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;

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

		shrinkctl->nr_to_scan = nr_to_scan;
		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_CLEAN;
		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);

		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++;