mm/vmscan.c

/*
 *  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/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;

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

	/* Allocation order */
	int order;

	/*
	 * 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 (total_size >> priority) pages at once */
	int priority;

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

	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;

	/* Can cgroups be reclaimed below their normal consumption range? */
	unsigned int may_thrash:1;

	unsigned int hibernation_mode:1;

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

	/* 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;
};

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

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

unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat)
{
	unsigned long nr;

	nr = node_page_state_snapshot(pgdat, NR_ACTIVE_FILE) +
	     node_page_state_snapshot(pgdat, NR_INACTIVE_FILE) +
	     node_page_state_snapshot(pgdat, NR_ISOLATED_FILE);

	if (get_nr_swap_pages() > 0)
		nr += node_page_state_snapshot(pgdat, NR_ACTIVE_ANON) +
		      node_page_state_snapshot(pgdat, NR_INACTIVE_ANON) +
		      node_page_state_snapshot(pgdat, NR_ISOLATED_ANON);

	return nr;
}

bool pgdat_reclaimable(struct pglist_data *pgdat)
{
	return node_page_state_snapshot(pgdat, NR_PAGES_SCANNED) <
		pgdat_reclaimable_pages(pgdat) * 6;
}

/**
 * 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 register_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;

	down_write(&shrinker_rwsem);
	list_add_tail(&shrinker->list, &shrinker_list);
	up_write(&shrinker_rwsem);
	return 0;
}
EXPORT_SYMBOL(register_shrinker);

/*
 * Remove one
 */
void unregister_shrinker(struct shrinker *shrinker)
{
	down_write(&shrinker_rwsem);
	list_del(&shrinker->list);
	up_write(&shrinker_rwsem);
	kfree(shrinker->nr_deferred);
}
EXPORT_SYMBOL(unregister_shrinker);

#define SHRINK_BATCH 128

static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
				    struct shrinker *shrinker,
				    unsigned long nr_scanned,
				    unsigned long nr_eligible)
{
	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;
	long min_cache_size = batch_size;

	if (current_is_kswapd())
		min_cache_size = 0;

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

	/*
	 * 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 = (4 * nr_scanned) / shrinker->seeks;
	delta *= freeable;
	do_div(delta, nr_eligible + 1);
	total_scan += delta;
	if (total_scan < 0) {
		pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
		       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,
				   nr_scanned, nr_eligible,
				   freeable, delta, total_scan);

	/*
	 * 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 > min_cache_size ||
	       total_scan >= freeable) {
		unsigned long ret;
		unsigned long nr_to_scan = min(batch_size, total_scan);

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

		count_vm_events(SLABS_SCANNED, nr_to_scan);
		total_scan -= nr_to_scan;
		scanned += nr_to_scan;

		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;
}

/**
 * shrink_slab - shrink slab caches
 * @gfp_mask: allocation context
 * @nid: node whose slab caches to target
 * @memcg: memory cgroup whose slab caches to target
 * @nr_scanned: pressure numerator
 * @nr_eligible: pressure denominator
 *
 * 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. If it is not NULL,
 * only shrinkers with SHRINKER_MEMCG_AWARE set will be called to scan
 * objects from the memory cgroup specified. Otherwise, only unaware
 * shrinkers are called.
 *
 * @nr_scanned and @nr_eligible form a ratio that indicate how much of
 * the available objects should be scanned.  Page reclaim for example
 * passes the number of pages scanned and the number of pages on the
 * LRU lists that it considered on @nid, plus a bias in @nr_scanned
 * when it encountered mapped pages.  The ratio is further biased by
 * the ->seeks setting of the shrink function, which indicates the
 * cost to recreate an object relative to that of an LRU page.
 *
 * Returns the number of reclaimed slab objects.
 */
static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
				 struct mem_cgroup *memcg,
				 unsigned long nr_scanned,
				 unsigned long nr_eligible)
{
	struct shrinker *shrinker;
	unsigned long freed = 0;

	if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
		return 0;

	if (nr_scanned == 0)
		nr_scanned = SWAP_CLUSTER_MAX;

	if (!down_read_trylock(&shrinker_rwsem)) {
		/*
		 * If we would return 0, our callers would understand that we
		 * have nothing else to shrink and give up trying. By returning
		 * 1 we keep it going and assume we'll be able to shrink next
		 * time.
		 */
		freed = 1;
		goto out;
	}

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

		/*
		 * If kernel memory accounting is disabled, we ignore
		 * SHRINKER_MEMCG_AWARE flag and call all shrinkers
		 * passing NULL for memcg.
		 */
		if (memcg_kmem_enabled() &&
		    !!memcg != !!(shrinker->flags & SHRINKER_MEMCG_AWARE))
			continue;

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

		freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible);
	}

	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;
		do {
			freed += shrink_slab(GFP_KERNEL, nid, memcg,
					     1000, 1000);
		} 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.
	 */
	return page_count(page) - page_has_private(page) == 2;
}

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\n", __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;

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

	spin_lock_irqsave(&mapping->tree_lock, 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 tree_lock, then this ordering is not required.
	 */
	if (!page_ref_freeze(page, 2))
		goto cannot_free;
	/* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
	if (unlikely(PageDirty(page))) {
		page_ref_unfreeze(page, 2);
		goto cannot_free;
	}

	if (PageSwapCache(page)) {
		swp_entry_t swap = { .val = page_private(page) };
		mem_cgroup_swapout(page, swap);
		__delete_from_swap_cache(page);
		spin_unlock_irqrestore(&mapping->tree_lock, flags);
		swapcache_free(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 page_tree.
		 */
		if (reclaimed && page_is_file_cache(page) &&
		    !mapping_exiting(mapping) && !dax_mapping(mapping))
			shadow = workingset_eviction(mapping, page);
		__delete_from_page_cache(page, shadow);
		spin_unlock_irqrestore(&mapping->tree_lock, flags);

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

	return 1;

cannot_free:
	spin_unlock_irqrestore(&mapping->tree_lock, 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)
{
	bool is_unevictable;
	int was_unevictable = PageUnevictable(page);

	VM_BUG_ON_PAGE(PageLRU(page), page);

redo:
	ClearPageUnevictable(page);

	if (page_evictable(page)) {
		/*
		 * For evictable pages, we can use the cache.
		 * In event of a race, worst case is we end up with an
		 * unevictable page on [in]active list.
		 * We know how to handle that.
		 */
		is_unevictable = false;
		lru_cache_add(page);
	} else {
		/*
		 * Put unevictable pages directly on zone's unevictable
		 * list.
		 */
		is_unevictable = true;
		add_page_to_unevictable_list(page);
		/*
		 * When racing with an mlock or AS_UNEVICTABLE clearing
		 * (page is unlocked) make sure that if the other thread
		 * does not observe our setting of PG_lru and fails
		 * isolation/check_move_unevictable_pages,
		 * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
		 * the page back to the evictable list.
		 *
		 * The other side is TestClearPageMlocked() or shmem_lock().
		 */
		smp_mb();
	}

	/*
	 * page's status can change while we move it among lru. If an evictable
	 * page is on unevictable list, it never be freed. To avoid that,
	 * check after we added it to the list, again.
	 */
	if (is_unevictable && page_evictable(page)) {
		if (!isolate_lru_page(page)) {
			put_page(page);
			goto redo;
		}
		/* This means someone else dropped this page from LRU
		 * So, it will be freed or putback to LRU again. There is
		 * nothing to do here.
		 */
	}

	if (was_unevictable && !is_unevictable)
		count_vm_event(UNEVICTABLE_PGRESCUED);
	else if (!was_unevictable && is_unevictable)
		count_vm_event(UNEVICTABLE_PGCULLED);

	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)) {
		*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,
				      unsigned long *ret_nr_dirty,
				      unsigned long *ret_nr_unqueued_dirty,
				      unsigned long *ret_nr_congested,
				      unsigned long *ret_nr_writeback,
				      unsigned long *ret_nr_immediate,
				      bool force_reclaim)
{
	LIST_HEAD(ret_pages);
	LIST_HEAD(free_pages);
	int pgactivate = 0;
	unsigned long nr_unqueued_dirty = 0;
	unsigned long nr_dirty = 0;
	unsigned long nr_congested = 0;
	unsigned long nr_reclaimed = 0;
	unsigned long nr_writeback = 0;
	unsigned long nr_immediate = 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;
		bool dirty, writeback;
		bool lazyfree = false;
		int ret = SWAP_SUCCESS;

		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);
		if (pgdat)
			VM_BUG_ON_PAGE(page_pgdat(page) != pgdat, page);

		sc->nr_scanned++;

		if (unlikely(!page_evictable(page)))
			goto cull_mlocked;

		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))
			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 zone 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.
		 */
		if (PageWriteback(page)) {
			/* Case 1 above */
			if (current_is_kswapd() &&
			    PageReclaim(page) &&
			    (pgdat && test_bit(PGDAT_WRITEBACK, &pgdat->flags))) {
				nr_immediate++;
				goto keep_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 keep_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:
			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.
		 */
		if (PageAnon(page) && !PageSwapCache(page)) {
			if (!(sc->gfp_mask & __GFP_IO))
				goto keep_locked;
			if (!add_to_swap(page, page_list))
				goto activate_locked;
			lazyfree = true;
			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;
		}

		VM_BUG_ON_PAGE(PageTransHuge(page), page);

		/*
		 * The page is mapped into the page tables of one or more
		 * processes. Try to unmap it here.
		 */
		if (page_mapped(page) && mapping) {
			switch (ret = try_to_unmap(page, lazyfree ?
				(ttu_flags | TTU_BATCH_FLUSH | TTU_LZFREE) :
				(ttu_flags | TTU_BATCH_FLUSH))) {
			case SWAP_FAIL:
				goto activate_locked;
			case SWAP_AGAIN:
				goto keep_locked;
			case SWAP_MLOCK:
				goto cull_mlocked;
			case SWAP_LZFREE:
				goto lazyfree;
			case SWAP_SUCCESS:
				; /* try to free the page below */
			}
		}

		if (PageDirty(page)) {
			/*
			 * Only kswapd can writeback filesystem pages to
			 * avoid risk of stack overflow but only writeback
			 * if many dirty pages have been encountered.
			 */
			if (page_is_file_cache(page) &&
					(!current_is_kswapd() ||
					(pgdat &&
					 !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 keep_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;
				}
			}
		}

lazyfree:
		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:
		if (ret == SWAP_LZFREE)
			count_vm_event(PGLAZYFREED);

		nr_reclaimed++;

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

cull_mlocked:
		if (PageSwapCache(page))
			try_to_free_swap(page);
		unlock_page(page);
		list_add(&page->lru, &ret_pages);
		continue;

activate_locked:
		/* Not a candidate for swapping, so reclaim swap space. */
		if (PageSwapCache(page) && mem_cgroup_swap_full(page))
			try_to_free_swap(page);
		VM_BUG_ON_PAGE(PageActive(page), page);
		SetPageActive(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_hot_cold_page_list(&free_pages, true);

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

	*ret_nr_dirty += nr_dirty;
	*ret_nr_congested += nr_congested;
	*ret_nr_unqueued_dirty += nr_unqueued_dirty;
	*ret_nr_writeback += nr_writeback;
	*ret_nr_immediate += nr_immediate;
	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,
		/* Doesn't allow to write out dirty page */
		.may_writepage = 0,
	};
	unsigned long ret, dummy1, dummy2, dummy3, dummy4, dummy5;
	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_UNMAP|TTU_IGNORE_ACCESS,
			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
	list_splice(&clean_pages, page_list);
	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret);
	return ret;
}

#ifdef CONFIG_PROCESS_RECLAIM
static unsigned long shrink_page(struct page *page,
					struct zone *zone,
					struct scan_control *sc,
					enum ttu_flags ttu_flags,
					unsigned long *dummy1,
					unsigned long *dummy2,
					unsigned long *dummy3,
					unsigned long *dummy4,
					unsigned long *dummy5,
					bool force_reclaim,
					struct list_head *ret_pages)
{
	int reclaimed;
	LIST_HEAD(page_list);
	list_add(&page->lru, &page_list);

	reclaimed = shrink_page_list(&page_list, zone->zone_pgdat, sc,
				ttu_flags, dummy1, dummy2, dummy3, dummy4,
				dummy5, force_reclaim);
	if (!reclaimed)
		list_splice(&page_list, ret_pages);

	return reclaimed;
}

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

	LIST_HEAD(ret_pages);
	struct page *page;
	unsigned long dummy1, dummy2, dummy3, dummy4, dummy5;
	unsigned long nr_reclaimed = 0;

	while (!list_empty(page_list)) {
		page = lru_to_page(page_list);
		list_del(&page->lru);

		ClearPageActive(page);
		nr_reclaimed += shrink_page(page, page_zone(page), &sc,
			TTU_UNMAP|TTU_IGNORE_ACCESS,
			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true,
			&ret_pages);
	}

	while (!list_empty(&ret_pages)) {
		page = lru_to_page(&ret_pages);
		list_del(&page->lru);
		dec_node_page_state(page, NR_ISOLATED_ANON +
				page_is_file_cache(page));
		putback_lru_page(page);
	}

	return nr_reclaimed;
}
#endif

/*
 * 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_CLEAN means that only clean pages should be isolated. This
	 * is used by reclaim when it is cannot write to backing storage
	 *
	 * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
	 * that it is possible to migrate without blocking
	 */
	if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) {
		/* All the caller can do on PageWriteback is block */
		if (PageWriteback(page))
			return ret;

		if (PageDirty(page)) {
			struct address_space *mapping;

			/* ISOLATE_CLEAN means only clean pages */
			if (mode & ISOLATE_CLEAN)
				return ret;

			/*
			 * Only pages without mappings or that have a
			 * ->migratepage callback are possible to migrate
			 * without blocking
			 */
			mapping = page_mapping(page);
			if (mapping && !mapping->a_ops->migratepage)
				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 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 scan, nr_pages;
	LIST_HEAD(pages_skipped);

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

		/*
		 * Account for scanned and skipped separetly to avoid the pgdat
		 * being prematurely marked unreclaimable by pgdat_reclaimable.
		 */
		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;
		unsigned long total_skipped = 0;

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

			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
			total_skipped += nr_skipped[zid];
		}

		/*
		 * Account skipped pages as a partial scan as the pgdat may be
		 * close to unreclaimable. If the LRU list is empty, account
		 * skipped pages as a full scan.
		 */
		scan += list_empty(src) ? total_skipped : total_skipped >> 2;

		list_splice(&pages_skipped, src);
	}
	*nr_scanned = scan;
	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
				    nr_taken, mode, is_file_lru(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);

		SetPageLRU(page);
		lru = page_lru(page);
		add_page_to_lru_list(page, lruvec, lru);

		if (is_active_lru(lru)) {
			int file = is_file_lru(lru);
			int numpages = hpage_nr_pages(page);
			reclaim_stat->recent_rotated[file] += numpages;
		}
		if (put_page_testzero(page)) {
			__ClearPageLRU(page);
			__ClearPageActive(page);
			del_page_from_lru_list(page, lruvec, lru);

			if (unlikely(PageCompound(page))) {
				spin_unlock_irq(&pgdat->lru_lock);
				mem_cgroup_uncharge(page);
				(*get_compound_page_dtor(page))(page);
				spin_lock_irq(&pgdat->lru_lock);
			} else
				list_add(&page->lru, &pages_to_free);
		}
	}

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

/*
 * If a kernel thread (such as nfsd for loop-back mounts) services
 * a backing device by writing to the page cache it sets PF_LESS_THROTTLE.
 * In that case we should only throttle if the backing device it is
 * writing to is congested.  In other cases it is safe to throttle.
 */
static int current_may_throttle(void)
{
	return !(current->flags & PF_LESS_THROTTLE) ||
		current->backing_dev_info == NULL ||
		bdi_write_congested(current->backing_dev_info);
}

static bool inactive_reclaimable_pages(struct lruvec *lruvec,
				struct scan_control *sc, enum lru_list lru)
{
	int zid;
	struct zone *zone;
	int file = is_file_lru(lru);
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);

	if (!global_reclaim(sc))
		return true;

	for (zid = sc->reclaim_idx; zid >= 0; zid--) {
		zone = &pgdat->node_zones[zid];
		if (!managed_zone(zone))
			continue;

		if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
				LRU_FILE * file) >= SWAP_CLUSTER_MAX)
			return true;
	}

	return false;
}

/*
 * shrink_inactive_list() is a helper for shrink_node().  It returns the number
 * of reclaimed pages
 */
static noinline_for_stack 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 long nr_reclaimed = 0;
	unsigned long nr_taken;
	unsigned long nr_dirty = 0;
	unsigned long nr_congested = 0;
	unsigned long nr_unqueued_dirty = 0;
	unsigned long nr_writeback = 0;
	unsigned long nr_immediate = 0;
	isolate_mode_t isolate_mode = 0;
	int file = is_file_lru(lru);
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;

	if (!inactive_reclaimable_pages(lruvec, sc, lru))
		return 0;

	while (unlikely(too_many_isolated(pgdat, file, sc))) {
		congestion_wait(BLK_RW_ASYNC, HZ/10);

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

	lru_add_drain();

	if (!sc->may_unmap)
		isolate_mode |= ISOLATE_UNMAPPED;
	if (!sc->may_writepage)
		isolate_mode |= ISOLATE_CLEAN;

	spin_lock_irq(&pgdat->lru_lock);

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

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
	reclaim_stat->recent_scanned[file] += nr_taken;

	if (global_reclaim(sc)) {
		__mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned);
		if (current_is_kswapd())
			__count_vm_events(PGSCAN_KSWAPD, nr_scanned);
		else
			__count_vm_events(PGSCAN_DIRECT, nr_scanned);
	}
	spin_unlock_irq(&pgdat->lru_lock);

	if (nr_taken == 0)
		return 0;

	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, TTU_UNMAP,
				&nr_dirty, &nr_unqueued_dirty, &nr_congested,
				&nr_writeback, &nr_immediate,
				false);

	spin_lock_irq(&pgdat->lru_lock);

	if (global_reclaim(sc)) {
		if (current_is_kswapd())
			__count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed);
		else
			__count_vm_events(PGSTEAL_DIRECT, nr_reclaimed);
	}

	putback_inactive_pages(lruvec, &page_list);

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);

	spin_unlock_irq(&pgdat->lru_lock);

	mem_cgroup_uncharge_list(&page_list);
	free_hot_cold_page_list(&page_list, true);

	/*
	 * 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 zone is flagged ZONE_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 (nr_writeback && nr_writeback == nr_taken)
		set_bit(PGDAT_WRITEBACK, &pgdat->flags);

	/*
	 * Legacy memcg will stall in page writeback so avoid forcibly
	 * stalling here.
	 */
	if (sane_reclaim(sc)) {
		/*
		 * Tag a zone as congested if all the dirty pages scanned were
		 * backed by a congested BDI and wait_iff_congested will stall.
		 */
		if (nr_dirty && nr_dirty == nr_congested)
			set_bit(PGDAT_CONGESTED, &pgdat->flags);

		/*
		 * If dirty pages are scanned that are not queued for IO, it
		 * implies that flushers are not keeping up. In this case, flag
		 * the pgdat PGDAT_DIRTY and kswapd will start writing pages from
		 * reclaim context.
		 */
		if (nr_unqueued_dirty == nr_taken)
			set_bit(PGDAT_DIRTY, &pgdat->flags);

		/*
		 * If kswapd scans pages marked marked for immediate
		 * reclaim and under writeback (nr_immediate), it implies
		 * that pages are cycling through the LRU faster than
		 * they are written so also forcibly stall.
		 */
		if (nr_immediate && current_may_throttle())
			congestion_wait(BLK_RW_ASYNC, HZ/10);
	}

	/*
	 * Stall direct reclaim for IO completions if underlying BDIs or zone
	 * is congested. Allow kswapd to continue until it starts encountering
	 * unqueued dirty pages or cycling through the LRU too quickly.
	 */
	if (!sc->hibernation_mode && !current_is_kswapd() &&
	    current_may_throttle())
		wait_iff_congested(pgdat, BLK_RW_ASYNC, HZ/10);

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

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

static void move_active_pages_to_lru(struct lruvec *lruvec,
				     struct list_head *list,
				     struct list_head *pages_to_free,
				     enum lru_list lru)
{
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
	unsigned long pgmoved = 0;
	struct page *page;
	int nr_pages;

	while (!list_empty(list)) {
		page = lru_to_page(list);
		lruvec = mem_cgroup_page_lruvec(page, pgdat);

		VM_BUG_ON_PAGE(PageLRU(page), page);
		SetPageLRU(page);

		nr_pages = hpage_nr_pages(page);
		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
		list_move(&page->lru, &lruvec->lists[lru]);
		pgmoved += nr_pages;

		if (put_page_testzero(page)) {
			__ClearPageLRU(page);
			__ClearPageActive(page);
			del_page_from_lru_list(page, lruvec, lru);

			if (unlikely(PageCompound(page))) {
				spin_unlock_irq(&pgdat->lru_lock);
				mem_cgroup_uncharge(page);
				(*get_compound_page_dtor(page))(page);
				spin_lock_irq(&pgdat->lru_lock);
			} else
				list_add(&page->lru, pages_to_free);
		}
	}

	if (!is_active_lru(lru))
		__count_vm_events(PGDEACTIVATE, pgmoved);
}

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 pages which were snipped off */
	LIST_HEAD(l_active);
	LIST_HEAD(l_inactive);
	struct page *page;
	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
	unsigned long nr_rotated = 0;
	isolate_mode_t isolate_mode = 0;
	int file = is_file_lru(lru);
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);

	lru_add_drain();

	if (!sc->may_unmap)
		isolate_mode |= ISOLATE_UNMAPPED;
	if (!sc->may_writepage)
		isolate_mode |= ISOLATE_CLEAN;

	spin_lock_irq(&pgdat->lru_lock);

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

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
	reclaim_stat->recent_scanned[file] += nr_taken;

	if (global_reclaim(sc))
		__mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned);
	__count_vm_events(PGREFILL, nr_scanned);

	spin_unlock_irq(&pgdat->lru_lock);

	while (!list_empty(&l_hold)) {
		cond_resched();
		page = lru_to_page(&l_hold);
		list_del(&page->lru);

		if (unlikely(!page_evictable(page))) {
			putback_lru_page(page);
			continue;
		}

		if (unlikely(buffer_heads_over_limit)) {
			if (page_has_private(page) && trylock_page(page)) {
				if (page_has_private(page))
					try_to_release_page(page, 0);
				unlock_page(page);
			}
		}

		if (page_referenced(page, 0, sc->target_mem_cgroup,
				    &vm_flags)) {
			nr_rotated += hpage_nr_pages(page);
			/*
			 * Identify referenced, file-backed active pages 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 pages
			 * are not likely to be evicted by use-once streaming
			 * IO, plus JVM can create lots of anon VM_EXEC pages,
			 * so we ignore them here.
			 */
			if ((vm_flags & VM_EXEC) && page_is_file_cache(page)) {
				list_add(&page->lru, &l_active);
				continue;
			}
		}

		ClearPageActive(page);	/* we are de-activating */
		list_add(&page->lru, &l_inactive);
	}

	/*
	 * Move pages back to the lru list.
	 */
	spin_lock_irq(&pgdat->lru_lock);
	/*
	 * Count referenced pages from currently used mappings as rotated,
	 * even though only some of them are actually re-activated.  This
	 * helps balance scan pressure between file and anonymous pages in
	 * get_scan_count.
	 */
	reclaim_stat->recent_rotated[file] += nr_rotated;

	move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
	move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
	spin_unlock_irq(&pgdat->lru_lock);

	mem_cgroup_uncharge_list(&l_hold);
	free_hot_cold_page_list(&l_hold, true);
}

/*
 * 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.
 *
 * The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages
 * on this LRU, maintained by the pageout code. A zone->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_list_is_low(struct lruvec *lruvec, bool file,
						struct scan_control *sc)
{
	unsigned long inactive_ratio;
	unsigned long inactive, active;
	enum lru_list inactive_lru = file * LRU_FILE;
	enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
	unsigned long gb;

	/*
	 * If we don't have swap space, anonymous page deactivation
	 * is pointless.
	 */
	if (!file && !total_swap_pages)
		return false;

	inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
	active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);

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

	return inactive * inactive_ratio < active;
}

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 (inactive_list_is_low(lruvec, is_file_lru(lru), sc))
			shrink_active_list(nr_to_scan, lruvec, sc, lru);
		return 0;
	}

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

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

/*
 * Determine how aggressively the anon and file LRU lists should be
 * scanned.  The relative value of each set of LRU lists is determined
 * by looking at the fraction of the pages scanned we did rotate back
 * onto the active list instead of evict.
 *
 * 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 mem_cgroup *memcg,
			   struct scan_control *sc, unsigned long *nr,
			   unsigned long *lru_pages)
{
	int swappiness = mem_cgroup_swappiness(memcg);
	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
	u64 fraction[2];
	u64 denominator = 0;	/* gcc */
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
	unsigned long anon_prio, file_prio;
	enum scan_balance scan_balance;
	unsigned long anon, file;
	bool force_scan = false;
	unsigned long ap, fp;
	enum lru_list lru;
	bool some_scanned;
	int pass;

	/*
	 * If the zone or memcg is small, nr[l] can be 0.  This
	 * results in no scanning on this priority and a potential
	 * priority drop.  Global direct reclaim can go to the next
	 * zone and tends to have no problems. Global kswapd is for
	 * zone balancing and it needs to scan a minimum amount. When
	 * reclaiming for a memcg, a priority drop can cause high
	 * latencies, so it's better to scan a minimum amount there as
	 * well.
	 */
	if (current_is_kswapd()) {
		if (!pgdat_reclaimable(pgdat))
			force_scan = true;
		if (!mem_cgroup_online(memcg))
			force_scan = true;
	}
	if (!global_reclaim(sc))
		force_scan = true;

	/* If we have no swap space, do not bother scanning anon pages. */
	if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
		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 (!global_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;
	}

	/*
	 * 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 (global_reclaim(sc)) {
		unsigned long pgdatfile;
		unsigned long pgdatfree;
		int z;
		unsigned long total_high_wmark = 0;

		pgdatfree = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
		pgdatfile = 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);
		}

		if (unlikely(pgdatfile + pgdatfree <= total_high_wmark)) {
			scan_balance = SCAN_ANON;
			goto out;
		}
	}

	/*
	 * If there is enough inactive page cache, i.e. if the size of the
	 * inactive list is greater than that of the active list *and* the
	 * inactive list actually has some pages to scan on this priority, we
	 * do not reclaim anything from the anonymous working set right now.
	 * Without the second condition we could end up never scanning an
	 * lruvec even if it has plenty of old anonymous pages unless the
	 * system is under heavy pressure.
	 */
	if (!IS_ENABLED(CONFIG_BALANCE_ANON_FILE_RECLAIM) &&
	    !inactive_list_is_low(lruvec, true, sc) &&
	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
		scan_balance = SCAN_FILE;
		goto out;
	}

	scan_balance = SCAN_FRACT;

	/*
	 * With swappiness at 100, anonymous and file have the same priority.
	 * This scanning priority is essentially the inverse of IO cost.
	 */
	anon_prio = swappiness;
	file_prio = 200 - anon_prio;

	/*
	 * OK, so we have swap space and a fair amount of page cache
	 * pages.  We use the recently rotated / recently scanned
	 * ratios to determine how valuable each cache is.
	 *
	 * Because workloads change over time (and to avoid overflow)
	 * we keep these statistics as a floating average, which ends
	 * up weighing recent references more than old ones.
	 *
	 * anon in [0], file in [1]
	 */

	anon  = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
		lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
	file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
		lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);

	spin_lock_irq(&pgdat->lru_lock);
	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
		reclaim_stat->recent_scanned[0] /= 2;
		reclaim_stat->recent_rotated[0] /= 2;
	}

	if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
		reclaim_stat->recent_scanned[1] /= 2;
		reclaim_stat->recent_rotated[1] /= 2;
	}

	/*
	 * The amount of pressure on anon vs file pages is inversely
	 * proportional to the fraction of recently scanned pages on
	 * each list that were recently referenced and in active use.
	 */
	ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1);
	ap /= reclaim_stat->recent_rotated[0] + 1;

	fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
	fp /= reclaim_stat->recent_rotated[1] + 1;
	spin_unlock_irq(&pgdat->lru_lock);

	fraction[0] = ap;
	fraction[1] = fp;
	denominator = ap + fp + 1;
out:
	some_scanned = false;
	/* Only use force_scan on second pass. */
	for (pass = 0; !some_scanned && pass < 2; pass++) {
		*lru_pages = 0;
		for_each_evictable_lru(lru) {
			int file = is_file_lru(lru);
			unsigned long size;
			unsigned long scan;

			size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
			scan = size >> sc->priority;

			if (!scan && pass && force_scan)
				scan = min(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.
				 */
				scan = div64_u64(scan * fraction[file],
							denominator);
				break;
			case SCAN_FILE:
			case SCAN_ANON:
				/* Scan one type exclusively */
				if ((scan_balance == SCAN_FILE) != file) {
					size = 0;
					scan = 0;
				}
				break;
			default:
				/* Look ma, no brain */
				BUG();
			}

			*lru_pages += size;
			nr[lru] = scan;

			/*
			 * Skip the second pass and don't force_scan,
			 * if we found something to scan.
			 */
			some_scanned |= !!scan;
		}
	}
}

/*
 * This is a basic per-node page freer.  Used by both kswapd and direct reclaim.
 */
static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg,
			      struct scan_control *sc, unsigned long *lru_pages)
{
	struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
	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, memcg, sc, nr, lru_pages);

	/* 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 = (global_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 (inactive_list_is_low(lruvec, false, sc))
		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_zone() that it will have enough free pages to succeed.
 * It will give up earlier than that if there is difficulty reclaiming pages.
 */
static inline bool should_continue_reclaim(struct pglist_data *pgdat,
					unsigned long nr_reclaimed,
					unsigned long nr_scanned,
					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;

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

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

	/* If compaction would go ahead or the allocation would succeed, stop */
	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 */
			;
		}
	}
	return true;
}

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

	do {
		struct mem_cgroup *root = sc->target_mem_cgroup;
		struct mem_cgroup_reclaim_cookie reclaim = {
			.pgdat = pgdat,
			.priority = sc->priority,
		};
		unsigned long node_lru_pages = 0;
		struct mem_cgroup *memcg;

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

		memcg = mem_cgroup_iter(root, NULL, &reclaim);
		do {
			unsigned long lru_pages;
			unsigned long reclaimed;
			unsigned long scanned;

			if (mem_cgroup_low(root, memcg)) {
				if (!sc->may_thrash)
					continue;
				mem_cgroup_events(memcg, MEMCG_LOW, 1);
			}

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

			shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
			node_lru_pages += lru_pages;

			if (memcg)
				shrink_slab(sc->gfp_mask, pgdat->node_id,
					    memcg, sc->nr_scanned - scanned,
					    lru_pages);

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

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

		/*
		 * Shrink the slab caches in the same proportion that
		 * the eligible LRU pages were scanned.
		 */
		if (global_reclaim(sc))
			shrink_slab(sc->gfp_mask, pgdat->node_id, NULL,
				    sc->nr_scanned - nr_scanned,
				    node_lru_pages);

		/*
		 * Record the subtree's reclaim efficiency. The reclaimed
		 * pages from slab is excluded here because the corresponding
		 * scanned pages is not accounted. Moreover, freeing a page
		 * by slab shrinking depends on each slab's object population,
		 * making the cost model (i.e. scan:free) different from that
		 * of LRU.
		 */
		vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
			   sc->nr_scanned - nr_scanned,
			   sc->nr_reclaimed - nr_reclaimed);

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

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

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

	return reclaimable;
}

/*
 * 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);
}

/*
 * 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;

	/*
	 * 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 (global_reclaim(sc)) {
			if (!cpuset_zone_allowed(zone,
						 GFP_KERNEL | __GFP_HARDWALL))
				continue;

			if (sc->priority != DEF_PRIORITY &&
			    !pgdat_reclaimable(zone->zone_pgdat))
				continue;	/* Let kswapd poll it */

			/*
			 * 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() */
		}

		/* 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);
	}

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

/*
 * 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;
	unsigned long total_scanned = 0;
	unsigned long writeback_threshold;
retry:
	delayacct_freepages_start();

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

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

		total_scanned += sc->nr_scanned;
		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;

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

	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;

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

	return 0;
}

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

	for (i = 0; i <= ZONE_NORMAL; i++) {
		zone = &pgdat->node_zones[i];
		if (!managed_zone(zone) ||
		    pgdat_reclaimable_pages(pgdat) == 0)
			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)) {
		pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
						(enum zone_type)ZONE_NORMAL);
		wake_up_interruptible(&pgdat->kswapd_wait);
	}

	return wmark_ok;
}

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

		goto check_pending;
	}

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

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

out:
	return false;
}

unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
				gfp_t gfp_mask, nodemask_t *nodemask)
{
	unsigned long nr_reclaimed;
	struct scan_control sc = {
		.nr_to_reclaim = SWAP_CLUSTER_MAX,
		.gfp_mask = (gfp_mask = memalloc_noio_flags(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,
	};

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

	trace_mm_vmscan_direct_reclaim_begin(order,
				sc.may_writepage,
				gfp_mask,
				sc.reclaim_idx);

	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);

	trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);

	return nr_reclaimed;
}

#ifdef CONFIG_MEMCG

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 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,
	};
	unsigned long lru_pages;

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

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

	/*
	 * 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_node_memcg(pgdat, memcg, &sc, &lru_pages);

	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,
					   bool may_swap)
{
	struct zonelist *zonelist;
	unsigned long nr_reclaimed;
	int nid;
	struct scan_control sc = {
		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
		.gfp_mask = (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 = may_swap,
	};

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

	zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK];

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

	current->flags |= PF_MEMALLOC;
	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
	current->flags &= ~PF_MEMALLOC;

	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);

	return nr_reclaimed;
}
#endif

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

	if (!total_swap_pages)
		return;

	memcg = mem_cgroup_iter(NULL, NULL, NULL);
	do {
		struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);

		if (inactive_list_is_low(lruvec, false, sc))
			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
					   sc, LRU_ACTIVE_ANON);

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

static bool zone_balanced(struct zone *zone, int order, int classzone_idx)
{
	unsigned long mark = high_wmark_pages(zone);

	if (!zone_watermark_ok_safe(zone, order, mark, classzone_idx))
		return false;

	/*
	 * If any eligible zone is balanced then the node is not considered
	 * to be congested or dirty
	 */
	clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
	clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);

	return true;
}

/*
 * Prepare kswapd for sleeping. This verifies that there are no processes
 * waiting in throttle_direct_reclaim() and that watermarks have been met.
 *
 * Returns true if kswapd is ready to sleep
 */
static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
{
	int i;

	/*
	 * The throttled processes are normally woken up in balance_pgdat() as
	 * soon as pfmemalloc_watermark_ok() 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);

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

		if (!managed_zone(zone))
			continue;

		if (!zone_balanced(zone, order, classzone_idx))
			return false;
	}

	return true;
}

/*
 * 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;
}

/*
 * 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 is 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 classzone_idx)
{
	int i;
	unsigned long nr_soft_reclaimed;
	unsigned long nr_soft_scanned;
	struct zone *zone;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.order = order,
		.priority = DEF_PRIORITY,
		.may_writepage = !laptop_mode,
		.may_unmap = 1,
		.may_swap = 1,
	};
	count_vm_event(PAGEOUTRUN);

	do {
		bool raise_priority = true;

		sc.nr_reclaimed = 0;
		sc.reclaim_idx = classzone_idx;

		/*
		 * 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;
			}
		}

		/*
		 * Only reclaim if there are no eligible zones. Check from
		 * high to low zone as allocations prefer higher zones.
		 * Scanning from low to high zone would allow congestion to be
		 * cleared during a very small window when a small low
		 * zone was balanced even under extreme pressure when the
		 * overall node may be congested. Note that sc.reclaim_idx
		 * is not used as buffer_heads_over_limit may have adjusted
		 * it.
		 */
		for (i = classzone_idx; i >= 0; i--) {
			zone = pgdat->node_zones + i;
			if (!managed_zone(zone))
				continue;

			if (zone_balanced(zone, sc.order, classzone_idx))
				goto out;
		}

		/*
		 * 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 || !pgdat_reclaimable(pgdat))
			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) &&
				pfmemalloc_watermark_ok(pgdat))
			wake_up_all(&pgdat->pfmemalloc_wait);

		/* Check if kswapd should be suspending */
		if (try_to_freeze() || kthread_should_stop())
			break;

		/*
		 * Raise priority if scanning rate is too low or there was no
		 * progress in reclaiming pages
		 */
		if (raise_priority || !sc.nr_reclaimed)
			sc.priority--;
	} while (sc.priority >= 1);

out:
	/*
	 * 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;
}

static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
				unsigned int classzone_idx)
{
	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 */
	if (prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) {
		/*
		 * 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, classzone_idx);

		remaining = schedule_timeout(HZ/10);

		/*
		 * If woken prematurely then reset kswapd_classzone_idx and
		 * order. The values will either be from a wakeup request or
		 * the previous request that slept prematurely.
		 */
		if (remaining) {
			pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
			pgdat->kswapd_order = max(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, classzone_idx)) {
		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, classzone_idx;
	pg_data_t *pgdat = (pg_data_t*)p;
	struct task_struct *tsk = current;

	struct reclaim_state reclaim_state = {
		.reclaimed_slab = 0,
	};
	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);

	lockdep_set_current_reclaim_state(GFP_KERNEL);

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

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

	pgdat->kswapd_order = alloc_order = reclaim_order = 0;
	pgdat->kswapd_classzone_idx = classzone_idx = 0;
	for ( ; ; ) {
		bool ret;

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

		/* Read the new order and classzone_idx */
		alloc_order = reclaim_order = pgdat->kswapd_order;
		classzone_idx = pgdat->kswapd_classzone_idx;
		pgdat->kswapd_order = 0;
		pgdat->kswapd_classzone_idx = 0;

		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, classzone_idx,
						alloc_order);
		reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
		if (reclaim_order < alloc_order)
			goto kswapd_try_sleep;

		alloc_order = reclaim_order = pgdat->kswapd_order;
		classzone_idx = pgdat->kswapd_classzone_idx;
	}

	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
	current->reclaim_state = NULL;
	lockdep_clear_current_reclaim_state();

	return 0;
}

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

	if (!managed_zone(zone))
		return;

	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
		return;
	pgdat = zone->zone_pgdat;
	pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
	if (!waitqueue_active(&pgdat->kswapd_wait))
		return;

	/* Only wake kswapd if all zones are unbalanced */
	for (z = 0; z <= classzone_idx; z++) {
		zone = pgdat->node_zones + z;
		if (!managed_zone(zone))
			continue;

		if (zone_balanced(zone, order, classzone_idx))
			return;
	}

	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
	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 reclaim_state reclaim_state;
	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);
	struct task_struct *p = current;
	unsigned long nr_reclaimed;

	p->flags |= PF_MEMALLOC;
	lockdep_set_current_reclaim_state(sc.gfp_mask);
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);

	p->reclaim_state = NULL;
	lockdep_clear_current_reclaim_state();
	p->flags &= ~PF_MEMALLOC;

	return nr_reclaimed;
}
#endif /* CONFIG_HIBERNATION */

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

	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
		for_each_node_state(nid, N_MEMORY) {
			pg_data_t *pgdat = NODE_DATA(nid);
			const struct cpumask *mask;

			mask = cpumask_of_node(pgdat->node_id);

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

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

	if (pgdat->kswapd)
		return 0;

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

/*
 * Called by memory hotplug when all memory in a node is offlined.  Caller must
 * hold mem_hotplug_begin/end().
 */
void kswapd_stop(int nid)
{
	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;

	if (kswapd) {
		kthread_stop(kswapd);
		NODE_DATA(nid)->kswapd = NULL;
	}
}

static int __init kswapd_init(void)
{
	int nid;

	swap_setup();
	for_each_node_state(nid, N_MEMORY)
 		kswapd_run(nid);
	hotcpu_notifier(cpu_callback, 0);
	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;

#define RECLAIM_OFF 0
#define RECLAIM_ZONE (1<<0)	/* Run shrink_inactive_list on the zone */
#define RECLAIM_WRITE (1<<1)	/* Writeout pages during reclaim */
#define RECLAIM_UNMAP (1<<2)	/* Unmap pages during reclaim */

/*
 * 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;
	struct reclaim_state reclaim_state;
	int classzone_idx = gfp_zone(gfp_mask);
	struct scan_control sc = {
		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
		.gfp_mask = (gfp_mask = memalloc_noio_flags(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 = classzone_idx,
	};

	cond_resched();
	/*
	 * We need to be able to allocate from the reserves for RECLAIM_UNMAP
	 * and we also need to be able to write out pages for RECLAIM_WRITE
	 * and RECLAIM_UNMAP.
	 */
	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
	lockdep_set_current_reclaim_state(gfp_mask);
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

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

	p->reclaim_state = NULL;
	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
	lockdep_clear_current_reclaim_state();
	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 &&
	    sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
		return NODE_RECLAIM_FULL;

	if (!pgdat_reclaimable(pgdat))
		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

/*
 * page_evictable - test whether a page is evictable
 * @page: the page to test
 *
 * Test whether page is evictable--i.e., should be placed on active/inactive
 * lists vs unevictable list.
 *
 * Reasons page might not be evictable:
 * (1) page's mapping marked unevictable
 * (2) page is part of an mlocked VMA
 *
 */
int page_evictable(struct page *page)
{
	return !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
}

#ifdef CONFIG_SHMEM
/**
 * check_move_unevictable_pages - check pages for evictability and move to appropriate zone lru list
 * @pages:	array of pages to check
 * @nr_pages:	number of pages to check
 *
 * Checks pages for evictability and moves them to the appropriate lru list.
 *
 * This function is only used for SysV IPC SHM_UNLOCK.
 */
void check_move_unevictable_pages(struct page **pages, int nr_pages)
{
	struct lruvec *lruvec;
	struct pglist_data *pgdat = NULL;
	int pgscanned = 0;
	int pgrescued = 0;
	int i;

	for (i = 0; i < nr_pages; i++) {
		struct page *page = pages[i];
		struct pglist_data *pagepgdat = page_pgdat(page);

		pgscanned++;
		if (pagepgdat != pgdat) {
			if (pgdat)
				spin_unlock_irq(&pgdat->lru_lock);
			pgdat = pagepgdat;
			spin_lock_irq(&pgdat->lru_lock);
		}
		lruvec = mem_cgroup_page_lruvec(page, pgdat);

		if (!PageLRU(page) || !PageUnevictable(page))
			continue;

		if (page_evictable(page)) {
			enum lru_list lru = page_lru_base_type(page);

			VM_BUG_ON_PAGE(PageActive(page), page);
			ClearPageUnevictable(page);
			del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE);
			add_page_to_lru_list(page, lruvec, lru);
			pgrescued++;
		}
	}

	if (pgdat) {
		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
		spin_unlock_irq(&pgdat->lru_lock);
	}
}
#endif /* CONFIG_SHMEM */