path: root/KNOWNBUGS

/*
 *  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.
 */

#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 <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 {
	/* 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;

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

	unsigned long hibernation_mode;

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

	int may_writepage;

	/* Can mapped pages be reclaimed? */
	int may_unmap;

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

	int order;

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

	/*
	 * 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;

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

#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))

#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;
unsigned long vm_total_pages;	/* The total number of pages which the VM controls */

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

static unsigned long zone_reclaimable_pages(struct zone *zone)
{
	int nr;

	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
	     zone_page_state(zone, NR_INACTIVE_FILE);

	if (get_nr_swap_pages() > 0)
		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
		      zone_page_state(zone, NR_INACTIVE_ANON);

	return nr;
}

bool zone_reclaimable(struct zone *zone)
{
	return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
}

static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
	if (!mem_cgroup_disabled())
		return mem_cgroup_get_lru_size(lruvec, lru);

	return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru);
}

/*
 * Add a shrinker callback to be called from the vm.
 */
int register_shrinker(struct shrinker *shrinker)
{
	size_t size = sizeof(*shrinker->nr_deferred);

	/*
	 * If we only have one possible node in the system anyway, save
	 * ourselves the trouble and disable NUMA aware behavior. This way we
	 * will save memory and some small loop time later.
	 */
	if (nr_node_ids == 1)
		shrinker->flags &= ~SHRINKER_NUMA_AWARE;

	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
shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
		 unsigned long nr_pages_scanned, unsigned long lru_pages)
{
	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;

	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_pages_scanned) / shrinker->seeks;
	delta *= freeable;
	do_div(delta, lru_pages + 1);
	total_scan += delta;
	if (total_scan < 0) {
		printk(KERN_ERR
		"shrink_slab: %pF negative objects to delete nr=%ld\n",
		       shrinker->scan_objects, total_scan);
		total_scan = freeable;
	}

	/*
	 * 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_pages_scanned, lru_pages,
				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;

		cond_resched();
	}

	/*
	 * 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 (total_scan > 0)
		new_nr = atomic_long_add_return(total_scan,
						&shrinker->nr_deferred[nid]);
	else
		new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);

	trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
	return freed;
}

/*
 * Call the shrink functions to age shrinkable caches
 *
 * Here we assume it costs one seek to replace a lru page and that it also
 * takes a seek to recreate a cache object.  With this in mind we age equal
 * percentages of the lru and ageable caches.  This should balance the seeks
 * generated by these structures.
 *
 * If the vm encountered mapped pages on the LRU it increase the pressure on
 * slab to avoid swapping.
 *
 * We do weird things to avoid (scanned*seeks*entries) overflowing 32 bits.
 *
 * `lru_pages' represents the number of on-LRU pages in all the zones which
 * are eligible for the caller's allocation attempt.  It is used for balancing
 * slab reclaim versus page reclaim.
 *
 * Returns the number of slab objects which we shrunk.
 */
unsigned long shrink_slab(struct shrink_control *shrinkctl,
			  unsigned long nr_pages_scanned,
			  unsigned long lru_pages)
{
	struct shrinker *shrinker;
	unsigned long freed = 0;

	if (nr_pages_scanned == 0)
		nr_pages_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) {
		if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) {
			shrinkctl->nid = 0;
			freed += shrink_slab_node(shrinkctl, shrinker,
					nr_pages_scanned, lru_pages);
			continue;
		}

		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
			if (node_online(shrinkctl->nid))
				freed += shrink_slab_node(shrinkctl, shrinker,
						nr_pages_scanned, lru_pages);

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

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_queue(struct backing_dev_info *bdi,
			      struct scan_control *sc)
{
	if (current->flags & PF_SWAPWRITE)
		return 1;
	if (!bdi_write_congested(bdi))
		return 1;
	if (bdi == 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_aio_write() 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);
				printk("%s: orphaned page\n", __func__);
				return PAGE_CLEAN;
			}
		}
		return PAGE_KEEP;
	}
	if (mapping->a_ops->writepage == NULL)
		return PAGE_ACTIVATE;
	if (!may_write_to_queue(mapping->backing_dev_info, 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, trace_reclaim_flags(page));
		inc_zone_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)
{
	BUG_ON(!PageLocked(page));
	BUG_ON(mapping != page_mapping(page));

	spin_lock_irq(&mapping->tree_lock);
	/*
	 * 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->_count.
	 *
	 * Note that if SetPageDirty is always performed via set_page_dirty,
	 * and thus under tree_lock, then this ordering is not required.
	 */
	if (!page_freeze_refs(page, 2))
		goto cannot_free;
	/* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
	if (unlikely(PageDirty(page))) {
		page_unfreeze_refs(page, 2);
		goto cannot_free;
	}

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

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

	return 1;

cannot_free:
	spin_unlock_irq(&mapping->tree_lock);
	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_unfreeze_refs(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 zone *zone,
				      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();

	mem_cgroup_uncharge_start();
	while (!list_empty(page_list)) {
		struct address_space *mapping;
		struct page *page;
		int may_enter_fs;
		enum page_references references = PAGEREF_RECLAIM_CLEAN;
		bool dirty, writeback;

		cond_resched();

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

		if (!trylock_page(page))
			goto keep;

		VM_BUG_ON_PAGE(PageActive(page), page);
		VM_BUG_ON_PAGE(page_zone(page) != zone, 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 ((mapping && bdi_write_congested(mapping->backing_dev_info)) ||
		    (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 reclaim encounters a page, memcg encounters a
		 *    page that is not marked for immediate reclaim or
		 *    the caller does not have __GFP_IO. In this case mark
		 *    the page for immediate reclaim and continue scanning.
		 *
		 *    __GFP_IO is checked  because a loop driver thread 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.
		 *
		 *    Don't require __GFP_FS, since we're not going into the
		 *    FS, just waiting on its writeback completion. Worryingly,
		 *    ext4 gfs2 and xfs allocate pages with
		 *    grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing
		 *    may_enter_fs here is liable to OOM on them.
		 *
		 * 3) memcg encounters a page that is not 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) &&
			    zone_is_reclaim_writeback(zone)) {
				nr_immediate++;
				goto keep_locked;

			/* Case 2 above */
			} else if (global_reclaim(sc) ||
			    !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) {
				/*
				 * 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 {
				wait_on_page_writeback(page);
			}
		}

		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;
			may_enter_fs = 1;

			/* Adding to swap updated mapping */
			mapping = page_mapping(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 (try_to_unmap(page, ttu_flags)) {
			case SWAP_FAIL:
				goto activate_locked;
			case SWAP_AGAIN:
				goto keep_locked;
			case SWAP_MLOCK:
				goto cull_mlocked;
			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() ||
					 !zone_is_reclaim_dirty(zone))) {
				/*
				 * Immediately reclaim when written back.
				 * Similar in principal to deactivate_page()
				 * except we already have the page isolated
				 * and know it's dirty
				 */
				inc_zone_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, try to write it out here */
			switch (pageout(page, mapping, sc)) {
			case PAGE_KEEP:
				goto keep_locked;
			case PAGE_ACTIVATE:
				goto activate_locked;
			case PAGE_SUCCESS:
				if (PageWriteback(page))
					goto keep;
				if (PageDirty(page))
					goto keep;

				/*
				 * A synchronous write - probably a ramdisk.  Go
				 * ahead and try to reclaim the page.
				 */
				if (!trylock_page(page))
					goto keep;
				if (PageDirty(page) || PageWriteback(page))
					goto keep_locked;
				mapping = page_mapping(page);
			case PAGE_CLEAN:
				; /* try to free the page below */
			}
		}

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

		if (!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.
		 */
		__clear_page_locked(page);
free_it:
		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);
		putback_lru_page(page);
		continue;

activate_locked:
		/* Not a candidate for swapping, so reclaim swap space. */
		if (PageSwapCache(page) && vm_swap_full())
			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);
	}

	free_hot_cold_page_list(&free_pages, 1);

	list_splice(&ret_pages, page_list);
	count_vm_events(PGACTIVATE, pgactivate);
	mem_cgroup_uncharge_end();
	*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,
	};
	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) &&
		    !isolated_balloon_page(page)) {
			ClearPageActive(page);
			list_move(&page->lru, &clean_pages);
		}
	}

	ret = shrink_page_list(&clean_pages, zone, &sc,
			TTU_UNMAP|TTU_IGNORE_ACCESS,
			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
	list_splice(&clean_pages, page_list);
	__mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
	return ret;
}

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

	/* Only take pages on the LRU. */
	if (!PageLRU(page))
		return ret;

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

	ret = -EBUSY;

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

/*
 * 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 scan;

	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
		struct page *page;
		int nr_pages;

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

		VM_BUG_ON_PAGE(!PageLRU(page), page);

		switch (__isolate_lru_page(page, mode)) {
		case 0:
			nr_pages = hpage_nr_pages(page);
			mem_cgroup_update_lru_size(lruvec, lru, -nr_pages);
			list_move(&page->lru, dst);
			nr_taken += nr_pages;
			break;

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

		default:
			BUG();
		}
	}

	*nr_scanned = scan;
	trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
				    nr_taken, mode, is_file_lru(lru));
	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);

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

		spin_lock_irq(&zone->lru_lock);
		lruvec = mem_cgroup_page_lruvec(page, zone);
		if (PageLRU(page)) {
			int lru = page_lru(page);
			get_page(page);
			ClearPageLRU(page);