd or
	 * workqueues. They may be required for reclaim to make
	 * forward progress (e.g. journalling workqueues or kthreads).
	 */
	if (!current_is_kswapd() &&
	    current->flags & (PF_IO_WORKER|PF_KTHREAD)) {
		cond_resched();
		return;
	}

	/*
	 * These figures are pulled out of thin air.
	 * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many
	 * parallel reclaimers which is a short-lived event so the timeout is
	 * short. Failing to make progress or waiting on writeback are
	 * potentially long-lived events so use a longer timeout. This is shaky
	 * logic as a failure to make progress could be due to anything from
	 * writeback to a slow device to excessive references pages at the tail
	 * of the inactive LRU.
	 */
	switch(reason) {
	case VMSCAN_THROTTLE_WRITEBACK:
		timeout = HZ/10;

		if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) {
			WRITE_ONCE(pgdat->nr_reclaim_start,
				node_page_state(pgdat, NR_THROTTLED_WRITTEN));
		}

		break;
	case VMSCAN_THROTTLE_CONGESTED:
		fallthrough;
	case VMSCAN_THROTTLE_NOPROGRESS:
		if (skip_throttle_noprogress(pgdat)) {
			cond_resched();
			return;
		}

		timeout = 1;

		break;
	case VMSCAN_THROTTLE_ISOLATED:
		timeout = HZ/50;
		break;
	default:
		WARN_ON_ONCE(1);
		timeout = HZ;
		break;
	}

	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
	ret = schedule_timeout(timeout);
	finish_wait(wqh, &wait);

	if (reason == VMSCAN_THROTTLE_WRITEBACK)
		atomic_dec(&pgdat->nr_writeback_throttled);

	trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout),
				jiffies_to_usecs(timeout - ret),
				reason);
}

/*
 * Account for pages written if tasks are throttled waiting on dirty
 * pages to clean. If enough pages have been cleaned since throttling
 * started then wakeup the throttled tasks.
 */
void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
							int nr_throttled)
{
	unsigned long nr_written;

	node_stat_add_folio(folio, NR_THROTTLED_WRITTEN);

	/*
	 * This is an inaccurate read as the per-cpu deltas may not
	 * be synchronised. However, given that the system is
	 * writeback throttled, it is not worth taking the penalty
	 * of getting an accurate count. At worst, the throttle
	 * timeout guarantees forward progress.
	 */
	nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) -
		READ_ONCE(pgdat->nr_reclaim_start);

	if (nr_written > SWAP_CLUSTER_MAX * nr_throttled)
		wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]);
}

/* possible outcome of pageout() */
typedef enum {
	/* failed to write page out, page is locked */
	PAGE_KEEP,
	/* move page to the active list, page is locked */
	PAGE_ACTIVATE,
	/* page has been sent to the disk successfully, page is unlocked */
	PAGE_SUCCESS,
	/* page is clean and locked */
	PAGE_CLEAN,
} pageout_t;

/*
 * pageout is called by shrink_page_list() for each dirty page.
 * Calls ->writepage().
 */
static pageout_t pageout(struct folio *folio, struct address_space *mapping,
			 struct swap_iocb **plug)
{
	/*
	 * If the folio is dirty, only perform writeback if that write
	 * will be non-blocking.  To prevent this allocation from being
	 * stalled by pagecache activity.  But note that there may be
	 * stalls if we need to run get_block().  We could test
	 * PagePrivate for that.
	 *
	 * If this process is currently in __generic_file_write_iter() against
	 * this folio's queue, we can perform writeback even if that
	 * will block.
	 *
	 * If the folio is swapcache, write it back even if that would
	 * block, for some throttling. This happens by accident, because
	 * swap_backing_dev_info is bust: it doesn't reflect the
	 * congestion state of the swapdevs.  Easy to fix, if needed.
	 */
	if (!is_page_cache_freeable(folio))
		return PAGE_KEEP;
	if (!mapping) {
		/*
		 * Some data journaling orphaned folios can have
		 * folio->mapping == NULL while being dirty with clean buffers.
		 */
		if (folio_test_private(folio)) {
			if (try_to_free_buffers(folio)) {
				folio_clear_dirty(folio);
				pr_info("%s: orphaned folio\n", __func__);
				return PAGE_CLEAN;
			}
		}
		return PAGE_KEEP;
	}
	if (mapping->a_ops->writepage == NULL)
		return PAGE_ACTIVATE;

	if (folio_clear_dirty_for_io(folio)) {
		int res;
		struct writeback_control wbc = {
			.sync_mode = WB_SYNC_NONE,
			.nr_to_write = SWAP_CLUSTER_MAX,
			.range_start = 0,
			.range_end = LLONG_MAX,
			.for_reclaim = 1,
			.swap_plug = plug,
		};

		folio_set_reclaim(folio);
		res = mapping->a_ops->writepage(&folio->page, &wbc);
		if (res < 0)
			handle_write_error(mapping, folio, res);
		if (res == AOP_WRITEPAGE_ACTIVATE) {
			folio_clear_reclaim(folio);
			return PAGE_ACTIVATE;
		}

		if (!folio_test_writeback(folio)) {
			/* synchronous write or broken a_ops? */
			folio_clear_reclaim(folio);
		}
		trace_mm_vmscan_write_folio(folio);
		node_stat_add_folio(folio, NR_VMSCAN_WRITE);
		return PAGE_SUCCESS;
	}

	return PAGE_CLEAN;
}

/*
 * Same as remove_mapping, but if the page is removed from the mapping, it
 * gets returned with a refcount of 0.
 */
static int __remove_mapping(struct address_space *mapping, struct folio *folio,
			    bool reclaimed, struct mem_cgroup *target_memcg)
{
	int refcount;
	void *shadow = NULL;

	BUG_ON(!folio_test_locked(folio));
	BUG_ON(mapping != folio_mapping(folio));

	if (!folio_test_swapcache(folio))
		spin_lock(&mapping->host->i_lock);
	xa_lock_irq(&mapping->i_pages);
	/*
	 * The non racy check for a busy page.
	 *
	 * Must be careful with the order of the tests. When someone has
	 * a ref to the page, it may be possible that they dirty it then
	 * drop the reference. So if PageDirty is tested before page_count
	 * here, then the following race may occur:
	 *
	 * get_user_pages(&page);
	 * [user mapping goes away]
	 * write_to(page);
	 *				!PageDirty(page)    [good]
	 * SetPageDirty(page);
	 * put_page(page);
	 *				!page_count(page)   [good, discard it]
	 *
	 * [oops, our write_to data is lost]
	 *
	 * Reversing the order of the tests ensures such a situation cannot
	 * escape unnoticed. The smp_rmb is needed to ensure the page->flags
	 * load is not satisfied before that of page->_refcount.
	 *
	 * Note that if SetPageDirty is always performed via set_page_dirty,
	 * and thus under the i_pages lock, then this ordering is not required.
	 */
	refcount = 1 + folio_nr_pages(folio);
	if (!folio_ref_freeze(folio, refcount))
		goto cannot_free;
	/* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */
	if (unlikely(folio_test_dirty(folio))) {
		folio_ref_unfreeze(folio, refcount);
		goto cannot_free;
	}

	if (folio_test_swapcache(folio)) {
		swp_entry_t swap = folio_swap_entry(folio);
		mem_cgroup_swapout(folio, swap);
		if (reclaimed && !mapping_exiting(mapping))
			shadow = workingset_eviction(folio, target_memcg);
		__delete_from_swap_cache(folio, swap, shadow);
		xa_unlock_irq(&mapping->i_pages);
		put_swap_page(&folio->page, swap);
	} else {
		void (*free_folio)(struct folio *);

		free_folio = mapping->a_ops->free_folio;
		/*
		 * Remember a shadow entry for reclaimed file cache in
		 * order to detect refaults, thus thrashing, later on.
		 *
		 * But don't store shadows in an address space that is
		 * already exiting.  This is not just an optimization,
		 * inode reclaim needs to empty out the radix tree or
		 * the nodes are lost.  Don't plant shadows behind its
		 * back.
		 *
		 * We also don't store shadows for DAX mappings because the
		 * only page cache pages found in these are zero pages
		 * covering holes, and because we don't want to mix DAX
		 * exceptional entries and shadow exceptional entries in the
		 * same address_space.
		 */
		if (reclaimed && folio_is_file_lru(folio) &&
		    !mapping_exiting(mapping) && !dax_mapping(mapping))
			shadow = workingset_eviction(folio, target_memcg);
		__filemap_remove_folio(folio, shadow);
		xa_unlock_irq(&mapping->i_pages);
		if (mapping_shrinkable(mapping))
			inode_add_lru(mapping->host);
		spin_unlock(&mapping->host->i_lock);

		if (free_folio)
			free_folio(folio);
	}

	return 1;

cannot_free:
	xa_unlock_irq(&mapping->i_pages);
	if (!folio_test_swapcache(folio))
		spin_unlock(&mapping->host->i_lock);
	return 0;
}

/**
 * remove_mapping() - Attempt to remove a folio from its mapping.
 * @mapping: The address space.
 * @folio: The folio to remove.
 *
 * If the folio is dirty, under writeback or if someone else has a ref
 * on it, removal will fail.
 * Return: The number of pages removed from the mapping.  0 if the folio
 * could not be removed.
 * Context: The caller should have a single refcount on the folio and
 * hold its lock.
 */
long remove_mapping(struct address_space *mapping, struct folio *folio)
{
	if (__remove_mapping(mapping, folio, false, NULL)) {
		/*
		 * Unfreezing the refcount with 1 effectively
		 * drops the pagecache ref for us without requiring another
		 * atomic operation.
		 */
		folio_ref_unfreeze(folio, 1);
		return folio_nr_pages(folio);
	}
	return 0;
}

/**
 * folio_putback_lru - Put previously isolated folio onto appropriate LRU list.
 * @folio: Folio to be returned to an LRU list.
 *
 * Add previously isolated @folio to appropriate LRU list.
 * The folio may still be unevictable for other reasons.
 *
 * Context: lru_lock must not be held, interrupts must be enabled.
 */
void folio_putback_lru(struct folio *folio)
{
	folio_add_lru(folio);
	folio_put(folio);		/* drop ref from isolate */
}

enum page_references {
	PAGEREF_RECLAIM,
	PAGEREF_RECLAIM_CLEAN,
	PAGEREF_KEEP,
	PAGEREF_ACTIVATE,
};

static enum page_references folio_check_references(struct folio *folio,
						  struct scan_control *sc)
{
	int referenced_ptes, referenced_folio;
	unsigned long vm_flags;

	referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup,
					   &vm_flags);
	referenced_folio = folio_test_clear_referenced(folio);

	/*
	 * The supposedly reclaimable folio was found to be in a VM_LOCKED vma.
	 * Let the folio, now marked Mlocked, be moved to the unevictable list.
	 */
	if (vm_flags & VM_LOCKED)
		return PAGEREF_ACTIVATE;

	/* rmap lock contention: rotate */
	if (referenced_ptes == -1)
		return PAGEREF_KEEP;

	if (referenced_ptes) {
		/*
		 * All mapped folios start out with page table
		 * references from the instantiating fault, so we need
		 * to look twice if a mapped file/anon folio is used more
		 * than once.
		 *
		 * Mark it and spare it for another trip around the
		 * inactive list.  Another page table reference will
		 * lead to its activation.
		 *
		 * Note: the mark is set for activated folios as well
		 * so that recently deactivated but used folios are
		 * quickly recovered.
		 */
		folio_set_referenced(folio);

		if (referenced_folio || referenced_ptes > 1)
			return PAGEREF_ACTIVATE;

		/*
		 * Activate file-backed executable folios after first usage.
		 */
		if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio))
			return PAGEREF_ACTIVATE;

		return PAGEREF_KEEP;
	}

	/* Reclaim if clean, defer dirty folios to writeback */
	if (referenced_folio && folio_is_file_lru(folio))
		return PAGEREF_RECLAIM_CLEAN;

	return PAGEREF_RECLAIM;
}

/* Check if a page is dirty or under writeback */
static void folio_check_dirty_writeback(struct folio *folio,
				       bool *dirty, bool *writeback)
{
	struct address_space *mapping;

	/*
	 * Anonymous pages are not handled by flushers and must be written
	 * from reclaim context. Do not stall reclaim based on them.
	 * MADV_FREE anonymous pages are put into inactive file list too.
	 * They could be mistakenly treated as file lru. So further anon
	 * test is needed.
	 */
	if (!folio_is_file_lru(folio) ||
	    (folio_test_anon(folio) && !folio_test_swapbacked(folio))) {
		*dirty = false;
		*writeback = false;
		return;
	}

	/* By default assume that the folio flags are accurate */
	*dirty = folio_test_dirty(folio);
	*writeback = folio_test_writeback(folio);

	/* Verify dirty/writeback state if the filesystem supports it */
	if (!folio_test_private(folio))
		return;

	mapping = folio_mapping(folio);
	if (mapping && mapping->a_ops->is_dirty_writeback)
		mapping->a_ops->is_dirty_writeback(folio, dirty, writeback);
}

static struct page *alloc_demote_page(struct page *page, unsigned long node)
{
	struct migration_target_control mtc = {
		/*
		 * Allocate from 'node', or fail quickly and quietly.
		 * When this happens, 'page' will likely just be discarded
		 * instead of migrated.
		 */
		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
			    __GFP_THISNODE  | __GFP_NOWARN |
			    __GFP_NOMEMALLOC | GFP_NOWAIT,
		.nid = node
	};

	return alloc_migration_target(page, (unsigned long)&mtc);
}

/*
 * Take pages on @demote_list and attempt to demote them to
 * another node.  Pages which are not demoted are left on
 * @demote_pages.
 */
static unsigned int demote_page_list(struct list_head *demote_pages,
				     struct pglist_data *pgdat)
{
	int target_nid = next_demotion_node(pgdat->node_id);
	unsigned int nr_succeeded;

	if (list_empty(demote_pages))
		return 0;

	if (target_nid == NUMA_NO_NODE)
		return 0;

	/* Demotion ignores all cpuset and mempolicy settings */
	migrate_pages(demote_pages, alloc_demote_page, NULL,
			    target_nid, MIGRATE_ASYNC, MR_DEMOTION,
			    &nr_succeeded);

	if (current_is_kswapd())
		__count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded);
	else
		__count_vm_events(PGDEMOTE_DIRECT, nr_succeeded);

	return nr_succeeded;
}

static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask)
{
	if (gfp_mask & __GFP_FS)
		return true;
	if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO))
		return false;
	/*
	 * We can "enter_fs" for swap-cache with only __GFP_IO
	 * providing this isn't SWP_FS_OPS.
	 * ->flags can be updated non-atomicially (scan_swap_map_slots),
	 * but that will never affect SWP_FS_OPS, so the data_race
	 * is safe.
	 */
	return !data_race(folio_swap_flags(folio) & SWP_FS_OPS);
}

/*
 * shrink_page_list() returns the number of reclaimed pages
 */
static unsigned int shrink_page_list(struct list_head *page_list,
				     struct pglist_data *pgdat,
				     struct scan_control *sc,
				     struct reclaim_stat *stat,
				     bool ignore_references)
{
	LIST_HEAD(ret_pages);
	LIST_HEAD(free_pages);
	LIST_HEAD(demote_pages);
	unsigned int nr_reclaimed = 0;
	unsigned int pgactivate = 0;
	bool do_demote_pass;
	struct swap_iocb *plug = NULL;

	memset(stat, 0, sizeof(*stat));
	cond_resched();
	do_demote_pass = can_demote(pgdat->node_id, sc);

retry:
	while (!list_empty(page_list)) {
		struct address_space *mapping;
		struct folio *folio;
		enum page_references references = PAGEREF_RECLAIM;
		bool dirty, writeback;
		unsigned int nr_pages;

		cond_resched();

		folio = lru_to_folio(page_list);
		list_del(&folio->lru);

		if (!folio_trylock(folio))
			goto keep;

		VM_BUG_ON_FOLIO(folio_test_active(folio), folio);

		nr_pages = folio_nr_pages(folio);

		/* Account the number of base pages */
		sc->nr_scanned += nr_pages;

		if (unlikely(!folio_evictable(folio)))
			goto activate_locked;

		if (!sc->may_unmap && folio_mapped(folio))
			goto keep_locked;

		/*
		 * The number of dirty pages determines if a node is marked
		 * reclaim_congested. kswapd will stall and start writing
		 * folios if the tail of the LRU is all dirty unqueued folios.
		 */
		folio_check_dirty_writeback(folio, &dirty, &writeback);
		if (dirty || writeback)
			stat->nr_dirty += nr_pages;

		if (dirty && !writeback)
			stat->nr_unqueued_dirty += nr_pages;

		/*
		 * Treat this folio as congested if folios are cycling
		 * through the LRU so quickly that the folios marked
		 * for immediate reclaim are making it to the end of
		 * the LRU a second time.
		 */
		if (writeback && folio_test_reclaim(folio))
			stat->nr_congested += nr_pages;

		/*
		 * If a folio at the tail of the LRU is under writeback, there
		 * are three cases to consider.
		 *
		 * 1) If reclaim is encountering an excessive number
		 *    of folios under writeback and this folio has both
		 *    the writeback and reclaim flags set, then it
		 *    indicates that folios are being queued for I/O but
		 *    are being recycled through the LRU before the I/O
		 *    can complete. Waiting on the folio itself risks an
		 *    indefinite stall if it is impossible to writeback
		 *    the folio due to I/O error or disconnected storage
		 *    so instead note that the LRU is being scanned too
		 *    quickly and the caller can stall after the folio
		 *    list has been processed.
		 *
		 * 2) Global or new memcg reclaim encounters a folio that is
		 *    not marked for immediate reclaim, or the caller does not
		 *    have __GFP_FS (or __GFP_IO if it's simply going to swap,
		 *    not to fs). In this case mark the folio for immediate
		 *    reclaim and continue scanning.
		 *
		 *    Require may_enter_fs() because we would wait on fs, which
		 *    may not have submitted I/O yet. And the loop driver might
		 *    enter reclaim, and deadlock if it waits on a folio for
		 *    which it is needed to do the write (loop masks off
		 *    __GFP_IO|__GFP_FS for this reason); but more thought
		 *    would probably show more reasons.
		 *
		 * 3) Legacy memcg encounters a folio that already has the
		 *    reclaim flag set. memcg does not have any dirty folio
		 *    throttling so we could easily OOM just because too many
		 *    folios are in writeback and there is nothing else to
		 *    reclaim. Wait for the writeback to complete.
		 *
		 * In cases 1) and 2) we activate the folios to get them out of
		 * the way while we continue scanning for clean folios on the
		 * inactive list and refilling from the active list. The
		 * observation here is that waiting for disk writes is more
		 * expensive than potentially causing reloads down the line.
		 * Since they're marked for immediate reclaim, they won't put
		 * memory pressure on the cache working set any longer than it
		 * takes to write them to disk.
		 */
		if (folio_test_writeback(folio)) {
			/* Case 1 above */
			if (current_is_kswapd() &&
			    folio_test_reclaim(folio) &&
			    test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
				stat->nr_immediate += nr_pages;
				goto activate_locked;

			/* Case 2 above */
			} else if (writeback_throttling_sane(sc) ||
			    !folio_test_reclaim(folio) ||
			    !may_enter_fs(folio, sc->gfp_mask)) {
				/*
				 * This is slightly racy -
				 * folio_end_writeback() might have
				 * just cleared the reclaim flag, then
				 * setting the reclaim flag here ends up
				 * interpreted as the readahead flag - but
				 * that does not matter enough to care.
				 * What we do want is for this folio to
				 * have the reclaim flag set next time
				 * memcg reclaim reaches the tests above,
				 * so it will then wait for writeback to
				 * avoid OOM; and it's also appropriate
				 * in global reclaim.
				 */
				folio_set_reclaim(folio);
				stat->nr_writeback += nr_pages;
				goto activate_locked;

			/* Case 3 above */
			} else {
				folio_unlock(folio);
				folio_wait_writeback(folio);
				/* then go back and try same folio again */
				list_add_tail(&folio->lru, page_list);
				continue;
			}
		}

		if (!ignore_references)
			references = folio_check_references(folio, sc);

		switch (references) {
		case PAGEREF_ACTIVATE:
			goto activate_locked;
		case PAGEREF_KEEP:
			stat->nr_ref_keep += nr_pages;
			goto keep_locked;
		case PAGEREF_RECLAIM:
		case PAGEREF_RECLAIM_CLEAN:
			; /* try to reclaim the folio below */
		}

		/*
		 * Before reclaiming the folio, try to relocate
		 * its contents to another node.
		 */
		if (do_demote_pass &&
		    (thp_migration_supported() || !folio_test_large(folio))) {
			list_add(&folio->lru, &demote_pages);
			folio_unlock(folio);
			continue;
		}

		/*
		 * Anonymous process memory has backing store?
		 * Try to allocate it some swap space here.
		 * Lazyfree folio could be freed directly
		 */
		if (folio_test_anon(folio) && folio_test_swapbacked(folio)) {
			if (!folio_test_swapcache(folio)) {
				if (!(sc->gfp_mask & __GFP_IO))
					goto keep_locked;
				if (folio_maybe_dma_pinned(folio))
					goto keep_locked;
				if (folio_test_large(folio)) {
					/* cannot split folio, skip it */
					if (!can_split_folio(folio, NULL))
						goto activate_locked;
					/*
					 * Split folios without a PMD map right
					 * away. Chances are some or all of the
					 * tail pages can be freed without IO.
					 */
					if (!folio_entire_mapcount(folio) &&
					    split_folio_to_list(folio,
								page_list))
						goto activate_locked;
				}
				if (!add_to_swap(folio)) {
					if (!folio_test_large(folio))
						goto activate_locked_split;
					/* Fallback to swap normal pages */
					if (split_folio_to_list(folio,
								page_list))
						goto activate_locked;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
					count_vm_event(THP_SWPOUT_FALLBACK);
#endif
					if (!add_to_swap(folio))
						goto activate_locked_split;
				}
			}
		} else if (folio_test_swapbacked(folio) &&
			   folio_test_large(folio)) {
			/* Split shmem folio */
			if (split_folio_to_list(folio, page_list))
				goto keep_locked;
		}

		/*
		 * If the folio was split above, the tail pages will make
		 * their own pass through this function and be accounted
		 * then.
		 */
		if ((nr_pages > 1) && !folio_test_large(folio)) {
			sc->nr_scanned -= (nr_pages - 1);
			nr_pages = 1;
		}

		/*
		 * The folio is mapped into the page tables of one or more
		 * processes. Try to unmap it here.
		 */
		if (folio_mapped(folio)) {
			enum ttu_flags flags = TTU_BATCH_FLUSH;
			bool was_swapbacked = folio_test_swapbacked(folio);

			if (folio_test_pmd_mappable(folio))
				flags |= TTU_SPLIT_HUGE_PMD;

			try_to_unmap(folio, flags);
			if (folio_mapped(folio)) {
				stat->nr_unmap_fail += nr_pages;
				if (!was_swapbacked &&
				    folio_test_swapbacked(folio))
					stat->nr_lazyfree_fail += nr_pages;
				goto activate_locked;
			}
		}

		mapping = folio_mapping(folio);
		if (folio_test_dirty(folio)) {
			/*
			 * Only kswapd can writeback filesystem folios
			 * to avoid risk of stack overflow. But avoid
			 * injecting inefficient single-folio I/O into
			 * flusher writeback as much as possible: only
			 * write folios when we've encountered many
			 * dirty folios, and when we've already scanned
			 * the rest of the LRU for clean folios and see
			 * the same dirty folios again (with the reclaim
			 * flag set).
			 */
			if (folio_is_file_lru(folio) &&
			    (!current_is_kswapd() ||
			     !folio_test_reclaim(folio) ||
			     !test_bit(PGDAT_DIRTY, &pgdat->flags))) {
				/*
				 * Immediately reclaim when written back.
				 * Similar in principle to deactivate_page()
				 * except we already have the folio isolated
				 * and know it's dirty
				 */
				node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE,
						nr_pages);
				folio_set_reclaim(folio);

				goto activate_locked;
			}

			if (references == PAGEREF_RECLAIM_CLEAN)
				goto keep_locked;
			if (!may_enter_fs(folio, sc->gfp_mask))
				goto keep_locked;
			if (!sc->may_writepage)
				goto keep_locked;

			/*
			 * Folio is dirty. Flush the TLB if a writable entry
			 * potentially exists to avoid CPU writes after I/O
			 * starts and then write it out here.
			 */
			try_to_unmap_flush_dirty();
			switch (pageout(folio, mapping, &plug)) {
			case PAGE_KEEP:
				goto keep_locked;
			case PAGE_ACTIVATE:
				goto activate_locked;
			case PAGE_SUCCESS:
				stat->nr_pageout += nr_pages;

				if (folio_test_writeback(folio))
					goto keep;
				if (folio_test_dirty(folio))
					goto keep;

				/*
				 * A synchronous write - probably a ramdisk.  Go
				 * ahead and try to reclaim the folio.
				 */
				if (!folio_trylock(folio))
					goto keep;
				if (folio_test_dirty(folio) ||
				    folio_test_writeback(folio))
					goto keep_locked;
				mapping = folio_mapping(folio);
				fallthrough;
			case PAGE_CLEAN:
				; /* try to free the folio below */
			}
		}

		/*
		 * If the folio has buffers, try to free the buffer
		 * mappings associated with this folio. If we succeed
		 * we try to free the folio as well.
		 *
		 * We do this even if the folio is dirty.
		 * filemap_release_folio() does not perform I/O, but it
		 * is possible for a folio to have the dirty flag set,
		 * but it is actually clean (all its buffers are clean).
		 * This happens if the buffers were written out directly,
		 * with submit_bh(). ext3 will do this, as well as
		 * the blockdev mapping.  filemap_release_folio() will
		 * discover that cleanness and will drop the buffers
		 * and mark the folio clean - it can be freed.
		 *
		 * Rarely, folios can have buffers and no ->mapping.
		 * These are the folios which were not successfully
		 * invalidated in truncate_cleanup_folio().  We try to
		 * drop those buffers here and if that worked, and the
		 * folio is no longer mapped into process address space
		 * (refcount == 1) it can be freed.  Otherwise, leave
		 * the folio on the LRU so it is swappable.
		 */
		if (folio_has_private(folio)) {
			if (!filemap_release_folio(folio, sc->gfp_mask))
				goto activate_locked;
			if (!mapping && folio_ref_count(folio) == 1) {
				folio_unlock(folio);
				if (folio_put_testzero(folio))
					goto free_it;
				else {
					/*
					 * rare race with speculative reference.
					 * the speculative reference will free
					 * this folio shortly, so we may
					 * increment nr_reclaimed here (and
					 * leave it off the LRU).
					 */
					nr_reclaimed += nr_pages;
					continue;
				}
			}
		}

		if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) {
			/* follow __remove_mapping for reference */
			if (!folio_ref_freeze(folio, 1))
				goto keep_locked;
			/*
			 * The folio has only one reference left, which is
			 * from the isolation. After the caller puts the
			 * folio back on the lru and drops the reference, the
			 * folio will be freed anyway. It doesn't matter
			 * which lru it goes on. So we don't bother checking
			 * the dirty flag here.
			 */
			count_vm_events(PGLAZYFREED, nr_pages);
			count_memcg_folio_events(folio, PGLAZYFREED, nr_pages);
		} else if (!mapping || !__remove_mapping(mapping, folio, true,
							 sc->target_mem_cgroup))
			goto keep_locked;

		folio_unlock(folio);
free_it:
		/*
		 * Folio may get swapped out as a whole, need to account
		 * all pages in it.
		 */
		nr_reclaimed += nr_pages;

		/*
		 * Is there need to periodically free_page_list? It would
		 * appear not as the counts should be low
		 */
		if (unlikely(folio_test_large(folio)))
			destroy_large_folio(folio);
		else
			list_add(&folio->lru, &free_pages);
		continue;

activate_locked_split:
		/*
		 * The tail pages that are failed to add into swap cache
		 * reach here.  Fixup nr_scanned and nr_pages.
		 */
		if (nr_pages > 1) {
			sc->nr_scanned -= (nr_pages - 1);
			nr_pages = 1;
		}
activate_locked:
		/* Not a candidate for swapping, so reclaim swap space. */
		if (folio_test_swapcache(folio) &&
		    (mem_cgroup_swap_full(&folio->page) ||
		     folio_test_mlocked(folio)))
			try_to_free_swap(&folio->page);
		VM_BUG_ON_FOLIO(folio_test_active(folio), folio);
		if (!folio_test_mlocked(folio)) {
			int type = folio_is_file_lru(folio);
			folio_set_active(folio);
			stat->nr_activate[type] += nr_pages;
			count_memcg_folio_events(folio, PGACTIVATE, nr_pages);
		}
keep_locked:
		folio_unlock(folio);
keep:
		list_add(&folio->lru, &ret_pages);
		VM_BUG_ON_FOLIO(folio_test_lru(folio) ||
				folio_test_unevictable(folio), folio);
	}
	/* 'page_list' is always empty here */

	/* Migrate folios selected for demotion */
	nr_reclaimed += demote_page_list(&demote_pages, pgdat);
	/* Folios that could not be demoted are still in @demote_pages */
	if (!list_empty(&demote_pages)) {
		/* Folios which weren't demoted go back on @page_list for retry: */
		list_splice_init(&demote_pages, page_list);
		do_demote_pass = false;
		goto retry;
	}

	pgactivate = stat->nr_activate[0] + stat->nr_activate[1];

	mem_cgroup_uncharge_list(&free_pages);
	try_to_unmap_flush();
	free_unref_page_list(&free_pages);

	list_splice(&ret_pages, page_list);
	count_vm_events(PGACTIVATE, pgactivate);

	if (plug)
		swap_write_unplug(plug);
	return nr_reclaimed;
}

unsigned int reclaim_clean_pages_from_list(struct zone *zone,
					    struct list_head *folio_list)
{
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_unmap = 1,
	};
	struct reclaim_stat stat;
	unsigned int nr_reclaimed;
	struct folio *folio, *next;
	LIST_HEAD(clean_folios);
	unsigned int noreclaim_flag;

	list_for_each_entry_safe(folio, next, folio_list, lru) {
		if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) &&
		    !folio_test_dirty(folio) && !__folio_test_movable(folio) &&
		    !folio_test_unevictable(folio)) {
			folio_clear_active(folio);
			list_move(&folio->lru, &clean_folios);
		}
	}

	/*
	 * We should be safe here since we are only dealing with file pages and
	 * we are not kswapd and therefore cannot write dirty file pages. But
	 * call memalloc_noreclaim_save() anyway, just in case these conditions
	 * change in the future.
	 */
	noreclaim_flag = memalloc_noreclaim_save();
	nr_reclaimed = shrink_page_list(&clean_folios, zone->zone_pgdat, &sc,
					&stat, true);
	memalloc_noreclaim_restore(noreclaim_flag);

	list_splice(&clean_folios, folio_list);
	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
			    -(long)nr_reclaimed);
	/*
	 * Since lazyfree pages are isolated from file LRU from the beginning,
	 * they will rotate back to anonymous LRU in the end if it failed to
	 * discard so isolated count will be mismatched.
	 * Compensate the isolated count for both LRU lists.
	 */
	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
			    stat.nr_lazyfree_fail);
	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
			    -(long)stat.nr_lazyfree_fail);
	return nr_reclaimed;
}

/*
 * Update LRU sizes after isolating pages. The LRU size updates must
 * be complete before mem_cgroup_update_lru_size due to a sanity check.
 */
static __always_inline void update_lru_sizes(struct lruvec *lruvec,
			enum lru_list lru, unsigned long *nr_zone_taken)
{
	int zid;

	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
		if (!nr_zone_taken[zid])
			continue;

		update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
	}

}

/*
 * Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
 *
 * lruvec->lru_lock is heavily contended.  Some of the functions that
 * shrink the lists perform better by taking out a batch of pages
 * and working on them outside the LRU lock.
 *
 * For pagecache intensive workloads, this function is the hottest
 * spot in the kernel (apart from copy_*_user functions).
 *
 * Lru_lock must be held before calling this function.
 *
 * @nr_to_scan:	The number of eligible pages to look through on the list.
 * @lruvec:	The LRU vector to pull pages from.
 * @dst:	The temp list to put pages on to.
 * @nr_scanned:	The number of pages that were scanned.
 * @sc:		The scan_control struct for this reclaim session
 * @lru:	LRU list id for isolating
 *
 * returns how many pages were moved onto *@dst.
 */
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
		struct lruvec *lruvec, struct list_head *dst,
		unsigned long *nr_scanned, struct scan_control *sc,
		enum lru_list lru)
{
	struct list_head *src = &lruvec->lists[lru];
	unsigned long nr_taken = 0;
	unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
	unsigned long skipped = 0;
	unsigned long scan, total_scan, nr_pages;
	LIST_HEAD(folios_skipped);

	total_scan = 0;
	scan = 0;
	while (scan < nr_to_scan && !list_empty(src)) {
		struct list_head *move_to = src;
		struct folio *folio;

		folio = lru_to_folio(src);
		prefetchw_prev_lru_folio(folio, src, flags);

		nr_pages = folio_nr_pages(folio);
		total_scan += nr_pages;

		if (folio_zonenum(folio) > sc->reclaim_idx) {
			nr_skipped[folio_zonenum(folio)] += nr_pages;
			move_to = &folios_skipped;
			goto move;
		}

		/*
		 * Do not count skipped folios because that makes the function
		 * return with no isolated folios if the LRU mostly contains
		 * ineligible folios.  This causes the VM to not reclaim any
		 * folios, triggering a premature OOM.
		 * Account all pages in a folio.
		 */
		scan += nr_pages;

		if (!folio_test_lru(folio))
			goto move;
		if (!sc->may_unmap && folio_mapped(folio))
			goto move;

		/*
		 * Be careful not to clear the lru flag until after we're
		 * sure the folio is not being freed elsewhere -- the
		 * folio release code relies on it.
		 */
		if (unlikely(!folio_try_get(folio)))
			goto move;

		if (!folio_test_clear_lru(folio)) {
			/* Another thread is already isolating this folio */
			folio_put(folio);
			goto move;
		}

		nr_taken += nr_pages;
		nr_zone_taken[folio_zonenum(folio)] += nr_pages;
		move_to = dst;
move:
		list_move(&folio->lru, move_to);
	}

	/*
	 * Splice any skipped folios to the start of the LRU list. Note that
	 * this disrupts the LRU order when reclaiming for lower zones but
	 * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX
	 * scanning would soon rescan the same folios to skip and waste lots
	 * of cpu cycles.
	 */
	if (!list_empty(&folios_skipped)) {
		int zid;

		list_splice(&folios_skipped, src);
		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
			if (!nr_skipped[zid])
				continue;

			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
			skipped += nr_skipped[zid];
		}
	}
	*nr_scanned = total_scan;
	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
				    total_scan, skipped, nr_taken,
				    sc->may_unmap ? 0 : ISOLATE_UNMAPPED, lru);
	update_lru_sizes(lruvec, lru, nr_zone_taken);
	return nr_taken;
}

/**
 * folio_isolate_lru() - Try to isolate a folio from its LRU list.
 * @folio: Folio to isolate from its LRU list.
 *
 * Isolate a @folio from an LRU list and adjust the vmstat statistic
 * corresponding to whatever LRU list the folio was on.
 *
 * The folio will have its LRU flag cleared.  If it was found on the
 * active list, it will have the Active flag set.  If it was found on the
 * unevictable list, it will have the Unevictable flag set.  These flags
 * may need to be cleared by the caller before letting the page go.
 *
 * Context:
 *
 * (1) Must be called with an elevated refcount on the page. This is a
 *     fundamental difference from isolate_lru_pages() (which is called
 *     without a stable reference).
 * (2) The lru_lock must not be held.
 * (3) Interrupts must be enabled.
 *
 * Return: 0 if the folio was removed from an LRU list.
 * -EBUSY if the folio was not on an LRU list.
 */
int folio_isolate_lru(struct folio *folio)
{
	int ret = -EBUSY;

	VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio);

	if (folio_test_clear_lru(folio)) {
		struct lruvec *lruvec;

		folio_get(folio);
		lruvec = folio_lruvec_lock_irq(folio);
		lruvec_del_folio(lruvec, folio);
		unlock_page_lruvec_irq(lruvec);
		ret = 0;
	}

	return ret;
}

/*
 * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
 * then get rescheduled. When there are massive number of tasks doing page
 * allocation, such sleeping direct reclaimers may keep piling up on each CPU,
 * the LRU list will go small and be scanned faster than necessary, leading to
 * unnecessary swapping, thrashing and OOM.
 */
static int too_many_isolated(struct pglist_data *pgdat, int file,
		struct scan_control *sc)
{
	unsigned long inactive, isolated;
	bool too_many;

	if (current_is_kswapd())
		return 0;

	if (!writeback_throttling_sane(sc))
		return 0;

	if (file) {
		inactive = node_page_state(pgdat, NR_INACTIVE_FILE);
		isolated = node_page_state(pgdat, NR_ISOLATED_FILE);
	} else {
		inactive = node_page_state(pgdat, NR_INACTIVE_ANON);
		isolated = node_page_state(pgdat, NR_ISOLATED_ANON);
	}

	/*
	 * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
	 * won't get blocked by normal direct-reclaimers, forming a circular
	 * deadlock.
	 */
	if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
		inactive >>= 3;

	too_many = isolated > inactive;

	/* Wake up tasks throttled due to too_many_isolated. */
	if (!too_many)
		wake_throttle_isolated(pgdat);

	return too_many;
}

/*
 * move_pages_to_lru() moves folios from private @list to appropriate LRU list.
 * On return, @list is reused as a list of folios to be freed by the caller.
 *
 * Returns the number of pages moved to the given lruvec.
 */
static unsigned int move_pages_to_lru(struct lruvec *lruvec,
				      struct list_head *list)
{
	int nr_pages, nr_moved = 0;
	LIST_HEAD(folios_to_free);

	while (!list_empty(list)) {
		struct folio *folio = lru_to_folio(list);

		VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
		list_del(&folio->lru);
		if (unlikely(!folio_evictable(folio))) {
			spin_unlock_irq(&lruvec->lru_lock);
			folio_putback_lru(folio);
			spin_lock_irq(&lruvec->lru_lock);
			continue;
		}

		/*
		 * The folio_set_lru needs to be kept here for list integrity.
		 * Otherwise:
		 *   #0 move_pages_to_lru             #1 release_pages
		 *   if (!folio_put_testzero())
		 *				      if (folio_put_testzero())
		 *				        !lru //skip lru_lock
		 *     folio_set_lru()
		 *     list_add(&folio->lru,)
		 *                                        list_add(&folio->lru,)
		 */
		folio_set_lru(folio);

		if (unlikely(folio_put_testzero(folio))) {
			__folio_clear_lru_flags(folio);

			if (unlikely(folio_test_large(folio))) {
				spin_unlock_irq(&lruvec->lru_lock);
				destroy_large_folio(folio);
				spin_lock_irq(&lruvec->lru_lock);
			} else
				list_add(&folio->lru, &folios_to_free);

			continue;
		}

		/*
		 * All pages were isolated from the same lruvec (and isolation
		 * inhibits memcg migration).
		 */
		VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio);
		lruvec_add_folio(lruvec, folio);
		nr_pages = folio_nr_pages(folio);
		nr_moved += nr_pages;
		if (folio_test_active(folio))
			workingset_age_nonresident(lruvec, nr_pages);
	}

	/*
	 * To save our caller's stack, now use input list for pages to free.
	 */
	list_splice(&folios_to_free, list);

	return nr_moved;
}

/*
 * If a kernel thread (such as nfsd for loop-back mounts) services a backing
 * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case
 * we should not throttle.  Otherwise it is safe to do so.
 */
static int current_may_throttle(void)
{
	return !(current->flags & PF_LOCAL_THROTTLE);
}

/*
 * shrink_inactive_list() is a helper for shrink_node().  It returns the number
 * of reclaimed pages
 */
static unsigned long
shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
		     struct scan_control *sc, enum lru_list lru)
{
	LIST_HEAD(page_list);
	unsigned long nr_scanned;
	unsigned int nr_reclaimed = 0;
	unsigned long nr_taken;
	struct reclaim_stat stat;
	bool file = is_file_lru(lru);
	enum vm_event_item item;
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
	bool stalled = false;

	while (unlikely(too_many_isolated(pgdat, file, sc))) {
		if (stalled)
			return 0;

		/* wait a bit for the reclaimer. */
		stalled = true;
		reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED);

		/* We are about to die and free our memory. Return now. */
		if (fatal_signal_pending(current))
			return SWAP_CLUSTER_MAX;
	}

	lru_add_drain();

	spin_lock_irq(&lruvec->lru_lock);

	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
				     &nr_scanned, sc, lru);

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
	item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
	if (!cgroup_reclaim(sc))
		__count_vm_events(item, nr_scanned);
	__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
	__count_vm_events(PGSCAN_ANON + file, nr_scanned);

	spin_unlock_irq(&lruvec->lru_lock);

	if (nr_taken == 0)
		return 0;

	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);

	spin_lock_irq(&lruvec->lru_lock);
	move_pages_to_lru(lruvec, &page_list);

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
	if (!cgroup_reclaim(sc))
		__count_vm_events(item, nr_reclaimed);
	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
	__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
	spin_unlock_irq(&lruvec->lru_lock);

	lru_note_cost(lruvec, file, stat.nr_pageout);
	mem_cgroup_uncharge_list(&page_list);
	free_unref_page_list(&page_list);

	/*
	 * If dirty pages are scanned that are not queued for IO, it
	 * implies that flushers are not doing their job. This can
	 * happen when memory pressure pushes dirty pages to the end of
	 * the LRU before the dirty limits are breached and the dirty
	 * data has expired. It can also happen when the proportion of
	 * dirty pages grows not through writes but through memory
	 * pressure reclaiming all the clean cache. And in some cases,
	 * the flushers simply cannot keep up with the allocation
	 * rate. Nudge the flusher threads in case they are asleep.
	 */
	if (stat.nr_unqueued_dirty == nr_taken)
		wakeup_flusher_threads(WB_REASON_VMSCAN);

	sc->nr.dirty += stat.nr_dirty;
	sc->nr.congested += stat.nr_congested;
	sc->nr.unqueued_dirty += stat.nr_unqueued_dirty;
	sc->nr.writeback += stat.nr_writeback;
	sc->nr.immediate += stat.nr_immediate;
	sc->nr.taken += nr_taken;
	if (file)
		sc->nr.file_taken += nr_taken;

	trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
			nr_scanned, nr_reclaimed, &stat, sc->priority, file);
	return nr_reclaimed;
}

/*
 * shrink_active_list() moves folios from the active LRU to the inactive LRU.
 *
 * We move them the other way if the folio is referenced by one or more
 * processes.
 *
 * If the folios are mostly unmapped, the processing is fast and it is
 * appropriate to hold lru_lock across the whole operation.  But if
 * the folios are mapped, the processing is slow (folio_referenced()), so
 * we should drop lru_lock around each folio.  It's impossible to balance
 * this, so instead we remove the folios from the LRU while processing them.
 * It is safe to rely on the active flag against the non-LRU folios in here
 * because nobody will play with that bit on a non-LRU folio.
 *
 * The downside is that we have to touch folio->_refcount against each folio.
 * But we had to alter folio->flags anyway.
 */
static void shrink_active_list(unsigned long nr_to_scan,
			       struct lruvec *lruvec,
			       struct scan_control *sc,
			       enum lru_list lru)
{
	unsigned long nr_taken;
	unsigned long nr_scanned;
	unsigned long vm_flags;
	LIST_HEAD(l_hold);	/* The folios which were snipped off */
	LIST_HEAD(l_active);
	LIST_HEAD(l_inactive);
	unsigned nr_deactivate, nr_activate;
	unsigned nr_rotated = 0;
	int file = is_file_lru(lru);
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);

	lru_add_drain();

	spin_lock_irq(&lruvec->lru_lock);

	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
				     &nr_scanned, sc, lru);

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);

	if (!cgroup_reclaim(sc))
		__count_vm_events(PGREFILL, nr_scanned);
	__count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);

	spin_unlock_irq(&lruvec->lru_lock);

	while (!list_empty(&l_hold)) {
		struct folio *folio;

		cond_resched();
		folio = lru_to_folio(&l_hold);
		list_del(&folio->lru);

		if (unlikely(!folio_evictable(folio))) {
			folio_putback_lru(folio);
			continue;
		}

		if (unlikely(buffer_heads_over_limit)) {
			if (folio_test_private(folio) && folio_trylock(folio)) {
				if (folio_test_private(folio))
					filemap_release_folio(folio, 0);
				folio_unlock(folio);
			}
		}

		/* Referenced or rmap lock contention: rotate */
		if (folio_referenced(folio, 0, sc->target_mem_cgroup,
				     &vm_flags) != 0) {
			/*
			 * Identify referenced, file-backed active folios and
			 * give them one more trip around the active list. So
			 * that executable code get better chances to stay in
			 * memory under moderate memory pressure.  Anon folios
			 * are not likely to be evicted by use-once streaming
			 * IO, plus JVM can create lots of anon VM_EXEC folios,
			 * so we ignore them here.
			 */
			if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) {
				nr_rotated += folio_nr_pages(folio);
				list_add(&folio->lru, &l_active);
				continue;
			}
		}

		folio_clear_active(folio);	/* we are de-activating */
		folio_set_workingset(folio);
		list_add(&folio->lru, &l_inactive);
	}

	/*
	 * Move folios back to the lru list.
	 */
	spin_lock_irq(&lruvec->lru_lock);

	nr_activate = move_pages_to_lru(lruvec, &l_active);
	nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
	/* Keep all free folios in l_active list */
	list_splice(&l_inactive, &l_active);

	__count_vm_events(PGDEACTIVATE, nr_deactivate);
	__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
	spin_unlock_irq(&lruvec->lru_lock);

	mem_cgroup_uncharge_list(&l_active);
	free_unref_page_list(&l_active);
	trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
			nr_deactivate, nr_rotated, sc->priority, file);
}

static unsigned int reclaim_page_list(struct list_head *page_list,
				      struct pglist_data *pgdat)
{
	struct reclaim_stat dummy_stat;
	unsigned int nr_reclaimed;
	struct folio *folio;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_writepage = 1,
		.may_unmap = 1,
		.may_swap = 1,
		.no_demotion = 1,
	};

	nr_reclaimed = shrink_page_list(page_list, pgdat, &sc, &dummy_stat, false);
	while (!list_empty(page_list)) {
		folio = lru_to_folio(page_list);
		list_del(&folio->lru);
		folio_putback_lru(folio);
	}

	return nr_reclaimed;
}

unsigned long reclaim_pages(struct list_head *folio_list)
{
	int nid;
	unsigned int nr_reclaimed = 0;
	LIST_HEAD(node_folio_list);
	unsigned int noreclaim_flag;

	if (list_empty(folio_list))
		return nr_reclaimed;

	noreclaim_flag = memalloc_noreclaim_save();

	nid = folio_nid(lru_to_folio(folio_list));
	do {
		struct folio *folio = lru_to_folio(folio_list);

		if (nid == folio_nid(folio)) {
			folio_clear_active(folio);
			list_move(&folio->lru, &node_folio_list);
			continue;
		}

		nr_reclaimed += reclaim_page_list(&node_folio_list, NODE_DATA(nid));
		nid = folio_nid(lru_to_folio(folio_list));
	} while (!list_empty(folio_list));

	nr_reclaimed += reclaim_page_list(&node_folio_list, NODE_DATA(nid));

	memalloc_noreclaim_restore(noreclaim_flag);

	return nr_reclaimed;
}

static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
				 struct lruvec *lruvec, struct scan_control *sc)
{
	if (is_active_lru(lru)) {
		if (sc->may_deactivate & (1 << is_file_lru(lru)))
			shrink_active_list(nr_to_scan, lruvec, sc, lru);
		else
			sc->skipped_deactivate = 1;
		return 0;
	}

	return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
}

/*
 * The inactive anon list should be small enough that the VM never has
 * to do too much work.
 *
 * The inactive file list should be small enough to leave most memory
 * to the established workingset on the scan-resistant active list,
 * but large enough to avoid thrashing the aggregate readahead window.
 *
 * Both inactive lists should also be large enough that each inactive
 * page has a chance to be referenced again before it is reclaimed.
 *
 * If that fails and refaulting is observed, the inactive list grows.
 *
 * The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages
 * on this LRU, maintained by the pageout code. An inactive_ratio
 * of 3 means 3:1 or 25% of the pages are kept on the inactive list.
 *
 * total     target    max
 * memory    ratio     inactive
 * -------------------------------------
 *   10MB       1         5MB
 *  100MB       1        50MB
 *    1GB       3       250MB
 *   10GB      10       0.9GB
 *  100GB      31         3GB
 *    1TB     101        10GB
 *   10TB     320        32GB
 */
static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru)
{
	enum lru_list active_lru = inactive_lru + LRU_ACTIVE;
	unsigned long inactive, active;
	unsigned long inactive_ratio;
	unsigned long gb;

	inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru);
	active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru);

	gb = (inactive + active) >> (30 - PAGE_SHIFT);
	if (gb)
		inactive_ratio = int_sqrt(10 * gb);
	else
		inactive_ratio = 1;

	return inactive * inactive_ratio < active;
}

enum scan_balance {
	SCAN_EQUAL,
	SCAN_FRACT,
	SCAN_ANON,
	SCAN_FILE,
};

static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc)
{
	unsigned long file;
	struct lruvec *target_lruvec;

	target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);

	/*
	 * Flush the memory cgroup stats, so that we read accurate per-memcg
	 * lruvec stats for heuristics.
	 */
	mem_cgroup_flush_stats();

	/*
	 * Determine the scan balance between anon and file LRUs.
	 */
	spin_lock_irq(&target_lruvec->lru_lock);
	sc->anon_cost = target_lruvec->anon_cost;
	sc->file_cost = target_lruvec->file_cost;
	spin_unlock_irq(&target_lruvec->lru_lock);

	/*
	 * Target desirable inactive:active list ratios for the anon
	 * and file LRU lists.
	 */
	if (!sc->force_deactivate) {
		unsigned long refaults;

		/*
		 * When refaults are being observed, it means a new
		 * workingset is being established. Deactivate to get
		 * rid of any stale active pages quickly.
		 */
		refaults = lruvec_page_state(target_lruvec,
				WORKINGSET_ACTIVATE_ANON);
		if (refaults != target_lruvec->refaults[WORKINGSET_ANON] ||
			inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
			sc->may_deactivate |= DEACTIVATE_ANON;
		else
			sc->may_deactivate &= ~DEACTIVATE_ANON;

		refaults = lruvec_page_state(target_lruvec,
				WORKINGSET_ACTIVATE_FILE);
		if (refaults != target_lruvec->refaults[WORKINGSET_FILE] ||
		    inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
			sc->may_deactivate |= DEACTIVATE_FILE;
		else
			sc->may_deactivate &= ~DEACTIVATE_FILE;
	} else
		sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE;

	/*
	 * If we have plenty of inactive file pages that aren't
	 * thrashing, try to reclaim those first before touching
	 * anonymous pages.
	 */
	file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
	if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
		sc->cache_trim_mode = 1;
	else
		sc->cache_trim_mode = 0;

	/*
	 * Prevent the reclaimer from falling into the cache trap: as
	 * cache pages start out inactive, every cache fault will tip
	 * the scan balance towards the file LRU.  And as the file LRU
	 * shrinks, so does the window for rotation from references.
	 * This means we have a runaway feedback loop where a tiny
	 * thrashing file LRU becomes infinitely more attractive than
	 * anon pages.  Try to detect this based on file LRU size.
	 */
	if (!cgroup_reclaim(sc)) {
		unsigned long total_high_wmark = 0;
		unsigned long free, anon;
		int z;

		free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
		file = node_page_state(pgdat, NR_ACTIVE_FILE) +
			   node_page_state(pgdat, NR_INACTIVE_FILE);

		for (z = 0; z < MAX_NR_ZONES; z++) {
			struct zone *zone = &pgdat->node_zones[z];

			if (!managed_zone(zone))
				continue;

			total_high_wmark += high_wmark_pages(zone);
		}

		/*
		 * Consider anon: if that's low too, this isn't a
		 * runaway file reclaim problem, but rather just
		 * extreme pressure. Reclaim as per usual then.
		 */
		anon = node_page_state(pgdat, NR_INACTIVE_ANON);

		sc->file_is_tiny =
			file + free <= total_high_wmark &&
			!(sc->may_deactivate & DEACTIVATE_ANON) &&
			anon >> sc->priority;
	}
}

/*
 * Determine how aggressively the anon and file LRU lists should be
 * scanned.
 *
 * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan
 * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan
 */
static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
			   unsigned long *nr)
{
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
	unsigned long anon_cost, file_cost, total_cost;
	int swappiness = mem_cgroup_swappiness(memcg);
	u64 fraction[ANON_AND_FILE];
	u64 denominator = 0;	/* gcc */
	enum scan_balance scan_balance;
	unsigned long ap, fp;
	enum lru_list lru;

	/* If we have no swap space, do not bother scanning anon pages. */
	if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) {
		scan_balance = SCAN_FILE;
		goto out;
	}

	/*
	 * Global reclaim will swap to prevent OOM even with no
	 * swappiness, but memcg users want to use this knob to
	 * disable swapping for individual groups completely when
	 * using the memory controller's swap limit feature would be
	 * too expensive.
	 */
	if (cgroup_reclaim(sc) && !swappiness) {
		scan_balance = SCAN_FILE;
		goto out;
	}

	/*
	 * Do not apply any pressure balancing cleverness when the
	 * system is close to OOM, scan both anon and file equally
	 * (unless the swappiness setting disagrees with swapping).
	 */
	if (!sc->priority && swappiness) {
		scan_balance = SCAN_EQUAL;
		goto out;
	}

	/*
	 * If the system is almost out of file pages, force-scan anon.
	 */
	if (sc->file_is_tiny) {
		scan_balance = SCAN_ANON;
		goto out;
	}

	/*
	 * If there is enough inactive page cache, we do not reclaim
	 * anything from the anonymous working right now.
	 */
	if (sc->cache_trim_mode) {
		scan_balance = SCAN_FILE;
		goto out;
	}

	scan_balance = SCAN_FRACT;
	/*
	 * Calculate the pressure balance between anon and file pages.
	 *
	 * The amount of pressure we put on each LRU is inversely
	 * proportional to the cost of reclaiming each list, as
	 * determined by the share of pages that are refaulting, times
	 * the relative IO cost of bringing back a swapped out
	 * anonymous page vs reloading a filesystem page (swappiness).
	 *
	 * Although we limit that influence to ensure no list gets
	 * left behind completely: at least a third of the pressure is
	 * applied, before swappiness.
	 *
	 * With swappiness at 100, anon and file have equal IO cost.
	 */
	total_cost = sc->anon_cost + sc->file_cost;
	anon_cost = total_cost + sc->anon_cost;
	file_cost = total_cost + sc->file_cost;
	total_cost = anon_cost + file_cost;

	ap = swappiness * (total_cost + 1);
	ap /= anon_cost + 1;

	fp = (200 - swappiness) * (total_cost + 1);
	fp /= file_cost + 1;

	fraction[0] = ap;
	fraction[1] = fp;
	denominator = ap + fp;
out:
	for_each_evictable_lru(lru) {
		int file = is_file_lru(lru);
		unsigned long lruvec_size;
		unsigned long low, min;
		unsigned long scan;

		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
		mem_cgroup_protection(sc->target_mem_cgroup, memcg,
				      &min, &low);

		if (min || low) {
			/*
			 * Scale a cgroup's reclaim pressure by proportioning
			 * its current usage to its memory.low or memory.min
			 * setting.
			 *
			 * This is important, as otherwise scanning aggression
			 * becomes extremely binary -- from nothing as we
			 * approach the memory protection threshold, to totally
			 * nominal as we exceed it.  This results in requiring
			 * setting extremely liberal protection thresholds. It
			 * also means we simply get no protection at all if we
			 * set it too low, which is not ideal.
			 *
			 * If there is any protection in place, we reduce scan
			 * pressure by how much of the total memory used is
			 * within protection thresholds.
			 *
			 * There is one special case: in the first reclaim pass,
			 * we skip over all groups that are within their low
			 * protection. If that fails to reclaim enough pages to
			 * satisfy the reclaim goal, we come back and override
			 * the best-effort low protection. However, we still
			 * ideally want to honor how well-behaved groups are in
			 * that case instead of simply punishing them all
			 * equally. As such, we reclaim them based on how much
			 * memory they are using, reducing the scan pressure
			 * again by how much of the total memory used is under
			 * hard protection.
			 */
			unsigned long cgroup_size = mem_cgroup_size(memcg);
			unsigned long protection;

			/* memory.low scaling, make sure we retry before OOM */
			if (!sc->memcg_low_reclaim && low > min) {
				protection = low;
				sc->memcg_low_skipped = 1;
			} else {
				protection = min;
			}

			/* Avoid TOCTOU with earlier protection check */
			cgroup_size = max(cgroup_size, protection);

			scan = lruvec_size - lruvec_size * protection /
				(cgroup_size + 1);

			/*
			 * Minimally target SWAP_CLUSTER_MAX pages to keep
			 * reclaim moving forwards, avoiding decrementing
			 * sc->priority further than desirable.
			 */
			scan = max(scan, SWAP_CLUSTER_MAX);
		} else {
			scan = lruvec_size;
		}

		scan >>= sc->priority;

		/*
		 * If the cgroup's already been deleted, make sure to
		 * scrape out the remaining cache.
		 */
		if (!scan && !mem_cgroup_online(memcg))
			scan = min(lruvec_size, SWAP_CLUSTER_MAX);

		switch (scan_balance) {
		case SCAN_EQUAL:
			/* Scan lists relative to size */
			break;
		case SCAN_FRACT:
			/*
			 * Scan types proportional to swappiness and
			 * their relative recent reclaim efficiency.
			 * Make sure we don't miss the last page on
			 * the offlined memory cgroups because of a
			 * round-off error.
			 */
			scan = mem_cgroup_online(memcg) ?
			       div64_u64(scan * fraction[file], denominator) :
			       DIV64_U64_ROUND_UP(scan * fraction[file],
						  denominator);
			break;
		case SCAN_FILE:
		case SCAN_ANON:
			/* Scan one type exclusively */
			if ((scan_balance == SCAN_FILE) != file)
				scan = 0;
			break;
		default:
			/* Look ma, no brain */
			BUG();
		}

		nr[lru] = scan;
	}
}

/*
 * Anonymous LRU management is a waste if there is
 * ultimately no way to reclaim the memory.
 */
static bool can_age_anon_pages(struct pglist_data *pgdat,
			       struct scan_control *sc)
{
	/* Aging the anon LRU is valuable if swap is present: */
	if (total_swap_pages > 0)
		return true;

	/* Also valuable if anon pages can be demoted: */
	return can_demote(pgdat->node_id, sc);
}

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;

	get_scan_count(lruvec, sc, nr);

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

	/*
	 * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
	 * event that can occur when there is little memory pressure e.g.
	 * multiple streaming readers/writers. Hence, we do not abort scanning
	 * when the requested number of pages are reclaimed when scanning at
	 * DEF_PRIORITY on the assumption that the fact we are direct
	 * reclaiming implies that kswapd is not keeping up and it is best to
	 * do a batch of work at once. For memcg reclaim one check is made to
	 * abort proportional reclaim if either the file or anon lru has already
	 * dropped to zero at the first pass.
	 */
	scan_adjusted = (!cgroup_reclaim(sc) && !current_is_kswapd() &&
			 sc->priority == DEF_PRIORITY);

	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);
			}
		}

		cond_resched();

		if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
			continue;

		/*
		 * For kswapd and memcg, reclaim at least the number of pages
		 * requested. Ensure that the anon and file LRUs are scanned
		 * 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];

		/*
		 * It's just vindictive to attack the larger once the smaller
		 * has gone to zero.  And given the way we stop scanning the
		 * smaller below, this makes sure that we only make one nudge
		 * towards proportionality once we've got nr_to_reclaim.
		 */
		if (!nr_file || !nr_anon)
			break;

		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 (can_age_anon_pages(lruvec_pgdat(lruvec), sc) &&
	    inactive_is_low(lruvec, LRU_INACTIVE_ANON))
		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
				   sc, LRU_ACTIVE_ANON);
}

/* 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_pages() 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 pglist_data *pgdat,
					unsigned long nr_reclaimed,
					struct scan_control *sc)
{
	unsigned long pages_for_compaction;
	unsigned long inactive_lru_pages;
	int z;

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

	/*
	 * 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
	 * with the risk reclaim/compaction and the resulting allocation attempt
	 * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL
	 * allocations through requiring that the full LRU list has been scanned
	 * first, by assuming that zero delta of sc->nr_scanned means full LRU
	 * scan, but that approximation was wrong, and there were corner cases
	 * where always a non-zero amount of pages were scanned.
	 */
	if (!nr_reclaimed)
		return false;

	/* If compaction would go ahead or the allocation would succeed, stop */
	for (z = 0; z <= sc->reclaim_idx; z++) {
		struct zone *zone = &pgdat->node_zones[z];
		if (!managed_zone(zone))
			continue;

		switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
		case COMPACT_SUCCESS:
		case COMPACT_CONTINUE:
			return false;
		default:
			/* check next zone */
			;
		}
	}

	/*
	 * If we have not reclaimed enough pages for compaction and the
	 * inactive lists are large enough, continue reclaiming
	 */
	pages_for_compaction = compact_gap(sc->order);
	inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
	if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
		inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);

	return inactive_lru_pages > pages_for_compaction;
}

static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
{
	struct mem_cgroup *target_memcg = sc->target_mem_cgroup;
	struct mem_cgroup *memcg;

	memcg = mem_cgroup_iter(target_memcg, NULL, NULL);
	do {
		struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
		unsigned long reclaimed;
		unsigned long scanned;

		/*
		 * This loop can become CPU-bound when target memcgs
		 * aren't eligible for reclaim - either because they
		 * don't have any reclaimable pages, or because their
		 * memory is explicitly protected. Avoid soft lockups.
		 */
		cond_resched();

		mem_cgroup_calculate_protection(target_memcg, memcg);

		if (mem_cgroup_below_min(memcg)) {
			/*
			 * Hard protection.
			 * If there is no reclaimable memory, OOM.
			 */
			continue;
		} else if (mem_cgroup_below_low(memcg)) {
			/*
			 * Soft protection.
			 * Respect the protection only as long as
			 * there is an unprotected supply
			 * of reclaimable memory from other cgroups.
			 */
			if (!sc->memcg_low_reclaim) {
				sc->memcg_low_skipped = 1;
				continue;
			}
			memcg_memory_event(memcg, MEMCG_LOW);
		}

		reclaimed = sc->nr_reclaimed;
		scanned = sc->nr_scanned;

		shrink_lruvec(lruvec, sc);

		shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
			    sc->priority);

		/* Record the group's reclaim efficiency */
		if (!sc->proactive)
			vmpressure(sc->gfp_mask, memcg, false,
				   sc->nr_scanned - scanned,
				   sc->nr_reclaimed - reclaimed);

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

static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
{
	struct reclaim_state *reclaim_state = current->reclaim_state;
	unsigned long nr_reclaimed, nr_scanned;
	struct lruvec *target_lruvec;
	bool reclaimable = false;

	target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);

again:
	memset(&sc->nr, 0, sizeof(sc->nr));

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

	prepare_scan_count(pgdat, sc);

	shrink_node_memcgs(pgdat, sc);

	if (reclaim_state) {
		sc->nr_reclaimed += reclaim_state->reclaimed_slab;
		reclaim_state->reclaimed_slab = 0;
	}

	/* Record the subtree's reclaim efficiency */
	if (!sc->proactive)
		vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
			   sc->nr_scanned - nr_scanned,
			   sc->nr_reclaimed - nr_reclaimed);

	if (sc->nr_reclaimed - nr_reclaimed)
		reclaimable = true;

	if (current_is_kswapd()) {
		/*
		 * If reclaim is isolating dirty pages under writeback,
		 * it implies that the long-lived page allocation rate
		 * is exceeding the page laundering rate. Either the
		 * global limits are not being effective at throttling
		 * processes due to the page distribution throughout
		 * zones or there is heavy usage of a slow backing
		 * device. The only option is to throttle from reclaim
		 * context which is not ideal as there is no guarantee
		 * the dirtying process is throttled in the same way
		 * balance_dirty_pages() manages.
		 *
		 * Once a node is flagged PGDAT_WRITEBACK, kswapd will
		 * count the number of pages under pages flagged for
		 * immediate reclaim and stall if any are encountered
		 * in the nr_immediate check below.
		 */
		if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
			set_bit(PGDAT_WRITEBACK, &pgdat->flags);

		/* Allow kswapd to start writing pages during reclaim.*/
		if (sc->nr.unqueued_dirty == sc->nr.file_taken)
			set_bit(PGDAT_DIRTY, &pgdat->flags);

		/*
		 * If kswapd scans pages marked for immediate
		 * reclaim and under writeback (nr_immediate), it
		 * implies that pages are cycling through the LRU
		 * faster than they are written so forcibly stall
		 * until some pages complete writeback.
		 */
		if (sc->nr.immediate)
			reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
	}

	/*
	 * Tag a node/memcg as congested if all the dirty pages were marked
	 * for writeback and immediate reclaim (counted in nr.congested).
	 *
	 * Legacy memcg will stall in page writeback so avoid forcibly
	 * stalling in reclaim_throttle().
	 */
	if ((current_is_kswapd() ||
	     (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) &&
	    sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
		set_bit(LRUVEC_CONGESTED, &target_lruvec->flags);

	/*
	 * Stall direct reclaim for IO completions if the lruvec is
	 * node is congested. Allow kswapd to continue until it
	 * starts encountering unqueued dirty pages or cycling through
	 * the LRU too quickly.
	 */
	if (!current_is_kswapd() && current_may_throttle() &&
	    !sc->hibernation_mode &&
	    test_bit(LRUVEC_CONGESTED, &target_lruvec->flags))
		reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED);

	if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
				    sc))
		goto again;

	/*
	 * Kswapd gives up on balancing particular nodes after too
	 * many failures to reclaim anything from them and goes to
	 * sleep. On reclaim progress, reset the failure counter. A
	 * successful direct reclaim run will revive a dormant kswapd.
	 */
	if (reclaimable)
		pgdat->kswapd_failures = 0;
}

/*
 * Returns true if compaction should go ahead for a costly-order request, or
 * the allocation would already succeed without compaction. Return false if we
 * should reclaim first.
 */
static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
{
	unsigned long watermark;
	enum compact_result suitable;

	suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx);
	if (suitable == COMPACT_SUCCESS)
		/* Allocation should succeed already. Don't reclaim. */
		return true;
	if (suitable == COMPACT_SKIPPED)
		/* Compaction cannot yet proceed. Do reclaim. */
		return false;

	/*
	 * Compaction is already possible, but it takes time to run and there
	 * are potentially other callers using the pages just freed. So proceed
	 * with reclaim to make a buffer of free pages available to give
	 * compaction a reasonable chance of completing and allocating the page.
	 * Note that we won't actually reclaim the whole buffer in one attempt
	 * as the target watermark in should_continue_reclaim() is lower. But if
	 * we are already above the high+gap watermark, don't reclaim at all.
	 */
	watermark = high_wmark_pages(zone) + compact_gap(sc->order);

	return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx);
}

static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc)
{
	/*
	 * If reclaim is making progress greater than 12% efficiency then
	 * wake all the NOPROGRESS throttled tasks.
	 */
	if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) {
		wait_queue_head_t *wqh;

		wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS];
		if (waitqueue_active(wqh))
			wake_up(wqh);

		return;
	}

	/*
	 * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will
	 * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages
	 * under writeback and marked for immediate reclaim at the tail of the
	 * LRU.
	 */
	if (current_is_kswapd() || cgroup_reclaim(sc))
		return;

	/* Throttle if making no progress at high prioities. */
	if (sc->priority == 1 && !sc->nr_reclaimed)
		reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS);
}

/*
 * 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.
 *
 * If a zone is deemed to be full of pinned pages then just give it a light
 * scan then give up on it.
 */
static void 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;
	gfp_t orig_mask;
	pg_data_t *last_pgdat = NULL;
	pg_data_t *first_pgdat = NULL;

	/*
	 * 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
	 */
	orig_mask = sc->gfp_mask;
	if (buffer_heads_over_limit) {
		sc->gfp_mask |= __GFP_HIGHMEM;
		sc->reclaim_idx = gfp_zone(sc->gfp_mask);
	}

	for_each_zone_zonelist_nodemask(zone, z, zonelist,
					sc->reclaim_idx, sc->nodemask) {
		/*
		 * Take care memory controller reclaiming has small influence
		 * to global LRU.
		 */
		if (!cgroup_reclaim(sc)) {
			if (!cpuset_zone_allowed(zone,
						 GFP_KERNEL | __GFP_HARDWALL))
				continue;

			/*
			 * 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 (IS_ENABLED(CONFIG_COMPACTION) &&
			    sc->order > PAGE_ALLOC_COSTLY_ORDER &&
			    compaction_ready(zone, sc)) {
				sc->compaction_ready = true;
				continue;
			}

			/*
			 * Shrink each node in the zonelist once. If the
			 * zonelist is ordered by zone (not the default) then a
			 * node may be shrunk multiple times but in that case
			 * the user prefers lower zones being preserved.
			 */
			if (zone->zone_pgdat == last_pgdat)
				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->zone_pgdat,
						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() */
		}

		if (!first_pgdat)
			first_pgdat = zone->zone_pgdat;

		/* See comment about same check for global reclaim above */
		if (zone->zone_pgdat == last_pgdat)
			continue;
		last_pgdat = zone->zone_pgdat;
		shrink_node(zone->zone_pgdat, sc);
	}

	if (first_pgdat)
		consider_reclaim_throttle(first_pgdat, sc);

	/*
	 * Restore to original mask to avoid the impact on the caller if we
	 * promoted it to __GFP_HIGHMEM.
	 */
	sc->gfp_mask = orig_mask;
}

static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat)
{
	struct lruvec *target_lruvec;
	unsigned long refaults;

	target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON);
	target_lruvec->refaults[WORKINGSET_ANON] = refaults;
	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE);
	target_lruvec->refaults[WORKINGSET_FILE] = refaults;
}

/*
 * 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)
{
	int initial_priority = sc->priority;
	pg_data_t *last_pgdat;
	struct zoneref *z;
	struct zone *zone;
retry:
	delayacct_freepages_start();

	if (!cgroup_reclaim(sc))
		__count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1);

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

		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
			break;

		if (sc->compaction_ready)
			break;

		/*
		 * If we're getting trouble reclaiming, start doing
		 * writepage even in laptop mode.
		 */
		if (sc->priority < DEF_PRIORITY - 2)
			sc->may_writepage = 1;
	} while (--sc->priority >= 0);

	last_pgdat = NULL;
	for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx,
					sc->nodemask) {
		if (zone->zone_pgdat == last_pgdat)
			continue;
		last_pgdat = zone->zone_pgdat;

		snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat);

		if (cgroup_reclaim(sc)) {
			struct lruvec *lruvec;

			lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup,
						   zone->zone_pgdat);
			clear_bit(LRUVEC_CONGESTED, &lruvec->flags);
		}
	}

	delayacct_freepages_end();

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

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

	/*
	 * We make inactive:active ratio decisions based on the node's
	 * composition of memory, but a restrictive reclaim_idx or a
	 * memory.low cgroup setting can exempt large amounts of
	 * memory from reclaim. Neither of which are very common, so
	 * instead of doing costly eligibility calculations of the
	 * entire cgroup subtree up front, we assume the estimates are
	 * good, and retry with forcible deactivation if that fails.
	 */
	if (sc->skipped_deactivate) {
		sc->priority = initial_priority;
		sc->force_deactivate = 1;
		sc->skipped_deactivate = 0;
		goto retry;
	}

	/* Untapped cgroup reserves?  Don't OOM, retry. */
	if (sc->memcg_low_skipped) {
		sc->priority = initial_priority;
		sc->force_deactivate = 0;
		sc->memcg_low_reclaim = 1;
		sc->memcg_low_skipped = 0;
		goto retry;
	}

	return 0;
}

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

	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
		return true;

	for (i = 0; i <= ZONE_NORMAL; i++) {
		zone = &pgdat->node_zones[i];
		if (!managed_zone(zone))
			continue;

		if (!zone_reclaimable_pages(zone))
			continue;

		pfmemalloc_reserve += min_wmark_pages(zone);
		free_pages += zone_page_state(zone, NR_FREE_PAGES);
	}

	/* If there are no reserves (unexpected config) then do not throttle */
	if (!pfmemalloc_reserve)
		return true;

	wmark_ok = free_pages > pfmemalloc_reserve / 2;

	/* kswapd must be awake if processes are being throttled */
	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
		if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL)
			WRITE_ONCE(pgdat->kswapd_highest_zoneidx, 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 zoneref *z;
	struct zone *zone;
	pg_data_t *pgdat = NULL;

	/*
	 * 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 by finding the first node
	 * with a usable ZONE_NORMAL or lower zone. The expectation is that
	 * GFP_KERNEL will be required for allocating network buffers when
	 * swapping over the network so ZONE_HIGHMEM is unusable.
	 *
	 * Throttling is based on the first usable node and throttled processes
	 * wait on a queue until kswapd makes progress and wakes them. There
	 * is an affinity then between processes waking up and where reclaim
	 * progress has been made assuming the process wakes on the same node.
	 * More importantly, processes running on remote nodes will not compete
	 * for remote pfmemalloc reserves and processes on different nodes
	 * should make reasonable progress.
	 */
	for_each_zone_zonelist_nodemask(zone, z, zonelist,
					gfp_zone(gfp_mask), nodemask) {
		if (zone_idx(zone) > ZONE_NORMAL)
			continue;

		/* Throttle based on the first usable node */
		pgdat = zone->zone_pgdat;
		if (allow_direct_reclaim(pgdat))
			goto out;
		break;
	}

	/* If no zone was usable by the allocation flags then do not throttle */
	if (!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,
			allow_direct_reclaim(pgdat), HZ);
	else
		/* Throttle until kswapd wakes the process */
		wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
			allow_direct_reclaim(pgdat));

	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 = {
		.nr_to_reclaim = SWAP_CLUSTER_MAX,
		.gfp_mask = current_gfp_context(gfp_mask),
		.reclaim_idx = gfp_zone(gfp_mask),
		.order = order,
		.nodemask = nodemask,
		.priority = DEF_PRIORITY,
		.may_writepage = !laptop_mode,
		.may_unmap = 1,
		.may_swap = 1,
	};

	/*
	 * scan_control uses s8 fields for order, priority, and reclaim_idx.
	 * Confirm they are large enough for max values.
	 */
	BUILD_BUG_ON(MAX_ORDER > S8_MAX);
	BUILD_BUG_ON(DEF_PRIORITY > S8_MAX);
	BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX);

	/*
	 * 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(sc.gfp_mask, zonelist, nodemask))
		return 1;

	set_task_reclaim_state(current, &sc.reclaim_state);
	trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask);

	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);

	trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
	set_task_reclaim_state(current, NULL);

	return nr_reclaimed;
}

#ifdef CONFIG_MEMCG

/* Only used by soft limit reclaim. Do not reuse for anything else. */
unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
						gfp_t gfp_mask, bool noswap,
						pg_data_t *pgdat,
						unsigned long *nr_scanned)
{
	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
	struct scan_control sc = {
		.nr_to_reclaim = SWAP_CLUSTER_MAX,
		.target_mem_cgroup = memcg,
		.may_writepage = !laptop_mode,
		.may_unmap = 1,
		.reclaim_idx = MAX_NR_ZONES - 1,
		.may_swap = !noswap,
	};

	WARN_ON_ONCE(!current->reclaim_state);

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

	trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
						      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_node 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,
					   unsigned long nr_pages,
					   gfp_t gfp_mask,
					   unsigned int reclaim_options)
{
	unsigned long nr_reclaimed;
	unsigned int noreclaim_flag;
	struct scan_control sc = {
		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
		.gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) |
				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
		.reclaim_idx = MAX_NR_ZONES - 1,
		.target_mem_cgroup = memcg,
		.priority = DEF_PRIORITY,
		.may_writepage = !laptop_mode,
		.may_unmap = 1,
		.may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
		.proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
	};
	/*
	 * Traverse the ZONELIST_FALLBACK zonelist of the current node to put
	 * equal pressure on all the nodes. This is based on the assumption that
	 * the reclaim does not bail out early.
	 */
	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);

	set_task_reclaim_state(current, &sc.reclaim_state);
	trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
	noreclaim_flag = memalloc_noreclaim_save();

	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);

	memalloc_noreclaim_restore(noreclaim_flag);
	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
	set_task_reclaim_state(current, NULL);

	return nr_reclaimed;
}
#endif

static void age_active_anon(struct pglist_data *pgdat,
				struct scan_control *sc)
{
	struct mem_cgroup *memcg;
	struct lruvec *lruvec;

	if (!can_age_anon_pages(pgdat, sc))
		return;

	lruvec = mem_cgroup_lruvec(NULL, pgdat);
	if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON))
		return;

	memcg = mem_cgroup_iter(NULL, NULL, NULL);
	do {
		lruvec = mem_cgroup_lruvec(memcg, pgdat);
		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
				   sc, LRU_ACTIVE_ANON);
		memcg = mem_cgroup_iter(NULL, memcg, NULL);
	} while (memcg);
}

static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx)
{
	int i;
	struct zone *zone;

	/*
	 * Check for watermark boosts top-down as the higher zones
	 * are more likely to be boosted. Both watermarks and boosts
	 * should not be checked at the same time as reclaim would
	 * start prematurely when there is no boosting and a lower
	 * zone is balanced.
	 */
	for (i = highest_zoneidx; i >= 0; i--) {
		zone = pgdat->node_zones + i;
		if (!managed_zone(zone))
			continue;

		if (zone->watermark_boost)
			return true;
	}

	return false;
}

/*
 * Returns true if there is an eligible zone balanced for the request order
 * and highest_zoneidx
 */
static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
{
	int i;
	unsigned long mark = -1;
	struct zone *zone;

	/*
	 * Check watermarks bottom-up as lower zones are more likely to
	 * meet watermarks.
	 */
	for (i = 0; i <= highest_zoneidx; i++) {
		zone = pgdat->node_zones + i;

		if (!managed_zone(zone))
			continue;

		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
			mark = wmark_pages(zone, WMARK_PROMO);
		else
			mark = high_wmark_pages(zone);
		if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx))
			return true;
	}

	/*
	 * If a node has no managed zone within highest_zoneidx, it does not
	 * need balancing by definition. This can happen if a zone-restricted
	 * allocation tries to wake a remote kswapd.
	 */
	if (mark == -1)
		return true;

	return false;
}

/* Clear pgdat state for congested, dirty or under writeback. */
static void clear_pgdat_congested(pg_data_t *pgdat)
{
	struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat);

	clear_bit(LRUVEC_CONGESTED, &lruvec->flags);
	clear_bit(PGDAT_DIRTY, &pgdat->flags);
	clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
}

/*
 * 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,
				int highest_zoneidx)
{
	/*
	 * The throttled processes are normally woken up in balance_pgdat() as
	 * soon as allow_direct_reclaim() is true. But there is a potential
	 * race between when kswapd checks the watermarks and a process gets
	 * throttled. There is also a potential race if processes get
	 * throttled, kswapd wakes, a large process exits thereby balancing the
	 * zones, which causes kswapd to exit balance_pgdat() before reaching
	 * the wake up checks. If kswapd is going to sleep, no process should
	 * be sleeping on pfmemalloc_wait, so wake them now if necessary. If
	 * the wake up is premature, processes will wake kswapd and get
	 * throttled again. The difference from wake ups in balance_pgdat() is
	 * that here we are under prepare_to_wait().
	 */
	if (waitqueue_active(&pgdat->pfmemalloc_wait))
		wake_up_all(&pgdat->pfmemalloc_wait);

	/* Hopeless node, leave it to direct reclaim */
	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
		return true;

	if (pgdat_balanced(pgdat, order, highest_zoneidx)) {
		clear_pgdat_congested(pgdat);
		return true;
	}

	return false;
}

/*
 * kswapd shrinks a node of pages that are at or below the highest usable
 * zone that is currently unbalanced.
 *
 * 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_node(pg_data_t *pgdat,
			       struct scan_control *sc)
{
	struct zone *zone;
	int z;

	/* Reclaim a number of pages proportional to the number of zones */
	sc->nr_to_reclaim = 0;
	for (z = 0; z <= sc->reclaim_idx; z++) {
		zone = pgdat->node_zones + z;
		if (!managed_zone(zone))
			continue;

		sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
	}

	/*
	 * Historically care was taken to put equal pressure on all zones but
	 * now pressure is applied based on node LRU order.
	 */
	shrink_node(pgdat, sc);

	/*
	 * Fragmentation may mean that the system cannot be rebalanced for
	 * high-order allocations. If twice the allocation size has been
	 * reclaimed then recheck watermarks only at order-0 to prevent
	 * excessive reclaim. Assume that a process requested a high-order
	 * can direct reclaim/compact.
	 */
	if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order))
		sc->order = 0;

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

/* Page allocator PCP high watermark is lowered if reclaim is active. */
static inline void
update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active)
{
	int i;
	struct zone *zone;

	for (i = 0; i <= highest_zoneidx; i++) {
		zone = pgdat->node_zones + i;

		if (!managed_zone(zone))
			continue;

		if (active)
			set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags);
		else
			clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags);
	}
}

static inline void
set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx)
{
	update_reclaim_active(pgdat, highest_zoneidx, true);
}

static inline void
clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx)
{
	update_reclaim_active(pgdat, highest_zoneidx, false);
}

/*
 * For kswapd, balance_pgdat() will reclaim pages across a node from zones
 * that are eligible for use by the caller until at least one zone is
 * balanced.
 *
 * Returns the order kswapd finished reclaiming at.
 *
 * 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), any page in that zone
 * or lower is eligible for reclaim until at least one usable zone is
 * balanced.
 */
static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
{
	int i;
	unsigned long nr_soft_reclaimed;
	unsigned long nr_soft_scanned;
	unsigned long pflags;
	unsigned long nr_boost_reclaim;
	unsigned long zone_boosts[MAX_NR_ZONES] = { 0, };
	bool boosted;
	struct zone *zone;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.order = order,
		.may_unmap = 1,
	};

	set_task_reclaim_state(current, &sc.reclaim_state);
	psi_memstall_enter(&pflags);
	__fs_reclaim_acquire(_THIS_IP_);

	count_vm_event(PAGEOUTRUN);

	/*
	 * Account for the reclaim boost. Note that the zone boost is left in
	 * place so that parallel allocations that are near the watermark will
	 * stall or direct reclaim until kswapd is finished.
	 */
	nr_boost_reclaim = 0;
	for (i = 0; i <= highest_zoneidx; i++) {
		zone = pgdat->node_zones + i;
		if (!managed_zone(zone))
			continue;

		nr_boost_reclaim += zone->watermark_boost;
		zone_boosts[i] = zone->watermark_boost;
	}
	boosted = nr_boost_reclaim;

restart:
	set_reclaim_active(pgdat, highest_zoneidx);
	sc.priority = DEF_PRIORITY;
	do {
		unsigned long nr_reclaimed = sc.nr_reclaimed;
		bool raise_priority = true;
		bool balanced;
		bool ret;

		sc.reclaim_idx = highest_zoneidx;

		/*
		 * If the number of buffer_heads exceeds the maximum allowed
		 * then consider reclaiming from all zones. This has a dual
		 * purpose -- on 64-bit systems it is expected that
		 * buffer_heads are stripped during active rotation. On 32-bit
		 * systems, highmem pages can pin lowmem memory and shrinking
		 * buffers can relieve lowmem pressure. Reclaim may still not
		 * go ahead if all eligible zones for the original allocation
		 * request are balanced to avoid excessive reclaim from kswapd.
		 */
		if (buffer_heads_over_limit) {
			for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
				zone = pgdat->node_zones + i;
				if (!managed_zone(zone))
					continue;

				sc.reclaim_idx = i;
				break;
			}
		}

		/*
		 * If the pgdat is imbalanced then ignore boosting and preserve
		 * the watermarks for a later time and restart. Note that the
		 * zone watermarks will be still reset at the end of balancing
		 * on the grounds that the normal reclaim should be enough to
		 * re-evaluate if boosting is required when kswapd next wakes.
		 */
		balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx);
		if (!balanced && nr_boost_reclaim) {
			nr_boost_reclaim = 0;
			goto restart;
		}

		/*
		 * If boosting is not active then only reclaim if there are no
		 * eligible zones. Note that sc.reclaim_idx is not used as
		 * buffer_heads_over_limit may have adjusted it.
		 */
		if (!nr_boost_reclaim && balanced)
			goto out;

		/* Limit the priority of boosting to avoid reclaim writeback */
		if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2)
			raise_priority = false;

		/*
		 * Do not writeback or swap pages for boosted reclaim. The
		 * intent is to relieve pressure not issue sub-optimal IO
		 * from reclaim context. If no pages are reclaimed, the
		 * reclaim will be aborted.
		 */
		sc.may_writepage = !laptop_mode && !nr_boost_reclaim;
		sc.may_swap = !nr_boost_reclaim;

		/*
		 * Do some background aging of the anon list, to give
		 * pages a chance to be referenced before reclaiming. All
		 * pages are rotated regardless of classzone as this is
		 * about consistent aging.
		 */
		age_active_anon(pgdat, &sc);

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

		/* Call soft limit reclaim before calling shrink_node. */
		sc.nr_scanned = 0;
		nr_soft_scanned = 0;
		nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order,
						sc.gfp_mask, &nr_soft_scanned);
		sc.nr_reclaimed += nr_soft_reclaimed;

		/*
		 * There should be no need to raise the scanning priority if
		 * enough pages are already being scanned that that high
		 * watermark would be met at 100% efficiency.
		 */
		if (kswapd_shrink_node(pgdat, &sc))
			raise_priority = false;

		/*
		 * If the low watermark is met there is no need for processes
		 * to be throttled on pfmemalloc_wait as they should not be
		 * able to safely make forward progress. Wake them
		 */
		if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
				allow_direct_reclaim(pgdat))
			wake_up_all(&pgdat->pfmemalloc_wait);

		/* Check if kswapd should be suspending */
		__fs_reclaim_release(_THIS_IP_);
		ret = try_to_freeze();
		__fs_reclaim_acquire(_THIS_IP_);
		if (ret || kthread_should_stop())
			break;

		/*
		 * Raise priority if scanning rate is too low or there was no
		 * progress in reclaiming pages
		 */
		nr_reclaimed = sc.nr_reclaimed - nr_reclaimed;
		nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed);

		/*
		 * If reclaim made no progress for a boost, stop reclaim as
		 * IO cannot be queued and it could be an infinite loop in
		 * extreme circumstances.
		 */
		if (nr_boost_reclaim && !nr_reclaimed)
			break;

		if (raise_priority || !nr_reclaimed)
			sc.priority--;
	} while (sc.priority >= 1);

	if (!sc.nr_reclaimed)
		pgdat->kswapd_failures++;

out:
	clear_reclaim_active(pgdat, highest_zoneidx);

	/* If reclaim was boosted, account for the reclaim done in this pass */
	if (boosted) {
		unsigned long flags;

		for (i = 0; i <= highest_zoneidx; i++) {
			if (!zone_boosts[i])
				continue;

			/* Increments are under the zone lock */
			zone = pgdat->node_zones + i;
			spin_lock_irqsave(&zone->lock, flags);
			zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]);
			spin_unlock_irqrestore(&zone->lock, flags);
		}

		/*
		 * As there is now likely space, wakeup kcompact to defragment
		 * pageblocks.
		 */
		wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx);
	}

	snapshot_refaults(NULL, pgdat);
	__fs_reclaim_release(_THIS_IP_);
	psi_memstall_leave(&pflags);
	set_task_reclaim_state(current, NULL);

	/*
	 * Return the order kswapd stopped reclaiming at as
	 * prepare_kswapd_sleep() takes it into account. If another caller
	 * entered the allocator slow path while kswapd was awake, order will
	 * remain at the higher level.
	 */
	return sc.order;
}

/*
 * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to
 * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is
 * not a valid index then either kswapd runs for first time or kswapd couldn't
 * sleep after previous reclaim attempt (node is still unbalanced). In that
 * case return the zone index of the previous kswapd reclaim cycle.
 */
static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat,
					   enum zone_type prev_highest_zoneidx)
{
	enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx);

	return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx;
}

static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
				unsigned int highest_zoneidx)
{
	long remaining = 0;
	DEFINE_WAIT(wait);

	if (freezing(current) || kthread_should_stop())
		return;

	prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);

	/*
	 * Try to sleep for a short interval. Note that kcompactd will only be
	 * woken if it is possible to sleep for a short interval. This is
	 * deliberate on the assumption that if reclaim cannot keep an
	 * eligible zone balanced that it's also unlikely that compaction will
	 * succeed.
	 */
	if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
		/*
		 * Compaction records what page blocks it recently failed to
		 * isolate pages from and skips them in the future scanning.
		 * When kswapd is going to sleep, it is reasonable to assume
		 * that pages and compaction may succeed so reset the cache.
		 */
		reset_isolation_suitable(pgdat);

		/*
		 * We have freed the memory, now we should compact it to make
		 * allocation of the requested order possible.
		 */
		wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx);

		remaining = schedule_timeout(HZ/10);

		/*
		 * If woken prematurely then reset kswapd_highest_zoneidx and
		 * order. The values will either be from a wakeup request or
		 * the previous request that slept prematurely.
		 */
		if (remaining) {
			WRITE_ONCE(pgdat->kswapd_highest_zoneidx,
					kswapd_highest_zoneidx(pgdat,
							highest_zoneidx));

			if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
				WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
		}

		finish_wait(&pgdat->kswapd_wait, &wait);
		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
	}

	/*
	 * After a short sleep, check if it was a premature sleep. If not, then
	 * go fully to sleep until explicitly woken up.
	 */
	if (!remaining &&
	    prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
		trace_mm_vmscan_kswapd_sleep(pgdat->node_id);

		/*
		 * vmstat counters are not perfectly accurate and the estimated
		 * value for counters such as NR_FREE_PAGES can deviate from the
		 * true value by nr_online_cpus * threshold. To avoid the zone
		 * watermarks being breached while under pressure, we reduce the
		 * per-cpu vmstat threshold while kswapd is awake and restore
		 * them before going back to sleep.
		 */
		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);

		if (!kthread_should_stop())
			schedule();

		set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
	} else {
		if (remaining)
			count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
		else
			count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
	}
	finish_wait(&pgdat->kswapd_wait, &wait);
}

/*
 * 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 int alloc_order, reclaim_order;
	unsigned int highest_zoneidx = MAX_NR_ZONES - 1;
	pg_data_t *pgdat = (pg_data_t *)p;
	struct task_struct *tsk = current;
	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);

	if (!cpumask_empty(cpumask))
		set_cpus_allowed_ptr(tsk, cpumask);

	/*
	 * 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_KSWAPD;
	set_freezable();

	WRITE_ONCE(pgdat->kswapd_order, 0);
	WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);
	atomic_set(&pgdat->nr_writeback_throttled, 0);
	for ( ; ; ) {
		bool ret;

		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
		highest_zoneidx = kswapd_highest_zoneidx(pgdat,
							highest_zoneidx);

kswapd_try_sleep:
		kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
					highest_zoneidx);

		/* Read the new order and highest_zoneidx */
		alloc_order = READ_ONCE(pgdat->kswapd_order);
		highest_zoneidx = kswapd_highest_zoneidx(pgdat,
							highest_zoneidx);
		WRITE_ONCE(pgdat->kswapd_order, 0);
		WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);

		ret = try_to_freeze();
		if (kthread_should_stop())
			break;

		/*
		 * We can speed up thawing tasks if we don't call balance_pgdat
		 * after returning from the refrigerator
		 */
		if (ret)
			continue;

		/*
		 * Reclaim begins at the requested order but if a high-order
		 * reclaim fails then kswapd falls back to reclaiming for
		 * order-0. If that happens, kswapd will consider sleeping
		 * for the order it finished reclaiming at (reclaim_order)
		 * but kcompactd is woken to compact for the original
		 * request (alloc_order).
		 */
		trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx,
						alloc_order);
		reclaim_order = balance_pgdat(pgdat, alloc_order,
						highest_zoneidx);
		if (reclaim_order < alloc_order)
			goto kswapd_try_sleep;
	}

	tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD);

	return 0;
}

/*
 * A zone is low on free memory or too fragmented for high-order memory.  If
 * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's
 * pgdat.  It will wake up kcompactd after reclaiming memory.  If kswapd reclaim
 * has failed or is not needed, still wake up kcompactd if only compaction is
 * needed.
 */
void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
		   enum zone_type highest_zoneidx)
{
	pg_data_t *pgdat;
	enum zone_type curr_idx;

	if (!managed_zone(zone))
		return;

	if (!cpuset_zone_allowed(zone, gfp_flags))
		return;

	pgdat = zone->zone_pgdat;
	curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx);

	if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx)
		WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx);

	if (READ_ONCE(pgdat->kswapd_order) < order)
		WRITE_ONCE(pgdat->kswapd_order, order);

	if (!waitqueue_active(&pgdat->kswapd_wait))
		return;

	/* Hopeless node, leave it to direct reclaim if possible */
	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ||
	    (pgdat_balanced(pgdat, order, highest_zoneidx) &&
	     !pgdat_watermark_boosted(pgdat, highest_zoneidx))) {
		/*
		 * There may be plenty of free memory available, but it's too
		 * fragmented for high-order allocations.  Wake up kcompactd
		 * and rely on compaction_suitable() to determine if it's
		 * needed.  If it fails, it will defer subsequent attempts to
		 * ratelimit its work.
		 */
		if (!(gfp_flags & __GFP_DIRECT_RECLAIM))
			wakeup_kcompactd(pgdat, order, highest_zoneidx);
		return;
	}

	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order,
				      gfp_flags);
	wake_up_interruptible(&pgdat->kswapd_wait);
}

#ifdef CONFIG_HIBERNATION
/*
 * Try to free `nr_to_reclaim' 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_to_reclaim)
{
	struct scan_control sc = {
		.nr_to_reclaim = nr_to_reclaim,
		.gfp_mask = GFP_HIGHUSER_MOVABLE,
		.reclaim_idx = MAX_NR_ZONES - 1,
		.priority = DEF_PRIORITY,
		.may_writepage = 1,
		.may_unmap = 1,
		.may_swap = 1,
		.hibernation_mode = 1,
	};
	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
	unsigned long nr_reclaimed;
	unsigned int noreclaim_flag;

	fs_reclaim_acquire(sc.gfp_mask);
	noreclaim_flag = memalloc_noreclaim_save();
	set_task_reclaim_state(current, &sc.reclaim_state);

	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);

	set_task_reclaim_state(current, NULL);
	memalloc_noreclaim_restore(noreclaim_flag);
	fs_reclaim_release(sc.gfp_mask);

	return nr_reclaimed;
}
#endif /* CONFIG_HIBERNATION */

/*
 * This kswapd start function will be called by init and node-hot-add.
 */
void kswapd_run(int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);

	pgdat_kswapd_lock(pgdat);
	if (!pgdat->kswapd) {
		pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
		if (IS_ERR(pgdat->kswapd)) {
			/* failure at boot is fatal */
			BUG_ON(system_state < SYSTEM_RUNNING);
			pr_err("Failed to start kswapd on node %d\n", nid);
			pgdat->kswapd = NULL;
		}
	}
	pgdat_kswapd_unlock(pgdat);
}

/*
 * Called by memory hotplug when all memory in a node is offlined.  Caller must
 * be holding mem_hotplug_begin/done().
 */
void kswapd_stop(int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);
	struct task_struct *kswapd;

	pgdat_kswapd_lock(pgdat);
	kswapd = pgdat->kswapd;
	if (kswapd) {
		kthread_stop(kswapd);
		pgdat->kswapd = NULL;
	}
	pgdat_kswapd_unlock(pgdat);
}

static int __init kswapd_init(void)
{
	int nid;

	swap_setup();
	for_each_node_state(nid, N_MEMORY)
 		kswapd_run(nid);
	return 0;
}

module_init(kswapd_init)

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

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

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

/*
 * If the number of slab pages in a zone grows beyond this percentage then
 * slab reclaim needs to occur.
 */
int sysctl_min_slab_ratio = 5;

static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat)
{
	unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED);
	unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) +
		node_page_state(pgdat, NR_ACTIVE_FILE);

	/*
	 * It's possible for there to be more file mapped pages than
	 * accounted for by the pages on the file LRU lists because
	 * tmpfs pages accounted for as ANON can also be FILE_MAPPED
	 */
	return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
}

/* Work out how many page cache pages we can reclaim in this reclaim_mode */
static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat)
{
	unsigned long nr_pagecache_reclaimable;
	unsigned long delta = 0;

	/*
	 * If RECLAIM_UNMAP is set, then all file pages are considered
	 * potentially reclaimable. Otherwise, we have to worry about
	 * pages like swapcache and node_unmapped_file_pages() provides
	 * a better estimate
	 */
	if (node_reclaim_mode & RECLAIM_UNMAP)
		nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES);
	else
		nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat);

	/* If we can't clean pages, remove dirty pages from consideration */
	if (!(node_reclaim_mode & RECLAIM_WRITE))
		delta += node_page_state(pgdat, NR_FILE_DIRTY);

	/* Watch for any possible underflows due to delta */
	if (unlikely(delta > nr_pagecache_reclaimable))
		delta = nr_pagecache_reclaimable;

	return nr_pagecache_reclaimable - delta;
}

/*
 * Try to free up some pages from this node through reclaim.
 */
static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
{
	/* Minimum pages needed in order to stay on node */
	const unsigned long nr_pages = 1 << order;
	struct task_struct *p = current;
	unsigned int noreclaim_flag;
	struct scan_control sc = {
		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
		.gfp_mask = current_gfp_context(gfp_mask),
		.order = order,
		.priority = NODE_RECLAIM_PRIORITY,
		.may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
		.may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
		.may_swap = 1,
		.reclaim_idx = gfp_zone(gfp_mask),
	};
	unsigned long pflags;

	trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order,
					   sc.gfp_mask);

	cond_resched();
	psi_memstall_enter(&pflags);
	fs_reclaim_acquire(sc.gfp_mask);
	/*
	 * We need to be able to allocate from the reserves for RECLAIM_UNMAP
	 */
	noreclaim_flag = memalloc_noreclaim_save();
	set_task_reclaim_state(p, &sc.reclaim_state);

	if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages ||
	    node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) {
		/*
		 * Free memory by calling shrink node with increasing
		 * priorities until we have enough memory freed.
		 */
		do {
			shrink_node(pgdat, &sc);
		} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
	}

	set_task_reclaim_state(p, NULL);
	memalloc_noreclaim_restore(noreclaim_flag);
	fs_reclaim_release(sc.gfp_mask);
	psi_memstall_leave(&pflags);

	trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed);

	return sc.nr_reclaimed >= nr_pages;
}

int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
{
	int ret;

	/*
	 * Node reclaim reclaims unmapped file backed pages and
	 * slab pages if we are over the defined limits.
	 *
	 * A small portion of unmapped file backed pages is needed for
	 * file I/O otherwise pages read by file I/O will be immediately
	 * thrown out if the node is overallocated. So we do not reclaim
	 * if less than a specified percentage of the node is used by
	 * unmapped file backed pages.
	 */
	if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
	    node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <=
	    pgdat->min_slab_pages)
		return NODE_RECLAIM_FULL;

	/*
	 * Do not scan if the allocation should not be delayed.
	 */
	if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
		return NODE_RECLAIM_NOSCAN;

	/*
	 * Only run node reclaim on the local node or on nodes that do not
	 * have associated processors. This will favor the local processor
	 * over remote processors and spread off node memory allocations
	 * as wide as possible.
	 */
	if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id())
		return NODE_RECLAIM_NOSCAN;

	if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags))
		return NODE_RECLAIM_NOSCAN;

	ret = __node_reclaim(pgdat, gfp_mask, order);
	clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags);

	if (!ret)
		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);

	return ret;
}
#endif

void check_move_unevictable_pages(struct pagevec *pvec)
{
	struct folio_batch fbatch;
	unsigned i;

	folio_batch_init(&fbatch);
	for (i = 0; i < pvec->nr; i++) {
		struct page *page = pvec->pages[i];

		if (PageTransTail(page))
			continue;
		folio_batch_add(&fbatch, page_folio(page));
	}
	check_move_unevictable_folios(&fbatch);
}
EXPORT_SYMBOL_GPL(check_move_unevictable_pages);

/**
 * check_move_unevictable_folios - Move evictable folios to appropriate zone
 * lru list
 * @fbatch: Batch of lru folios to check.
 *
 * Checks folios for evictability, if an evictable folio is in the unevictable
 * lru list, moves it to the appropriate evictable lru list. This function
 * should be only used for lru folios.
 */
void check_move_unevictable_folios(struct folio_batch *fbatch)
{
	struct lruvec *lruvec = NULL;
	int pgscanned = 0;
	int pgrescued = 0;
	int i;

	for (i = 0; i < fbatch->nr; i++) {
		struct folio *folio = fbatch->folios[i];
		int nr_pages = folio_nr_pages(folio);

		pgscanned += nr_pages;

		/* block memcg migration while the folio moves between lrus */
		if (!folio_test_clear_lru(folio))
			continue;

		lruvec = folio_lruvec_relock_irq(folio, lruvec);
		if (folio_evictable(folio) && folio_test_unevictable(folio)) {
			lruvec_del_folio(lruvec, folio);
			folio_clear_unevictable(folio);
			lruvec_add_folio(lruvec, folio);
			pgrescued += nr_pages;
		}
		folio_set_lru(folio);
	}

	if (lruvec) {
		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
		unlock_page_lruvec_irq(lruvec);
	} else if (pgscanned) {
		count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
	}
}
EXPORT_SYMBOL_GPL(check_move_unevictable_folios);