fault-injection: add ability to export fault_attr in arbitrary directory

[~shefty/rdma-dev.git] / mm / page_alloc.c

/*
 *  linux/mm/page_alloc.c
 *
 *  Manages the free list, the system allocates free pages here.
 *  Note that kmalloc() lives in slab.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *  Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
 *  Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
 *  Zone balancing, Kanoj Sarcar, SGI, Jan 2000
 *  Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
 *          (lots of bits borrowed from Ingo Molnar & Andrew Morton)
 */

#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/jiffies.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/kmemcheck.h>
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/oom.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>
#include <linux/vmstat.h>
#include <linux/mempolicy.h>
#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <linux/pfn.h>
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
#include <linux/page-isolation.h>
#include <linux/page_cgroup.h>
#include <linux/debugobjects.h>
#include <linux/kmemleak.h>
#include <linux/memory.h>
#include <linux/compaction.h>
#include <trace/events/kmem.h>
#include <linux/ftrace_event.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>

#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"

#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DEFINE_PER_CPU(int, numa_node);
EXPORT_PER_CPU_SYMBOL(numa_node);
#endif

#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
 * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
 * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
 * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem()
 * defined in <linux/topology.h>.
 */
DEFINE_PER_CPU(int, _numa_mem_);                /* Kernel "local memory" node */
EXPORT_PER_CPU_SYMBOL(_numa_mem_);
#endif

/*
 * Array of node states.
 */
nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
        [N_POSSIBLE] = NODE_MASK_ALL,
        [N_ONLINE] = { { [0] = 1UL } },
#ifndef CONFIG_NUMA
        [N_NORMAL_MEMORY] = { { [0] = 1UL } },
#ifdef CONFIG_HIGHMEM
        [N_HIGH_MEMORY] = { { [0] = 1UL } },
#endif
        [N_CPU] = { { [0] = 1UL } },
#endif  /* NUMA */
};
EXPORT_SYMBOL(node_states);

unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;

#ifdef CONFIG_PM_SLEEP
/*
 * The following functions are used by the suspend/hibernate code to temporarily
 * change gfp_allowed_mask in order to avoid using I/O during memory allocations
 * while devices are suspended.  To avoid races with the suspend/hibernate code,
 * they should always be called with pm_mutex held (gfp_allowed_mask also should
 * only be modified with pm_mutex held, unless the suspend/hibernate code is
 * guaranteed not to run in parallel with that modification).
 */

static gfp_t saved_gfp_mask;

void pm_restore_gfp_mask(void)
{
        WARN_ON(!mutex_is_locked(&pm_mutex));
        if (saved_gfp_mask) {
                gfp_allowed_mask = saved_gfp_mask;
                saved_gfp_mask = 0;
        }
}

void pm_restrict_gfp_mask(void)
{
        WARN_ON(!mutex_is_locked(&pm_mutex));
        WARN_ON(saved_gfp_mask);
        saved_gfp_mask = gfp_allowed_mask;
        gfp_allowed_mask &= ~GFP_IOFS;
}
#endif /* CONFIG_PM_SLEEP */

#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
int pageblock_order __read_mostly;
#endif

static void __free_pages_ok(struct page *page, unsigned int order);

/*
 * results with 256, 32 in the lowmem_reserve sysctl:
 *      1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
 *      1G machine -> (16M dma, 784M normal, 224M high)
 *      NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
 *      HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
 *      HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA
 *
 * TBD: should special case ZONE_DMA32 machines here - in those we normally
 * don't need any ZONE_NORMAL reservation
 */
int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
#ifdef CONFIG_ZONE_DMA
         256,
#endif
#ifdef CONFIG_ZONE_DMA32
         256,
#endif
#ifdef CONFIG_HIGHMEM
         32,
#endif
         32,
};

EXPORT_SYMBOL(totalram_pages);

static char * const zone_names[MAX_NR_ZONES] = {
#ifdef CONFIG_ZONE_DMA
         "DMA",
#endif
#ifdef CONFIG_ZONE_DMA32
         "DMA32",
#endif
         "Normal",
#ifdef CONFIG_HIGHMEM
         "HighMem",
#endif
         "Movable",
};

int min_free_kbytes = 1024;

static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
static unsigned long __meminitdata dma_reserve;

#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
  /*
   * MAX_ACTIVE_REGIONS determines the maximum number of distinct
   * ranges of memory (RAM) that may be registered with add_active_range().
   * Ranges passed to add_active_range() will be merged if possible
   * so the number of times add_active_range() can be called is
   * related to the number of nodes and the number of holes
   */
  #ifdef CONFIG_MAX_ACTIVE_REGIONS
    /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */
    #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS
  #else
    #if MAX_NUMNODES >= 32
      /* If there can be many nodes, allow up to 50 holes per node */
      #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50)
    #else
      /* By default, allow up to 256 distinct regions */
      #define MAX_ACTIVE_REGIONS 256
    #endif
  #endif

  static struct node_active_region __meminitdata early_node_map[MAX_ACTIVE_REGIONS];
  static int __meminitdata nr_nodemap_entries;
  static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
  static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
  static unsigned long __initdata required_kernelcore;
  static unsigned long __initdata required_movablecore;
  static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];

  /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
  int movable_zone;
  EXPORT_SYMBOL(movable_zone);
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */

#if MAX_NUMNODES > 1
int nr_node_ids __read_mostly = MAX_NUMNODES;
int nr_online_nodes __read_mostly = 1;
EXPORT_SYMBOL(nr_node_ids);
EXPORT_SYMBOL(nr_online_nodes);
#endif

int page_group_by_mobility_disabled __read_mostly;

static void set_pageblock_migratetype(struct page *page, int migratetype)
{

        if (unlikely(page_group_by_mobility_disabled))
                migratetype = MIGRATE_UNMOVABLE;

        set_pageblock_flags_group(page, (unsigned long)migratetype,
                                        PB_migrate, PB_migrate_end);
}

bool oom_killer_disabled __read_mostly;

#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
{
        int ret = 0;
        unsigned seq;
        unsigned long pfn = page_to_pfn(page);

        do {
                seq = zone_span_seqbegin(zone);
                if (pfn >= zone->zone_start_pfn + zone->spanned_pages)
                        ret = 1;
                else if (pfn < zone->zone_start_pfn)
                        ret = 1;
        } while (zone_span_seqretry(zone, seq));

        return ret;
}

static int page_is_consistent(struct zone *zone, struct page *page)
{
        if (!pfn_valid_within(page_to_pfn(page)))
                return 0;
        if (zone != page_zone(page))
                return 0;

        return 1;
}
/*
 * Temporary debugging check for pages not lying within a given zone.
 */
static int bad_range(struct zone *zone, struct page *page)
{
        if (page_outside_zone_boundaries(zone, page))
                return 1;
        if (!page_is_consistent(zone, page))
                return 1;

        return 0;
}
#else
static inline int bad_range(struct zone *zone, struct page *page)
{
        return 0;
}
#endif

static void bad_page(struct page *page)
{
        static unsigned long resume;
        static unsigned long nr_shown;
        static unsigned long nr_unshown;

        /* Don't complain about poisoned pages */
        if (PageHWPoison(page)) {
                reset_page_mapcount(page); /* remove PageBuddy */
                return;
        }

        /*
         * Allow a burst of 60 reports, then keep quiet for that minute;
         * or allow a steady drip of one report per second.
         */
        if (nr_shown == 60) {
                if (time_before(jiffies, resume)) {
                        nr_unshown++;
                        goto out;
                }
                if (nr_unshown) {
                        printk(KERN_ALERT
                              "BUG: Bad page state: %lu messages suppressed\n",
                                nr_unshown);
                        nr_unshown = 0;
                }
                nr_shown = 0;
        }
        if (nr_shown++ == 0)
                resume = jiffies + 60 * HZ;

        printk(KERN_ALERT "BUG: Bad page state in process %s  pfn:%05lx\n",
                current->comm, page_to_pfn(page));
        dump_page(page);

        dump_stack();
out:
        /* Leave bad fields for debug, except PageBuddy could make trouble */
        reset_page_mapcount(page); /* remove PageBuddy */
        add_taint(TAINT_BAD_PAGE);
}

/*
 * Higher-order pages are called "compound pages".  They are structured thusly:
 *
 * The first PAGE_SIZE page is called the "head page".
 *
 * The remaining PAGE_SIZE pages are called "tail pages".
 *
 * All pages have PG_compound set.  All pages have their ->private pointing at
 * the head page (even the head page has this).
 *
 * The first tail page's ->lru.next holds the address of the compound page's
 * put_page() function.  Its ->lru.prev holds the order of allocation.
 * This usage means that zero-order pages may not be compound.
 */

static void free_compound_page(struct page *page)
{
        __free_pages_ok(page, compound_order(page));
}

void prep_compound_page(struct page *page, unsigned long order)
{
        int i;
        int nr_pages = 1 << order;

        set_compound_page_dtor(page, free_compound_page);
        set_compound_order(page, order);
        __SetPageHead(page);
        for (i = 1; i < nr_pages; i++) {
                struct page *p = page + i;

                __SetPageTail(p);
                p->first_page = page;
        }
}

/* update __split_huge_page_refcount if you change this function */
static int destroy_compound_page(struct page *page, unsigned long order)
{
        int i;
        int nr_pages = 1 << order;
        int bad = 0;

        if (unlikely(compound_order(page) != order) ||
            unlikely(!PageHead(page))) {
                bad_page(page);
                bad++;
        }

        __ClearPageHead(page);

        for (i = 1; i < nr_pages; i++) {
                struct page *p = page + i;

                if (unlikely(!PageTail(p) || (p->first_page != page))) {
                        bad_page(page);
                        bad++;
                }
                __ClearPageTail(p);
        }

        return bad;
}

static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
{
        int i;

        /*
         * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO
         * and __GFP_HIGHMEM from hard or soft interrupt context.
         */
        VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt());
        for (i = 0; i < (1 << order); i++)
                clear_highpage(page + i);
}

static inline void set_page_order(struct page *page, int order)
{
        set_page_private(page, order);
        __SetPageBuddy(page);
}

static inline void rmv_page_order(struct page *page)
{
        __ClearPageBuddy(page);
        set_page_private(page, 0);
}

/*
 * Locate the struct page for both the matching buddy in our
 * pair (buddy1) and the combined O(n+1) page they form (page).
 *
 * 1) Any buddy B1 will have an order O twin B2 which satisfies
 * the following equation:
 *     B2 = B1 ^ (1 << O)
 * For example, if the starting buddy (buddy2) is #8 its order
 * 1 buddy is #10:
 *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
 *
 * 2) Any buddy B will have an order O+1 parent P which
 * satisfies the following equation:
 *     P = B & ~(1 << O)
 *
 * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
 */
static inline unsigned long
__find_buddy_index(unsigned long page_idx, unsigned int order)
{
        return page_idx ^ (1 << order);
}

/*
 * This function checks whether a page is free && is the buddy
 * we can do coalesce a page and its buddy if
 * (a) the buddy is not in a hole &&
 * (b) the buddy is in the buddy system &&
 * (c) a page and its buddy have the same order &&
 * (d) a page and its buddy are in the same zone.
 *
 * For recording whether a page is in the buddy system, we set ->_mapcount -2.
 * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock.
 *
 * For recording page's order, we use page_private(page).
 */
static inline int page_is_buddy(struct page *page, struct page *buddy,
                                                                int order)
{
        if (!pfn_valid_within(page_to_pfn(buddy)))
                return 0;

        if (page_zone_id(page) != page_zone_id(buddy))
                return 0;

        if (PageBuddy(buddy) && page_order(buddy) == order) {
                VM_BUG_ON(page_count(buddy) != 0);
                return 1;
        }
        return 0;
}

/*
 * Freeing function for a buddy system allocator.
 *
 * The concept of a buddy system is to maintain direct-mapped table
 * (containing bit values) for memory blocks of various "orders".
 * The bottom level table contains the map for the smallest allocatable
 * units of memory (here, pages), and each level above it describes
 * pairs of units from the levels below, hence, "buddies".
 * At a high level, all that happens here is marking the table entry
 * at the bottom level available, and propagating the changes upward
 * as necessary, plus some accounting needed to play nicely with other
 * parts of the VM system.
 * At each level, we keep a list of pages, which are heads of continuous
 * free pages of length of (1 << order) and marked with _mapcount -2. Page's
 * order is recorded in page_private(page) field.
 * So when we are allocating or freeing one, we can derive the state of the
 * other.  That is, if we allocate a small block, and both were   
 * free, the remainder of the region must be split into blocks.   
 * If a block is freed, and its buddy is also free, then this
 * triggers coalescing into a block of larger size.            
 *
 * -- wli
 */

static inline void __free_one_page(struct page *page,
                struct zone *zone, unsigned int order,
                int migratetype)
{
        unsigned long page_idx;
        unsigned long combined_idx;
        unsigned long uninitialized_var(buddy_idx);
        struct page *buddy;

        if (unlikely(PageCompound(page)))
                if (unlikely(destroy_compound_page(page, order)))
                        return;

        VM_BUG_ON(migratetype == -1);

        page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);

        VM_BUG_ON(page_idx & ((1 << order) - 1));
        VM_BUG_ON(bad_range(zone, page));

        while (order < MAX_ORDER-1) {
                buddy_idx = __find_buddy_index(page_idx, order);
                buddy = page + (buddy_idx - page_idx);
                if (!page_is_buddy(page, buddy, order))
                        break;

                /* Our buddy is free, merge with it and move up one order. */
                list_del(&buddy->lru);
                zone->free_area[order].nr_free--;
                rmv_page_order(buddy);
                combined_idx = buddy_idx & page_idx;
                page = page + (combined_idx - page_idx);
                page_idx = combined_idx;
                order++;
        }
        set_page_order(page, order);

        /*
         * If this is not the largest possible page, check if the buddy
         * of the next-highest order is free. If it is, it's possible
         * that pages are being freed that will coalesce soon. In case,
         * that is happening, add the free page to the tail of the list
         * so it's less likely to be used soon and more likely to be merged
         * as a higher order page
         */
        if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) {
                struct page *higher_page, *higher_buddy;
                combined_idx = buddy_idx & page_idx;
                higher_page = page + (combined_idx - page_idx);
                buddy_idx = __find_buddy_index(combined_idx, order + 1);
                higher_buddy = page + (buddy_idx - combined_idx);
                if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
                        list_add_tail(&page->lru,
                                &zone->free_area[order].free_list[migratetype]);
                        goto out;
                }
        }

        list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
out:
        zone->free_area[order].nr_free++;
}

/*
 * free_page_mlock() -- clean up attempts to free and mlocked() page.
 * Page should not be on lru, so no need to fix that up.
 * free_pages_check() will verify...
 */
static inline void free_page_mlock(struct page *page)
{
        __dec_zone_page_state(page, NR_MLOCK);
        __count_vm_event(UNEVICTABLE_MLOCKFREED);
}

static inline int free_pages_check(struct page *page)
{
        if (unlikely(page_mapcount(page) |
                (page->mapping != NULL)  |
                (atomic_read(&page->_count) != 0) |
                (page->flags & PAGE_FLAGS_CHECK_AT_FREE) |
                (mem_cgroup_bad_page_check(page)))) {
                bad_page(page);
                return 1;
        }
        if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
                page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
        return 0;
}

/*
 * Frees a number of pages from the PCP lists
 * Assumes all pages on list are in same zone, and of same order.
 * count is the number of pages to free.
 *
 * If the zone was previously in an "all pages pinned" state then look to
 * see if this freeing clears that state.
 *
 * And clear the zone's pages_scanned counter, to hold off the "all pages are
 * pinned" detection logic.
 */
static void free_pcppages_bulk(struct zone *zone, int count,
                                        struct per_cpu_pages *pcp)
{
        int migratetype = 0;
        int batch_free = 0;
        int to_free = count;

        spin_lock(&zone->lock);
        zone->all_unreclaimable = 0;
        zone->pages_scanned = 0;

        while (to_free) {
                struct page *page;
                struct list_head *list;

                /*
                 * Remove pages from lists in a round-robin fashion. A
                 * batch_free count is maintained that is incremented when an
                 * empty list is encountered.  This is so more pages are freed
                 * off fuller lists instead of spinning excessively around empty
                 * lists
                 */
                do {
                        batch_free++;
                        if (++migratetype == MIGRATE_PCPTYPES)
                                migratetype = 0;
                        list = &pcp->lists[migratetype];
                } while (list_empty(list));

                /* This is the only non-empty list. Free them all. */
                if (batch_free == MIGRATE_PCPTYPES)
                        batch_free = to_free;

                do {
                        page = list_entry(list->prev, struct page, lru);
                        /* must delete as __free_one_page list manipulates */
                        list_del(&page->lru);
                        /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
                        __free_one_page(page, zone, 0, page_private(page));
                        trace_mm_page_pcpu_drain(page, 0, page_private(page));
                } while (--to_free && --batch_free && !list_empty(list));
        }
        __mod_zone_page_state(zone, NR_FREE_PAGES, count);
        spin_unlock(&zone->lock);
}

static void free_one_page(struct zone *zone, struct page *page, int order,
                                int migratetype)
{
        spin_lock(&zone->lock);
        zone->all_unreclaimable = 0;
        zone->pages_scanned = 0;

        __free_one_page(page, zone, order, migratetype);
        __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
        spin_unlock(&zone->lock);
}

static bool free_pages_prepare(struct page *page, unsigned int order)
{
        int i;
        int bad = 0;

        trace_mm_page_free_direct(page, order);
        kmemcheck_free_shadow(page, order);

        if (PageAnon(page))
                page->mapping = NULL;
        for (i = 0; i < (1 << order); i++)
                bad += free_pages_check(page + i);
        if (bad)
                return false;

        if (!PageHighMem(page)) {
                debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
                debug_check_no_obj_freed(page_address(page),
                                           PAGE_SIZE << order);
        }
        arch_free_page(page, order);
        kernel_map_pages(page, 1 << order, 0);

        return true;
}

static void __free_pages_ok(struct page *page, unsigned int order)
{
        unsigned long flags;
        int wasMlocked = __TestClearPageMlocked(page);

        if (!free_pages_prepare(page, order))
                return;

        local_irq_save(flags);
        if (unlikely(wasMlocked))
                free_page_mlock(page);
        __count_vm_events(PGFREE, 1 << order);
        free_one_page(page_zone(page), page, order,
                                        get_pageblock_migratetype(page));
        local_irq_restore(flags);
}

/*
 * permit the bootmem allocator to evade page validation on high-order frees
 */
void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
{
        if (order == 0) {
                __ClearPageReserved(page);
                set_page_count(page, 0);
                set_page_refcounted(page);
                __free_page(page);
        } else {
                int loop;

                prefetchw(page);
                for (loop = 0; loop < BITS_PER_LONG; loop++) {
                        struct page *p = &page[loop];

                        if (loop + 1 < BITS_PER_LONG)
                                prefetchw(p + 1);
                        __ClearPageReserved(p);
                        set_page_count(p, 0);
                }

                set_page_refcounted(page);
                __free_pages(page, order);
        }
}


/*
 * The order of subdivision here is critical for the IO subsystem.
 * Please do not alter this order without good reasons and regression
 * testing. Specifically, as large blocks of memory are subdivided,
 * the order in which smaller blocks are delivered depends on the order
 * they're subdivided in this function. This is the primary factor
 * influencing the order in which pages are delivered to the IO
 * subsystem according to empirical testing, and this is also justified
 * by considering the behavior of a buddy system containing a single
 * large block of memory acted on by a series of small allocations.
 * This behavior is a critical factor in sglist merging's success.
 *
 * -- wli
 */
static inline void expand(struct zone *zone, struct page *page,
        int low, int high, struct free_area *area,
        int migratetype)
{
        unsigned long size = 1 << high;

        while (high > low) {
                area--;
                high--;
                size >>= 1;
                VM_BUG_ON(bad_range(zone, &page[size]));
                list_add(&page[size].lru, &area->free_list[migratetype]);
                area->nr_free++;
                set_page_order(&page[size], high);
        }
}

/*
 * This page is about to be returned from the page allocator
 */
static inline int check_new_page(struct page *page)
{
        if (unlikely(page_mapcount(page) |
                (page->mapping != NULL)  |
                (atomic_read(&page->_count) != 0)  |
                (page->flags & PAGE_FLAGS_CHECK_AT_PREP) |
                (mem_cgroup_bad_page_check(page)))) {
                bad_page(page);
                return 1;
        }
        return 0;
}

static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
{
        int i;

        for (i = 0; i < (1 << order); i++) {
                struct page *p = page + i;
                if (unlikely(check_new_page(p)))
                        return 1;
        }

        set_page_private(page, 0);
        set_page_refcounted(page);

        arch_alloc_page(page, order);
        kernel_map_pages(page, 1 << order, 1);

        if (gfp_flags & __GFP_ZERO)
                prep_zero_page(page, order, gfp_flags);

        if (order && (gfp_flags & __GFP_COMP))
                prep_compound_page(page, order);

        return 0;
}

/*
 * Go through the free lists for the given migratetype and remove
 * the smallest available page from the freelists
 */
static inline
struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
                                                int migratetype)
{
        unsigned int current_order;
        struct free_area * area;
        struct page *page;

        /* Find a page of the appropriate size in the preferred list */
        for (current_order = order; current_order < MAX_ORDER; ++current_order) {
                area = &(zone->free_area[current_order]);
                if (list_empty(&area->free_list[migratetype]))
                        continue;

                page = list_entry(area->free_list[migratetype].next,
                                                        struct page, lru);
                list_del(&page->lru);
                rmv_page_order(page);
                area->nr_free--;
                expand(zone, page, order, current_order, area, migratetype);
                return page;
        }

        return NULL;
}


/*
 * This array describes the order lists are fallen back to when
 * the free lists for the desirable migrate type are depleted
 */
static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = {
        [MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,   MIGRATE_RESERVE },
        [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,   MIGRATE_RESERVE },
        [MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
        [MIGRATE_RESERVE]     = { MIGRATE_RESERVE,     MIGRATE_RESERVE,   MIGRATE_RESERVE }, /* Never used */
};

/*
 * Move the free pages in a range to the free lists of the requested type.
 * Note that start_page and end_pages are not aligned on a pageblock
 * boundary. If alignment is required, use move_freepages_block()
 */
static int move_freepages(struct zone *zone,
                          struct page *start_page, struct page *end_page,
                          int migratetype)
{
        struct page *page;
        unsigned long order;
        int pages_moved = 0;

#ifndef CONFIG_HOLES_IN_ZONE
        /*
         * page_zone is not safe to call in this context when
         * CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant
         * anyway as we check zone boundaries in move_freepages_block().
         * Remove at a later date when no bug reports exist related to
         * grouping pages by mobility
         */
        BUG_ON(page_zone(start_page) != page_zone(end_page));
#endif

        for (page = start_page; page <= end_page;) {
                /* Make sure we are not inadvertently changing nodes */
                VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone));

                if (!pfn_valid_within(page_to_pfn(page))) {
                        page++;
                        continue;
                }

                if (!PageBuddy(page)) {
                        page++;
                        continue;
                }

                order = page_order(page);
                list_move(&page->lru,
                          &zone->free_area[order].free_list[migratetype]);
                page += 1 << order;
                pages_moved += 1 << order;
        }

        return pages_moved;
}

static int move_freepages_block(struct zone *zone, struct page *page,
                                int migratetype)
{
        unsigned long start_pfn, end_pfn;
        struct page *start_page, *end_page;

        start_pfn = page_to_pfn(page);
        start_pfn = start_pfn & ~(pageblock_nr_pages-1);
        start_page = pfn_to_page(start_pfn);
        end_page = start_page + pageblock_nr_pages - 1;
        end_pfn = start_pfn + pageblock_nr_pages - 1;

        /* Do not cross zone boundaries */
        if (start_pfn < zone->zone_start_pfn)
                start_page = page;
        if (end_pfn >= zone->zone_start_pfn + zone->spanned_pages)
                return 0;

        return move_freepages(zone, start_page, end_page, migratetype);
}

static void change_pageblock_range(struct page *pageblock_page,
                                        int start_order, int migratetype)
{
        int nr_pageblocks = 1 << (start_order - pageblock_order);

        while (nr_pageblocks--) {
                set_pageblock_migratetype(pageblock_page, migratetype);
                pageblock_page += pageblock_nr_pages;
        }
}

/* Remove an element from the buddy allocator from the fallback list */
static inline struct page *
__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
{
        struct free_area * area;
        int current_order;
        struct page *page;
        int migratetype, i;

        /* Find the largest possible block of pages in the other list */
        for (current_order = MAX_ORDER-1; current_order >= order;
                                                --current_order) {
                for (i = 0; i < MIGRATE_TYPES - 1; i++) {
                        migratetype = fallbacks[start_migratetype][i];

                        /* MIGRATE_RESERVE handled later if necessary */
                        if (migratetype == MIGRATE_RESERVE)
                                continue;

                        area = &(zone->free_area[current_order]);
                        if (list_empty(&area->free_list[migratetype]))
                                continue;

                        page = list_entry(area->free_list[migratetype].next,
                                        struct page, lru);
                        area->nr_free--;

                        /*
                         * If breaking a large block of pages, move all free
                         * pages to the preferred allocation list. If falling
                         * back for a reclaimable kernel allocation, be more
                         * aggressive about taking ownership of free pages
                         */
                        if (unlikely(current_order >= (pageblock_order >> 1)) ||
                                        start_migratetype == MIGRATE_RECLAIMABLE ||
                                        page_group_by_mobility_disabled) {
                                unsigned long pages;
                                pages = move_freepages_block(zone, page,
                                                                start_migratetype);

                                /* Claim the whole block if over half of it is free */
                                if (pages >= (1 << (pageblock_order-1)) ||
                                                page_group_by_mobility_disabled)
                                        set_pageblock_migratetype(page,
                                                                start_migratetype);

                                migratetype = start_migratetype;
                        }

                        /* Remove the page from the freelists */
                        list_del(&page->lru);
                        rmv_page_order(page);

                        /* Take ownership for orders >= pageblock_order */
                        if (current_order >= pageblock_order)
                                change_pageblock_range(page, current_order,
                                                        start_migratetype);

                        expand(zone, page, order, current_order, area, migratetype);

                        trace_mm_page_alloc_extfrag(page, order, current_order,
                                start_migratetype, migratetype);

                        return page;
                }
        }

        return NULL;
}

/*
 * Do the hard work of removing an element from the buddy allocator.
 * Call me with the zone->lock already held.
 */
static struct page *__rmqueue(struct zone *zone, unsigned int order,
                                                int migratetype)
{
        struct page *page;

retry_reserve:
        page = __rmqueue_smallest(zone, order, migratetype);

        if (unlikely(!page) && migratetype != MIGRATE_RESERVE) {
                page = __rmqueue_fallback(zone, order, migratetype);

                /*
                 * Use MIGRATE_RESERVE rather than fail an allocation. goto
                 * is used because __rmqueue_smallest is an inline function
                 * and we want just one call site
                 */
                if (!page) {
                        migratetype = MIGRATE_RESERVE;
                        goto retry_reserve;
                }
        }

        trace_mm_page_alloc_zone_locked(page, order, migratetype);
        return page;
}

/* 
 * Obtain a specified number of elements from the buddy allocator, all under
 * a single hold of the lock, for efficiency.  Add them to the supplied list.
 * Returns the number of new pages which were placed at *list.
 */
static int rmqueue_bulk(struct zone *zone, unsigned int order, 
                        unsigned long count, struct list_head *list,
                        int migratetype, int cold)
{
        int i;
        
        spin_lock(&zone->lock);
        for (i = 0; i < count; ++i) {
                struct page *page = __rmqueue(zone, order, migratetype);
                if (unlikely(page == NULL))
                        break;

                /*
                 * Split buddy pages returned by expand() are received here
                 * in physical page order. The page is added to the callers and
                 * list and the list head then moves forward. From the callers
                 * perspective, the linked list is ordered by page number in
                 * some conditions. This is useful for IO devices that can
                 * merge IO requests if the physical pages are ordered
                 * properly.
                 */
                if (likely(cold == 0))
                        list_add(&page->lru, list);
                else
                        list_add_tail(&page->lru, list);
                set_page_private(page, migratetype);
                list = &page->lru;
        }
        __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
        spin_unlock(&zone->lock);
        return i;
}

#ifdef CONFIG_NUMA
/*
 * Called from the vmstat counter updater to drain pagesets of this
 * currently executing processor on remote nodes after they have
 * expired.
 *
 * Note that this function must be called with the thread pinned to
 * a single processor.
 */
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
{
        unsigned long flags;
        int to_drain;

        local_irq_save(flags);
        if (pcp->count >= pcp->batch)
                to_drain = pcp->batch;
        else
                to_drain = pcp->count;
        free_pcppages_bulk(zone, to_drain, pcp);
        pcp->count -= to_drain;
        local_irq_restore(flags);
}
#endif

/*
 * Drain pages of the indicated processor.
 *
 * The processor must either be the current processor and the
 * thread pinned to the current processor or a processor that
 * is not online.
 */
static void drain_pages(unsigned int cpu)
{
        unsigned long flags;
        struct zone *zone;

        for_each_populated_zone(zone) {
                struct per_cpu_pageset *pset;
                struct per_cpu_pages *pcp;

                local_irq_save(flags);
                pset = per_cpu_ptr(zone->pageset, cpu);

                pcp = &pset->pcp;
                if (pcp->count) {
                        free_pcppages_bulk(zone, pcp->count, pcp);
                        pcp->count = 0;
                }
                local_irq_restore(flags);
        }
}

/*
 * Spill all of this CPU's per-cpu pages back into the buddy allocator.
 */
void drain_local_pages(void *arg)
{
        drain_pages(smp_processor_id());
}

/*
 * Spill all the per-cpu pages from all CPUs back into the buddy allocator
 */
void drain_all_pages(void)
{
        on_each_cpu(drain_local_pages, NULL, 1);
}

#ifdef CONFIG_HIBERNATION

void mark_free_pages(struct zone *zone)
{
        unsigned long pfn, max_zone_pfn;
        unsigned long flags;
        int order, t;
        struct list_head *curr;

        if (!zone->spanned_pages)
                return;

        spin_lock_irqsave(&zone->lock, flags);

        max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
        for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
                if (pfn_valid(pfn)) {
                        struct page *page = pfn_to_page(pfn);

                        if (!swsusp_page_is_forbidden(page))
                                swsusp_unset_page_free(page);
                }

        for_each_migratetype_order(order, t) {
                list_for_each(curr, &zone->free_area[order].free_list[t]) {
                        unsigned long i;

                        pfn = page_to_pfn(list_entry(curr, struct page, lru));
                        for (i = 0; i < (1UL << order); i++)
                                swsusp_set_page_free(pfn_to_page(pfn + i));
                }
        }
        spin_unlock_irqrestore(&zone->lock, flags);
}
#endif /* CONFIG_PM */

/*
 * Free a 0-order page
 * cold == 1 ? free a cold page : free a hot page
 */
void free_hot_cold_page(struct page *page, int cold)
{
        struct zone *zone = page_zone(page);
        struct per_cpu_pages *pcp;
        unsigned long flags;
        int migratetype;
        int wasMlocked = __TestClearPageMlocked(page);

        if (!free_pages_prepare(page, 0))
                return;

        migratetype = get_pageblock_migratetype(page);
        set_page_private(page, migratetype);
        local_irq_save(flags);
        if (unlikely(wasMlocked))
                free_page_mlock(page);
        __count_vm_event(PGFREE);

        /*
         * We only track unmovable, reclaimable and movable on pcp lists.
         * Free ISOLATE pages back to the allocator because they are being
         * offlined but treat RESERVE as movable pages so we can get those
         * areas back if necessary. Otherwise, we may have to free
         * excessively into the page allocator
         */
        if (migratetype >= MIGRATE_PCPTYPES) {
                if (unlikely(migratetype == MIGRATE_ISOLATE)) {
                        free_one_page(zone, page, 0, migratetype);
                        goto out;
                }
                migratetype = MIGRATE_MOVABLE;
        }

        pcp = &this_cpu_ptr(zone->pageset)->pcp;
        if (cold)
                list_add_tail(&page->lru, &pcp->lists[migratetype]);
        else
                list_add(&page->lru, &pcp->lists[migratetype]);
        pcp->count++;
        if (pcp->count >= pcp->high) {
                free_pcppages_bulk(zone, pcp->batch, pcp);
                pcp->count -= pcp->batch;
        }

out:
        local_irq_restore(flags);
}

/*
 * split_page takes a non-compound higher-order page, and splits it into
 * n (1<<order) sub-pages: page[0..n]
 * Each sub-page must be freed individually.
 *
 * Note: this is probably too low level an operation for use in drivers.
 * Please consult with lkml before using this in your driver.
 */
void split_page(struct page *page, unsigned int order)
{
        int i;

        VM_BUG_ON(PageCompound(page));
        VM_BUG_ON(!page_count(page));

#ifdef CONFIG_KMEMCHECK
        /*
         * Split shadow pages too, because free(page[0]) would
         * otherwise free the whole shadow.
         */
        if (kmemcheck_page_is_tracked(page))
                split_page(virt_to_page(page[0].shadow), order);
#endif

        for (i = 1; i < (1 << order); i++)
                set_page_refcounted(page + i);
}

/*
 * Similar to split_page except the page is already free. As this is only
 * being used for migration, the migratetype of the block also changes.
 * As this is called with interrupts disabled, the caller is responsible
 * for calling arch_alloc_page() and kernel_map_page() after interrupts
 * are enabled.
 *
 * Note: this is probably too low level an operation for use in drivers.
 * Please consult with lkml before using this in your driver.
 */
int split_free_page(struct page *page)
{
        unsigned int order;
        unsigned long watermark;
        struct zone *zone;

        BUG_ON(!PageBuddy(page));

        zone = page_zone(page);
        order = page_order(page);

        /* Obey watermarks as if the page was being allocated */
        watermark = low_wmark_pages(zone) + (1 << order);
        if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
                return 0;

        /* Remove page from free list */
        list_del(&page->lru);
        zone->free_area[order].nr_free--;
        rmv_page_order(page);
        __mod_zone_page_state(zone, NR_FREE_PAGES, -(1UL << order));

        /* Split into individual pages */
        set_page_refcounted(page);
        split_page(page, order);

        if (order >= pageblock_order - 1) {
                struct page *endpage = page + (1 << order) - 1;
                for (; page < endpage; page += pageblock_nr_pages)
                        set_pageblock_migratetype(page, MIGRATE_MOVABLE);
        }

        return 1 << order;
}

/*
 * Really, prep_compound_page() should be called from __rmqueue_bulk().  But
 * we cheat by calling it from here, in the order > 0 path.  Saves a branch
 * or two.
 */
static inline
struct page *buffered_rmqueue(struct zone *preferred_zone,
                        struct zone *zone, int order, gfp_t gfp_flags,
                        int migratetype)
{
        unsigned long flags;
        struct page *page;
        int cold = !!(gfp_flags & __GFP_COLD);

again:
        if (likely(order == 0)) {
                struct per_cpu_pages *pcp;
                struct list_head *list;

                local_irq_save(flags);
                pcp = &this_cpu_ptr(zone->pageset)->pcp;
                list = &pcp->lists[migratetype];
                if (list_empty(list)) {
                        pcp->count += rmqueue_bulk(zone, 0,
                                        pcp->batch, list,
                                        migratetype, cold);
                        if (unlikely(list_empty(list)))
                                goto failed;
                }

                if (cold)
                        page = list_entry(list->prev, struct page, lru);
                else
                        page = list_entry(list->next, struct page, lru);

                list_del(&page->lru);
                pcp->count--;
        } else {
                if (unlikely(gfp_flags & __GFP_NOFAIL)) {
                        /*
                         * __GFP_NOFAIL is not to be used in new code.
                         *
                         * All __GFP_NOFAIL callers should be fixed so that they
                         * properly detect and handle allocation failures.
                         *
                         * We most definitely don't want callers attempting to
                         * allocate greater than order-1 page units with
                         * __GFP_NOFAIL.
                         */
                        WARN_ON_ONCE(order > 1);
                }
                spin_lock_irqsave(&zone->lock, flags);
                page = __rmqueue(zone, order, migratetype);
                spin_unlock(&zone->lock);
                if (!page)
                        goto failed;
                __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
        }

        __count_zone_vm_events(PGALLOC, zone, 1 << order);
        zone_statistics(preferred_zone, zone, gfp_flags);
        local_irq_restore(flags);

        VM_BUG_ON(bad_range(zone, page));
        if (prep_new_page(page, order, gfp_flags))
                goto again;
        return page;

failed:
        local_irq_restore(flags);
        return NULL;
}

/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN         WMARK_MIN
#define ALLOC_WMARK_LOW         WMARK_LOW
#define ALLOC_WMARK_HIGH        WMARK_HIGH
#define ALLOC_NO_WATERMARKS     0x04 /* don't check watermarks at all */

/* Mask to get the watermark bits */
#define ALLOC_WMARK_MASK        (ALLOC_NO_WATERMARKS-1)

#define ALLOC_HARDER            0x10 /* try to alloc harder */
#define ALLOC_HIGH              0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET            0x40 /* check for correct cpuset */

#ifdef CONFIG_FAIL_PAGE_ALLOC

static struct {
        struct fault_attr attr;

        u32 ignore_gfp_highmem;
        u32 ignore_gfp_wait;
        u32 min_order;
} fail_page_alloc = {
        .attr = FAULT_ATTR_INITIALIZER,
        .ignore_gfp_wait = 1,
        .ignore_gfp_highmem = 1,
        .min_order = 1,
};

static int __init setup_fail_page_alloc(char *str)
{
        return setup_fault_attr(&fail_page_alloc.attr, str);
}
__setup("fail_page_alloc=", setup_fail_page_alloc);

static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
        if (order < fail_page_alloc.min_order)
                return 0;
        if (gfp_mask & __GFP_NOFAIL)
                return 0;
        if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
                return 0;
        if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
                return 0;

        return should_fail(&fail_page_alloc.attr, 1 << order);
}

#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

static int __init fail_page_alloc_debugfs(void)
{
        mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
        struct dentry *dir;

        dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
                                        &fail_page_alloc.attr);
        if (IS_ERR(dir))
                return PTR_ERR(dir);

        if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
                                &fail_page_alloc.ignore_gfp_wait))
                goto fail;
        if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir,
                                &fail_page_alloc.ignore_gfp_highmem))
                goto fail;
        if (!debugfs_create_u32("min-order", mode, dir,
                                &fail_page_alloc.min_order))
                goto fail;

        return 0;
fail:
        debugfs_remove_recursive(dir);

        return -ENOMEM;
}

late_initcall(fail_page_alloc_debugfs);

#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */

#else /* CONFIG_FAIL_PAGE_ALLOC */

static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
        return 0;
}

#endif /* CONFIG_FAIL_PAGE_ALLOC */

/*
 * Return true if free pages are above 'mark'. This takes into account the order
 * of the allocation.
 */
static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
                      int classzone_idx, int alloc_flags, long free_pages)
{
        /* free_pages my go negative - that's OK */
        long min = mark;
        int o;

        free_pages -= (1 << order) + 1;
        if (alloc_flags & ALLOC_HIGH)
                min -= min / 2;
        if (alloc_flags & ALLOC_HARDER)
                min -= min / 4;

        if (free_pages <= min + z->lowmem_reserve[classzone_idx])
                return false;
        for (o = 0; o < order; o++) {
                /* At the next order, this order's pages become unavailable */
                free_pages -= z->free_area[o].nr_free << o;

                /* Require fewer higher order pages to be free */
                min >>= 1;

                if (free_pages <= min)
                        return false;
        }
        return true;
}

bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
                      int classzone_idx, int alloc_flags)
{
        return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
                                        zone_page_state(z, NR_FREE_PAGES));
}

bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
                      int classzone_idx, int alloc_flags)
{
        long free_pages = zone_page_state(z, NR_FREE_PAGES);

        if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
                free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);

        return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
                                                                free_pages);
}

#ifdef CONFIG_NUMA
/*
 * zlc_setup - Setup for "zonelist cache".  Uses cached zone data to
 * skip over zones that are not allowed by the cpuset, or that have
 * been recently (in last second) found to be nearly full.  See further
 * comments in mmzone.h.  Reduces cache footprint of zonelist scans
 * that have to skip over a lot of full or unallowed zones.
 *
 * If the zonelist cache is present in the passed in zonelist, then
 * returns a pointer to the allowed node mask (either the current
 * tasks mems_allowed, or node_states[N_HIGH_MEMORY].)
 *
 * If the zonelist cache is not available for this zonelist, does
 * nothing and returns NULL.
 *
 * If the fullzones BITMAP in the zonelist cache is stale (more than
 * a second since last zap'd) then we zap it out (clear its bits.)
 *
 * We hold off even calling zlc_setup, until after we've checked the
 * first zone in the zonelist, on the theory that most allocations will
 * be satisfied from that first zone, so best to examine that zone as
 * quickly as we can.
 */
static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
        struct zonelist_cache *zlc;     /* cached zonelist speedup info */
        nodemask_t *allowednodes;       /* zonelist_cache approximation */

        zlc = zonelist->zlcache_ptr;
        if (!zlc)
                return NULL;

        if (time_after(jiffies, zlc->last_full_zap + HZ)) {
                bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
                zlc->last_full_zap = jiffies;
        }

        allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
                                        &cpuset_current_mems_allowed :
                                        &node_states[N_HIGH_MEMORY];
        return allowednodes;
}

/*
 * Given 'z' scanning a zonelist, run a couple of quick checks to see
 * if it is worth looking at further for free memory:
 *  1) Check that the zone isn't thought to be full (doesn't have its
 *     bit set in the zonelist_cache fullzones BITMAP).
 *  2) Check that the zones node (obtained from the zonelist_cache
 *     z_to_n[] mapping) is allowed in the passed in allowednodes mask.
 * Return true (non-zero) if zone is worth looking at further, or
 * else return false (zero) if it is not.
 *
 * This check -ignores- the distinction between various watermarks,
 * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ...  If a zone is
 * found to be full for any variation of these watermarks, it will
 * be considered full for up to one second by all requests, unless
 * we are so low on memory on all allowed nodes that we are forced
 * into the second scan of the zonelist.
 *
 * In the second scan we ignore this zonelist cache and exactly
 * apply the watermarks to all zones, even it is slower to do so.
 * We are low on memory in the second scan, and should leave no stone
 * unturned looking for a free page.
 */
static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
                                                nodemask_t *allowednodes)
{
        struct zonelist_cache *zlc;     /* cached zonelist speedup info */
        int i;                          /* index of *z in zonelist zones */
        int n;                          /* node that zone *z is on */

        zlc = zonelist->zlcache_ptr;
        if (!zlc)
                return 1;

        i = z - zonelist->_zonerefs;
        n = zlc->z_to_n[i];

        /* This zone is worth trying if it is allowed but not full */
        return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones);
}

/*
 * Given 'z' scanning a zonelist, set the corresponding bit in
 * zlc->fullzones, so that subsequent attempts to allocate a page
 * from that zone don't waste time re-examining it.
 */
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
        struct zonelist_cache *zlc;     /* cached zonelist speedup info */
        int i;                          /* index of *z in zonelist zones */

        zlc = zonelist->zlcache_ptr;
        if (!zlc)
                return;

        i = z - zonelist->_zonerefs;

        set_bit(i, zlc->fullzones);
}

/*
 * clear all zones full, called after direct reclaim makes progress so that
 * a zone that was recently full is not skipped over for up to a second
 */
static void zlc_clear_zones_full(struct zonelist *zonelist)
{
        struct zonelist_cache *zlc;     /* cached zonelist speedup info */

        zlc = zonelist->zlcache_ptr;
        if (!zlc)
                return;

        bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
}

#else   /* CONFIG_NUMA */

static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
        return NULL;
}

static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
                                nodemask_t *allowednodes)
{
        return 1;
}

static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
}

static void zlc_clear_zones_full(struct zonelist *zonelist)
{
}
#endif  /* CONFIG_NUMA */

/*
 * get_page_from_freelist goes through the zonelist trying to allocate
 * a page.
 */
static struct page *
get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
                struct zonelist *zonelist, int high_zoneidx, int alloc_flags,
                struct zone *preferred_zone, int migratetype)
{
        struct zoneref *z;
        struct page *page = NULL;
        int classzone_idx;
        struct zone *zone;
        nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
        int zlc_active = 0;             /* set if using zonelist_cache */
        int did_zlc_setup = 0;          /* just call zlc_setup() one time */

        classzone_idx = zone_idx(preferred_zone);
zonelist_scan:
        /*
         * Scan zonelist, looking for a zone with enough free.
         * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
         */
        for_each_zone_zonelist_nodemask(zone, z, zonelist,
                                                high_zoneidx, nodemask) {
                if (NUMA_BUILD && zlc_active &&
                        !zlc_zone_worth_trying(zonelist, z, allowednodes))
                                continue;
                if ((alloc_flags & ALLOC_CPUSET) &&
                        !cpuset_zone_allowed_softwall(zone, gfp_mask))
                                continue;

                BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
                if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
                        unsigned long mark;
                        int ret;

                        mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
                        if (zone_watermark_ok(zone, order, mark,
                                    classzone_idx, alloc_flags))
                                goto try_this_zone;

                        if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
                                /*
                                 * we do zlc_setup if there are multiple nodes
                                 * and before considering the first zone allowed
                                 * by the cpuset.
                                 */
                                allowednodes = zlc_setup(zonelist, alloc_flags);
                                zlc_active = 1;
                                did_zlc_setup = 1;
                        }

                        if (zone_reclaim_mode == 0)
                                goto this_zone_full;

                        /*
                         * As we may have just activated ZLC, check if the first
                         * eligible zone has failed zone_reclaim recently.
                         */
                        if (NUMA_BUILD && zlc_active &&
                                !zlc_zone_worth_trying(zonelist, z, allowednodes))
                                continue;

                        ret = zone_reclaim(zone, gfp_mask, order);
                        switch (ret) {
                        case ZONE_RECLAIM_NOSCAN:
                                /* did not scan */
                                continue;
                        case ZONE_RECLAIM_FULL:
                                /* scanned but unreclaimable */
                                continue;
                        default:
                                /* did we reclaim enough */
                                if (!zone_watermark_ok(zone, order, mark,
                                                classzone_idx, alloc_flags))
                                        goto this_zone_full;
                        }
                }

try_this_zone:
                page = buffered_rmqueue(preferred_zone, zone, order,
                                                gfp_mask, migratetype);
                if (page)
                        break;
this_zone_full:
                if (NUMA_BUILD)
                        zlc_mark_zone_full(zonelist, z);
        }

        if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
                /* Disable zlc cache for second zonelist scan */
                zlc_active = 0;
                goto zonelist_scan;
        }
        return page;
}

/*
 * Large machines with many possible nodes should not always dump per-node
 * meminfo in irq context.
 */
static inline bool should_suppress_show_mem(void)
{
        bool ret = false;

#if NODES_SHIFT > 8
        ret = in_interrupt();
#endif
        return ret;
}

static DEFINE_RATELIMIT_STATE(nopage_rs,
                DEFAULT_RATELIMIT_INTERVAL,
                DEFAULT_RATELIMIT_BURST);

void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
{
        va_list args;
        unsigned int filter = SHOW_MEM_FILTER_NODES;

        if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
                return;

        /*
         * This documents exceptions given to allocations in certain
         * contexts that are allowed to allocate outside current's set
         * of allowed nodes.
         */
        if (!(gfp_mask & __GFP_NOMEMALLOC))
                if (test_thread_flag(TIF_MEMDIE) ||
                    (current->flags & (PF_MEMALLOC | PF_EXITING)))
                        filter &= ~SHOW_MEM_FILTER_NODES;
        if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
                filter &= ~SHOW_MEM_FILTER_NODES;

        if (fmt) {
                printk(KERN_WARNING);
                va_start(args, fmt);
                vprintk(fmt, args);
                va_end(args);
        }

        pr_warning("%s: page allocation failure: order:%d, mode:0x%x\n",
                   current->comm, order, gfp_mask);

        dump_stack();
        if (!should_suppress_show_mem())
                show_mem(filter);
}

static inline int
should_alloc_retry(gfp_t gfp_mask, unsigned int order,
                                unsigned long pages_reclaimed)
{
        /* Do not loop if specifically requested */
        if (gfp_mask & __GFP_NORETRY)
                return 0;

        /*
         * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
         * means __GFP_NOFAIL, but that may not be true in other
         * implementations.
         */
        if (order <= PAGE_ALLOC_COSTLY_ORDER)
                return 1;

        /*
         * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
         * specified, then we retry until we no longer reclaim any pages
         * (above), or we've reclaimed an order of pages at least as
         * large as the allocation's order. In both cases, if the
         * allocation still fails, we stop retrying.
         */
        if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
                return 1;

        /*
         * Don't let big-order allocations loop unless the caller
         * explicitly requests that.
         */
        if (gfp_mask & __GFP_NOFAIL)
                return 1;

        return 0;
}

static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
        struct zonelist *zonelist, enum zone_type high_zoneidx,
        nodemask_t *nodemask, struct zone *preferred_zone,
        int migratetype)
{
        struct page *page;

        /* Acquire the OOM killer lock for the zones in zonelist */
        if (!try_set_zonelist_oom(zonelist, gfp_mask)) {
                schedule_timeout_uninterruptible(1);
                return NULL;
        }

        /*
         * Go through the zonelist yet one more time, keep very high watermark
         * here, this is only to catch a parallel oom killing, we must fail if
         * we're still under heavy pressure.
         */
        page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
                order, zonelist, high_zoneidx,
                ALLOC_WMARK_HIGH|ALLOC_CPUSET,
                preferred_zone, migratetype);
        if (page)
                goto out;

        if (!(gfp_mask & __GFP_NOFAIL)) {
                /* The OOM killer will not help higher order allocs */
                if (order > PAGE_ALLOC_COSTLY_ORDER)
                        goto out;
                /* The OOM killer does not needlessly kill tasks for lowmem */
                if (high_zoneidx < ZONE_NORMAL)
                        goto out;
                /*
                 * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
                 * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
                 * The caller should handle page allocation failure by itself if
                 * it specifies __GFP_THISNODE.
                 * Note: Hugepage uses it but will hit PAGE_ALLOC_COSTLY_ORDER.
                 */
                if (gfp_mask & __GFP_THISNODE)
                        goto out;
        }
        /* Exhausted what can be done so it's blamo time */
        out_of_memory(zonelist, gfp_mask, order, nodemask);

out:
        clear_zonelist_oom(zonelist, gfp_mask);
        return page;
}

#ifdef CONFIG_COMPACTION
/* Try memory compaction for high-order allocations before reclaim */
static struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
        struct zonelist *zonelist, enum zone_type high_zoneidx,
        nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
        int migratetype, unsigned long *did_some_progress,
        bool sync_migration)
{
        struct page *page;

        if (!order || compaction_deferred(preferred_zone))
                return NULL;

        current->flags |= PF_MEMALLOC;
        *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
                                                nodemask, sync_migration);
        current->flags &= ~PF_MEMALLOC;
        if (*did_some_progress != COMPACT_SKIPPED) {

                /* Page migration frees to the PCP lists but we want merging */
                drain_pages(get_cpu());
                put_cpu();

                page = get_page_from_freelist(gfp_mask, nodemask,
                                order, zonelist, high_zoneidx,
                                alloc_flags, preferred_zone,
                                migratetype);
                if (page) {
                        preferred_zone->compact_considered = 0;
                        preferred_zone->compact_defer_shift = 0;
                        count_vm_event(COMPACTSUCCESS);
                        return page;
                }

                /*
                 * It's bad if compaction run occurs and fails.
                 * The most likely reason is that pages exist,
                 * but not enough to satisfy watermarks.
                 */
                count_vm_event(COMPACTFAIL);
                defer_compaction(preferred_zone);

                cond_resched();
        }

        return NULL;
}
#else
static inline struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
        struct zonelist *zonelist, enum zone_type high_zoneidx,
        nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
        int migratetype, unsigned long *did_some_progress,
        bool sync_migration)
{
        return NULL;
}
#endif /* CONFIG_COMPACTION */

/* The really slow allocator path where we enter direct reclaim */
static inline struct page *
__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
        struct zonelist *zonelist, enum zone_type high_zoneidx,
        nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
        int migratetype, unsigned long *did_some_progress)
{
        struct page *page = NULL;
        struct reclaim_state reclaim_state;
        bool drained = false;

        cond_resched();

        /* We now go into synchronous reclaim */
        cpuset_memory_pressure_bump();
        current->flags |= PF_MEMALLOC;
        lockdep_set_current_reclaim_state(gfp_mask);
        reclaim_state.reclaimed_slab = 0;
        current->reclaim_state = &reclaim_state;

        *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);

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

        cond_resched();

        if (unlikely(!(*did_some_progress)))
                return NULL;

        /* After successful reclaim, reconsider all zones for allocation */
        if (NUMA_BUILD)
                zlc_clear_zones_full(zonelist);

retry:
        page = get_page_from_freelist(gfp_mask, nodemask, order,
                                        zonelist, high_zoneidx,
                                        alloc_flags, preferred_zone,
                                        migratetype);

        /*
         * If an allocation failed after direct reclaim, it could be because
         * pages are pinned on the per-cpu lists. Drain them and try again
         */
        if (!page && !drained) {
                drain_all_pages();
                drained = true;
                goto retry;
        }

        return page;
}

/*
 * This is called in the allocator slow-path if the allocation request is of
 * sufficient urgency to ignore watermarks and take other desperate measures
 */
static inline struct page *
__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
        struct zonelist *zonelist, enum zone_type high_zoneidx,
        nodemask_t *nodemask, struct zone *preferred_zone,
        int migratetype)
{
        struct page *page;

        do {
                page = get_page_from_freelist(gfp_mask, nodemask, order,
                        zonelist, high_zoneidx, ALLOC_NO_WATERMARKS,
                        preferred_zone, migratetype);

                if (!page && gfp_mask & __GFP_NOFAIL)
                        wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
        } while (!page && (gfp_mask & __GFP_NOFAIL));

        return page;
}

static inline
void wake_all_kswapd(unsigned int order, struct zonelist *zonelist,
                                                enum zone_type high_zoneidx,
                                                enum zone_type classzone_idx)
{
        struct zoneref *z;
        struct zone *zone;

        for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
                wakeup_kswapd(zone, order, classzone_idx);
}

static inline int
gfp_to_alloc_flags(gfp_t gfp_mask)
{
        int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
        const gfp_t wait = gfp_mask & __GFP_WAIT;

        /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
        BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);

        /*
         * The caller may dip into page reserves a bit more if the caller
         * cannot run direct reclaim, or if the caller has realtime scheduling
         * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
         * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
         */
        alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);

        if (!wait) {
                /*
                 * Not worth trying to allocate harder for
                 * __GFP_NOMEMALLOC even if it can't schedule.
                 */
                if  (!(gfp_mask & __GFP_NOMEMALLOC))
                        alloc_flags |= ALLOC_HARDER;
                /*
                 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
                 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
                 */
                alloc_flags &= ~ALLOC_CPUSET;
        } else if (unlikely(rt_task(current)) && !in_interrupt())
                alloc_flags |= ALLOC_HARDER;

        if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
                if (!in_interrupt() &&
                    ((current->flags & PF_MEMALLOC) ||
                     unlikely(test_thread_flag(TIF_MEMDIE))))
                        alloc_flags |= ALLOC_NO_WATERMARKS;
        }

        return alloc_flags;
}

static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
        struct zonelist *zonelist, enum zone_type high_zoneidx,
        nodemask_t *nodemask, struct zone *preferred_zone,
        int migratetype)
{
        const gfp_t wait = gfp_mask & __GFP_WAIT;
        struct page *page = NULL;
        int alloc_flags;
        unsigned long pages_reclaimed = 0;
        unsigned long did_some_progress;
        bool sync_migration = false;

        /*
         * In the slowpath, we sanity check order to avoid ever trying to
         * reclaim >= MAX_ORDER areas which will never succeed. Callers may
         * be using allocators in order of preference for an area that is
         * too large.
         */
        if (order >= MAX_ORDER) {
                WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
                return NULL;
        }

        /*
         * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
         * __GFP_NOWARN set) should not cause reclaim since the subsystem
         * (f.e. slab) using GFP_THISNODE may choose to trigger reclaim
         * using a larger set of nodes after it has established that the
         * allowed per node queues are empty and that nodes are
         * over allocated.
         */
        if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
                goto nopage;

restart:
        if (!(gfp_mask & __GFP_NO_KSWAPD))
                wake_all_kswapd(order, zonelist, high_zoneidx,
                                                zone_idx(preferred_zone));

        /*
         * OK, we're below the kswapd watermark and have kicked background
         * reclaim. Now things get more complex, so set up alloc_flags according
         * to how we want to proceed.
         */
        alloc_flags = gfp_to_alloc_flags(gfp_mask);

        /*
         * Find the true preferred zone if the allocation is unconstrained by
         * cpusets.
         */
        if (!(alloc_flags & ALLOC_CPUSET) && !nodemask)
                first_zones_zonelist(zonelist, high_zoneidx, NULL,
                                        &preferred_zone);

rebalance:
        /* This is the last chance, in general, before the goto nopage. */
        page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
                        high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
                        preferred_zone, migratetype);
        if (page)
                goto got_pg;

        /* Allocate without watermarks if the context allows */
        if (alloc_flags & ALLOC_NO_WATERMARKS) {
                page = __alloc_pages_high_priority(gfp_mask, order,
                                zonelist, high_zoneidx, nodemask,
                                preferred_zone, migratetype);
                if (page)
                        goto got_pg;
        }

        /* Atomic allocations - we can't balance anything */
        if (!wait)
                goto nopage;

        /* Avoid recursion of direct reclaim */
        if (current->flags & PF_MEMALLOC)
                goto nopage;

        /* Avoid allocations with no watermarks from looping endlessly */
        if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
                goto nopage;

        /*
         * Try direct compaction. The first pass is asynchronous. Subsequent
         * attempts after direct reclaim are synchronous
         */
        page = __alloc_pages_direct_compact(gfp_mask, order,
                                        zonelist, high_zoneidx,
                                        nodemask,
                                        alloc_flags, preferred_zone,
                                        migratetype, &did_some_progress,
                                        sync_migration);
        if (page)
                goto got_pg;
        sync_migration = true;

        /* Try direct reclaim and then allocating */
        page = __alloc_pages_direct_reclaim(gfp_mask, order,
                                        zonelist, high_zoneidx,
                                        nodemask,
                                        alloc_flags, preferred_zone,
                                        migratetype, &did_some_progress);
        if (page)
                goto got_pg;

        /*
         * If we failed to make any progress reclaiming, then we are
         * running out of options and have to consider going OOM
         */
        if (!did_some_progress) {
                if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
                        if (oom_killer_disabled)
                                goto nopage;
                        page = __alloc_pages_may_oom(gfp_mask, order,
                                        zonelist, high_zoneidx,
                                        nodemask, preferred_zone,
                                        migratetype);
                        if (page)
                                goto got_pg;

                        if (!(gfp_mask & __GFP_NOFAIL)) {
                                /*
                                 * The oom killer is not called for high-order
                                 * allocations that may fail, so if no progress
                                 * is being made, there are no other options and
                                 * retrying is unlikely to help.
                                 */
                                if (order > PAGE_ALLOC_COSTLY_ORDER)
                                        goto nopage;
                                /*
                                 * The oom killer is not called for lowmem
                                 * allocations to prevent needlessly killing
                                 * innocent tasks.
                                 */
                                if (high_zoneidx < ZONE_NORMAL)
                                        goto nopage;
                        }

                        goto restart;
                }
        }

        /* Check if we should retry the allocation */
        pages_reclaimed += did_some_progress;
        if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
                /* Wait for some write requests to complete then retry */
                wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
                goto rebalance;
        } else {
                /*
                 * High-order allocations do not necessarily loop after
                 * direct reclaim and reclaim/compaction depends on compaction
                 * being called after reclaim so call directly if necessary
                 */
                page = __alloc_pages_direct_compact(gfp_mask, order,
                                        zonelist, high_zoneidx,
                                        nodemask,
                                        alloc_flags, preferred_zone,
                                        migratetype, &did_some_progress,
                                        sync_migration);
                if (page)
                        goto got_pg;
        }

nopage:
        warn_alloc_failed(gfp_mask, order, NULL);
        return page;
got_pg:
        if (kmemcheck_enabled)
                kmemcheck_pagealloc_alloc(page, order, gfp_mask);
        return page;

}

/*
 * This is the 'heart' of the zoned buddy allocator.
 */
struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
                        struct zonelist *zonelist, nodemask_t *nodemask)
{
        enum zone_type high_zoneidx = gfp_zone(gfp_mask);
        struct zone *preferred_zone;
        struct page *page;
        int migratetype = allocflags_to_migratetype(gfp_mask);

        gfp_mask &= gfp_allowed_mask;

        lockdep_trace_alloc(gfp_mask);

        might_sleep_if(gfp_mask & __GFP_WAIT);

        if (should_fail_alloc_page(gfp_mask, order))
                return NULL;

        /*
         * Check the zones suitable for the gfp_mask contain at least one
         * valid zone. It's possible to have an empty zonelist as a result
         * of GFP_THISNODE and a memoryless node
         */
        if (unlikely(!zonelist->_zonerefs->zone))
                return NULL;

        get_mems_allowed();
        /* The preferred zone is used for statistics later */
        first_zones_zonelist(zonelist, high_zoneidx,
                                nodemask ? : &cpuset_current_mems_allowed,
                                &preferred_zone);
        if (!preferred_zone) {
                put_mems_allowed();
                return NULL;
        }

        /* First allocation attempt */
        page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
                        zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET,
                        preferred_zone, migratetype);
        if (unlikely(!page))
                page = __alloc_pages_slowpath(gfp_mask, order,
                                zonelist, high_zoneidx, nodemask,
                                preferred_zone, migratetype);
        put_mems_allowed();

        trace_mm_page_alloc(page, order, gfp_mask, migratetype);
        return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);

/*
 * Common helper functions.
 */
unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
        struct page *page;

        /*
         * __get_free_pages() returns a 32-bit address, which cannot represent
         * a highmem page
         */
        VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);

        page = alloc_pages(gfp_mask, order);
        if (!page)
                return 0;
        return (unsigned long) page_address(page);
}
EXPORT_SYMBOL(__get_free_pages);

unsigned long get_zeroed_page(gfp_t gfp_mask)
{
        return __get_free_pages(gfp_mask | __GFP_ZERO, 0);
}
EXPORT_SYMBOL(get_zeroed_page);

void __pagevec_free(struct pagevec *pvec)
{
        int i = pagevec_count(pvec);

        while (--i >= 0) {
                trace_mm_pagevec_free(pvec->pages[i], pvec->cold);
                free_hot_cold_page(pvec->pages[i], pvec->cold);
        }
}

void __free_pages(struct page *page, unsigned int order)
{
        if (put_page_testzero(page)) {
                if (order == 0)
                        free_hot_cold_page(page, 0);
                else
                        __free_pages_ok(page, order);
        }
}

EXPORT_SYMBOL(__free_pages);

void free_pages(unsigned long addr, unsigned int order)
{
        if (addr != 0) {
                VM_BUG_ON(!virt_addr_valid((void *)addr));
                __free_pages(virt_to_page((void *)addr), order);
        }
}

EXPORT_SYMBOL(free_pages);

static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
{
        if (addr) {
                unsigned long alloc_end = addr + (PAGE_SIZE << order);
                unsigned long used = addr + PAGE_ALIGN(size);

                split_page(virt_to_page((void *)addr), order);
                while (used < alloc_end) {
                        free_page(used);
                        used += PAGE_SIZE;
                }
        }
        return (void *)addr;
}

/**
 * alloc_pages_exact - allocate an exact number physically-contiguous pages.
 * @size: the number of bytes to allocate
 * @gfp_mask: GFP flags for the allocation
 *
 * This function is similar to alloc_pages(), except that it allocates the
 * minimum number of pages to satisfy the request.  alloc_pages() can only
 * allocate memory in power-of-two pages.
 *
 * This function is also limited by MAX_ORDER.
 *
 * Memory allocated by this function must be released by free_pages_exact().
 */
void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
{
        unsigned int order = get_order(size);
        unsigned long addr;

        addr = __get_free_pages(gfp_mask, order);
        return make_alloc_exact(addr, order, size);
}
EXPORT_SYMBOL(alloc_pages_exact);

/**
 * alloc_pages_exact_nid - allocate an exact number of physically-contiguous
 *                         pages on a node.
 * @nid: the preferred node ID where memory should be allocated
 * @size: the number of bytes to allocate
 * @gfp_mask: GFP flags for the allocation
 *
 * Like alloc_pages_exact(), but try to allocate on node nid first before falling
 * back.
 * Note this is not alloc_pages_exact_node() which allocates on a specific node,
 * but is not exact.
 */
void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
{
        unsigned order = get_order(size);
        struct page *p = alloc_pages_node(nid, gfp_mask, order);
        if (!p)
                return NULL;
        return make_alloc_exact((unsigned long)page_address(p), order, size);
}
EXPORT_SYMBOL(alloc_pages_exact_nid);

/**
 * free_pages_exact - release memory allocated via alloc_pages_exact()
 * @virt: the value returned by alloc_pages_exact.
 * @size: size of allocation, same value as passed to alloc_pages_exact().
 *
 * Release the memory allocated by a previous call to alloc_pages_exact.
 */
void free_pages_exact(void *virt, size_t size)
{
        unsigned long addr = (unsigned long)virt;
        unsigned long end = addr + PAGE_ALIGN(size);

        while (addr < end) {
                free_page(addr);
                addr += PAGE_SIZE;
        }
}
EXPORT_SYMBOL(free_pages_exact);

static unsigned int nr_free_zone_pages(int offset)
{
        struct zoneref *z;
        struct zone *zone;

        /* Just pick one node, since fallback list is circular */
        unsigned int sum = 0;

        struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);

        for_each_zone_zonelist(zone, z, zonelist, offset) {
                unsigned long size = zone->present_pages;
                unsigned long high = high_wmark_pages(zone);
                if (size > high)
                        sum += size - high;
        }

        return sum;
}

/*
 * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL
 */
unsigned int nr_free_buffer_pages(void)
{
        return nr_free_zone_pages(gfp_zone(GFP_USER));
}
EXPORT_SYMBOL_GPL(nr_free_buffer_pages);

/*
 * Amount of free RAM allocatable within all zones
 */
unsigned int nr_free_pagecache_pages(void)
{
        return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
}

static inline void show_node(struct zone *zone)
{
        if (NUMA_BUILD)
                printk("Node %d ", zone_to_nid(zone));
}

void si_meminfo(struct sysinfo *val)
{
        val->totalram = totalram_pages;
        val->sharedram = 0;
        val->freeram = global_page_state(NR_FREE_PAGES);
        val->bufferram = nr_blockdev_pages();
        val->totalhigh = totalhigh_pages;
        val->freehigh = nr_free_highpages();
        val->mem_unit = PAGE_SIZE;
}

EXPORT_SYMBOL(si_meminfo);

#ifdef CONFIG_NUMA
void si_meminfo_node(struct sysinfo *val, int nid)
{
        pg_data_t *pgdat = NODE_DATA(nid);

        val->totalram = pgdat->node_present_pages;
        val->freeram = node_page_state(nid, NR_FREE_PAGES);
#ifdef CONFIG_HIGHMEM
        val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
        val->freehigh = zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM],
                        NR_FREE_PAGES);
#else
        val->totalhigh = 0;
        val->freehigh = 0;
#endif
        val->mem_unit = PAGE_SIZE;
}
#endif

/*
 * Determine whether the node should be displayed or not, depending on whether
 * SHOW_MEM_FILTER_NODES was passed to show_free_areas().
 */
bool skip_free_areas_node(unsigned int flags, int nid)
{
        bool ret = false;

        if (!(flags & SHOW_MEM_FILTER_NODES))
                goto out;

        get_mems_allowed();
        ret = !node_isset(nid, cpuset_current_mems_allowed);
        put_mems_allowed();
out:
        return ret;
}

#define K(x) ((x) << (PAGE_SHIFT-10))

/*
 * Show free area list (used inside shift_scroll-lock stuff)
 * We also calculate the percentage fragmentation. We do this by counting the
 * memory on each free list with the exception of the first item on the list.
 * Suppresses nodes that are not allowed by current's cpuset if
 * SHOW_MEM_FILTER_NODES is passed.
 */
void show_free_areas(unsigned int filter)
{
        int cpu;
        struct zone *zone;

        for_each_populated_zone(zone) {
                if (skip_free_areas_node(filter, zone_to_nid(zone)))
                        continue;
                show_node(zone);
                printk("%s per-cpu:\n", zone->name);

                for_each_online_cpu(cpu) {
                        struct per_cpu_pageset *pageset;

                        pageset = per_cpu_ptr(zone->pageset, cpu);

                        printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
                               cpu, pageset->pcp.high,
                               pageset->pcp.batch, pageset->pcp.count);
                }
        }

        printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
                " active_file:%lu inactive_file:%lu isolated_file:%lu\n"
                " unevictable:%lu"
                " dirty:%lu writeback:%lu unstable:%lu\n"
                " free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n"
                " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n",
                global_page_state(NR_ACTIVE_ANON),
                global_page_state(NR_INACTIVE_ANON),
                global_page_state(NR_ISOLATED_ANON),
                global_page_state(NR_ACTIVE_FILE),
                global_page_state(NR_INACTIVE_FILE),
                global_page_state(NR_ISOLATED_FILE),
                global_page_state(NR_UNEVICTABLE),
                global_page_state(NR_FILE_DIRTY),
                global_page_state(NR_WRITEBACK),
                global_page_state(NR_UNSTABLE_NFS),
                global_page_state(NR_FREE_PAGES),
                global_page_state(NR_SLAB_RECLAIMABLE),
                global_page_state(NR_SLAB_UNRECLAIMABLE),
                global_page_state(NR_FILE_MAPPED),
                global_page_state(NR_SHMEM),
                global_page_state(NR_PAGETABLE),
                global_page_state(NR_BOUNCE));

        for_each_populated_zone(zone) {
                int i;

                if (skip_free_areas_node(filter, zone_to_nid(zone)))
                        continue;
                show_node(zone);
                printk("%s"
                        " free:%lukB"
                        " min:%lukB"
                        " low:%lukB"
                        " high:%lukB"
                        " active_anon:%lukB"
                        " inactive_anon:%lukB"
                        " active_file:%lukB"
                        " inactive_file:%lukB"
                        " unevictable:%lukB"
                        " isolated(anon):%lukB"
                        " isolated(file):%lukB"
                        " present:%lukB"
                        " mlocked:%lukB"
                        " dirty:%lukB"
                        " writeback:%lukB"
                        " mapped:%lukB"
                        " shmem:%lukB"
                        " slab_reclaimable:%lukB"
                        " slab_unreclaimable:%lukB"
                        " kernel_stack:%lukB"
                        " pagetables:%lukB"
                        " unstable:%lukB"
                        " bounce:%lukB"
                        " writeback_tmp:%lukB"
                        " pages_scanned:%lu"
                        " all_unreclaimable? %s"
                        "\n",
                        zone->name,
                        K(zone_page_state(zone, NR_FREE_PAGES)),
                        K(min_wmark_pages(zone)),
                        K(low_wmark_pages(zone)),
                        K(high_wmark_pages(zone)),
                        K(zone_page_state(zone, NR_ACTIVE_ANON)),
                        K(zone_page_state(zone, NR_INACTIVE_ANON)),
                        K(zone_page_state(zone, NR_ACTIVE_FILE)),
                        K(zone_page_state(zone, NR_INACTIVE_FILE)),
                        K(zone_page_state(zone, NR_UNEVICTABLE)),
                        K(zone_page_state(zone, NR_ISOLATED_ANON)),
                        K(zone_page_state(zone, NR_ISOLATED_FILE)),
                        K(zone->present_pages),
                        K(zone_page_state(zone, NR_MLOCK)),
                        K(zone_page_state(zone, NR_FILE_DIRTY)),
                        K(zone_page_state(zone, NR_WRITEBACK)),
                        K(zone_page_state(zone, NR_FILE_MAPPED)),
                        K(zone_page_state(zone, NR_SHMEM)),
                        K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
                        K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
                        zone_page_state(zone, NR_KERNEL_STACK) *
                                THREAD_SIZE / 1024,
                        K(zone_page_state(zone, NR_PAGETABLE)),
                        K(zone_page_state(zone, NR_UNSTABLE_NFS)),
                        K(zone_page_state(zone, NR_BOUNCE)),
                        K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
                        zone->pages_scanned,
                        (zone->all_unreclaimable ? "yes" : "no")
                        );
                printk("lowmem_reserve[]:");
                for (i = 0; i < MAX_NR_ZONES; i++)
                        printk(" %lu", zone->lowmem_reserve[i]);
                printk("\n");
        }

        for_each_populated_zone(zone) {
                unsigned long nr[MAX_ORDER], flags, order, total = 0;

                if (skip_free_areas_node(filter, zone_to_nid(zone)))
                        continue;
                show_node(zone);
                printk("%s: ", zone->name);

                spin_lock_irqsave(&zone->lock, flags);
                for (order = 0; order < MAX_ORDER; order++) {
                        nr[order] = zone->free_area[order].nr_free;
                        total += nr[order] << order;
                }
                spin_unlock_irqrestore(&zone->lock, flags);
                for (order = 0; order < MAX_ORDER; order++)
                        printk("%lu*%lukB ", nr[order], K(1UL) << order);
                printk("= %lukB\n", K(total));
        }

        printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES));

        show_swap_cache_info();
}

static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
{
        zoneref->zone = zone;
        zoneref->zone_idx = zone_idx(zone);
}

/*
 * Builds allocation fallback zone lists.
 *
 * Add all populated zones of a node to the zonelist.
 */
static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
                                int nr_zones, enum zone_type zone_type)
{
        struct zone *zone;

        BUG_ON(zone_type >= MAX_NR_ZONES);
        zone_type++;

        do {
                zone_type--;
                zone = pgdat->node_zones + zone_type;
                if (populated_zone(zone)) {
                        zoneref_set_zone(zone,
                                &zonelist->_zonerefs[nr_zones++]);
                        check_highest_zone(zone_type);
                }

        } while (zone_type);
        return nr_zones;
}


/*
 *  zonelist_order:
 *  0 = automatic detection of better ordering.
 *  1 = order by ([node] distance, -zonetype)
 *  2 = order by (-zonetype, [node] distance)
 *
 *  If not NUMA, ZONELIST_ORDER_ZONE and ZONELIST_ORDER_NODE will create
 *  the same zonelist. So only NUMA can configure this param.
 */
#define ZONELIST_ORDER_DEFAULT  0
#define ZONELIST_ORDER_NODE     1
#define ZONELIST_ORDER_ZONE     2

/* zonelist order in the kernel.
 * set_zonelist_order() will set this to NODE or ZONE.
 */
static int current_zonelist_order = ZONELIST_ORDER_DEFAULT;
static char zonelist_order_name[3][8] = {"Default", "Node", "Zone"};


#ifdef CONFIG_NUMA
/* The value user specified ....changed by config */
static int user_zonelist_order = ZONELIST_ORDER_DEFAULT;
/* string for sysctl */
#define NUMA_ZONELIST_ORDER_LEN 16
char numa_zonelist_order[16] = "default";

/*
 * interface for configure zonelist ordering.
 * command line option "numa_zonelist_order"
 *      = "[dD]efault   - default, automatic configuration.
 *      = "[nN]ode      - order by node locality, then by zone within node
 *      = "[zZ]one      - order by zone, then by locality within zone
 */

static int __parse_numa_zonelist_order(char *s)
{
        if (*s == 'd' || *s == 'D') {
                user_zonelist_order = ZONELIST_ORDER_DEFAULT;
        } else if (*s == 'n' || *s == 'N') {
                user_zonelist_order = ZONELIST_ORDER_NODE;
        } else if (*s == 'z' || *s == 'Z') {
                user_zonelist_order = ZONELIST_ORDER_ZONE;
        } else {
                printk(KERN_WARNING
                        "Ignoring invalid numa_zonelist_order value:  "
                        "%s\n", s);
                return -EINVAL;
        }
        return 0;
}

static __init int setup_numa_zonelist_order(char *s)
{
        int ret;

        if (!s)
                return 0;

        ret = __parse_numa_zonelist_order(s);
        if (ret == 0)
                strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN);

        return ret;
}
early_param("numa_zonelist_order", setup_numa_zonelist_order);

/*
 * sysctl handler for numa_zonelist_order
 */
int numa_zonelist_order_handler(ctl_table *table, int write,
                void __user *buffer, size_t *length,
                loff_t *ppos)
{
        char saved_string[NUMA_ZONELIST_ORDER_LEN];
        int ret;
        static DEFINE_MUTEX(zl_order_mutex);

        mutex_lock(&zl_order_mutex);
        if (write)
                strcpy(saved_string, (char*)table->data);
        ret = proc_dostring(table, write, buffer, length, ppos);
        if (ret)
                goto out;
        if (write) {
                int oldval = user_zonelist_order;
                if (__parse_numa_zonelist_order((char*)table->data)) {
                        /*
                         * bogus value.  restore saved string
                         */
                        strncpy((char*)table->data, saved_string,
                                NUMA_ZONELIST_ORDER_LEN);
                        user_zonelist_order = oldval;
                } else if (oldval != user_zonelist_order) {
                        mutex_lock(&zonelists_mutex);
                        build_all_zonelists(NULL);
                        mutex_unlock(&zonelists_mutex);
                }
        }
out:
        mutex_unlock(&zl_order_mutex);
        return ret;
}


#define MAX_NODE_LOAD (nr_online_nodes)
static int node_load[MAX_NUMNODES];

/**
 * find_next_best_node - find the next node that should appear in a given node's fallback list
 * @node: node whose fallback list we're appending
 * @used_node_mask: nodemask_t of already used nodes
 *
 * We use a number of factors to determine which is the next node that should
 * appear on a given node's fallback list.  The node should not have appeared
 * already in @node's fallback list, and it should be the next closest node
 * according to the distance array (which contains arbitrary distance values
 * from each node to each node in the system), and should also prefer nodes
 * with no CPUs, since presumably they'll have very little allocation pressure
 * on them otherwise.
 * It returns -1 if no node is found.
 */
static int find_next_best_node(int node, nodemask_t *used_node_mask)
{
        int n, val;
        int min_val = INT_MAX;
        int best_node = -1;
        const struct cpumask *tmp = cpumask_of_node(0);

        /* Use the local node if we haven't already */
        if (!node_isset(node, *used_node_mask)) {
                node_set(node, *used_node_mask);
                return node;
        }

        for_each_node_state(n, N_HIGH_MEMORY) {

                /* Don't want a node to appear more than once */
                if (node_isset(n, *used_node_mask))
                        continue;

                /* Use the distance array to find the distance */
                val = node_distance(node, n);

                /* Penalize nodes under us ("prefer the next node") */
                val += (n < node);

                /* Give preference to headless and unused nodes */
                tmp = cpumask_of_node(n);
                if (!cpumask_empty(tmp))
                        val += PENALTY_FOR_NODE_WITH_CPUS;

                /* Slight preference for less loaded node */
                val *= (MAX_NODE_LOAD*MAX_NUMNODES);
                val += node_load[n];

                if (val < min_val) {
                        min_val = val;
                        best_node = n;
                }
        }

        if (best_node >= 0)
                node_set(best_node, *used_node_mask);

        return best_node;
}


/*
 * Build zonelists ordered by node and zones within node.
 * This results in maximum locality--normal zone overflows into local
 * DMA zone, if any--but risks exhausting DMA zone.
 */
static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
{
        int j;
        struct zonelist *zonelist;

        zonelist = &pgdat->node_zonelists[0];
        for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
                ;
        j = build_zonelists_node(NODE_DATA(node), zonelist, j,
                                                        MAX_NR_ZONES - 1);
        zonelist->_zonerefs[j].zone = NULL;
        zonelist->_zonerefs[j].zone_idx = 0;
}

/*
 * Build gfp_thisnode zonelists
 */
static void build_thisnode_zonelists(pg_data_t *pgdat)
{
        int j;
        struct zonelist *zonelist;

        zonelist = &pgdat->node_zonelists[1];
        j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
        zonelist->_zonerefs[j].zone = NULL;
        zonelist->_zonerefs[j].zone_idx = 0;
}

/*
 * Build zonelists ordered by zone and nodes within zones.
 * This results in conserving DMA zone[s] until all Normal memory is
 * exhausted, but results in overflowing to remote node while memory
 * may still exist in local DMA zone.
 */
static int node_order[MAX_NUMNODES];

static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
{
        int pos, j, node;
        int zone_type;          /* needs to be signed */
        struct zone *z;
        struct zonelist *zonelist;

        zonelist = &pgdat->node_zonelists[0];
        pos = 0;
        for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) {
                for (j = 0; j < nr_nodes; j++) {
                        node = node_order[j];
                        z = &NODE_DATA(node)->node_zones[zone_type];
                        if (populated_zone(z)) {
                                zoneref_set_zone(z,
                                        &zonelist->_zonerefs[pos++]);
                                check_highest_zone(zone_type);
                        }
                }
        }
        zonelist->_zonerefs[pos].zone = NULL;
        zonelist->_zonerefs[pos].zone_idx = 0;
}

static int default_zonelist_order(void)
{
        int nid, zone_type;
        unsigned long low_kmem_size,total_size;
        struct zone *z;
        int average_size;
        /*
         * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
         * If they are really small and used heavily, the system can fall
         * into OOM very easily.
         * This function detect ZONE_DMA/DMA32 size and configures zone order.
         */
        /* Is there ZONE_NORMAL ? (ex. ppc has only DMA zone..) */
        low_kmem_size = 0;
        total_size = 0;
        for_each_online_node(nid) {
                for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
                        z = &NODE_DATA(nid)->node_zones[zone_type];
                        if (populated_zone(z)) {
                                if (zone_type < ZONE_NORMAL)
                                        low_kmem_size += z->present_pages;
                                total_size += z->present_pages;
                        } else if (zone_type == ZONE_NORMAL) {
                                /*
                                 * If any node has only lowmem, then node order
                                 * is preferred to allow kernel allocations
                                 * locally; otherwise, they can easily infringe
                                 * on other nodes when there is an abundance of
                                 * lowmem available to allocate from.
                                 */
                                return ZONELIST_ORDER_NODE;
                        }
                }
        }
        if (!low_kmem_size ||  /* there are no DMA area. */
            low_kmem_size > total_size/2) /* DMA/DMA32 is big. */
                return ZONELIST_ORDER_NODE;
        /*
         * look into each node's config.
         * If there is a node whose DMA/DMA32 memory is very big area on
         * local memory, NODE_ORDER may be suitable.
         */
        average_size = total_size /
                                (nodes_weight(node_states[N_HIGH_MEMORY]) + 1);
        for_each_online_node(nid) {
                low_kmem_size = 0;
                total_size = 0;
                for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
                        z = &NODE_DATA(nid)->node_zones[zone_type];
                        if (populated_zone(z)) {
                                if (zone_type < ZONE_NORMAL)
                                        low_kmem_size += z->present_pages;
                                total_size += z->present_pages;
                        }
                }
                if (low_kmem_size &&
                    total_size > average_size && /* ignore small node */
                    low_kmem_size > total_size * 70/100)
                        return ZONELIST_ORDER_NODE;
        }
        return ZONELIST_ORDER_ZONE;
}

static void set_zonelist_order(void)
{
        if (user_zonelist_order == ZONELIST_ORDER_DEFAULT)
                current_zonelist_order = default_zonelist_order();
        else
                current_zonelist_order = user_zonelist_order;
}

static void build_zonelists(pg_data_t *pgdat)
{
        int j, node, load;
        enum zone_type i;
        nodemask_t used_mask;
        int local_node, prev_node;
        struct zonelist *zonelist;
        int order = current_zonelist_order;

        /* initialize zonelists */
        for (i = 0; i < MAX_ZONELISTS; i++) {
                zonelist = pgdat->node_zonelists + i;
                zonelist->_zonerefs[0].zone = NULL;
                zonelist->_zonerefs[0].zone_idx = 0;
        }

        /* NUMA-aware ordering of nodes */
        local_node = pgdat->node_id;
        load = nr_online_nodes;
        prev_node = local_node;
        nodes_clear(used_mask);

        memset(node_order, 0, sizeof(node_order));
        j = 0;

        while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
                int distance = node_distance(local_node, node);

                /*
                 * If another node is sufficiently far away then it is better
                 * to reclaim pages in a zone before going off node.
                 */
                if (distance > RECLAIM_DISTANCE)
                        zone_reclaim_mode = 1;

                /*
                 * We don't want to pressure a particular node.
                 * So adding penalty to the first node in same
                 * distance group to make it round-robin.
                 */
                if (distance != node_distance(local_node, prev_node))
                        node_load[node] = load;

                prev_node = node;
                load--;
                if (order == ZONELIST_ORDER_NODE)
                        build_zonelists_in_node_order(pgdat, node);
                else
                        node_order[j++] = node; /* remember order */
        }

        if (order == ZONELIST_ORDER_ZONE) {
                /* calculate node order -- i.e., DMA last! */
                build_zonelists_in_zone_order(pgdat, j);
        }

        build_thisnode_zonelists(pgdat);
}

/* Construct the zonelist performance cache - see further mmzone.h */
static void build_zonelist_cache(pg_data_t *pgdat)
{
        struct zonelist *zonelist;
        struct zonelist_cache *zlc;
        struct zoneref *z;

        zonelist = &pgdat->node_zonelists[0];
        zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
        bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
        for (z = zonelist->_zonerefs; z->zone; z++)
                zlc->z_to_n[z - zonelist->_zonerefs] = zonelist_node_idx(z);
}

#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
 * Return node id of node used for "local" allocations.
 * I.e., first node id of first zone in arg node's generic zonelist.
 * Used for initializing percpu 'numa_mem', which is used primarily
 * for kernel allocations, so use GFP_KERNEL flags to locate zonelist.
 */
int local_memory_node(int node)
{
        struct zone *zone;

        (void)first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
                                   gfp_zone(GFP_KERNEL),
                                   NULL,
                                   &zone);
        return zone->node;
}
#endif

#else   /* CONFIG_NUMA */

static void set_zonelist_order(void)
{
        current_zonelist_order = ZONELIST_ORDER_ZONE;
}

static void build_zonelists(pg_data_t *pgdat)
{
        int node, local_node;
        enum zone_type j;
        struct zonelist *zonelist;

        local_node = pgdat->node_id;

        zonelist = &pgdat->node_zonelists[0];
        j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);

        /*
         * Now we build the zonelist so that it contains the zones
         * of all the other nodes.
         * We don't want to pressure a particular node, so when
         * building the zones for node N, we make sure that the
         * zones coming right after the local ones are those from
         * node N+1 (modulo N)
         */
        for (node = local_node + 1; node < MAX_NUMNODES; node++) {
                if (!node_online(node))
                        continue;
                j = build_zonelists_node(NODE_DATA(node), zonelist, j,
                                                        MAX_NR_ZONES - 1);
        }
        for (node = 0; node < local_node; node++) {
                if (!node_online(node))
                        continue;
                j = build_zonelists_node(NODE_DATA(node), zonelist, j,
                                                        MAX_NR_ZONES - 1);
        }

        zonelist->_zonerefs[j].zone = NULL;
        zonelist->_zonerefs[j].zone_idx = 0;
}

/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
static void build_zonelist_cache(pg_data_t *pgdat)
{
        pgdat->node_zonelists[0].zlcache_ptr = NULL;
}

#endif  /* CONFIG_NUMA */

/*
 * Boot pageset table. One per cpu which is going to be used for all
 * zones and all nodes. The parameters will be set in such a way
 * that an item put on a list will immediately be handed over to
 * the buddy list. This is safe since pageset manipulation is done
 * with interrupts disabled.
 *
 * The boot_pagesets must be kept even after bootup is complete for
 * unused processors and/or zones. They do play a role for bootstrapping
 * hotplugged processors.
 *
 * zoneinfo_show() and maybe other functions do
 * not check if the processor is online before following the pageset pointer.
 * Other parts of the kernel may not check if the zone is available.
 */
static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
static void setup_zone_pageset(struct zone *zone);

/*
 * Global mutex to protect against size modification of zonelists
 * as well as to serialize pageset setup for the new populated zone.
 */
DEFINE_MUTEX(zonelists_mutex);

/* return values int ....just for stop_machine() */
static __init_refok int __build_all_zonelists(void *data)
{
        int nid;
        int cpu;

#ifdef CONFIG_NUMA
        memset(node_load, 0, sizeof(node_load));
#endif
        for_each_online_node(nid) {
                pg_data_t *pgdat = NODE_DATA(nid);

                build_zonelists(pgdat);
                build_zonelist_cache(pgdat);
        }

        /*
         * Initialize the boot_pagesets that are going to be used
         * for bootstrapping processors. The real pagesets for
         * each zone will be allocated later when the per cpu
         * allocator is available.
         *
         * boot_pagesets are used also for bootstrapping offline
         * cpus if the system is already booted because the pagesets
         * are needed to initialize allocators on a specific cpu too.
         * F.e. the percpu allocator needs the page allocator which
         * needs the percpu allocator in order to allocate its pagesets
         * (a chicken-egg dilemma).
         */
        for_each_possible_cpu(cpu) {
                setup_pageset(&per_cpu(boot_pageset, cpu), 0);

#ifdef CONFIG_HAVE_MEMORYLESS_NODES
                /*
                 * We now know the "local memory node" for each node--
                 * i.e., the node of the first zone in the generic zonelist.
                 * Set up numa_mem percpu variable for on-line cpus.  During
                 * boot, only the boot cpu should be on-line;  we'll init the
                 * secondary cpus' numa_mem as they come on-line.  During
                 * node/memory hotplug, we'll fixup all on-line cpus.
                 */
                if (cpu_online(cpu))
                        set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
#endif
        }

        return 0;
}

/*
 * Called with zonelists_mutex held always
 * unless system_state == SYSTEM_BOOTING.
 */
void __ref build_all_zonelists(void *data)
{
        set_zonelist_order();

        if (system_state == SYSTEM_BOOTING) {
                __build_all_zonelists(NULL);
                mminit_verify_zonelist();
                cpuset_init_current_mems_allowed();
        } else {
                /* we have to stop all cpus to guarantee there is no user
                   of zonelist */
#ifdef CONFIG_MEMORY_HOTPLUG
                if (data)
                        setup_zone_pageset((struct zone *)data);
#endif
                stop_machine(__build_all_zonelists, NULL, NULL);
                /* cpuset refresh routine should be here */
        }
        vm_total_pages = nr_free_pagecache_pages();
        /*
         * Disable grouping by mobility if the number of pages in the
         * system is too low to allow the mechanism to work. It would be
         * more accurate, but expensive to check per-zone. This check is
         * made on memory-hotadd so a system can start with mobility
         * disabled and enable it later
         */
        if (vm_total_pages < (pageblock_nr_pages * MIGRATE_TYPES))
                page_group_by_mobility_disabled = 1;
        else
                page_group_by_mobility_disabled = 0;

        printk("Built %i zonelists in %s order, mobility grouping %s.  "
                "Total pages: %ld\n",
                        nr_online_nodes,
                        zonelist_order_name[current_zonelist_order],
                        page_group_by_mobility_disabled ? "off" : "on",
                        vm_total_pages);
#ifdef CONFIG_NUMA
        printk("Policy zone: %s\n", zone_names[policy_zone]);
#endif
}

/*
 * Helper functions to size the waitqueue hash table.
 * Essentially these want to choose hash table sizes sufficiently
 * large so that collisions trying to wait on pages are rare.
 * But in fact, the number of active page waitqueues on typical
 * systems is ridiculously low, less than 200. So this is even
 * conservative, even though it seems large.
 *
 * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
 * waitqueues, i.e. the size of the waitq table given the number of pages.
 */
#define PAGES_PER_WAITQUEUE     256

#ifndef CONFIG_MEMORY_HOTPLUG
static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
{
        unsigned long size = 1;

        pages /= PAGES_PER_WAITQUEUE;

        while (size < pages)
                size <<= 1;

        /*
         * Once we have dozens or even hundreds of threads sleeping
         * on IO we've got bigger problems than wait queue collision.
         * Limit the size of the wait table to a reasonable size.
         */
        size = min(size, 4096UL);

        return max(size, 4UL);
}
#else
/*
 * A zone's size might be changed by hot-add, so it is not possible to determine
 * a suitable size for its wait_table.  So we use the maximum size now.
 *
 * The max wait table size = 4096 x sizeof(wait_queue_head_t).   ie:
 *
 *    i386 (preemption config)    : 4096 x 16 = 64Kbyte.
 *    ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte.
 *    ia64, x86-64 (preemption)   : 4096 x 24 = 96Kbyte.
 *
 * The maximum entries are prepared when a zone's memory is (512K + 256) pages
 * or more by the traditional way. (See above).  It equals:
 *
 *    i386, x86-64, powerpc(4K page size) : =  ( 2G + 1M)byte.
 *    ia64(16K page size)                 : =  ( 8G + 4M)byte.
 *    powerpc (64K page size)             : =  (32G +16M)byte.
 */
static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
{
        return 4096UL;
}
#endif

/*
 * This is an integer logarithm so that shifts can be used later
 * to extract the more random high bits from the multiplicative
 * hash function before the remainder is taken.
 */
static inline unsigned long wait_table_bits(unsigned long size)
{
        return ffz(~size);
}

#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))

/*
 * Check if a pageblock contains reserved pages
 */
static int pageblock_is_reserved(unsigned long start_pfn, unsigned long end_pfn)
{
        unsigned long pfn;

        for (pfn = start_pfn; pfn < end_pfn; pfn++) {
                if (!pfn_valid_within(pfn) || PageReserved(pfn_to_page(pfn)))
                        return 1;
        }
        return 0;
}

/*
 * Mark a number of pageblocks as MIGRATE_RESERVE. The number
 * of blocks reserved is based on min_wmark_pages(zone). The memory within
 * the reserve will tend to store contiguous free pages. Setting min_free_kbytes
 * higher will lead to a bigger reserve which will get freed as contiguous
 * blocks as reclaim kicks in
 */
static void setup_zone_migrate_reserve(struct zone *zone)
{
        unsigned long start_pfn, pfn, end_pfn, block_end_pfn;
        struct page *page;
        unsigned long block_migratetype;
        int reserve;

        /* Get the start pfn, end pfn and the number of blocks to reserve */
        start_pfn = zone->zone_start_pfn;
        end_pfn = start_pfn + zone->spanned_pages;
        reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
                                                        pageblock_order;

        /*
         * Reserve blocks are generally in place to help high-order atomic
         * allocations that are short-lived. A min_free_kbytes value that
         * would result in more than 2 reserve blocks for atomic allocations
         * is assumed to be in place to help anti-fragmentation for the
         * future allocation of hugepages at runtime.
         */
        reserve = min(2, reserve);

        for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
                if (!pfn_valid(pfn))
                        continue;
                page = pfn_to_page(pfn);

                /* Watch out for overlapping nodes */
                if (page_to_nid(page) != zone_to_nid(zone))
                        continue;

                /* Blocks with reserved pages will never free, skip them. */
                block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
                if (pageblock_is_reserved(pfn, block_end_pfn))
                        continue;

                block_migratetype = get_pageblock_migratetype(page);

                /* If this block is reserved, account for it */
                if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
                        reserve--;
                        continue;
                }

                /* Suitable for reserving if this block is movable */
                if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
                        set_pageblock_migratetype(page, MIGRATE_RESERVE);
                        move_freepages_block(zone, page, MIGRATE_RESERVE);
                        reserve--;
                        continue;
                }

                /*
                 * If the reserve is met and this is a previous reserved block,
                 * take it back
                 */
                if (block_migratetype == MIGRATE_RESERVE) {
                        set_pageblock_migratetype(page, MIGRATE_MOVABLE);
                        move_freepages_block(zone, page, MIGRATE_MOVABLE);
                }
        }
}

/*
 * Initially all pages are reserved - free ones are freed
 * up by free_all_bootmem() once the early boot process is
 * done. Non-atomic initialization, single-pass.
 */
void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
                unsigned long start_pfn, enum memmap_context context)
{
        struct page *page;
        unsigned long end_pfn = start_pfn + size;
        unsigned long pfn;
        struct zone *z;

        if (highest_memmap_pfn < end_pfn - 1)
                highest_memmap_pfn = end_pfn - 1;

        z = &NODE_DATA(nid)->node_zones[zone];
        for (pfn = start_pfn; pfn < end_pfn; pfn++) {
                /*
                 * There can be holes in boot-time mem_map[]s
                 * handed to this function.  They do not