/*
 *  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/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 "internal.h"

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

/*
 * reclaim_mode determines how the inactive list is shrunk
 * RECLAIM_MODE_SINGLE: Reclaim only order-0 pages
 * RECLAIM_MODE_ASYNC:  Do not block
 * RECLAIM_MODE_SYNC:   Allow blocking e.g. call wait_on_page_writeback
 * RECLAIM_MODE_LUMPYRECLAIM: For high-order allocations, take a reference
 *                      page from the LRU and reclaim all pages within a
 *                      naturally aligned range
 * RECLAIM_MODE_COMPACTION: For high-order allocations, reclaim a number of
 *                      order-0 pages and then compact the zone
 */
typedef unsigned __bitwise__ reclaim_mode_t;
#define RECLAIM_MODE_SINGLE             ((__force reclaim_mode_t)0x01u)
#define RECLAIM_MODE_ASYNC              ((__force reclaim_mode_t)0x02u)
#define RECLAIM_MODE_SYNC               ((__force reclaim_mode_t)0x04u)
#define RECLAIM_MODE_LUMPYRECLAIM       ((__force reclaim_mode_t)0x08u)
#define RECLAIM_MODE_COMPACTION         ((__force reclaim_mode_t)0x10u)

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;

        /*
         * Intend to reclaim enough continuous memory rather than reclaim
         * enough amount of memory. i.e, mode for high order allocation.
         */
        reclaim_mode_t reclaim_mode;

        /*
         * 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;
};

struct mem_cgroup_zone {
        struct mem_cgroup *mem_cgroup;
        struct zone *zone;
};

#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;
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_CGROUP_MEM_RES_CTLR
static bool global_reclaim(struct scan_control *sc)
{
        return !sc->target_mem_cgroup;
}

static bool scanning_global_lru(struct mem_cgroup_zone *mz)
{
        return !mz->mem_cgroup;
}
#else
static bool global_reclaim(struct scan_control *sc)
{
        return true;
}

static bool scanning_global_lru(struct mem_cgroup_zone *mz)
{
        return true;
}
#endif

static struct zone_reclaim_stat *get_reclaim_stat(struct mem_cgroup_zone *mz)
{
        if (!scanning_global_lru(mz))
                return mem_cgroup_get_reclaim_stat(mz->mem_cgroup, mz->zone);

        return &mz->zone->reclaim_stat;
}

static unsigned long zone_nr_lru_pages(struct mem_cgroup_zone *mz,
                                       enum lru_list lru)
{
        if (!scanning_global_lru(mz))
                return mem_cgroup_zone_nr_lru_pages(mz->mem_cgroup,
                                                    zone_to_nid(mz->zone),
                                                    zone_idx(mz->zone),
                                                    BIT(lru));

        return zone_page_state(mz->zone, NR_LRU_BASE + lru);
}


/*
 * Add a shrinker callback to be called from the vm
 */
void register_shrinker(struct shrinker *shrinker)
{
        atomic_long_set(&shrinker->nr_in_batch, 0);
        down_write(&shrinker_rwsem);
        list_add_tail(&shrinker->list, &shrinker_list);
        up_write(&shrinker_rwsem);
}
EXPORT_SYMBOL(register_shrinker);

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

static inline int do_shrinker_shrink(struct shrinker *shrinker,
                                     struct shrink_control *sc,
                                     unsigned long nr_to_scan)
{
        sc->nr_to_scan = nr_to_scan;
        return (*shrinker->shrink)(shrinker, sc);
}

#define SHRINK_BATCH 128
/*
 * 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 *shrink,
                          unsigned long nr_pages_scanned,
                          unsigned long lru_pages)
{
        struct shrinker *shrinker;
        unsigned long ret = 0;

        if (nr_pages_scanned == 0)
                nr_pages_scanned = SWAP_CLUSTER_MAX;

        if (!down_read_trylock(&shrinker_rwsem)) {
                /* Assume we'll be able to shrink next time */
                ret = 1;
                goto out;
        }

        list_for_each_entry(shrinker, &shrinker_list, list) {
                unsigned long long delta;
                long total_scan;
                long max_pass;
                int shrink_ret = 0;
                long nr;
                long new_nr;
                long batch_size = shrinker->batch ? shrinker->batch
                                                  : SHRINK_BATCH;

                max_pass = do_shrinker_shrink(shrinker, shrink, 0);
                if (max_pass <= 0)
                        continue;

                /*
                 * 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_in_batch, 0);

                total_scan = nr;
                delta = (4 * nr_pages_scanned) / shrinker->seeks;
                delta *= max_pass;
                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->shrink, total_scan);
                        total_scan = max_pass;
                }

                /*
                 * 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 >>>
                 * max_pass.  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 < max_pass / 4)
                        total_scan = min(total_scan, max_pass / 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 > max_pass * 2)
                        total_scan = max_pass * 2;

                trace_mm_shrink_slab_start(shrinker, shrink, nr,
                                        nr_pages_scanned, lru_pages,
                                        max_pass, delta, total_scan);

                while (total_scan >= batch_size) {
                        int nr_before;

                        nr_before = do_shrinker_shrink(shrinker, shrink, 0);
                        shrink_ret = do_shrinker_shrink(shrinker, shrink,
                                                        batch_size);
                        if (shrink_ret == -1)
                                break;
                        if (shrink_ret < nr_before)
                                ret += nr_before - shrink_ret;
                        count_vm_events(SLABS_SCANNED, batch_size);
                        total_scan -= batch_size;

                        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_in_batch);
                else
                        new_nr = atomic_long_read(&shrinker->nr_in_batch);

                trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
        }
        up_read(&shrinker_rwsem);
out:
        cond_resched();
        return ret;
}

static void set_reclaim_mode(int priority, struct scan_control *sc,
                                   bool sync)
{
        reclaim_mode_t syncmode = sync ? RECLAIM_MODE_SYNC : RECLAIM_MODE_ASYNC;

        /*
         * Initially assume we are entering either lumpy reclaim or
         * reclaim/compaction.Depending on the order, we will either set the
         * sync mode or just reclaim order-0 pages later.
         */
        if (COMPACTION_BUILD)
                sc->reclaim_mode = RECLAIM_MODE_COMPACTION;
        else
                sc->reclaim_mode = RECLAIM_MODE_LUMPYRECLAIM;

        /*
         * Avoid using lumpy reclaim or reclaim/compaction if possible by
         * restricting when its set to either costly allocations or when
         * under memory pressure
         */
        if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
                sc->reclaim_mode |= syncmode;
        else if (sc->order && priority < DEF_PRIORITY - 2)
                sc->reclaim_mode |= syncmode;
        else
                sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC;
}

static void reset_reclaim_mode(struct scan_control *sc)
{
        sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC;
}

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;

        /* lumpy reclaim for hugepage often need a lot of write */
        if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
                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, sc->reclaim_mode));
                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)
{
        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 *);

                freepage = mapping->a_ops->freepage;

                __delete_from_page_cache(page);
                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)) {
                /*
                 * 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)
{
        int lru;
        int active = !!TestClearPageActive(page);
        int was_unevictable = PageUnevictable(page);

        VM_BUG_ON(PageLRU(page));

redo:
        ClearPageUnevictable(page);

        if (page_evictable(page, NULL)) {
                /*
                 * 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.
                 */
                lru = active + page_lru_base_type(page);
                lru_cache_add_lru(page, lru);
        } else {
                /*
                 * Put unevictable pages directly on zone's unevictable
                 * list.
                 */
                lru = LRU_UNEVICTABLE;
                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 (lru == LRU_UNEVICTABLE && page_evictable(page, NULL)) {
                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 && lru != LRU_UNEVICTABLE)
                count_vm_event(UNEVICTABLE_PGRESCUED);
        else if (!was_unevictable && lru == LRU_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 mem_cgroup_zone *mz,
                                                  struct scan_control *sc)
{
        int referenced_ptes, referenced_page;
        unsigned long vm_flags;

        referenced_ptes = page_referenced(page, 1, mz->mem_cgroup, &vm_flags);
        referenced_page = TestClearPageReferenced(page);

        /* Lumpy reclaim - ignore references */
        if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
                return PAGEREF_RECLAIM;

        /*
         * 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 (PageAnon(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;
}

/*
 * shrink_page_list() returns the number of reclaimed pages
 */
static unsigned long shrink_page_list(struct list_head *page_list,
                                      struct mem_cgroup_zone *mz,
                                      struct scan_control *sc,
                                      int priority,
                                      unsigned long *ret_nr_dirty,
                                      unsigned long *ret_nr_writeback)
{
        LIST_HEAD(ret_pages);
        LIST_HEAD(free_pages);
        int pgactivate = 0;
        unsigned long nr_dirty = 0;
        unsigned long nr_congested = 0;
        unsigned long nr_reclaimed = 0;
        unsigned long nr_writeback = 0;

        cond_resched();

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

                cond_resched();

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

                if (!trylock_page(page))
                        goto keep;

                VM_BUG_ON(PageActive(page));
                VM_BUG_ON(page_zone(page) != mz->zone);

                sc->nr_scanned++;

                if (unlikely(!page_evictable(page, NULL)))
                        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));

                if (PageWriteback(page)) {
                        nr_writeback++;
                        /*
                         * Synchronous reclaim cannot queue pages for
                         * writeback due to the possibility of stack overflow
                         * but if it encounters a page under writeback, wait
                         * for the IO to complete.
                         */
                        if ((sc->reclaim_mode & RECLAIM_MODE_SYNC) &&
                            may_enter_fs)
                                wait_on_page_writeback(page);
                        else {
                                unlock_page(page);
                                goto keep_lumpy;
                        }
                }

                references = page_check_references(page, mz, 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))
                                goto activate_locked;
                        may_enter_fs = 1;
                }

                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_UNMAP)) {
                        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)) {
                        nr_dirty++;

                        /*
                         * Only kswapd can writeback filesystem pages to
                         * avoid risk of stack overflow but do not writeback
                         * unless under significant pressure.
                         */
                        if (page_is_file_cache(page) &&
                                        (!current_is_kswapd() || priority >= DEF_PRIORITY - 2)) {
                                /*
                                 * 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:
                                nr_congested++;
                                goto keep_locked;
                        case PAGE_ACTIVATE:
                                goto activate_locked;
                        case PAGE_SUCCESS:
                                if (PageWriteback(page))
                                        goto keep_lumpy;
                                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))
                        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);
                reset_reclaim_mode(sc);
                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(PageActive(page));
                SetPageActive(page);
                pgactivate++;
keep_locked:
                unlock_page(page);
keep:
                reset_reclaim_mode(sc);
keep_lumpy:
                list_add(&page->lru, &ret_pages);
                VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
        }

        /*
         * Tag a zone as congested if all the dirty pages encountered were
         * backed by a congested BDI. In this case, reclaimers should just
         * back off and wait for congestion to clear because further reclaim
         * will encounter the same problem
         */
        if (nr_dirty && nr_dirty == nr_congested && global_reclaim(sc))
                zone_set_flag(mz->zone, ZONE_CONGESTED);

        free_hot_cold_page_list(&free_pages, 1);

        list_splice(&ret_pages, page_list);
        count_vm_events(PGACTIVATE, pgactivate);
        *ret_nr_dirty += nr_dirty;
        *ret_nr_writeback += nr_writeback;
        return nr_reclaimed;
}

/*
 * 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 file)
{
        bool all_lru_mode;
        int ret = -EINVAL;

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

        all_lru_mode = (mode & (ISOLATE_ACTIVE|ISOLATE_INACTIVE)) ==
                (ISOLATE_ACTIVE|ISOLATE_INACTIVE);

        /*
         * When checking the active state, we need to be sure we are
         * dealing with comparible boolean values.  Take the logical not
         * of each.
         */
        if (!all_lru_mode && !PageActive(page) != !(mode & ISOLATE_ACTIVE))
                return ret;

        if (!all_lru_mode && !!page_is_file_cache(page) != file)
                return ret;

        /*
         * When this function is being called for lumpy reclaim, we
         * initially look into all LRU pages, active, inactive and
         * unevictable; only give shrink_page_list evictable pages.
         */
        if (PageUnevictable(page))
                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.
 * @mz:         The mem_cgroup_zone to pull pages from.
 * @dst:        The temp list to put pages on to.
 * @nr_scanned: The number of pages that were scanned.
 * @order:      The caller's attempted allocation order
 * @mode:       One of the LRU isolation modes
 * @active:     True [1] if isolating active pages
 * @file:       True [1] if isolating file [!anon] pages
 *
 * returns how many pages were moved onto *@dst.
 */
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
                struct mem_cgroup_zone *mz, struct list_head *dst,
                unsigned long *nr_scanned, int order, isolate_mode_t mode,
                int active, int file)
{
        struct lruvec *lruvec;
        struct list_head *src;
        unsigned long nr_taken = 0;
        unsigned long nr_lumpy_taken = 0;
        unsigned long nr_lumpy_dirty = 0;
        unsigned long nr_lumpy_failed = 0;
        unsigned long scan;
        int lru = LRU_BASE;

        lruvec = mem_cgroup_zone_lruvec(mz->zone, mz->mem_cgroup);
        if (active)
                lru += LRU_ACTIVE;
        if (file)
                lru += LRU_FILE;
        src = &lruvec->lists[lru];

        for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
                struct page *page;
                unsigned long pfn;
                unsigned long end_pfn;
                unsigned long page_pfn;
                int zone_id;

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

                VM_BUG_ON(!PageLRU(page));

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

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

                default:
                        BUG();
                }

                if (!order)
                        continue;

                /*
                 * Attempt to take all pages in the order aligned region
                 * surrounding the tag page.  Only take those pages of
                 * the same active state as that tag page.  We may safely
                 * round the target page pfn down to the requested order
                 * as the mem_map is guaranteed valid out to MAX_ORDER,
                 * where that page is in a different zone we will detect
                 * it from its zone id and abort this block scan.
                 */
                zone_id = page_zone_id(page);
                page_pfn = page_to_pfn(page);
                pfn = page_pfn & ~((1 << order) - 1);
                end_pfn = pfn + (1 << order);
                for (; pfn < end_pfn; pfn++) {
                        struct page *cursor_page;

                        /* The target page is in the block, ignore it. */
                        if (unlikely(pfn == page_pfn))
                                continue;

                        /* Avoid holes within the zone. */
                        if (unlikely(!pfn_valid_within(pfn)))
                                break;

                        cursor_page = pfn_to_page(pfn);

                        /* Check that we have not crossed a zone boundary. */
                        if (unlikely(page_zone_id(cursor_page) != zone_id))
                                break;

                        /*
                         * If we don't have enough swap space, reclaiming of
                         * anon page which don't already have a swap slot is
                         * pointless.
                         */
                        if (nr_swap_pages <= 0 && PageSwapBacked(cursor_page) &&
                            !PageSwapCache(cursor_page))
                                break;

                        if (__isolate_lru_page(cursor_page, mode, file) == 0) {
                                unsigned int isolated_pages;

                                mem_cgroup_lru_del(cursor_page);
                                list_move(&cursor_page->lru, dst);
                                isolated_pages = hpage_nr_pages(cursor_page);
                                nr_taken += isolated_pages;
                                nr_lumpy_taken += isolated_pages;
                                if (PageDirty(cursor_page))
                                        nr_lumpy_dirty += isolated_pages;
                                scan++;
                                pfn += isolated_pages - 1;
                        } else {
                                /*
                                 * Check if the page is freed already.
                                 *
                                 * We can't use page_count() as that
                                 * requires compound_head and we don't
                                 * have a pin on the page here. If a
                                 * page is tail, we may or may not
                                 * have isolated the head, so assume
                                 * it's not free, it'd be tricky to
                                 * track the head status without a
                                 * page pin.
                                 */
                                if (!PageTail(cursor_page) &&
                                    !atomic_read(&cursor_page->_count))
                                        continue;
                                break;
                        }
                }

                /* If we break out of the loop above, lumpy reclaim failed */
                if (pfn < end_pfn)
                        nr_lumpy_failed++;
        }

        *nr_scanned = scan;

        trace_mm_vmscan_lru_isolate(order,
                        nr_to_scan, scan,
                        nr_taken,
                        nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed,
                        mode, file);
        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_count(page));

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

                spin_lock_irq(&zone->lru_lock);
                if (PageLRU(page)) {
                        int lru = page_lru(page);
                        ret = 0;
                        get_page(page);
                        ClearPageLRU(page);

                        del_page_from_lru_list(zone, page, lru);
                }
                spin_unlock_irq(&zone->lru_lock);
        }
        return ret;
}

/*
 * Are there way too many processes in the direct reclaim path already?
 */
static int too_many_isolated(struct zone *zone, int file,
                struct scan_control *sc)
{
        unsigned long inactive, isolated;

        if (current_is_kswapd())
                return 0;

        if (!global_reclaim(sc))
                return 0;

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

        return isolated > inactive;
}

static noinline_for_stack void
putback_inactive_pages(struct mem_cgroup_zone *mz,
                       struct list_head *page_list)
{
        struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
        struct zone *zone = mz->zone;
        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(PageLRU(page));
                list_del(&page->lru);
                if (unlikely(!page_evictable(page, NULL))) {
                        spin_unlock_irq(&zone->lru_lock);
                        putback_lru_page(page);
                        spin_lock_irq(&zone->lru_lock);
                        continue;
                }
                SetPageLRU(page);
                lru = page_lru(page);
                add_page_to_lru_list(zone, page, 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(zone, page, lru);

                        if (unlikely(PageCompound(page))) {
                                spin_unlock_irq(&zone->lru_lock);
                                (*get_compound_page_dtor(page))(page);
                                spin_lock_irq(&zone->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);
}

static noinline_for_stack void
update_isolated_counts(struct mem_cgroup_zone *mz,
                       struct list_head *page_list,
                       unsigned long *nr_anon,
                       unsigned long *nr_file)
{
        struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
        struct zone *zone = mz->zone;
        unsigned int count[NR_LRU_LISTS] = { 0, };
        unsigned long nr_active = 0;
        struct page *page;
        int lru;

        /*
         * Count pages and clear active flags
         */
        list_for_each_entry(page, page_list, lru) {
                int numpages = hpage_nr_pages(page);
                lru = page_lru_base_type(page);
                if (PageActive(page)) {
                        lru += LRU_ACTIVE;
                        ClearPageActive(page);
                        nr_active += numpages;
                }
                count[lru] += numpages;
        }

        __count_vm_events(PGDEACTIVATE, nr_active);

        __mod_zone_page_state(zone, NR_ACTIVE_FILE,
                              -count[LRU_ACTIVE_FILE]);
        __mod_zone_page_state(zone, NR_INACTIVE_FILE,
                              -count[LRU_INACTIVE_FILE]);
        __mod_zone_page_state(zone, NR_ACTIVE_ANON,
                              -count[LRU_ACTIVE_ANON]);
        __mod_zone_page_state(zone, NR_INACTIVE_ANON,
                              -count[LRU_INACTIVE_ANON]);

        *nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
        *nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];

        reclaim_stat->recent_scanned[0] += *nr_anon;
        reclaim_stat->recent_scanned[1] += *nr_file;
}

/*
 * Returns true if a direct reclaim should wait on pages under writeback.
 *
 * If we are direct reclaiming for contiguous pages and we do not reclaim
 * everything in the list, try again and wait for writeback IO to complete.
 * This will stall high-order allocations noticeably. Only do that when really
 * need to free the pages under high memory pressure.
 */
static inline bool should_reclaim_stall(unsigned long nr_taken,
                                        unsigned long nr_freed,
                                        int priority,
                                        struct scan_control *sc)
{
        int lumpy_stall_priority;

        /* kswapd should not stall on sync IO */
        if (current_is_kswapd())
                return false;

        /* Only stall on lumpy reclaim */
        if (sc->reclaim_mode & RECLAIM_MODE_SINGLE)
                return false;

        /* If we have reclaimed everything on the isolated list, no stall */
        if (nr_freed == nr_taken)
                return false;

        /*
         * For high-order allocations, there are two stall thresholds.
         * High-cost allocations stall immediately where as lower
         * order allocations such as stacks require the scanning
         * priority to be much higher before stalling.
         */
        if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
                lumpy_stall_priority = DEF_PRIORITY;
        else
                lumpy_stall_priority = DEF_PRIORITY / 3;

        return priority <= lumpy_stall_priority;
}

/*
 * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
 * of reclaimed pages
 */
static noinline_for_stack unsigned long
shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
                     struct scan_control *sc, int priority, int file)
{
        LIST_HEAD(page_list);
        unsigned long nr_scanned;
        unsigned long nr_reclaimed = 0;
        unsigned long nr_taken;
        unsigned long nr_anon;
        unsigned long nr_file;
        unsigned long nr_dirty = 0;
        unsigned long nr_writeback = 0;
        isolate_mode_t reclaim_mode = ISOLATE_INACTIVE;
        struct zone *zone = mz->zone;

        while (unlikely(too_many_isolated(zone, 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;
        }

        set_reclaim_mode(priority, sc, false);
        if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
                reclaim_mode |= ISOLATE_ACTIVE;

        lru_add_drain();

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

        spin_lock_irq(&zone->lru_lock);

        nr_taken = isolate_lru_pages(nr_to_scan, mz, &page_list,
                                     &nr_scanned, sc->order,
                                     reclaim_mode, 0, file);
        if (global_reclaim(sc)) {
                zone->pages_scanned += nr_scanned;
                if (current_is_kswapd())
                        __count_zone_vm_events(PGSCAN_KSWAPD, zone,
                                               nr_scanned);
                else
                        __count_zone_vm_events(PGSCAN_DIRECT, zone,
                                               nr_scanned);
        }

        if (nr_taken == 0) {
                spin_unlock_irq(&zone->lru_lock);
                return 0;
        }

        update_isolated_counts(mz, &page_list, &nr_anon, &nr_file);

        __mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon);
        __mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file);

        spin_unlock_irq(&zone->lru_lock);

        nr_reclaimed = shrink_page_list(&page_list, mz, sc, priority,
                                                &nr_dirty, &nr_writeback);

        /* Check if we should syncronously wait for writeback */
        if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) {
                set_reclaim_mode(priority, sc, true);
                nr_reclaimed += shrink_page_list(&page_list, mz, sc,
                                        priority, &nr_dirty, &nr_writeback);
        }

        spin_lock_irq(&zone->lru_lock);

        if (current_is_kswapd())
                __count_vm_events(KSWAPD_STEAL, nr_reclaimed);
        __count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);

        putback_inactive_pages(mz, &page_list);

        __mod_zone_page_state(zone, NR_ISOLATED_ANON, -nr_anon);
        __mod_zone_page_state(zone, NR_ISOLATED_FILE, -nr_file);

        spin_unlock_irq(&zone->lru_lock);

        free_hot_cold_page_list(&page_list, 1);

        /*
         * 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.
         *
         * This scales the number of dirty pages that must be under writeback
         * before throttling depending on priority. It is a simple backoff
         * function that has the most effect in the range DEF_PRIORITY to
         * DEF_PRIORITY-2 which is the priority reclaim is considered to be
         * in trouble and reclaim is considered to be in trouble.
         *
         * DEF_PRIORITY   100% isolated pages must be PageWriteback to throttle
         * DEF_PRIORITY-1  50% must be PageWriteback
         * DEF_PRIORITY-2  25% must be PageWriteback, kswapd in trouble
         * ...
         * DEF_PRIORITY-6 For SWAP_CLUSTER_MAX isolated pages, throttle if any
         *                     isolated page is PageWriteback
         */
        if (nr_writeback && nr_writeback >= (nr_taken >> (DEF_PRIORITY-priority)))
                wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);

        trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,
                zone_idx(zone),
                nr_scanned, nr_reclaimed,
                priority,
                trace_shrink_flags(file, sc->reclaim_mode));
        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->_count against each page.
 * But we had to alter page->flags anyway.
 */

static void move_active_pages_to_lru(struct zone *zone,
                                     struct list_head *list,
                                     struct list_head *pages_to_free,
                                     enum lru_list lru)
{
        unsigned long pgmoved = 0;
        struct page *page;

        if (buffer_heads_over_limit) {
                spin_unlock_irq(&zone->lru_lock);
                list_for_each_entry(page, list, lru) {
                        if (page_has_private(page) && trylock_page(page)) {
                                if (page_has_private(page))
                                        try_to_release_page(page, 0);
                                unlock_page(page);
                        }
                }
                spin_lock_irq(&zone->lru_lock);
        }

        while (!list_empty(list)) {
                struct lruvec *lruvec;

                page = lru_to_page(list);

                VM_BUG_ON(PageLRU(page));
                SetPageLRU(page);

                lruvec = mem_cgroup_lru_add_list(zone, page, lru);
                list_move(&page->lru, &lruvec->lists[lru]);
                pgmoved += hpage_nr_pages(page);

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

                        if (unlikely(PageCompound(page))) {
                                spin_unlock_irq(&zone->lru_lock);
                                (*get_compound_page_dtor(page))(page);
                                spin_lock_irq(&zone->lru_lock);
                        } else
                                list_add(&page->lru, pages_to_free);
                }
        }
        __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
        if (!is_active_lru(lru))
                __count_vm_events(PGDEACTIVATE, pgmoved);
}

static void shrink_active_list(unsigned long nr_to_scan,
                               struct mem_cgroup_zone *mz,
                               struct scan_control *sc,
                               int priority, int file)
{
        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 = get_reclaim_stat(mz);
        unsigned long nr_rotated = 0;
        isolate_mode_t reclaim_mode = ISOLATE_ACTIVE;
        struct zone *zone = mz->zone;

        lru_add_drain();

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

        spin_lock_irq(&zone->lru_lock);

        nr_taken = isolate_lru_pages(nr_to_scan, mz, &l_hold,
                                     &nr_scanned, sc->order,
                                     reclaim_mode, 1, file);
        if (global_reclaim(sc))
                zone->pages_scanned += nr_scanned;

        reclaim_stat->recent_scanned[file] += nr_taken;

        __count_zone_vm_events(PGREFILL, zone, nr_scanned);
        if (file)
                __mod_zone_page_state(zone, NR_ACTIVE_FILE, -nr_taken);
        else
                __mod_zone_page_state(zone, NR_ACTIVE_ANON, -nr_taken);
        __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
        spin_unlock_irq(&zone->lru_lock);

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

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

                if (page_referenced(page, 0, mz->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(&zone->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_ratio.
         */
        reclaim_stat->recent_rotated[file] += nr_rotated;

        move_active_pages_to_lru(zone, &l_active, &l_hold,
                                                LRU_ACTIVE + file * LRU_FILE);
        move_active_pages_to_lru(zone, &l_inactive, &l_hold,
                                                LRU_BASE   + file * LRU_FILE);
        __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
        spin_unlock_irq(&zone->lru_lock);

        free_hot_cold_page_list(&l_hold, 1);
}

#ifdef CONFIG_SWAP
static int inactive_anon_is_low_global(struct zone *zone)
{
        unsigned long active, inactive;

        active = zone_page_state(zone, NR_ACTIVE_ANON);
        inactive = zone_page_state(zone, NR_INACTIVE_ANON);

        if (inactive * zone->inactive_ratio < active)
                return 1;

        return 0;
}

/**
 * inactive_anon_is_low - check if anonymous pages need to be deactivated
 * @zone: zone to check
 * @sc:   scan control of this context
 *
 * Returns true if the zone does not have enough inactive anon pages,
 * meaning some active anon pages need to be deactivated.
 */
static int inactive_anon_is_low(struct mem_cgroup_zone *mz)
{
        /*
         * If we don't have swap space, anonymous page deactivation
         * is pointless.
         */
        if (!total_swap_pages)
                return 0;

        if (!scanning_global_lru(mz))
                return mem_cgroup_inactive_anon_is_low(mz->mem_cgroup,
                                                       mz->zone);

        return inactive_anon_is_low_global(mz->zone);
}
#else
static inline int inactive_anon_is_low(struct mem_cgroup_zone *mz)
{
        return 0;
}
#endif

static int inactive_file_is_low_global(struct zone *zone)
{
        unsigned long active, inactive;

        active = zone_page_state(zone, NR_ACTIVE_FILE);
        inactive = zone_page_state(zone, NR_INACTIVE_FILE);

        return (active > inactive);
}

/**
 * inactive_file_is_low - check if file pages need to be deactivated
 * @mz: memory cgroup and zone to check
 *
 * When the system is doing streaming IO, memory pressure here
 * ensures that active file pages get deactivated, until more
 * than half of the file pages are on the inactive list.
 *
 * Once we get to that situation, protect the system's working
 * set from being evicted by disabling active file page aging.
 *
 * This uses a different ratio than the anonymous pages, because
 * the page cache uses a use-once replacement algorithm.
 */
static int inactive_file_is_low(struct mem_cgroup_zone *mz)
{
        if (!scanning_global_lru(mz))
                return mem_cgroup_inactive_file_is_low(mz->mem_cgroup,
                                                       mz->zone);

        return inactive_file_is_low_global(mz->zone);
}

static int inactive_list_is_low(struct mem_cgroup_zone *mz, int file)
{
        if (file)
                return inactive_file_is_low(mz);
        else
                return inactive_anon_is_low(mz);
}

static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
                                 struct mem_cgroup_zone *mz,
                                 struct scan_control *sc, int priority)
{
        int file = is_file_lru(lru);

        if (is_active_lru(lru)) {
                if (inactive_list_is_low(mz, file))
                        shrink_active_list(nr_to_scan, mz, sc, priority, file);
                return 0;
        }

        return shrink_inactive_list(nr_to_scan, mz, sc, priority, file);
}

static int vmscan_swappiness(struct mem_cgroup_zone *mz,
                             struct scan_control *sc)
{
        if (global_reclaim(sc))
                return vm_swappiness;
        return mem_cgroup_swappiness(mz->mem_cgroup);
}

/*
 * 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 pages to scan; nr[1] = file pages to scan
 */
static void get_scan_count(struct mem_cgroup_zone *mz, struct scan_control *sc,
                           unsigned long *nr, int priority)
{
        unsigned long anon, file, free;
        unsigned long anon_prio, file_prio;
        unsigned long ap, fp;
        struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
        u64 fraction[2], denominator;
        enum lru_list lru;
        int noswap = 0;
        bool force_scan = false;

        /*
         * 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() && mz->zone->all_unreclaimable)
                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 || (nr_swap_pages <= 0)) {
                noswap = 1;
                fraction[0] = 0;
                fraction[1] = 1;
                denominator = 1;
                goto out;
        }

        anon  = zone_nr_lru_pages(mz, LRU_ACTIVE_ANON) +
                zone_nr_lru_pages(mz, LRU_INACTIVE_ANON);
        file  = zone_nr_lru_pages(mz, LRU_ACTIVE_FILE) +
                zone_nr_lru_pages(mz, LRU_INACTIVE_FILE);

        if (global_reclaim(sc)) {
                free  = zone_page_state(mz->zone, NR_FREE_PAGES);
                /* If we have very few page cache pages,
                   force-scan anon pages. */
                if (unlikely(file + free <= high_wmark_pages(mz->zone))) {
                        fraction[0] = 1;
                        fraction[1] = 0;
                        denominator = 1;
                        goto out;
                }
        }

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

        /*
         * 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]
         */
        spin_lock_irq(&mz->zone->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 + 1) * (reclaim_stat->recent_scanned[0] + 1);
        ap /= reclaim_stat->recent_rotated[0] + 1;

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

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