// SPDX-License-Identifier: GPL-2.0

  /*
   *  linux/mm/vmscan.c
   *
   *  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 try_to_release_page(),
  					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/delayacct.h>

  #include <linux/sysctl.h>

  #include <linux/oom.h>

  #include <linux/prefetch.h>

  #include <linux/printk.h>

  #include <linux/dax.h>

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

  #include <linux/balloon_compaction.h>

  #include "internal.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;

  	/* 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;

  	/*
  	 * Cgroups are not reclaimed below their configured memory.low,
  	 * unless we threaten to OOM. If any cgroups are skipped due to
  	 * memory.low and nothing was reclaimed, go back for memory.low.
  	 */
  	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;

  	/* 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;

  };

  #ifdef ARCH_HAS_PREFETCH
  #define prefetch_prev_lru_page(_page, _base, _field)			\
  	do {								\
  		if ((_page)->lru.prev != _base) {			\
  			struct page *prev;				\
  									\
  			prev = lru_to_page(&(_page->lru));		\
  			prefetch(&prev->_field);			\
  		}							\
  	} while (0)
  #else
  #define prefetch_prev_lru_page(_page, _base, _field) do { } while (0)
  #endif
  
  #ifdef ARCH_HAS_PREFETCHW
  #define prefetchw_prev_lru_page(_page, _base, _field)			\
  	do {								\
  		if ((_page)->lru.prev != _base) {			\
  			struct page *prev;				\
  									\
  			prev = lru_to_page(&(_page->lru));		\
  			prefetchw(&prev->_field);			\
  		}							\
  	} while (0)
  #else
  #define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0)
  #endif
  
  /*
   * From 0 .. 100.  Higher means more swappy.
   */
  int vm_swappiness = 60;

  /*
   * The total number of pages which are beyond the high watermark within all
   * zones.
   */
  unsigned long vm_total_pages;

  
  static LIST_HEAD(shrinker_list);
  static DECLARE_RWSEM(shrinker_rwsem);

  #ifdef CONFIG_MEMCG_KMEM

  
  /*
   * We allow subsystems to populate their shrinker-related
   * LRU lists before register_shrinker_prepared() is called
   * for the shrinker, since we don't want to impose
   * restrictions on their internal registration order.
   * In this case shrink_slab_memcg() may find corresponding
   * bit is set in the shrinkers map.
   *
   * This value is used by the function to detect registering
   * shrinkers and to skip do_shrink_slab() calls for them.
   */
  #define SHRINKER_REGISTERING ((struct shrinker *)~0UL)

  static DEFINE_IDR(shrinker_idr);
  static int shrinker_nr_max;
  
  static int prealloc_memcg_shrinker(struct shrinker *shrinker)
  {
  	int id, ret = -ENOMEM;
  
  	down_write(&shrinker_rwsem);
  	/* This may call shrinker, so it must use down_read_trylock() */

  	id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL);

  	if (id < 0)
  		goto unlock;

  	if (id >= shrinker_nr_max) {
  		if (memcg_expand_shrinker_maps(id)) {
  			idr_remove(&shrinker_idr, id);
  			goto unlock;
  		}

  		shrinker_nr_max = id + 1;

  	}

  	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);
  
  	down_write(&shrinker_rwsem);
  	idr_remove(&shrinker_idr, id);
  	up_write(&shrinker_rwsem);
  }
  #else /* CONFIG_MEMCG_KMEM */
  static int prealloc_memcg_shrinker(struct shrinker *shrinker)
  {
  	return 0;
  }
  
  static void unregister_memcg_shrinker(struct shrinker *shrinker)
  {
  }
  #endif /* CONFIG_MEMCG_KMEM */

  #ifdef CONFIG_MEMCG

  static bool global_reclaim(struct scan_control *sc)
  {

  	return !sc->target_mem_cgroup;

  }

  
  /**
   * sane_reclaim - is the usual dirty throttling mechanism operational?
   * @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 sane_reclaim(struct scan_control *sc)
  {
  	struct mem_cgroup *memcg = sc->target_mem_cgroup;
  
  	if (!memcg)
  		return true;
  #ifdef CONFIG_CGROUP_WRITEBACK

  	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))

  		return true;
  #endif
  	return false;
  }

  
  static void set_memcg_congestion(pg_data_t *pgdat,
  				struct mem_cgroup *memcg,
  				bool congested)
  {
  	struct mem_cgroup_per_node *mn;
  
  	if (!memcg)
  		return;
  
  	mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
  	WRITE_ONCE(mn->congested, congested);
  }
  
  static bool memcg_congested(pg_data_t *pgdat,
  			struct mem_cgroup *memcg)
  {
  	struct mem_cgroup_per_node *mn;
  
  	mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
  	return READ_ONCE(mn->congested);
  
  }

  #else

  static bool global_reclaim(struct scan_control *sc)
  {
  	return true;
  }

  
  static bool sane_reclaim(struct scan_control *sc)
  {
  	return true;
  }

  
  static inline void set_memcg_congestion(struct pglist_data *pgdat,
  				struct mem_cgroup *memcg, bool congested)
  {
  }
  
  static inline bool memcg_congested(struct pglist_data *pgdat,
  			struct mem_cgroup *memcg)
  {
  	return false;
  
  }

  #endif

  /*
   * 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 (get_nr_swap_pages() > 0)
  		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 for the whole LRU list)
   */
  unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)

  {

  	unsigned long lru_size;
  	int zid;

  	if (!mem_cgroup_disabled())

  		lru_size = mem_cgroup_get_lru_size(lruvec, lru);
  	else
  		lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);

  	for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) {
  		struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];
  		unsigned long size;

  		if (!managed_zone(zone))
  			continue;
  
  		if (!mem_cgroup_disabled())
  			size = mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
  		else
  			size = zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zid],
  				       NR_ZONE_LRU_BASE + lru);
  		lru_size -= min(size, lru_size);
  	}
  
  	return lru_size;

  }

  /*

   * Add a shrinker callback to be called from the vm.

   */

  int prealloc_shrinker(struct shrinker *shrinker)

  {

  	size_t 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;

  
  	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
  		if (prealloc_memcg_shrinker(shrinker))
  			goto free_deferred;
  	}

  	return 0;

  
  free_deferred:
  	kfree(shrinker->nr_deferred);
  	shrinker->nr_deferred = NULL;
  	return -ENOMEM;

  }
  
  void free_prealloced_shrinker(struct shrinker *shrinker)
  {

  	if (!shrinker->nr_deferred)
  		return;
  
  	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
  		unregister_memcg_shrinker(shrinker);

  	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);

  #ifdef CONFIG_MEMCG_KMEM

  	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
  		idr_replace(&shrinker_idr, shrinker, shrinker->id);

  #endif

  	up_write(&shrinker_rwsem);

  }
  
  int register_shrinker(struct shrinker *shrinker)
  {
  	int err = prealloc_shrinker(shrinker);
  
  	if (err)
  		return err;
  	register_shrinker_prepared(shrinker);

  	return 0;

  }

  EXPORT_SYMBOL(register_shrinker);

  
  /*
   * Remove one
   */

  void unregister_shrinker(struct shrinker *shrinker)

  {

  	if (!shrinker->nr_deferred)
  		return;

  	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
  		unregister_memcg_shrinker(shrinker);

  	down_write(&shrinker_rwsem);
  	list_del(&shrinker->list);
  	up_write(&shrinker_rwsem);

  	kfree(shrinker->nr_deferred);

  	shrinker->nr_deferred = NULL;

  }

  EXPORT_SYMBOL(unregister_shrinker);

  
  #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;
  	int nid = shrinkctl->nid;
  	long batch_size = shrinker->batch ? shrinker->batch
  					  : SHRINK_BATCH;

  	long scanned = 0, next_deferred;

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

  	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 = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
  
  	total_scan = nr;

  	delta = freeable >> priority;
  	delta *= 4;
  	do_div(delta, shrinker->seeks);

  	total_scan += delta;
  	if (total_scan < 0) {

  		pr_err("shrink_slab: %pF negative objects to delete nr=%ld
  ",

  		       shrinker->scan_objects, total_scan);

  		total_scan = freeable;

  		next_deferred = nr;
  	} else
  		next_deferred = total_scan;

  
  	/*
  	 * We need to avoid excessive windup on filesystem shrinkers
  	 * due to large numbers of GFP_NOFS allocations causing the
  	 * shrinkers to return -1 all the time. This results in a large
  	 * nr being built up so when a shrink that can do some work
  	 * comes along it empties the entire cache due to nr >>>

  	 * freeable. This is bad for sustaining a working set in

  	 * memory.
  	 *
  	 * Hence only allow the shrinker to scan the entire cache when
  	 * a large delta change is calculated directly.
  	 */

  	if (delta < freeable / 4)
  		total_scan = min(total_scan, freeable / 2);

  
  	/*
  	 * Avoid risking looping forever due to too large nr value:
  	 * never try to free more than twice the estimate number of
  	 * freeable entries.
  	 */

  	if (total_scan > freeable * 2)
  		total_scan = freeable * 2;

  
  	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();
  	}

  	if (next_deferred >= scanned)
  		next_deferred -= scanned;
  	else
  		next_deferred = 0;

  	/*
  	 * move the unused scan count back into the shrinker in a
  	 * manner that handles concurrent updates. If we exhausted the
  	 * scan, there is no need to do an update.
  	 */

  	if (next_deferred > 0)
  		new_nr = atomic_long_add_return(next_deferred,

  						&shrinker->nr_deferred[nid]);
  	else
  		new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);

  	trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan);

  	return freed;

  }

  #ifdef CONFIG_MEMCG_KMEM
  static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
  			struct mem_cgroup *memcg, int priority)
  {
  	struct memcg_shrinker_map *map;

  	unsigned long ret, freed = 0;
  	int i;

  
  	if (!memcg_kmem_enabled() || !mem_cgroup_online(memcg))
  		return 0;
  
  	if (!down_read_trylock(&shrinker_rwsem))
  		return 0;
  
  	map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map,
  					true);
  	if (unlikely(!map))
  		goto unlock;
  
  	for_each_set_bit(i, map->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 == SHRINKER_REGISTERING)) {
  			if (!shrinker)
  				clear_bit(i, map->map);

  			continue;
  		}

  		ret = do_shrink_slab(&sc, shrinker, priority);

  		if (ret == SHRINK_EMPTY) {
  			clear_bit(i, map->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
  			 * memcg_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
  				memcg_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_KMEM */
  static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
  			struct mem_cgroup *memcg, int priority)
  {
  	return 0;
  }
  #endif /* CONFIG_MEMCG_KMEM */

  /**

   * 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;

  	if (!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 regsitration 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;

  }

  void drop_slab_node(int nid)
  {
  	unsigned long freed;
  
  	do {
  		struct mem_cgroup *memcg = NULL;
  
  		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 > 10);
  }
  
  void drop_slab(void)
  {
  	int nid;
  
  	for_each_online_node(nid)
  		drop_slab_node(nid);
  }

  static inline int is_page_cache_freeable(struct page *page)
  {

  	/*
  	 * A freeable page cache page is referenced only by the caller
  	 * that isolated the page, the page cache radix tree and
  	 * optional buffer heads at page->private.
  	 */

  	int radix_pins = PageTransHuge(page) && PageSwapCache(page) ?
  		HPAGE_PMD_NR : 1;
  	return page_count(page) - page_has_private(page) == 1 + radix_pins;

  }

  static int may_write_to_inode(struct inode *inode, struct scan_control *sc)

  {

  	if (current->flags & PF_SWAPWRITE)

  		return 1;

  	if (!inode_write_congested(inode))

  		return 1;

  	if (inode_to_bdi(inode) == current->backing_dev_info)

  		return 1;
  	return 0;
  }
  
  /*
   * We detected a synchronous write error writing a page 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 page and once
   * that page is locked, the mapping is pinned.
   *
   * We're allowed to run sleeping lock_page() here because we know the caller has
   * __GFP_FS.
   */
  static void handle_write_error(struct address_space *mapping,
  				struct page *page, int error)
  {

  	lock_page(page);

  	if (page_mapping(page) == mapping)
  		mapping_set_error(mapping, error);

  	unlock_page(page);
  }

  /* 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 page *page, struct address_space *mapping,

  			 struct scan_control *sc)

  {
  	/*
  	 * If the page 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 page's queue, we can perform writeback even if that
  	 * will block.
  	 *
  	 * If the page 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(page))
  		return PAGE_KEEP;
  	if (!mapping) {
  		/*
  		 * Some data journaling orphaned pages can have
  		 * page->mapping == NULL while being dirty with clean buffers.
  		 */

  		if (page_has_private(page)) {

  			if (try_to_free_buffers(page)) {
  				ClearPageDirty(page);

  				pr_info("%s: orphaned page
  ", __func__);

  				return PAGE_CLEAN;
  			}
  		}
  		return PAGE_KEEP;
  	}
  	if (mapping->a_ops->writepage == NULL)
  		return PAGE_ACTIVATE;

  	if (!may_write_to_inode(mapping->host, sc))

  		return PAGE_KEEP;
  
  	if (clear_page_dirty_for_io(page)) {
  		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,
  		};
  
  		SetPageReclaim(page);
  		res = mapping->a_ops->writepage(page, &wbc);
  		if (res < 0)
  			handle_write_error(mapping, page, res);

  		if (res == AOP_WRITEPAGE_ACTIVATE) {

  			ClearPageReclaim(page);
  			return PAGE_ACTIVATE;
  		}

  		if (!PageWriteback(page)) {
  			/* synchronous write or broken a_ops? */
  			ClearPageReclaim(page);
  		}

  		trace_mm_vmscan_writepage(page);

  		inc_node_page_state(page, 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 page *page,
  			    bool reclaimed)

  {

  	unsigned long flags;

  	int refcount;

  	BUG_ON(!PageLocked(page));
  	BUG_ON(mapping != page_mapping(page));

  	xa_lock_irqsave(&mapping->i_pages, flags);

  	/*

  	 * 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.

  	 */

  	if (unlikely(PageTransHuge(page)) && PageSwapCache(page))
  		refcount = 1 + HPAGE_PMD_NR;
  	else
  		refcount = 2;
  	if (!page_ref_freeze(page, refcount))

  		goto cannot_free;

  	/* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */

  	if (unlikely(PageDirty(page))) {

  		page_ref_unfreeze(page, refcount);

  		goto cannot_free;

  	}

  
  	if (PageSwapCache(page)) {
  		swp_entry_t swap = { .val = page_private(page) };

  		mem_cgroup_swapout(page, swap);

  		__delete_from_swap_cache(page);

  		xa_unlock_irqrestore(&mapping->i_pages, flags);

  		put_swap_page(page, swap);

  	} else {

  		void (*freepage)(struct page *);

  		void *shadow = NULL;

  
  		freepage = mapping->a_ops->freepage;

  		/*
  		 * 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 optizimation,
  		 * 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 && page_is_file_cache(page) &&

  		    !mapping_exiting(mapping) && !dax_mapping(mapping))

  			shadow = workingset_eviction(mapping, page);

  		__delete_from_page_cache(page, shadow);

  		xa_unlock_irqrestore(&mapping->i_pages, flags);

  
  		if (freepage != NULL)
  			freepage(page);

  	}

  	return 1;
  
  cannot_free:

  	xa_unlock_irqrestore(&mapping->i_pages, flags);

  	return 0;
  }

  /*

   * Attempt to detach a locked page from its ->mapping.  If it is dirty or if
   * someone else has a ref on the page, abort and return 0.  If it was
   * successfully detached, return 1.  Assumes the caller has a single ref on
   * this page.
   */
  int remove_mapping(struct address_space *mapping, struct page *page)
  {

  	if (__remove_mapping(mapping, page, false)) {

  		/*
  		 * Unfreezing the refcount with 1 rather than 2 effectively
  		 * drops the pagecache ref for us without requiring another
  		 * atomic operation.
  		 */

  		page_ref_unfreeze(page, 1);

  		return 1;
  	}
  	return 0;
  }

  /**
   * putback_lru_page - put previously isolated page onto appropriate LRU list
   * @page: page to be put back to appropriate lru list
   *
   * Add previously isolated @page to appropriate LRU list.
   * Page may still be unevictable for other reasons.
   *
   * lru_lock must not be held, interrupts must be enabled.
   */

  void putback_lru_page(struct page *page)
  {

  	lru_cache_add(page);

  	put_page(page);		/* drop ref from isolate */
  }

  enum page_references {
  	PAGEREF_RECLAIM,
  	PAGEREF_RECLAIM_CLEAN,

  	PAGEREF_KEEP,

  	PAGEREF_ACTIVATE,
  };
  
  static enum page_references page_check_references(struct page *page,
  						  struct scan_control *sc)
  {

  	int referenced_ptes, referenced_page;

  	unsigned long vm_flags;

  	referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
  					  &vm_flags);

  	referenced_page = TestClearPageReferenced(page);

  	/*
  	 * Mlock lost the isolation race with us.  Let try_to_unmap()
  	 * move the page to the unevictable list.
  	 */
  	if (vm_flags & VM_LOCKED)
  		return PAGEREF_RECLAIM;

  	if (referenced_ptes) {

  		if (PageSwapBacked(page))

  			return PAGEREF_ACTIVATE;
  		/*
  		 * All mapped pages start out with page table
  		 * references from the instantiating fault, so we need
  		 * to look twice if a mapped file page 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 pages as well
  		 * so that recently deactivated but used pages are
  		 * quickly recovered.
  		 */
  		SetPageReferenced(page);

  		if (referenced_page || referenced_ptes > 1)

  			return PAGEREF_ACTIVATE;

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

  		return PAGEREF_KEEP;
  	}

  
  	/* Reclaim if clean, defer dirty pages to writeback */

  	if (referenced_page && !PageSwapBacked(page))

  		return PAGEREF_RECLAIM_CLEAN;
  
  	return PAGEREF_RECLAIM;

  }

  /* Check if a page is dirty or under writeback */
  static void page_check_dirty_writeback(struct page *page,
  				       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
  	 */

  	if (!page_is_file_cache(page) ||
  	    (PageAnon(page) && !PageSwapBacked(page))) {

  		*dirty = false;
  		*writeback = false;
  		return;
  	}
  
  	/* By default assume that the page flags are accurate */
  	*dirty = PageDirty(page);
  	*writeback = PageWriteback(page);

  
  	/* Verify dirty/writeback state if the filesystem supports it */
  	if (!page_has_private(page))
  		return;
  
  	mapping = page_mapping(page);
  	if (mapping && mapping->a_ops->is_dirty_writeback)
  		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);

  }

  /*

   * shrink_page_list() returns the number of reclaimed pages

   */

  static unsigned long shrink_page_list(struct list_head *page_list,

  				      struct pglist_data *pgdat,

  				      struct scan_control *sc,

  				      enum ttu_flags ttu_flags,

  				      struct reclaim_stat *stat,

  				      bool force_reclaim)

  {
  	LIST_HEAD(ret_pages);

  	LIST_HEAD(free_pages);

  	int pgactivate = 0;

  	unsigned nr_unqueued_dirty = 0;
  	unsigned nr_dirty = 0;
  	unsigned nr_congested = 0;
  	unsigned nr_reclaimed = 0;
  	unsigned nr_writeback = 0;
  	unsigned nr_immediate = 0;

  	unsigned nr_ref_keep = 0;
  	unsigned nr_unmap_fail = 0;

  
  	cond_resched();

  	while (!list_empty(page_list)) {
  		struct address_space *mapping;
  		struct page *page;
  		int may_enter_fs;

  		enum page_references references = PAGEREF_RECLAIM_CLEAN;

  		bool dirty, writeback;

  
  		cond_resched();
  
  		page = lru_to_page(page_list);
  		list_del(&page->lru);

  		if (!trylock_page(page))

  			goto keep;

  		VM_BUG_ON_PAGE(PageActive(page), page);

  
  		sc->nr_scanned++;

  		if (unlikely(!page_evictable(page)))

  			goto activate_locked;

  		if (!sc->may_unmap && page_mapped(page))

  			goto keep_locked;

  		/* Double the slab pressure for mapped and swapcache pages */

  		if ((page_mapped(page) || PageSwapCache(page)) &&
  		    !(PageAnon(page) && !PageSwapBacked(page)))

  			sc->nr_scanned++;

  		may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
  			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));

  		/*

  		 * The number of dirty pages determines if a node is marked

  		 * reclaim_congested which affects wait_iff_congested. kswapd
  		 * will stall and start writing pages if the tail of the LRU
  		 * is all dirty unqueued pages.
  		 */
  		page_check_dirty_writeback(page, &dirty, &writeback);
  		if (dirty || writeback)
  			nr_dirty++;
  
  		if (dirty && !writeback)
  			nr_unqueued_dirty++;

  		/*
  		 * Treat this page as congested if the underlying BDI is or if
  		 * pages are cycling through the LRU so quickly that the
  		 * pages marked for immediate reclaim are making it to the
  		 * end of the LRU a second time.
  		 */

  		mapping = page_mapping(page);

  		if (((dirty || writeback) && mapping &&

  		     inode_write_congested(mapping->host)) ||

  		    (writeback && PageReclaim(page)))

  			nr_congested++;
  
  		/*

  		 * If a page at the tail of the LRU is under writeback, there
  		 * are three cases to consider.
  		 *
  		 * 1) If reclaim is encountering an excessive number of pages
  		 *    under writeback and this page is both under writeback and
  		 *    PageReclaim then it indicates that pages are being queued
  		 *    for IO but are being recycled through the LRU before the
  		 *    IO can complete. Waiting on the page itself risks an
  		 *    indefinite stall if it is impossible to writeback the
  		 *    page due to IO error or disconnected storage so instead

  		 *    note that the LRU is being scanned too quickly and the
  		 *    caller can stall after page list has been processed.

  		 *

  		 * 2) Global or new memcg reclaim encounters a page 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 page for immediate

  		 *    reclaim and continue scanning.

  		 *

  		 *    Require may_enter_fs because we would wait on fs, which
  		 *    may not have submitted IO yet. And the loop driver might

  		 *    enter reclaim, and deadlock if it waits on a page 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 page that is already marked

  		 *    PageReclaim. memcg does not have any dirty pages
  		 *    throttling so we could easily OOM just because too many
  		 *    pages are in writeback and there is nothing else to
  		 *    reclaim. Wait for the writeback to complete.

  		 *
  		 * In cases 1) and 2) we activate the pages to get them out of
  		 * the way while we continue scanning for clean pages 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 (PageWriteback(page)) {

  			/* Case 1 above */
  			if (current_is_kswapd() &&
  			    PageReclaim(page) &&

  			    test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {

  				nr_immediate++;

  				goto activate_locked;

  
  			/* Case 2 above */

  			} else if (sane_reclaim(sc) ||

  			    !PageReclaim(page) || !may_enter_fs) {

  				/*
  				 * This is slightly racy - end_page_writeback()
  				 * might have just cleared PageReclaim, then
  				 * setting PageReclaim here end up interpreted
  				 * as PageReadahead - but that does not matter
  				 * enough to care.  What we do want is for this
  				 * page to have PageReclaim set next time memcg
  				 * reclaim reaches the tests above, so it will
  				 * then wait_on_page_writeback() to avoid OOM;
  				 * and it's also appropriate in global reclaim.
  				 */
  				SetPageReclaim(page);

  				nr_writeback++;

  				goto activate_locked;

  
  			/* Case 3 above */
  			} else {

  				unlock_page(page);

  				wait_on_page_writeback(page);

  				/* then go back and try same page again */
  				list_add_tail(&page->lru, page_list);
  				continue;

  			}

  		}

  		if (!force_reclaim)
  			references = page_check_references(page, sc);

  		switch (references) {
  		case PAGEREF_ACTIVATE:

  			goto activate_locked;

  		case PAGEREF_KEEP:

  			nr_ref_keep++;

  			goto keep_locked;

  		case PAGEREF_RECLAIM:
  		case PAGEREF_RECLAIM_CLEAN:
  			; /* try to reclaim the page below */
  		}

  		/*
  		 * Anonymous process memory has backing store?
  		 * Try to allocate it some swap space here.

  		 * Lazyfree page could be freed directly

  		 */

  		if (PageAnon(page) && PageSwapBacked(page)) {
  			if (!PageSwapCache(page)) {
  				if (!(sc->gfp_mask & __GFP_IO))
  					goto keep_locked;
  				if (PageTransHuge(page)) {
  					/* cannot split THP, skip it */
  					if (!can_split_huge_page(page, NULL))
  						goto activate_locked;
  					/*
  					 * Split pages without a PMD map right
  					 * away. Chances are some or all of the
  					 * tail pages can be freed without IO.
  					 */
  					if (!compound_mapcount(page) &&
  					    split_huge_page_to_list(page,
  								    page_list))
  						goto activate_locked;
  				}
  				if (!add_to_swap(page)) {
  					if (!PageTransHuge(page))
  						goto activate_locked;
  					/* Fallback to swap normal pages */
  					if (split_huge_page_to_list(page,
  								    page_list))
  						goto activate_locked;

  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
  					count_vm_event(THP_SWPOUT_FALLBACK);
  #endif

  					if (!add_to_swap(page))
  						goto activate_locked;
  				}

  				may_enter_fs = 1;

  				/* Adding to swap updated mapping */
  				mapping = page_mapping(page);
  			}

  		} else if (unlikely(PageTransHuge(page))) {
  			/* Split file THP */
  			if (split_huge_page_to_list(page, page_list))
  				goto keep_locked;

  		}

  
  		/*
  		 * The page is mapped into the page tables of one or more
  		 * processes. Try to unmap it here.
  		 */

  		if (page_mapped(page)) {

  			enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH;
  
  			if (unlikely(PageTransHuge(page)))
  				flags |= TTU_SPLIT_HUGE_PMD;
  			if (!try_to_unmap(page, flags)) {

  				nr_unmap_fail++;

  				goto activate_locked;

  			}
  		}
  
  		if (PageDirty(page)) {

  			/*

  			 * Only kswapd can writeback filesystem pages
  			 * to avoid risk of stack overflow. But avoid
  			 * injecting inefficient single-page IO into
  			 * flusher writeback as much as possible: only
  			 * write pages when we've encountered many
  			 * dirty pages, and when we've already scanned
  			 * the rest of the LRU for clean pages and see
  			 * the same dirty pages again (PageReclaim).

  			 */

  			if (page_is_file_cache(page) &&

  			    (!current_is_kswapd() || !PageReclaim(page) ||
  			     !test_bit(PGDAT_DIRTY, &pgdat->flags))) {

  				/*
  				 * Immediately reclaim when written back.
  				 * Similar in principal to deactivate_page()
  				 * except we already have the page isolated
  				 * and know it's dirty
  				 */

  				inc_node_page_state(page, NR_VMSCAN_IMMEDIATE);

  				SetPageReclaim(page);

  				goto activate_locked;

  			}

  			if (references == PAGEREF_RECLAIM_CLEAN)

  				goto keep_locked;

  			if (!may_enter_fs)

  				goto keep_locked;

  			if (!sc->may_writepage)

  				goto keep_locked;

  			/*
  			 * Page is dirty. Flush the TLB if a writable entry
  			 * potentially exists to avoid CPU writes after IO
  			 * starts and then write it out here.
  			 */
  			try_to_unmap_flush_dirty();

  			switch (pageout(page, mapping, sc)) {

  			case PAGE_KEEP:
  				goto keep_locked;
  			case PAGE_ACTIVATE:
  				goto activate_locked;
  			case PAGE_SUCCESS:

  				if (PageWriteback(page))

  					goto keep;

  				if (PageDirty(page))

  					goto keep;

  				/*
  				 * A synchronous write - probably a ramdisk.  Go
  				 * ahead and try to reclaim the page.
  				 */

  				if (!trylock_page(page))

  					goto keep;
  				if (PageDirty(page) || PageWriteback(page))
  					goto keep_locked;
  				mapping = page_mapping(page);
  			case PAGE_CLEAN:
  				; /* try to free the page below */
  			}
  		}
  
  		/*
  		 * If the page has buffers, try to free the buffer mappings
  		 * associated with this page. If we succeed we try to free
  		 * the page as well.
  		 *
  		 * We do this even if the page is PageDirty().
  		 * try_to_release_page() does not perform I/O, but it is
  		 * possible for a page to have PageDirty 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.

  		 * try_to_release_page() will discover that cleanness and will
  		 * drop the buffers and mark the page clean - it can be freed.
  		 *
  		 * Rarely, pages can have buffers and no ->mapping.  These are
  		 * the pages which were not successfully invalidated in
  		 * truncate_complete_page().  We try to drop those buffers here
  		 * and if that worked, and the page is no longer mapped into
  		 * process address space (page_count == 1) it can be freed.
  		 * Otherwise, leave the page on the LRU so it is swappable.
  		 */

  		if (page_has_private(page)) {

  			if (!try_to_release_page(page, sc->gfp_mask))
  				goto activate_locked;

  			if (!mapping && page_count(page) == 1) {
  				unlock_page(page);
  				if (put_page_testzero(page))
  					goto free_it;
  				else {
  					/*
  					 * rare race with speculative reference.
  					 * the speculative reference will free
  					 * this page shortly, so we may
  					 * increment nr_reclaimed here (and
  					 * leave it off the LRU).
  					 */
  					nr_reclaimed++;
  					continue;
  				}
  			}

  		}

  		if (PageAnon(page) && !PageSwapBacked(page)) {
  			/* follow __remove_mapping for reference */
  			if (!page_ref_freeze(page, 1))
  				goto keep_locked;
  			if (PageDirty(page)) {
  				page_ref_unfreeze(page, 1);
  				goto keep_locked;
  			}

  			count_vm_event(PGLAZYFREED);

  			count_memcg_page_event(page, PGLAZYFREED);

  		} else if (!mapping || !__remove_mapping(mapping, page, true))
  			goto keep_locked;

  		/*
  		 * At this point, we have no other references and there is
  		 * no way to pick any more up (removed from LRU, removed
  		 * from pagecache). Can use non-atomic bitops now (and
  		 * we obviously don't have to worry about waking up a process
  		 * waiting on the page lock, because there are no references.
  		 */

  		__ClearPageLocked(page);

  free_it:

  		nr_reclaimed++;

  
  		/*
  		 * Is there need to periodically free_page_list? It would
  		 * appear not as the counts should be low
  		 */

  		if (unlikely(PageTransHuge(page))) {
  			mem_cgroup_uncharge(page);
  			(*get_compound_page_dtor(page))(page);
  		} else
  			list_add(&page->lru, &free_pages);

  		continue;
  
  activate_locked:

  		/* Not a candidate for swapping, so reclaim swap space. */

  		if (PageSwapCache(page) && (mem_cgroup_swap_full(page) ||
  						PageMlocked(page)))

  			try_to_free_swap(page);

  		VM_BUG_ON_PAGE(PageActive(page), page);

  		if (!PageMlocked(page)) {
  			SetPageActive(page);
  			pgactivate++;

  			count_memcg_page_event(page, PGACTIVATE);

  		}

  keep_locked:
  		unlock_page(page);
  keep:
  		list_add(&page->lru, &ret_pages);

  		VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);

  	}

  	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 (stat) {
  		stat->nr_dirty = nr_dirty;
  		stat->nr_congested = nr_congested;
  		stat->nr_unqueued_dirty = nr_unqueued_dirty;
  		stat->nr_writeback = nr_writeback;
  		stat->nr_immediate = nr_immediate;

  		stat->nr_activate = pgactivate;
  		stat->nr_ref_keep = nr_ref_keep;
  		stat->nr_unmap_fail = nr_unmap_fail;

  	}

  	return nr_reclaimed;

  }

  unsigned long reclaim_clean_pages_from_list(struct zone *zone,
  					    struct list_head *page_list)
  {
  	struct scan_control sc = {
  		.gfp_mask = GFP_KERNEL,
  		.priority = DEF_PRIORITY,
  		.may_unmap = 1,
  	};

  	unsigned long ret;

  	struct page *page, *next;
  	LIST_HEAD(clean_pages);
  
  	list_for_each_entry_safe(page, next, page_list, lru) {

  		if (page_is_file_cache(page) && !PageDirty(page) &&

  		    !__PageMovable(page)) {

  			ClearPageActive(page);
  			list_move(&page->lru, &clean_pages);
  		}
  	}

  	ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,

  			TTU_IGNORE_ACCESS, NULL, true);

  	list_splice(&clean_pages, page_list);

  	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret);

  	return ret;
  }

  /*
   * Attempt to remove the specified page from its LRU.  Only take this page
   * if it is of the appropriate PageActive status.  Pages which are being
   * freed elsewhere are also ignored.
   *
   * page:	page to consider
   * mode:	one of the LRU isolation modes defined above
   *
   * returns 0 on success, -ve errno on failure.
   */

  int __isolate_lru_page(struct page *page, isolate_mode_t mode)

  {
  	int ret = -EINVAL;
  
  	/* Only take pages on the LRU. */
  	if (!PageLRU(page))
  		return ret;

  	/* Compaction should not handle unevictable pages but CMA can do so */
  	if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))

  		return ret;

  	ret = -EBUSY;

  	/*
  	 * To minimise LRU disruption, the caller can indicate that it only
  	 * wants to isolate pages it will be able to operate on without
  	 * blocking - clean pages for the most part.
  	 *

  	 * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
  	 * that it is possible to migrate without blocking
  	 */

  	if (mode & ISOLATE_ASYNC_MIGRATE) {

  		/* All the caller can do on PageWriteback is block */
  		if (PageWriteback(page))
  			return ret;
  
  		if (PageDirty(page)) {
  			struct address_space *mapping;

  			bool migrate_dirty;

  			/*
  			 * Only pages without mappings or that have a
  			 * ->migratepage callback are possible to migrate

  			 * without blocking. However, we can be racing with
  			 * truncation so it's necessary to lock the page
  			 * to stabilise the mapping as truncation holds
  			 * the page lock until after the page is removed
  			 * from the page cache.

  			 */

  			if (!trylock_page(page))
  				return ret;

  			mapping = page_mapping(page);

  			migrate_dirty = !mapping || mapping->a_ops->migratepage;

  			unlock_page(page);
  			if (!migrate_dirty)

  				return ret;
  		}
  	}

  	if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
  		return ret;

  	if (likely(get_page_unless_zero(page))) {
  		/*
  		 * Be careful not to clear PageLRU until after we're
  		 * sure the page is not being freed elsewhere -- the
  		 * page release code relies on it.
  		 */
  		ClearPageLRU(page);
  		ret = 0;
  	}
  
  	return ret;
  }

  
  /*
   * Update LRU sizes after isolating pages. The LRU size updates must
   * be complete before mem_cgroup_update_lru_size due to a santity 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]);

  #ifdef CONFIG_MEMCG

  		mem_cgroup_update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);

  #endif

  	}

  }

  /*

   * zone_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).
   *
   * Appropriate locks 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

   * @mode:	One of the LRU isolation modes

   * @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,

  		isolate_mode_t mode, 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(pages_skipped);

  	scan = 0;
  	for (total_scan = 0;
  	     scan < nr_to_scan && nr_taken < nr_to_scan && !list_empty(src);
  	     total_scan++) {

  		struct page *page;

  		page = lru_to_page(src);
  		prefetchw_prev_lru_page(page, src, flags);

  		VM_BUG_ON_PAGE(!PageLRU(page), page);

  		if (page_zonenum(page) > sc->reclaim_idx) {
  			list_move(&page->lru, &pages_skipped);

  			nr_skipped[page_zonenum(page)]++;

  			continue;
  		}

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

  		switch (__isolate_lru_page(page, mode)) {

  		case 0:

  			nr_pages = hpage_nr_pages(page);
  			nr_taken += nr_pages;
  			nr_zone_taken[page_zonenum(page)] += nr_pages;

  			list_move(&page->lru, dst);

  			break;
  
  		case -EBUSY:
  			/* else it is being freed elsewhere */
  			list_move(&page->lru, src);
  			continue;

  		default:
  			BUG();
  		}

  	}

  	/*
  	 * Splice any skipped pages 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 pages to skip and put the
  	 * system at risk of premature OOM.
  	 */

  	if (!list_empty(&pages_skipped)) {
  		int zid;

  		list_splice(&pages_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, mode, lru);

  	update_lru_sizes(lruvec, lru, nr_zone_taken);

  	return nr_taken;
  }

  /**
   * isolate_lru_page - tries to isolate a page from its LRU list
   * @page: page to isolate from its LRU list
   *
   * Isolates a @page from an LRU list, clears PageLRU and adjusts the
   * vmstat statistic corresponding to whatever LRU list the page was on.
   *
   * Returns 0 if the page was removed from an LRU list.
   * Returns -EBUSY if the page was not on an LRU list.
   *
   * The returned page will have PageLRU() cleared.  If it was found on

   * the active list, it will have PageActive set.  If it was found on
   * the unevictable list, it will have the PageUnevictable bit set. That flag
   * may need to be cleared by the caller before letting the page go.

   *
   * The vmstat statistic corresponding to the list on which the page was
   * found will be decremented.
   *
   * Restrictions:

   *

   * (1) Must be called with an elevated refcount on the page. This is a
   *     fundamentnal 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.
   */
  int isolate_lru_page(struct page *page)
  {
  	int ret = -EBUSY;

  	VM_BUG_ON_PAGE(!page_count(page), page);

  	WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");

  	if (PageLRU(page)) {
  		struct zone *zone = page_zone(page);

  		struct lruvec *lruvec;

  		spin_lock_irq(zone_lru_lock(zone));

  		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);

  		if (PageLRU(page)) {

  			int lru = page_lru(page);

  			get_page(page);

  			ClearPageLRU(page);

  			del_page_from_lru_list(page, lruvec, lru);
  			ret = 0;

  		}

  		spin_unlock_irq(zone_lru_lock(zone));

  	}
  	return ret;
  }

  /*

   * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
   * then get resheduled. 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;
  
  	if (current_is_kswapd())
  		return 0;

  	if (!sane_reclaim(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;

  	return isolated > inactive;
  }

  static noinline_for_stack void

  putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)

  {

  	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;

  	struct pglist_data *pgdat = lruvec_pgdat(lruvec);

  	LIST_HEAD(pages_to_free);

  	/*
  	 * Put back any unfreeable pages.
  	 */

  	while (!list_empty(page_list)) {

  		struct page *page = lru_to_page(page_list);

  		int lru;

  		VM_BUG_ON_PAGE(PageLRU(page), page);

  		list_del(&page->lru);

  		if (unlikely(!page_evictable(page))) {

  			spin_unlock_irq(&pgdat->lru_lock);

  			putback_lru_page(page);

  			spin_lock_irq(&pgdat->lru_lock);

  			continue;
  		}

  		lruvec = mem_cgroup_page_lruvec(page, pgdat);