Merge git://git.samba.org/sfrench/cifs-2.6

[linux-2.6.git] / mm / swap.c

/*
 *  linux/mm/swap.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 */

/*
 * This file contains the default values for the operation of the
 * Linux VM subsystem. Fine-tuning documentation can be found in
 * Documentation/sysctl/vm.txt.
 * Started 18.12.91
 * Swap aging added 23.2.95, Stephen Tweedie.
 * Buffermem limits added 12.3.98, Rik van Riel.
 */

#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/mm_inline.h>
#include <linux/percpu_counter.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/backing-dev.h>
#include <linux/memcontrol.h>
#include <linux/gfp.h>

#include "internal.h"

/* How many pages do we try to swap or page in/out together? */
int page_cluster;

static DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs);
static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);

/*
 * This path almost never happens for VM activity - pages are normally
 * freed via pagevecs.  But it gets used by networking.
 */
static void __page_cache_release(struct page *page)
{
        if (PageLRU(page)) {
                unsigned long flags;
                struct zone *zone = page_zone(page);

                spin_lock_irqsave(&zone->lru_lock, flags);
                VM_BUG_ON(!PageLRU(page));
                __ClearPageLRU(page);
                del_page_from_lru_list(zone, page, page_off_lru(page));
                spin_unlock_irqrestore(&zone->lru_lock, flags);
        }
}

static void __put_single_page(struct page *page)
{
        __page_cache_release(page);
        free_hot_cold_page(page, 0);
}

static void __put_compound_page(struct page *page)
{
        compound_page_dtor *dtor;

        __page_cache_release(page);
        dtor = get_compound_page_dtor(page);
        (*dtor)(page);
}

static void put_compound_page(struct page *page)
{
        if (unlikely(PageTail(page))) {
                /* __split_huge_page_refcount can run under us */
                struct page *page_head = compound_trans_head(page);

                if (likely(page != page_head &&
                           get_page_unless_zero(page_head))) {
                        unsigned long flags;
                        /*
                         * page_head wasn't a dangling pointer but it
                         * may not be a head page anymore by the time
                         * we obtain the lock. That is ok as long as it
                         * can't be freed from under us.
                         */
                        flags = compound_lock_irqsave(page_head);
                        if (unlikely(!PageTail(page))) {
                                /* __split_huge_page_refcount run before us */
                                compound_unlock_irqrestore(page_head, flags);
                                VM_BUG_ON(PageHead(page_head));
                                if (put_page_testzero(page_head))
                                        __put_single_page(page_head);
                        out_put_single:
                                if (put_page_testzero(page))
                                        __put_single_page(page);
                                return;
                        }
                        VM_BUG_ON(page_head != page->first_page);
                        /*
                         * We can release the refcount taken by
                         * get_page_unless_zero() now that
                         * __split_huge_page_refcount() is blocked on
                         * the compound_lock.
                         */
                        if (put_page_testzero(page_head))
                                VM_BUG_ON(1);
                        /* __split_huge_page_refcount will wait now */
                        VM_BUG_ON(page_mapcount(page) <= 0);
                        atomic_dec(&page->_mapcount);
                        VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
                        VM_BUG_ON(atomic_read(&page->_count) != 0);
                        compound_unlock_irqrestore(page_head, flags);
                        if (put_page_testzero(page_head)) {
                                if (PageHead(page_head))
                                        __put_compound_page(page_head);
                                else
                                        __put_single_page(page_head);
                        }
                } else {
                        /* page_head is a dangling pointer */
                        VM_BUG_ON(PageTail(page));
                        goto out_put_single;
                }
        } else if (put_page_testzero(page)) {
                if (PageHead(page))
                        __put_compound_page(page);
                else
                        __put_single_page(page);
        }
}

void put_page(struct page *page)
{
        if (unlikely(PageCompound(page)))
                put_compound_page(page);
        else if (put_page_testzero(page))
                __put_single_page(page);
}
EXPORT_SYMBOL(put_page);

/*
 * This function is exported but must not be called by anything other
 * than get_page(). It implements the slow path of get_page().
 */
bool __get_page_tail(struct page *page)
{
        /*
         * This takes care of get_page() if run on a tail page
         * returned by one of the get_user_pages/follow_page variants.
         * get_user_pages/follow_page itself doesn't need the compound
         * lock because it runs __get_page_tail_foll() under the
         * proper PT lock that already serializes against
         * split_huge_page().
         */
        unsigned long flags;
        bool got = false;
        struct page *page_head = compound_trans_head(page);

        if (likely(page != page_head && get_page_unless_zero(page_head))) {
                /*
                 * page_head wasn't a dangling pointer but it
                 * may not be a head page anymore by the time
                 * we obtain the lock. That is ok as long as it
                 * can't be freed from under us.
                 */
                flags = compound_lock_irqsave(page_head);
                /* here __split_huge_page_refcount won't run anymore */
                if (likely(PageTail(page))) {
                        __get_page_tail_foll(page, false);
                        got = true;
                }
                compound_unlock_irqrestore(page_head, flags);
                if (unlikely(!got))
                        put_page(page_head);
        }
        return got;
}
EXPORT_SYMBOL(__get_page_tail);

/**
 * put_pages_list() - release a list of pages
 * @pages: list of pages threaded on page->lru
 *
 * Release a list of pages which are strung together on page.lru.  Currently
 * used by read_cache_pages() and related error recovery code.
 */
void put_pages_list(struct list_head *pages)
{
        while (!list_empty(pages)) {
                struct page *victim;

                victim = list_entry(pages->prev, struct page, lru);
                list_del(&victim->lru);
                page_cache_release(victim);
        }
}
EXPORT_SYMBOL(put_pages_list);

static void pagevec_lru_move_fn(struct pagevec *pvec,
                                void (*move_fn)(struct page *page, void *arg),
                                void *arg)
{
        int i;
        struct zone *zone = NULL;
        unsigned long flags = 0;

        for (i = 0; i < pagevec_count(pvec); i++) {
                struct page *page = pvec->pages[i];
                struct zone *pagezone = page_zone(page);

                if (pagezone != zone) {
                        if (zone)
                                spin_unlock_irqrestore(&zone->lru_lock, flags);
                        zone = pagezone;
                        spin_lock_irqsave(&zone->lru_lock, flags);
                }

                (*move_fn)(page, arg);
        }
        if (zone)
                spin_unlock_irqrestore(&zone->lru_lock, flags);
        release_pages(pvec->pages, pvec->nr, pvec->cold);
        pagevec_reinit(pvec);
}

static void pagevec_move_tail_fn(struct page *page, void *arg)
{
        int *pgmoved = arg;

        if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
                enum lru_list lru = page_lru_base_type(page);
                struct lruvec *lruvec;

                lruvec = mem_cgroup_lru_move_lists(page_zone(page),
                                                   page, lru, lru);
                list_move_tail(&page->lru, &lruvec->lists[lru]);
                (*pgmoved)++;
        }
}

/*
 * pagevec_move_tail() must be called with IRQ disabled.
 * Otherwise this may cause nasty races.
 */
static void pagevec_move_tail(struct pagevec *pvec)
{
        int pgmoved = 0;

        pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved);
        __count_vm_events(PGROTATED, pgmoved);
}

/*
 * Writeback is about to end against a page which has been marked for immediate
 * reclaim.  If it still appears to be reclaimable, move it to the tail of the
 * inactive list.
 */
void rotate_reclaimable_page(struct page *page)
{
        if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
            !PageUnevictable(page) && PageLRU(page)) {
                struct pagevec *pvec;
                unsigned long flags;

                page_cache_get(page);
                local_irq_save(flags);
                pvec = &__get_cpu_var(lru_rotate_pvecs);
                if (!pagevec_add(pvec, page))
                        pagevec_move_tail(pvec);
                local_irq_restore(flags);
        }
}

static void update_page_reclaim_stat(struct zone *zone, struct page *page,
                                     int file, int rotated)
{
        struct zone_reclaim_stat *reclaim_stat = &zone->reclaim_stat;
        struct zone_reclaim_stat *memcg_reclaim_stat;

        memcg_reclaim_stat = mem_cgroup_get_reclaim_stat_from_page(page);

        reclaim_stat->recent_scanned[file]++;
        if (rotated)
                reclaim_stat->recent_rotated[file]++;

        if (!memcg_reclaim_stat)
                return;

        memcg_reclaim_stat->recent_scanned[file]++;
        if (rotated)
                memcg_reclaim_stat->recent_rotated[file]++;
}

static void __activate_page(struct page *page, void *arg)
{
        struct zone *zone = page_zone(page);

        if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
                int file = page_is_file_cache(page);
                int lru = page_lru_base_type(page);
                del_page_from_lru_list(zone, page, lru);

                SetPageActive(page);
                lru += LRU_ACTIVE;
                add_page_to_lru_list(zone, page, lru);
                __count_vm_event(PGACTIVATE);

                update_page_reclaim_stat(zone, page, file, 1);
        }
}

#ifdef CONFIG_SMP
static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);

static void activate_page_drain(int cpu)
{
        struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);

        if (pagevec_count(pvec))
                pagevec_lru_move_fn(pvec, __activate_page, NULL);
}

void activate_page(struct page *page)
{
        if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
                struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);

                page_cache_get(page);
                if (!pagevec_add(pvec, page))
                        pagevec_lru_move_fn(pvec, __activate_page, NULL);
                put_cpu_var(activate_page_pvecs);
        }
}

#else
static inline void activate_page_drain(int cpu)
{
}

void activate_page(struct page *page)
{
        struct zone *zone = page_zone(page);

        spin_lock_irq(&zone->lru_lock);
        __activate_page(page, NULL);
        spin_unlock_irq(&zone->lru_lock);
}
#endif

/*
 * Mark a page as having seen activity.
 *
 * inactive,unreferenced        ->      inactive,referenced
 * inactive,referenced          ->      active,unreferenced
 * active,unreferenced          ->      active,referenced
 */
void mark_page_accessed(struct page *page)
{
        if (!PageActive(page) && !PageUnevictable(page) &&
                        PageReferenced(page) && PageLRU(page)) {
                activate_page(page);
                ClearPageReferenced(page);
        } else if (!PageReferenced(page)) {
                SetPageReferenced(page);
        }
}
EXPORT_SYMBOL(mark_page_accessed);

void __lru_cache_add(struct page *page, enum lru_list lru)
{
        struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru];

        page_cache_get(page);
        if (!pagevec_add(pvec, page))
                __pagevec_lru_add(pvec, lru);
        put_cpu_var(lru_add_pvecs);
}
EXPORT_SYMBOL(__lru_cache_add);

/**
 * lru_cache_add_lru - add a page to a page list
 * @page: the page to be added to the LRU.
 * @lru: the LRU list to which the page is added.
 */
void lru_cache_add_lru(struct page *page, enum lru_list lru)
{
        if (PageActive(page)) {
                VM_BUG_ON(PageUnevictable(page));
                ClearPageActive(page);
        } else if (PageUnevictable(page)) {
                VM_BUG_ON(PageActive(page));
                ClearPageUnevictable(page);
        }

        VM_BUG_ON(PageLRU(page) || PageActive(page) || PageUnevictable(page));
        __lru_cache_add(page, lru);
}

/**
 * add_page_to_unevictable_list - add a page to the unevictable list
 * @page:  the page to be added to the unevictable list
 *
 * Add page directly to its zone's unevictable list.  To avoid races with
 * tasks that might be making the page evictable, through eg. munlock,
 * munmap or exit, while it's not on the lru, we want to add the page
 * while it's locked or otherwise "invisible" to other tasks.  This is
 * difficult to do when using the pagevec cache, so bypass that.
 */
void add_page_to_unevictable_list(struct page *page)
{
        struct zone *zone = page_zone(page);

        spin_lock_irq(&zone->lru_lock);
        SetPageUnevictable(page);
        SetPageLRU(page);
        add_page_to_lru_list(zone, page, LRU_UNEVICTABLE);
        spin_unlock_irq(&zone->lru_lock);
}

/*
 * If the page can not be invalidated, it is moved to the
 * inactive list to speed up its reclaim.  It is moved to the
 * head of the list, rather than the tail, to give the flusher
 * threads some time to write it out, as this is much more
 * effective than the single-page writeout from reclaim.
 *
 * If the page isn't page_mapped and dirty/writeback, the page
 * could reclaim asap using PG_reclaim.
 *
 * 1. active, mapped page -> none
 * 2. active, dirty/writeback page -> inactive, head, PG_reclaim
 * 3. inactive, mapped page -> none
 * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim
 * 5. inactive, clean -> inactive, tail
 * 6. Others -> none
 *
 * In 4, why it moves inactive's head, the VM expects the page would
 * be write it out by flusher threads as this is much more effective
 * than the single-page writeout from reclaim.
 */
static void lru_deactivate_fn(struct page *page, void *arg)
{
        int lru, file;
        bool active;
        struct zone *zone = page_zone(page);

        if (!PageLRU(page))
                return;

        if (PageUnevictable(page))
                return;

        /* Some processes are using the page */
        if (page_mapped(page))
                return;

        active = PageActive(page);

        file = page_is_file_cache(page);
        lru = page_lru_base_type(page);
        del_page_from_lru_list(zone, page, lru + active);
        ClearPageActive(page);
        ClearPageReferenced(page);
        add_page_to_lru_list(zone, page, lru);

        if (PageWriteback(page) || PageDirty(page)) {
                /*
                 * PG_reclaim could be raced with end_page_writeback
                 * It can make readahead confusing.  But race window
                 * is _really_ small and  it's non-critical problem.
                 */
                SetPageReclaim(page);
        } else {
                struct lruvec *lruvec;
                /*
                 * The page's writeback ends up during pagevec
                 * We moves tha page into tail of inactive.
                 */
                lruvec = mem_cgroup_lru_move_lists(zone, page, lru, lru);
                list_move_tail(&page->lru, &lruvec->lists[lru]);
                __count_vm_event(PGROTATED);
        }

        if (active)
                __count_vm_event(PGDEACTIVATE);
        update_page_reclaim_stat(zone, page, file, 0);
}

/*
 * Drain pages out of the cpu's pagevecs.
 * Either "cpu" is the current CPU, and preemption has already been
 * disabled; or "cpu" is being hot-unplugged, and is already dead.
 */
static void drain_cpu_pagevecs(int cpu)
{
        struct pagevec *pvecs = per_cpu(lru_add_pvecs, cpu);
        struct pagevec *pvec;
        int lru;

        for_each_lru(lru) {
                pvec = &pvecs[lru - LRU_BASE];
                if (pagevec_count(pvec))
                        __pagevec_lru_add(pvec, lru);
        }

        pvec = &per_cpu(lru_rotate_pvecs, cpu);
        if (pagevec_count(pvec)) {
                unsigned long flags;

                /* No harm done if a racing interrupt already did this */
                local_irq_save(flags);
                pagevec_move_tail(pvec);
                local_irq_restore(flags);
        }

        pvec = &per_cpu(lru_deactivate_pvecs, cpu);
        if (pagevec_count(pvec))
                pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);

        activate_page_drain(cpu);
}

/**
 * deactivate_page - forcefully deactivate a page
 * @page: page to deactivate
 *
 * This function hints the VM that @page is a good reclaim candidate,
 * for example if its invalidation fails due to the page being dirty
 * or under writeback.
 */
void deactivate_page(struct page *page)
{
        /*
         * In a workload with many unevictable page such as mprotect, unevictable
         * page deactivation for accelerating reclaim is pointless.
         */
        if (PageUnevictable(page))
                return;

        if (likely(get_page_unless_zero(page))) {
                struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);

                if (!pagevec_add(pvec, page))
                        pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
                put_cpu_var(lru_deactivate_pvecs);
        }
}

void lru_add_drain(void)
{
        drain_cpu_pagevecs(get_cpu());
        put_cpu();
}

static void lru_add_drain_per_cpu(struct work_struct *dummy)
{
        lru_add_drain();
}

/*
 * Returns 0 for success
 */
int lru_add_drain_all(void)
{
        return schedule_on_each_cpu(lru_add_drain_per_cpu);
}

/*
 * Batched page_cache_release().  Decrement the reference count on all the
 * passed pages.  If it fell to zero then remove the page from the LRU and
 * free it.
 *
 * Avoid taking zone->lru_lock if possible, but if it is taken, retain it
 * for the remainder of the operation.
 *
 * The locking in this function is against shrink_inactive_list(): we recheck
 * the page count inside the lock to see whether shrink_inactive_list()
 * grabbed the page via the LRU.  If it did, give up: shrink_inactive_list()
 * will free it.
 */
void release_pages(struct page **pages, int nr, int cold)
{
        int i;
        LIST_HEAD(pages_to_free);
        struct zone *zone = NULL;
        unsigned long uninitialized_var(flags);

        for (i = 0; i < nr; i++) {
                struct page *page = pages[i];

                if (unlikely(PageCompound(page))) {
                        if (zone) {
                                spin_unlock_irqrestore(&zone->lru_lock, flags);
                                zone = NULL;
                        }
                        put_compound_page(page);
                        continue;
                }

                if (!put_page_testzero(page))
                        continue;

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

                        if (pagezone != zone) {
                                if (zone)
                                        spin_unlock_irqrestore(&zone->lru_lock,
                                                                        flags);
                                zone = pagezone;
                                spin_lock_irqsave(&zone->lru_lock, flags);
                        }
                        VM_BUG_ON(!PageLRU(page));
                        __ClearPageLRU(page);
                        del_page_from_lru_list(zone, page, page_off_lru(page));
                }

                list_add(&page->lru, &pages_to_free);
        }
        if (zone)
                spin_unlock_irqrestore(&zone->lru_lock, flags);

        free_hot_cold_page_list(&pages_to_free, cold);
}
EXPORT_SYMBOL(release_pages);

/*
 * The pages which we're about to release may be in the deferred lru-addition
 * queues.  That would prevent them from really being freed right now.  That's
 * OK from a correctness point of view but is inefficient - those pages may be
 * cache-warm and we want to give them back to the page allocator ASAP.
 *
 * So __pagevec_release() will drain those queues here.  __pagevec_lru_add()
 * and __pagevec_lru_add_active() call release_pages() directly to avoid
 * mutual recursion.
 */
void __pagevec_release(struct pagevec *pvec)
{
        lru_add_drain();
        release_pages(pvec->pages, pagevec_count(pvec), pvec->cold);
        pagevec_reinit(pvec);
}
EXPORT_SYMBOL(__pagevec_release);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* used by __split_huge_page_refcount() */
void lru_add_page_tail(struct zone* zone,
                       struct page *page, struct page *page_tail)
{
        int uninitialized_var(active);
        enum lru_list lru;
        const int file = 0;

        VM_BUG_ON(!PageHead(page));
        VM_BUG_ON(PageCompound(page_tail));
        VM_BUG_ON(PageLRU(page_tail));
        VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&zone->lru_lock));

        SetPageLRU(page_tail);

        if (page_evictable(page_tail, NULL)) {
                if (PageActive(page)) {
                        SetPageActive(page_tail);
                        active = 1;
                        lru = LRU_ACTIVE_ANON;
                } else {
                        active = 0;
                        lru = LRU_INACTIVE_ANON;
                }
        } else {
                SetPageUnevictable(page_tail);
                lru = LRU_UNEVICTABLE;
        }

        if (likely(PageLRU(page)))
                list_add_tail(&page_tail->lru, &page->lru);
        else {
                struct list_head *list_head;
                /*
                 * Head page has not yet been counted, as an hpage,
                 * so we must account for each subpage individually.
                 *
                 * Use the standard add function to put page_tail on the list,
                 * but then correct its position so they all end up in order.
                 */
                add_page_to_lru_list(zone, page_tail, lru);
                list_head = page_tail->lru.prev;
                list_move_tail(&page_tail->lru, list_head);
        }

        if (!PageUnevictable(page))
                update_page_reclaim_stat(zone, page_tail, file, active);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

static void __pagevec_lru_add_fn(struct page *page, void *arg)
{
        enum lru_list lru = (enum lru_list)arg;
        struct zone *zone = page_zone(page);
        int file = is_file_lru(lru);
        int active = is_active_lru(lru);

        VM_BUG_ON(PageActive(page));
        VM_BUG_ON(PageUnevictable(page));
        VM_BUG_ON(PageLRU(page));

        SetPageLRU(page);
        if (active)
                SetPageActive(page);
        add_page_to_lru_list(zone, page, lru);
        update_page_reclaim_stat(zone, page, file, active);
}

/*
 * Add the passed pages to the LRU, then drop the caller's refcount
 * on them.  Reinitialises the caller's pagevec.
 */
void __pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
{
        VM_BUG_ON(is_unevictable_lru(lru));

        pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, (void *)lru);
}
EXPORT_SYMBOL(__pagevec_lru_add);

/**
 * pagevec_lookup - gang pagecache lookup
 * @pvec:       Where the resulting pages are placed
 * @mapping:    The address_space to search
 * @start:      The starting page index
 * @nr_pages:   The maximum number of pages
 *
 * pagevec_lookup() will search for and return a group of up to @nr_pages pages
 * in the mapping.  The pages are placed in @pvec.  pagevec_lookup() takes a
 * reference against the pages in @pvec.
 *
 * The search returns a group of mapping-contiguous pages with ascending
 * indexes.  There may be holes in the indices due to not-present pages.
 *
 * pagevec_lookup() returns the number of pages which were found.
 */
unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
                pgoff_t start, unsigned nr_pages)
{
        pvec->nr = find_get_pages(mapping, start, nr_pages, pvec->pages);
        return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup);

unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
                pgoff_t *index, int tag, unsigned nr_pages)
{
        pvec->nr = find_get_pages_tag(mapping, index, tag,
                                        nr_pages, pvec->pages);
        return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup_tag);

/*
 * Perform any setup for the swap system
 */
void __init swap_setup(void)
{
        unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT);

#ifdef CONFIG_SWAP
        bdi_init(swapper_space.backing_dev_info);
#endif

        /* Use a smaller cluster for small-memory machines */
        if (megs < 16)
                page_cluster = 2;
        else
                page_cluster = 3;
        /*
         * Right now other parts of the system means that we
         * _really_ don't want to cluster much more
         */
}