linux-next/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/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/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 <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))) {
		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));

		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))) {
		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_del(&page->lru);
		list_add(&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
			 * agressive 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);
	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 fail_page_alloc_attr {
	struct fault_attr attr;

	u32 ignore_gfp_highmem;
	u32 ignore_gfp_wait;
	u32 min_order;

#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

	struct dentry *ignore_gfp_highmem_file;
	struct dentry *ignore_gfp_wait_file;
	struct dentry *min_order_file;

#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */

} 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;
	int err;

	err = init_fault_attr_dentries(&fail_page_alloc.attr,
				       "fail_page_alloc");
	if (err)
		return err;
	dir = fail_page_alloc.attr.dentries.dir;

	fail_page_alloc.ignore_gfp_wait_file =
		debugfs_create_bool("ignore-gfp-wait", mode, dir,
				      &fail_page_alloc.ignore_gfp_wait);

	fail_page_alloc.ignore_gfp_highmem_file =
		debugfs_create_bool("ignore-gfp-highmem", mode, dir,
				      &fail_page_alloc.ignore_gfp_highmem);
	fail_page_alloc.min_order_file =
		debugfs_create_u32("min-order", mode, dir,
				   &fail_page_alloc.min_order);

	if (!fail_page_alloc.ignore_gfp_wait_file ||
            !fail_page_alloc.ignore_gfp_highmem_file ||
            !fail_page_alloc.min_order_file) {
		err = -ENOMEM;
		debugfs_remove(fail_page_alloc.ignore_gfp_wait_file);
		debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file);
		debugfs_remove(fail_page_alloc.min_order_file);
		cleanup_fault_attr_dentries(&fail_page_alloc.attr);
	}

	return err;
}

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);
}

#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)
{
}
#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))
				goto try_next_zone;

		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 (zone_reclaim_mode == 0)
				goto this_zone_full;

			ret = zone_reclaim(zone, gfp_mask, order);
			switch (ret) {
			case ZONE_RECLAIM_NOSCAN:
				/* did not scan */
				goto try_next_zone;
			case ZONE_RECLAIM_FULL:
				/* scanned but unreclaimable */
				goto this_zone_full;
			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);
try_next_zone:
		if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
			/*
			 * we do zlc_setup after the first zone is tried but only
			 * if there are multiple nodes make it worthwhile
			 */
			allowednodes = zlc_setup(zonelist, alloc_flags);
			zlc_active = 1;
			did_zlc_setup = 1;
		}
	}

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

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;

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);

	/* 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;

rebalance:
	/* 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:
	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
		printk(KERN_WARNING "%s: page allocation failure."
			" order:%d, mode:0x%x\n",
			current->comm, order, gfp_mask);
		dump_stack();
		show_mem();
	}
	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);

/**
 * 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);
	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;
}
EXPORT_SYMBOL(alloc_pages_exact);

/**
 * 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

#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.
 */
void show_free_areas(void)
{
	int cpu;
	struct zone *zone;

	for_each_populated_zone(zone) {
		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;

		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;

		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 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))

/*
 * 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;
	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. */
		if (PageReserved(page))
			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
		 * exist on hotplugged memory.
		 */
		if (context == MEMMAP_EARLY) {
			if (!early_pfn_valid(pfn))
				continue;
			if (!early_pfn_in_nid(pfn, nid))
				continue;
		}
		page = pfn_to_page(pfn);
		set_page_links(page, zone, nid, pfn);
		mminit_verify_page_links(page, zone, nid, pfn);
		init_page_count(page);
		reset_page_mapcount(page);
		SetPageReserved(page);
		/*
		 * Mark the block movable so that blocks are reserved for
		 * movable at startup. This will force kernel allocations
		 * to reserve their blocks rather than leaking throughout
		 * the address space during boot when many long-lived
		 * kernel allocations are made. Later some blocks near
		 * the start are marked MIGRATE_RESERVE by
		 * setup_zone_migrate_reserve()
		 *
		 * bitmap is created for zone's valid pfn range. but memmap
		 * can be created for invalid pages (for alignment)
		 * check here not to call set_pageblock_migratetype() against
		 * pfn out of zone.
		 */
		if ((z->zone_start_pfn <= pfn)
		    && (pfn < z->zone_start_pfn + z->spanned_pages)
		    && !(pfn & (pageblock_nr_pages - 1)))
			set_pageblock_migratetype(page, MIGRATE_MOVABLE);

		INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
		/* The shift won't overflow because ZONE_NORMAL is below 4G. */
		if (!is_highmem_idx(zone))
			set_page_address(page, __va(pfn << PAGE_SHIFT));
#endif
	}
}

static void __meminit zone_init_free_lists(struct zone *zone)
{
	int order, t;
	for_each_migratetype_order(order, t) {
		INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
		zone->free_area[order].nr_free = 0;
	}
}

#ifndef __HAVE_ARCH_MEMMAP_INIT
#define memmap_init(size, nid, zone, start_pfn) \
	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
#endif

static int zone_batchsize(struct zone *zone)
{
#ifdef CONFIG_MMU
	int batch;

	/*
	 * The per-cpu-pages pools are set to around 1000th of the
	 * size of the zone.  But no more than 1/2 of a meg.
	 *
	 * OK, so we don't know how big the cache is.  So guess.
	 */
	batch = zone->present_pages / 1024;
	if (batch * PAGE_SIZE > 512 * 1024)
		batch = (512 * 1024) / PAGE_SIZE;
	batch /= 4;		/* We effectively *= 4 below */
	if (batch < 1)
		batch = 1;

	/*
	 * Clamp the batch to a 2^n - 1 value. Having a power
	 * of 2 value was found to be more likely to have
	 * suboptimal cache aliasing properties in some cases.
	 *
	 * For example if 2 tasks are alternately allocating
	 * batches of pages, one task can end up with a lot
	 * of pages of one half of the possible page colors
	 * and the other with pages of the other colors.
	 */
	batch = rounddown_pow_of_two(batch + batch/2) - 1;

	return batch;

#else
	/* The deferral and batching of frees should be suppressed under NOMMU
	 * conditions.
	 *
	 * The problem is that NOMMU needs to be able to allocate large chunks
	 * of contiguous memory as there's no hardware page translation to
	 * assemble apparent contiguous memory from discontiguous pages.
	 *
	 * Queueing large contiguous runs of pages for batching, however,
	 * causes the pages to actually be freed in smaller chunks.  As there
	 * can be a significant delay between the individual batches being
	 * recycled, this leads to the once large chunks of space being
	 * fragmented and becoming unavailable for high-order allocations.
	 */
	return 0;
#endif
}

static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
	struct per_cpu_pages *pcp;
	int migratetype;

	memset(p, 0, sizeof(*p));

	pcp = &p->pcp;
	pcp->count = 0;
	pcp->high = 6 * batch;
	pcp->batch = max(1UL, 1 * batch);
	for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
		INIT_LIST_HEAD(&pcp->lists[migratetype]);
}

/*
 * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist
 * to the value high for the pageset p.
 */

static void setup_pagelist_highmark(struct per_cpu_pageset *p,
				unsigned long high)
{
	struct per_cpu_pages *pcp;

	pcp = &p->pcp;
	pcp->high = high;
	pcp->batch = max(1UL, high/4);
	if ((high/4) > (PAGE_SHIFT * 8))
		pcp->batch = PAGE_SHIFT * 8;
}

static __meminit void setup_zone_pageset(struct zone *zone)
{
	int cpu;

	zone->pageset = alloc_percpu(struct per_cpu_pageset);

	for_each_possible_cpu(cpu) {
		struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);

		setup_pageset(pcp, zone_batchsize(zone));

		if (percpu_pagelist_fraction)
			setup_pagelist_highmark(pcp,
				(zone->present_pages /
					percpu_pagelist_fraction));
	}
}

/*
 * Allocate per cpu pagesets and initialize them.
 * Before this call only boot pagesets were available.
 */
void __init setup_per_cpu_pageset(void)
{
	struct zone *zone;

	for_each_populated_zone(zone)
		setup_zone_pageset(zone);
}

static noinline __init_refok
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
	int i;
	struct pglist_data *pgdat = zone->zone_pgdat;
	size_t alloc_size;

	/*
	 * The per-page waitqueue mechanism uses hashed waitqueues
	 * per zone.
	 */
	zone->wait_table_hash_nr_entries =
		 wait_table_hash_nr_entries(zone_size_pages);
	zone->wait_table_bits =
		wait_table_bits(zone->wait_table_hash_nr_entries);
	alloc_size = zone->wait_table_hash_nr_entries
					* sizeof(wait_queue_head_t);

	if (!slab_is_available()) {
		zone->wait_table = (wait_queue_head_t *)
			alloc_bootmem_node(pgdat, alloc_size);
	} else {
		/*
		 * This case means that a zone whose size was 0 gets new memory
		 * via memory hot-add.
		 * But it may be the case that a new node was hot-added.  In
		 * this case vmalloc() will not be able to use this new node's
		 * memory - this wait_table must be initialized to use this new
		 * node itself as well.
		 * To use this new node's memory, further consideration will be
		 * necessary.
		 */
		zone->wait_table = vmalloc(alloc_size);
	}
	if (!zone->wait_table)
		return -ENOMEM;

	for(i = 0; i < zone->wait_table_hash_nr_entries; ++i)
		init_waitqueue_head(zone->wait_table + i);

	return 0;
}

static int __zone_pcp_update(void *data)
{
	struct zone *zone = data;
	int cpu;
	unsigned long batch = zone_batchsize(zone), flags;

	for_each_possible_cpu(cpu) {
		struct per_cpu_pageset *pset;
		struct per_cpu_pages *pcp;

		pset = per_cpu_ptr(zone->pageset, cpu);
		pcp = &pset->pcp;

		local_irq_save(flags);
		free_pcppages_bulk(zone, pcp->count, pcp);
		setup_pageset(pset, batch);
		local_irq_restore(flags);
	}
	return 0;
}

void zone_pcp_update(struct zone *zone)
{
	stop_machine(__zone_pcp_update, zone, NULL);
}

static __meminit void zone_pcp_init(struct zone *zone)
{
	/*
	 * per cpu subsystem is not up at this point. The following code
	 * relies on the ability of the linker to provide the
	 * offset of a (static) per cpu variable into the per cpu area.
	 */
	zone->pageset = &boot_pageset;

	if (zone->present_pages)
		printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%u\n",
			zone->name, zone->present_pages,
					 zone_batchsize(zone));
}

__meminit int init_currently_empty_zone(struct zone *zone,
					unsigned long zone_start_pfn,
					unsigned long size,
					enum memmap_context context)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int ret;
	ret = zone_wait_table_init(zone, size);
	if (ret)
		return ret;
	pgdat->nr_zones = zone_idx(zone) + 1;

	zone->zone_start_pfn = zone_start_pfn;

	mminit_dprintk(MMINIT_TRACE, "memmap_init",
			"Initialising map node %d zone %lu pfns %lu -> %lu\n",
			pgdat->node_id,
			(unsigned long)zone_idx(zone),
			zone_start_pfn, (zone_start_pfn + size));

	zone_init_free_lists(zone);

	return 0;
}

#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
 * Basic iterator support. Return the first range of PFNs for a node
 * Note: nid == MAX_NUMNODES returns first region regardless of node
 */
static int __meminit first_active_region_index_in_nid(int nid)
{
	int i;

	for (i = 0; i < nr_nodemap_entries; i++)
		if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
			return i;

	return -1;
}

/*
 * Basic iterator support. Return the next active range of PFNs for a node
 * Note: nid == MAX_NUMNODES returns next region regardless of node
 */
static int __meminit next_active_region_index_in_nid(int index, int nid)
{
	for (index = index + 1; index < nr_nodemap_entries; index++)
		if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
			return index;

	return -1;
}

#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
/*
 * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
 * Architectures may implement their own version but if add_active_range()
 * was used and there are no special requirements, this is a convenient
 * alternative
 */
int __meminit __early_pfn_to_nid(unsigned long pfn)
{
	int i;

	for (i = 0; i < nr_nodemap_entries; i++) {
		unsigned long start_pfn = early_node_map[i].start_pfn;
		unsigned long end_pfn = early_node_map[i].end_pfn;

		if (start_pfn <= pfn && pfn < end_pfn)
			return early_node_map[i].nid;
	}
	/* This is a memory hole */
	return -1;
}
#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */

int __meminit early_pfn_to_nid(unsigned long pfn)
{
	int nid;

	nid = __early_pfn_to_nid(pfn);
	if (nid >= 0)
		return nid;
	/* just returns 0 */
	return 0;
}

#ifdef CONFIG_NODES_SPAN_OTHER_NODES
bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
	int nid;

	nid = __early_pfn_to_nid(pfn);
	if (nid >= 0 && nid != node)
		return false;
	return true;
}
#endif

/* Basic iterator support to walk early_node_map[] */
#define for_each_active_range_index_in_nid(i, nid) \
	for (i = first_active_region_index_in_nid(nid); i != -1; \
				i = next_active_region_index_in_nid(i, nid))

/**
 * free_bootmem_with_active_regions - Call free_bootmem_node for each active range
 * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
 * @max_low_pfn: The highest PFN that will be passed to free_bootmem_node
 *
 * If an architecture guarantees that all ranges registered with
 * add_active_ranges() contain no holes and may be freed, this
 * this function may be used instead of calling free_bootmem() manually.
 */
void __init free_bootmem_with_active_regions(int nid,
						unsigned long max_low_pfn)
{
	int i;

	for_each_active_range_index_in_nid(i, nid) {
		unsigned long size_pages = 0;
		unsigned long end_pfn = early_node_map[i].end_pfn;

		if (early_node_map[i].start_pfn >= max_low_pfn)
			continue;

		if (end_pfn > max_low_pfn)
			end_pfn = max_low_pfn;

		size_pages = end_pfn - early_node_map[i].start_pfn;
		free_bootmem_node(NODE_DATA(early_node_map[i].nid),
				PFN_PHYS(early_node_map[i].start_pfn),
				size_pages << PAGE_SHIFT);
	}
}

#ifdef CONFIG_HAVE_MEMBLOCK
/*
 * Basic iterator support. Return the last range of PFNs for a node
 * Note: nid == MAX_NUMNODES returns last region regardless of node
 */
static int __meminit last_active_region_index_in_nid(int nid)
{
	int i;

	for (i = nr_nodemap_entries - 1; i >= 0; i--)
		if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
			return i;

	return -1;
}

/*
 * Basic iterator support. Return the previous active range of PFNs for a node
 * Note: nid == MAX_NUMNODES returns next region regardless of node
 */
static int __meminit previous_active_region_index_in_nid(int index, int nid)
{
	for (index = index - 1; index >= 0; index--)
		if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
			return index;

	return -1;
}

#define for_each_active_range_index_in_nid_reverse(i, nid) \
	for (i = last_active_region_index_in_nid(nid); i != -1; \
				i = previous_active_region_index_in_nid(i, nid))

u64 __init find_memory_core_early(int nid, u64 size, u64 align,
					u64 goal, u64 limit)
{
	int i;

	/* Need to go over early_node_map to find out good range for node */
	for_each_active_range_index_in_nid_reverse(i, nid) {
		u64 addr;
		u64 ei_start, ei_last;
		u64 final_start, final_end;

		ei_last = early_node_map[i].end_pfn;
		ei_last <<= PAGE_SHIFT;
		ei_start = early_node_map[i].start_pfn;
		ei_start <<= PAGE_SHIFT;

		final_start = max(ei_start, goal);
		final_end = min(ei_last, limit);

		if (final_start >= final_end)
			continue;

		addr = memblock_find_in_range(final_start, final_end, size, align);

		if (addr == MEMBLOCK_ERROR)
			continue;

		return addr;
	}

	return MEMBLOCK_ERROR;
}
#endif

int __init add_from_early_node_map(struct range *range, int az,
				   int nr_range, int nid)
{
	int i;
	u64 start, end;

	/* need to go over early_node_map to find out good range for node */
	for_each_active_range_index_in_nid(i, nid) {
		start = early_node_map[i].start_pfn;
		end = early_node_map[i].end_pfn;
		nr_range = add_range(range, az, nr_range, start, end);
	}
	return nr_range;
}

void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
{
	int i;
	int ret;

	for_each_active_range_index_in_nid(i, nid) {
		ret = work_fn(early_node_map[i].start_pfn,
			      early_node_map[i].end_pfn, data);
		if (ret)
			break;
	}
}
/**
 * sparse_memory_present_with_active_regions - Call memory_present for each active range
 * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
 *
 * If an architecture guarantees that all ranges registered with
 * add_active_ranges() contain no holes and may be freed, this
 * function may be used instead of calling memory_present() manually.
 */
void __init sparse_memory_present_with_active_regions(int nid)
{
	int i;

	for_each_active_range_index_in_nid(i, nid)
		memory_present(early_node_map[i].nid,
				early_node_map[i].start_pfn,
				early_node_map[i].end_pfn);
}

/**
 * get_pfn_range_for_nid - Return the start and end page frames for a node
 * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
 * @start_pfn: Passed by reference. On return, it will have the node start_pfn.
 * @end_pfn: Passed by reference. On return, it will have the node end_pfn.
 *
 * It returns the start and end page frame of a node based on information
 * provided by an arch calling add_active_range(). If called for a node
 * with no available memory, a warning is printed and the start and end
 * PFNs will be 0.
 */
void __meminit get_pfn_range_for_nid(unsigned int nid,
			unsigned long *start_pfn, unsigned long *end_pfn)
{
	int i;
	*start_pfn = -1UL;
	*end_pfn = 0;

	for_each_active_range_index_in_nid(i, nid) {
		*start_pfn = min(*start_pfn, early_node_map[i].start_pfn);
		*end_pfn = max(*end_pfn, early_node_map[i].end_pfn);
	}

	if (*start_pfn == -1UL)
		*start_pfn = 0;
}

/*
 * This finds a zone that can be used for ZONE_MOVABLE pages. The
 * assumption is made that zones within a node are ordered in monotonic
 * increasing memory addresses so that the "highest" populated zone is used
 */
static void __init find_usable_zone_for_movable(void)
{
	int zone_index;
	for (zone_index = MAX_NR_ZONES - 1; zone_index >= 0; zone_index--) {
		if (zone_index == ZONE_MOVABLE)
			continue;

		if (arch_zone_highest_possible_pfn[zone_index] >
				arch_zone_lowest_possible_pfn[zone_index])
			break;
	}

	VM_BUG_ON(zone_index == -1);
	movable_zone = zone_index;
}

/*
 * The zone ranges provided by the architecture do not include ZONE_MOVABLE
 * because it is sized independant of architecture. Unlike the other zones,
 * the starting point for ZONE_MOVABLE is not fixed. It may be different
 * in each node depending on the size of each node and how evenly kernelcore
 * is distributed. This helper function adjusts the zone ranges
 * provided by the architecture for a given node by using the end of the
 * highest usable zone for ZONE_MOVABLE. This preserves the assumption that
 * zones within a node are in order of monotonic increases memory addresses
 */
static void __meminit adjust_zone_range_for_zone_movable(int nid,
					unsigned long zone_type,
					unsigned long node_start_pfn,
					unsigned long node_end_pfn,
					unsigned long *zone_start_pfn,
					unsigned long *zone_end_pfn)
{
	/* Only adjust if ZONE_MOVABLE is on this node */
	if (zone_movable_pfn[nid]) {
		/* Size ZONE_MOVABLE */
		if (zone_type == ZONE_MOVABLE) {
			*zone_start_pfn = zone_movable_pfn[nid];
			*zone_end_pfn = min(node_end_pfn,
				arch_zone_highest_possible_pfn[movable_zone]);

		/* Adjust for ZONE_MOVABLE starting within this range */
		} else if (*zone_start_pfn < zone_movable_pfn[nid] &&
				*zone_end_pfn > zone_movable_pfn[nid]) {
			*zone_end_pfn = zone_movable_pfn[nid];

		/* Check if this whole range is within ZONE_MOVABLE */
		} else if (*zone_start_pfn >= zone_movable_pfn[nid])
			*zone_start_pfn = *zone_end_pfn;
	}
}

/*
 * Return the number of pages a zone spans in a node, including holes
 * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node()
 */
static unsigned long __meminit zone_spanned_pages_in_node(int nid,
					unsigned long zone_type,
					unsigned long *ignored)
{
	unsigned long node_start_pfn, node_end_pfn;
	unsigned long zone_start_pfn, zone_end_pfn;

	/* Get the start and end of the node and zone */
	get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
	zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
	zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
	adjust_zone_range_for_zone_movable(nid, zone_type,
				node_start_pfn, node_end_pfn,
				&zone_start_pfn, &zone_end_pfn);

	/* Check that this node has pages within the zone's required range */
	if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn)
		return 0;

	/* Move the zone boundaries inside the node if necessary */
	zone_end_pfn = min(zone_end_pfn, node_end_pfn);
	zone_start_pfn = max(zone_start_pfn, node_start_pfn);

	/* Return the spanned pages */
	return zone_end_pfn - zone_start_pfn;
}

/*
 * Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
 * then all holes in the requested range will be accounted for.
 */
unsigned long __meminit __absent_pages_in_range(int nid,
				unsigned long range_start_pfn,
				unsigned long range_end_pfn)
{
	int i = 0;
	unsigned long prev_end_pfn = 0, hole_pages = 0;
	unsigned long start_pfn;

	/* Find the end_pfn of the first active range of pfns in the node */
	i = first_active_region_index_in_nid(nid);
	if (i == -1)
		return 0;

	prev_end_pfn = min(early_node_map[i].start_pfn, range_end_pfn);

	/* Account for ranges before physical memory on this node */
	if (early_node_map[i].start_pfn > range_start_pfn)
		hole_pages = prev_end_pfn - range_start_pfn;

	/* Find all holes for the zone within the node */
	for (; i != -1; i = next_active_region_index_in_nid(i, nid)) {

		/* No need to continue if prev_end_pfn is outside the zone */
		if (prev_end_pfn >= range_end_pfn)
			break;

		/* Make sure the end of the zone is not within the hole */
		start_pfn = min(early_node_map[i].start_pfn, range_end_pfn);
		prev_end_pfn = max(prev_end_pfn, range_start_pfn);

		/* Update the hole size cound and move on */
		if (start_pfn > range_start_pfn) {
			BUG_ON(prev_end_pfn > start_pfn);
			hole_pages += start_pfn - prev_end_pfn;
		}
		prev_end_pfn = early_node_map[i].end_pfn;
	}

	/* Account for ranges past physical memory on this node */
	if (range_end_pfn > prev_end_pfn)
		hole_pages += range_end_pfn -
				max(range_start_pfn, prev_end_pfn);

	return hole_pages;
}

/**
 * absent_pages_in_range - Return number of page frames in holes within a range
 * @start_pfn: The start PFN to start searching for holes
 * @end_pfn: The end PFN to stop searching for holes
 *
 * It returns the number of pages frames in memory holes within a range.
 */
unsigned long __init absent_pages_in_range(unsigned long start_pfn,
							unsigned long end_pfn)
{
	return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn);
}

/* Return the number of page frames in holes in a zone on a node */
static unsigned long __meminit zone_absent_pages_in_node(int nid,
					unsigned long zone_type,
					unsigned long *ignored)
{
	unsigned long node_start_pfn, node_end_pfn;
	unsigned long zone_start_pfn, zone_end_pfn;

	get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
	zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type],
							node_start_pfn);
	zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type],
							node_end_pfn);

	adjust_zone_range_for_zone_movable(nid, zone_type,
			node_start_pfn, node_end_pfn,
			&zone_start_pfn, &zone_end_pfn);
	return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
}

#else
static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
					unsigned long zone_type,
					unsigned long *zones_size)
{
	return zones_size[zone_type];
}

static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
						unsigned long zone_type,
						unsigned long *zholes_size)
{
	if (!zholes_size)
		return 0;

	return zholes_size[zone_type];
}

#endif

static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
		unsigned long *zones_size, unsigned long *zholes_size)
{
	unsigned long realtotalpages, totalpages = 0;
	enum zone_type i;

	for (i = 0; i < MAX_NR_ZONES; i++)
		totalpages += zone_spanned_pages_in_node(pgdat->node_id, i,
								zones_size);
	pgdat->node_spanned_pages = totalpages;

	realtotalpages = totalpages;
	for (i = 0; i < MAX_NR_ZONES; i++)
		realtotalpages -=
			zone_absent_pages_in_node(pgdat->node_id, i,
								zholes_size);
	pgdat->node_present_pages = realtotalpages;
	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id,
							realtotalpages);
}

#ifndef CONFIG_SPARSEMEM
/*
 * Calculate the size of the zone->blockflags rounded to an unsigned long
 * Start by making sure zonesize is a multiple of pageblock_order by rounding
 * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally
 * round what is now in bits to nearest long in bits, then return it in
 * bytes.
 */
static unsigned long __init usemap_size(unsigned long zonesize)
{
	unsigned long usemapsize;

	usemapsize = roundup(zonesize, pageblock_nr_pages);
	usemapsize = usemapsize >> pageblock_order;
	usemapsize *= NR_PAGEBLOCK_BITS;
	usemapsize = roundup(usemapsize, 8 * sizeof(unsigned long));

	return usemapsize / 8;
}

static void __init setup_usemap(struct pglist_data *pgdat,
				struct zone *zone, unsigned long zonesize)
{
	unsigned long usemapsize = usemap_size(zonesize);
	zone->pageblock_flags = NULL;
	if (usemapsize)
		zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize);
}
#else
static inline void setup_usemap(struct pglist_data *pgdat,
				struct zone *zone, unsigned long zonesize) {}
#endif /* CONFIG_SPARSEMEM */

#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE

/* Return a sensible default order for the pageblock size. */
static inline int pageblock_default_order(void)
{
	if (HPAGE_SHIFT > PAGE_SHIFT)
		return HUGETLB_PAGE_ORDER;

	return MAX_ORDER-1;
}

/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
static inline void __init set_pageblock_order(unsigned int order)
{
	/* Check that pageblock_nr_pages has not already been setup */
	if (pageblock_order)
		return;

	/*
	 * Assume the largest contiguous order of interest is a huge page.
	 * This value may be variable depending on boot parameters on IA64
	 */
	pageblock_order = order;
}
#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */

/*
 * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
 * and pageblock_default_order() are unused as pageblock_order is set
 * at compile-time. See include/linux/pageblock-flags.h for the values of
 * pageblock_order based on the kernel config
 */
static inline int pageblock_default_order(unsigned int order)
{
	return MAX_ORDER-1;
}
#define set_pageblock_order(x)	do {} while (0)

#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */

/*
 * Set up the zone data structures:
 *   - mark all pages reserved
 *   - mark all memory queues empty
 *   - clear the memory bitmaps
 */
static void __paginginit free_area_init_core(struct pglist_data *pgdat,
		unsigned long *zones_size, unsigned long *zholes_size)
{
	enum zone_type j;
	int nid = pgdat->node_id;
	unsigned long zone_start_pfn = pgdat->node_start_pfn;
	int ret;

	pgdat_resize_init(pgdat);
	pgdat->nr_zones = 0;
	init_waitqueue_head(&pgdat->kswapd_wait);
	pgdat->kswapd_max_order = 0;
	pgdat_page_cgroup_init(pgdat);
	
	for (j = 0; j < MAX_NR_ZONES; j++) {
		struct zone *zone = pgdat->node_zones + j;
		unsigned long size, realsize, memmap_pages;
		enum lru_list l;

		size = zone_spanned_pages_in_node(nid, j, zones_size);
		realsize = size - zone_absent_pages_in_node(nid, j,
								zholes_size);

		/*
		 * Adjust realsize so that it accounts for how much memory
		 * is used by this zone for memmap. This affects the watermark
		 * and per-cpu initialisations
		 */
		memmap_pages =
			PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
		if (realsize >= memmap_pages) {
			realsize -= memmap_pages;
			if (memmap_pages)
				printk(KERN_DEBUG
				       "  %s zone: %lu pages used for memmap\n",
				       zone_names[j], memmap_pages);
		} else
			printk(KERN_WARNING
				"  %s zone: %lu pages exceeds realsize %lu\n",
				zone_names[j], memmap_pages, realsize);

		/* Account for reserved pages */
		if (j == 0 && realsize > dma_reserve) {
			realsize -= dma_reserve;
			printk(KERN_DEBUG "  %s zone: %lu pages reserved\n",
					zone_names[0], dma_reserve);
		}

		if (!is_highmem_idx(j))
			nr_kernel_pages += realsize;
		nr_all_pages += realsize;

		zone->spanned_pages = size;
		zone->present_pages = realsize;
#ifdef CONFIG_NUMA
		zone->node = nid;
		zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio)
						/ 100;
		zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100;
#endif
		zone->name = zone_names[j];
		spin_lock_init(&zone->lock);
		spin_lock_init(&zone->lru_lock);
		zone_seqlock_init(zone);
		zone->zone_pgdat = pgdat;

		zone_pcp_init(zone);
		for_each_lru(l) {
			INIT_LIST_HEAD(&zone->lru[l].list);
			zone->reclaim_stat.nr_saved_scan[l] = 0;
		}
		zone->reclaim_stat.recent_rotated[0] = 0;
		zone->reclaim_stat.recent_rotated[1] = 0;
		zone->reclaim_stat.recent_scanned[0] = 0;
		zone->reclaim_stat.recent_scanned[1] = 0;
		zap_zone_vm_stats(zone);
		zone->flags = 0;
		if (!size)
			continue;

		set_pageblock_order(pageblock_default_order());
		setup_usemap(pgdat, zone, size);
		ret = init_currently_empty_zone(zone, zone_start_pfn,
						size, MEMMAP_EARLY);
		BUG_ON(ret);
		memmap_init(size, nid, j, zone_start_pfn);
		zone_start_pfn += size;
	}
}

static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
{
	/* Skip empty nodes */
	if (!pgdat->node_spanned_pages)
		return;

#ifdef CONFIG_FLAT_NODE_MEM_MAP
	/* ia64 gets its own node_mem_map, before this, without bootmem */
	if (!pgdat->node_mem_map) {
		unsigned long size, start, end;
		struct page *map;

		/*
		 * The zone's endpoints aren't required to be MAX_ORDER
		 * aligned but the node_mem_map endpoints must be in order
		 * for the buddy allocator to function correctly.
		 */
		start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
		end = pgdat->node_start_pfn + pgdat->node_spanned_pages;
		end = ALIGN(end, MAX_ORDER_NR_PAGES);
		size =  (end - start) * sizeof(struct page);
		map = alloc_remap(pgdat->node_id, size);
		if (!map)
			map = alloc_bootmem_node(pgdat, size);
		pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
	}
#ifndef CONFIG_NEED_MULTIPLE_NODES
	/*
	 * With no DISCONTIG, the global mem_map is just set as node 0's
	 */
	if (pgdat == NODE_DATA(0)) {
		mem_map = NODE_DATA(0)->node_mem_map;
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
		if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
			mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET);
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
	}
#endif
#endif /* CONFIG_FLAT_NODE_MEM_MAP */
}

void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
		unsigned long node_start_pfn, unsigned long *zholes_size)
{
	pg_data_t *pgdat = NODE_DATA(nid);

	pgdat->node_id = nid;
	pgdat->node_start_pfn = node_start_pfn;
	calculate_node_totalpages(pgdat, zones_size, zholes_size);

	alloc_node_mem_map(pgdat);
#ifdef CONFIG_FLAT_NODE_MEM_MAP
	printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n",
		nid, (unsigned long)pgdat,
		(unsigned long)pgdat->node_mem_map);
#endif

	free_area_init_core(pgdat, zones_size, zholes_size);
}

#ifdef CONFIG_ARCH_POPULATES_NODE_MAP

#if MAX_NUMNODES > 1
/*
 * Figure out the number of possible node ids.
 */
static void __init setup_nr_node_ids(void)
{
	unsigned int node;
	unsigned int highest = 0;

	for_each_node_mask(node, node_possible_map)
		highest = node;
	nr_node_ids = highest + 1;
}
#else
static inline void setup_nr_node_ids(void)
{
}
#endif

/**
 * add_active_range - Register a range of PFNs backed by physical memory
 * @nid: The node ID the range resides on
 * @start_pfn: The start PFN of the available physical memory
 * @end_pfn: The end PFN of the available physical memory
 *
 * These ranges are stored in an early_node_map[] and later used by
 * free_area_init_nodes() to calculate zone sizes and holes. If the
 * range spans a memory hole, it is up to the architecture to ensure
 * the memory is not freed by the bootmem allocator. If possible
 * the range being registered will be merged with existing ranges.
 */
void __init add_active_range(unsigned int nid, unsigned long start_pfn,
						unsigned long end_pfn)
{
	int i;

	mminit_dprintk(MMINIT_TRACE, "memory_register",
			"Entering add_active_range(%d, %#lx, %#lx) "
			"%d entries of %d used\n",
			nid, start_pfn, end_pfn,
			nr_nodemap_entries, MAX_ACTIVE_REGIONS);

	mminit_validate_memmodel_limits(&start_pfn, &end_pfn);

	/* Merge with existing active regions if possible */
	for (i = 0; i < nr_nodemap_entries; i++) {
		if (early_node_map[i].nid != nid)
			continue;

		/* Skip if an existing region covers this new one */
		if (start_pfn >= early_node_map[i].start_pfn &&
				end_pfn <= early_node_map[i].end_pfn)
			return;

		/* Merge forward if suitable */
		if (start_pfn <= early_node_map[i].end_pfn &&
				end_pfn > early_node_map[i].end_pfn) {
			early_node_map[i].end_pfn = end_pfn;
			return;
		}

		/* Merge backward if suitable */
		if (start_pfn < early_node_map[i].start_pfn &&
				end_pfn >= early_node_map[i].start_pfn) {
			early_node_map[i].start_pfn = start_pfn;
			return;
		}
	}

	/* Check that early_node_map is large enough */
	if (i >= MAX_ACTIVE_REGIONS) {
		printk(KERN_CRIT "More than %d memory regions, truncating\n",
							MAX_ACTIVE_REGIONS);
		return;
	}

	early_node_map[i].nid = nid;
	early_node_map[i].start_pfn = start_pfn;
	early_node_map[i].end_pfn = end_pfn;
	nr_nodemap_entries = i + 1;
}

/**
 * remove_active_range - Shrink an existing registered range of PFNs
 * @nid: The node id the range is on that should be shrunk
 * @start_pfn: The new PFN of the range
 * @end_pfn: The new PFN of the range
 *
 * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node.
 * The map is kept near the end physical page range that has already been
 * registered. This function allows an arch to shrink an existing registered
 * range.
 */
void __init remove_active_range(unsigned int nid, unsigned long start_pfn,
				unsigned long end_pfn)
{
	int i, j;
	int removed = 0;

	printk(KERN_DEBUG "remove_active_range (%d, %lu, %lu)\n",
			  nid, start_pfn, end_pfn);

	/* Find the old active region end and shrink */
	for_each_active_range_index_in_nid(i, nid) {
		if (early_node_map[i].start_pfn >= start_pfn &&
		    early_node_map[i].end_pfn <= end_pfn) {
			/* clear it */
			early_node_map[i].start_pfn = 0;
			early_node_map[i].end_pfn = 0;
			removed = 1;
			continue;
		}
		if (early_node_map[i].start_pfn < start_pfn &&
		    early_node_map[i].end_pfn > start_pfn) {
			unsigned long temp_end_pfn = early_node_map[i].end_pfn;
			early_node_map[i].end_pfn = start_pfn;
			if (temp_end_pfn > end_pfn)
				add_active_range(nid, end_pfn, temp_end_pfn);
			continue;
		}
		if (early_node_map[i].start_pfn >= start_pfn &&
		    early_node_map[i].end_pfn > end_pfn &&
		    early_node_map[i].start_pfn < end_pfn) {
			early_node_map[i].start_pfn = end_pfn;
			continue;
		}
	}

	if (!removed)
		return;

	/* remove the blank ones */
	for (i = nr_nodemap_entries - 1; i > 0; i--) {
		if (early_node_map[i].nid != nid)
			continue;
		if (early_node_map[i].end_pfn)
			continue;
		/* we found it, get rid of it */
		for (j = i; j < nr_nodemap_entries - 1; j++)
			memcpy(&early_node_map[j], &early_node_map[j+1],
				sizeof(early_node_map[j]));
		j = nr_nodemap_entries - 1;
		memset(&early_node_map[j], 0, sizeof(early_node_map[j]));
		nr_nodemap_entries--;
	}
}

/**
 * remove_all_active_ranges - Remove all currently registered regions
 *
 * During discovery, it may be found that a table like SRAT is invalid
 * and an alternative discovery method must be used. This function removes
 * all currently registered regions.
 */
void __init remove_all_active_ranges(void)
{
	memset(early_node_map, 0, sizeof(early_node_map));
	nr_nodemap_entries = 0;
}

/* Compare two active node_active_regions */
static int __init cmp_node_active_region(const void *a, const void *b)
{
	struct node_active_region *arange = (struct node_active_region *)a;
	struct node_active_region *brange = (struct node_active_region *)b;

	/* Done this way to avoid overflows */
	if (arange->start_pfn > brange->start_pfn)
		return 1;
	if (arange->start_pfn < brange->start_pfn)
		return -1;

	return 0;
}

/* sort the node_map by start_pfn */
void __init sort_node_map(void)
{
	sort(early_node_map, (size_t)nr_nodemap_entries,
			sizeof(struct node_active_region),
			cmp_node_active_region, NULL);
}

/* Find the lowest pfn for a node */
static unsigned long __init find_min_pfn_for_node(int nid)
{
	int i;
	unsigned long min_pfn = ULONG_MAX;

	/* Assuming a sorted map, the first range found has the starting pfn */
	for_each_active_range_index_in_nid(i, nid)
		min_pfn = min(min_pfn, early_node_map[i].start_pfn);

	if (min_pfn == ULONG_MAX) {
		printk(KERN_WARNING
			"Could not find start_pfn for node %d\n", nid);
		return 0;
	}

	return min_pfn;
}

/**
 * find_min_pfn_with_active_regions - Find the minimum PFN registered
 *
 * It returns the minimum PFN based on information provided via
 * add_active_range().
 */
unsigned long __init find_min_pfn_with_active_regions(void)
{
	return find_min_pfn_for_node(MAX_NUMNODES);
}

/*
 * early_calculate_totalpages()
 * Sum pages in active regions for movable zone.
 * Populate N_HIGH_MEMORY for calculating usable_nodes.
 */
static unsigned long __init early_calculate_totalpages(void)
{
	int i;
	unsigned long totalpages = 0;

	for (i = 0; i < nr_nodemap_entries; i++) {
		unsigned long pages = early_node_map[i].end_pfn -
						early_node_map[i].start_pfn;
		totalpages += pages;
		if (pages)
			node_set_state(early_node_map[i].nid, N_HIGH_MEMORY);
	}
  	return totalpages;
}

/*
 * Find the PFN the Movable zone begins in each node. Kernel memory
 * is spread evenly between nodes as long as the nodes have enough
 * memory. When they don't, some nodes will have more kernelcore than
 * others
 */
static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
{
	int i, nid;
	unsigned long usable_startpfn;
	unsigned long kernelcore_node, kernelcore_remaining;
	/* save the state before borrow the nodemask */
	nodemask_t saved_node_state = node_states[N_HIGH_MEMORY];
	unsigned long totalpages = early_calculate_totalpages();
	int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);

	/*
	 * If movablecore was specified, calculate what size of
	 * kernelcore that corresponds so that memory usable for
	 * any allocation type is evenly spread. If both kernelcore
	 * and movablecore are specified, then the value of kernelcore
	 * will be used for required_kernelcore if it's greater than
	 * what movablecore would have allowed.
	 */
	if (required_movablecore) {
		unsigned long corepages;

		/*
		 * Round-up so that ZONE_MOVABLE is at least as large as what
		 * was requested by the user
		 */
		required_movablecore =
			roundup(required_movablecore, MAX_ORDER_NR_PAGES);
		corepages = totalpages - required_movablecore;

		required_kernelcore = max(required_kernelcore, corepages);
	}

	/* If kernelcore was not specified, there is no ZONE_MOVABLE */
	if (!required_kernelcore)
		goto out;

	/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
	find_usable_zone_for_movable();
	usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];

restart:
	/* Spread kernelcore memory as evenly as possible throughout nodes */
	kernelcore_node = required_kernelcore / usable_nodes;
	for_each_node_state(nid, N_HIGH_MEMORY) {
		/*
		 * Recalculate kernelcore_node if the division per node
		 * now exceeds what is necessary to satisfy the requested
		 * amount of memory for the kernel
		 */
		if (required_kernelcore < kernelcore_node)
			kernelcore_node = required_kernelcore / usable_nodes;

		/*
		 * As the map is walked, we track how much memory is usable
		 * by the kernel using kernelcore_remaining. When it is
		 * 0, the rest of the node is usable by ZONE_MOVABLE
		 */
		kernelcore_remaining = kernelcore_node;

		/* Go through each range of PFNs within this node */
		for_each_active_range_index_in_nid(i, nid) {
			unsigned long start_pfn, end_pfn;
			unsigned long size_pages;

			start_pfn = max(early_node_map[i].start_pfn,
						zone_movable_pfn[nid]);
			end_pfn = early_node_map[i].end_pfn;
			if (start_pfn >= end_pfn)
				continue;

			/* Account for what is only usable for kernelcore */
			if (start_pfn < usable_startpfn) {
				unsigned long kernel_pages;
				kernel_pages = min(end_pfn, usable_startpfn)
								- start_pfn;

				kernelcore_remaining -= min(kernel_pages,
							kernelcore_remaining);
				required_kernelcore -= min(kernel_pages,
							required_kernelcore);

				/* Continue if range is now fully accounted */
				if (end_pfn <= usable_startpfn) {

					/*
					 * Push zone_movable_pfn to the end so
					 * that if we have to rebalance
					 * kernelcore across nodes, we will
					 * not double account here
					 */
					zone_movable_pfn[nid] = end_pfn;
					continue;
				}
				start_pfn = usable_startpfn;
			}

			/*
			 * The usable PFN range for ZONE_MOVABLE is from
			 * start_pfn->end_pfn. Calculate size_pages as the
			 * number of pages used as kernelcore
			 */
			size_pages = end_pfn - start_pfn;
			if (size_pages > kernelcore_remaining)
				size_pages = kernelcore_remaining;
			zone_movable_pfn[nid] = start_pfn + size_pages;

			/*
			 * Some kernelcore has been met, update counts and
			 * break if the kernelcore for this node has been
			 * satisified
			 */
			required_kernelcore -= min(required_kernelcore,
								size_pages);
			kernelcore_remaining -= size_pages;
			if (!kernelcore_remaining)
				break;
		}
	}

	/*
	 * If there is still required_kernelcore, we do another pass with one
	 * less node in the count. This will push zone_movable_pfn[nid] further
	 * along on the nodes that still have memory until kernelcore is
	 * satisified
	 */
	usable_nodes--;
	if (usable_nodes && required_kernelcore > usable_nodes)
		goto restart;

	/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
	for (nid = 0; nid < MAX_NUMNODES; nid++)
		zone_movable_pfn[nid] =
			roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);

out:
	/* restore the node_state */
	node_states[N_HIGH_MEMORY] = saved_node_state;
}

/* Any regular memory on that node ? */
static void check_for_regular_memory(pg_data_t *pgdat)
{
#ifdef CONFIG_HIGHMEM
	enum zone_type zone_type;

	for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
		struct zone *zone = &pgdat->node_zones[zone_type];
		if (zone->present_pages)
			node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
	}
#endif
}

/**
 * free_area_init_nodes - Initialise all pg_data_t and zone data
 * @max_zone_pfn: an array of max PFNs for each zone
 *
 * This will call free_area_init_node() for each active node in the system.
 * Using the page ranges provided by add_active_range(), the size of each
 * zone in each node and their holes is calculated. If the maximum PFN
 * between two adjacent zones match, it is assumed that the zone is empty.
 * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed
 * that arch_max_dma32_pfn has no pages. It is also assumed that a zone
 * starts where the previous one ended. For example, ZONE_DMA32 starts
 * at arch_max_dma_pfn.
 */
void __init free_area_init_nodes(unsigned long *max_zone_pfn)
{
	unsigned long nid;
	int i;

	/* Sort early_node_map as initialisation assumes it is sorted */
	sort_node_map();

	/* Record where the zone boundaries are */
	memset(arch_zone_lowest_possible_pfn, 0,
				sizeof(arch_zone_lowest_possible_pfn));
	memset(arch_zone_highest_possible_pfn, 0,
				sizeof(arch_zone_highest_possible_pfn));
	arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions();
	arch_zone_highest_possible_pfn[0] = max_zone_pfn[0];
	for (i = 1; i < MAX_NR_ZONES; i++) {
		if (i == ZONE_MOVABLE)
			continue;
		arch_zone_lowest_possible_pfn[i] =
			arch_zone_highest_possible_pfn[i-1];
		arch_zone_highest_possible_pfn[i] =
			max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]);
	}
	arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0;
	arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0;

	/* Find the PFNs that ZONE_MOVABLE begins at in each node */
	memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
	find_zone_movable_pfns_for_nodes(zone_movable_pfn);

	/* Print out the zone ranges */
	printk("Zone PFN ranges:\n");
	for (i = 0; i < MAX_NR_ZONES; i++) {
		if (i == ZONE_MOVABLE)
			continue;
		printk("  %-8s ", zone_names[i]);
		if (arch_zone_lowest_possible_pfn[i] ==
				arch_zone_highest_possible_pfn[i])
			printk("empty\n");
		else
			printk("%0#10lx -> %0#10lx\n",
				arch_zone_lowest_possible_pfn[i],
				arch_zone_highest_possible_pfn[i]);
	}

	/* Print out the PFNs ZONE_MOVABLE begins at in each node */
	printk("Movable zone start PFN for each node\n");
	for (i = 0; i < MAX_NUMNODES; i++) {
		if (zone_movable_pfn[i])
			printk("  Node %d: %lu\n", i, zone_movable_pfn[i]);
	}

	/* Print out the early_node_map[] */
	printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
	for (i = 0; i < nr_nodemap_entries; i++)
		printk("  %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid,
						early_node_map[i].start_pfn,
						early_node_map[i].end_pfn);

	/* Initialise every node */
	mminit_verify_pageflags_layout();
	setup_nr_node_ids();
	for_each_online_node(nid) {
		pg_data_t *pgdat = NODE_DATA(nid);
		free_area_init_node(nid, NULL,
				find_min_pfn_for_node(nid), NULL);

		/* Any memory on that node */
		if (pgdat->node_present_pages)
			node_set_state(nid, N_HIGH_MEMORY);
		check_for_regular_memory(pgdat);
	}
}

static int __init cmdline_parse_core(char *p, unsigned long *core)
{
	unsigned long long coremem;
	if (!p)
		return -EINVAL;

	coremem = memparse(p, &p);
	*core = coremem >> PAGE_SHIFT;

	/* Paranoid check that UL is enough for the coremem value */
	WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);

	return 0;
}

/*
 * kernelcore=size sets the amount of memory for use for allocations that
 * cannot be reclaimed or migrated.
 */
static int __init cmdline_parse_kernelcore(char *p)
{
	return cmdline_parse_core(p, &required_kernelcore);
}

/*
 * movablecore=size sets the amount of memory for use for allocations that
 * can be reclaimed or migrated.
 */
static int __init cmdline_parse_movablecore(char *p)
{
	return cmdline_parse_core(p, &required_movablecore);
}

early_param("kernelcore", cmdline_parse_kernelcore);
early_param("movablecore", cmdline_parse_movablecore);

#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */

/**
 * set_dma_reserve - set the specified number of pages reserved in the first zone
 * @new_dma_reserve: The number of pages to mark reserved
 *
 * The per-cpu batchsize and zone watermarks are determined by present_pages.
 * In the DMA zone, a significant percentage may be consumed by kernel image
 * and other unfreeable allocations which can skew the watermarks badly. This
 * function may optionally be used to account for unfreeable pages in the
 * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and
 * smaller per-cpu batchsize.
 */
void __init set_dma_reserve(unsigned long new_dma_reserve)
{
	dma_reserve = new_dma_reserve;
}

void __init free_area_init(unsigned long *zones_size)
{
	free_area_init_node(0, zones_size,
			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
}

static int page_alloc_cpu_notify(struct notifier_block *self,
				 unsigned long action, void *hcpu)
{
	int cpu = (unsigned long)hcpu;

	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
		drain_pages(cpu);

		/*
		 * Spill the event counters of the dead processor
		 * into the current processors event counters.
		 * This artificially elevates the count of the current
		 * processor.
		 */
		vm_events_fold_cpu(cpu);

		/*
		 * Zero the differential counters of the dead processor
		 * so that the vm statistics are consistent.
		 *
		 * This is only okay since the processor is dead and cannot
		 * race with what we are doing.
		 */
		refresh_cpu_vm_stats(cpu);
	}
	return NOTIFY_OK;
}

void __init page_alloc_init(void)
{
	hotcpu_notifier(page_alloc_cpu_notify, 0);
}

/*
 * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio
 *	or min_free_kbytes changes.
 */
static void calculate_totalreserve_pages(void)
{
	struct pglist_data *pgdat;
	unsigned long reserve_pages = 0;
	enum zone_type i, j;

	for_each_online_pgdat(pgdat) {
		for (i = 0; i < MAX_NR_ZONES; i++) {
			struct zone *zone = pgdat->node_zones + i;
			unsigned long max = 0;

			/* Find valid and maximum lowmem_reserve in the zone */
			for (j = i; j < MAX_NR_ZONES; j++) {
				if (zone->lowmem_reserve[j] > max)
					max = zone->lowmem_reserve[j];
			}

			/* we treat the high watermark as reserved pages. */
			max += high_wmark_pages(zone);

			if (max > zone->present_pages)
				max = zone->present_pages;
			reserve_pages += max;
		}
	}
	totalreserve_pages = reserve_pages;
}

/*
 * setup_per_zone_lowmem_reserve - called whenever
 *	sysctl_lower_zone_reserve_ratio changes.  Ensures that each zone
 *	has a correct pages reserved value, so an adequate number of
 *	pages are left in the zone after a successful __alloc_pages().
 */
static void setup_per_zone_lowmem_reserve(void)
{
	struct pglist_data *pgdat;
	enum zone_type j, idx;

	for_each_online_pgdat(pgdat) {
		for (j = 0; j < MAX_NR_ZONES; j++) {
			struct zone *zone = pgdat->node_zones + j;
			unsigned long present_pages = zone->present_pages;

			zone->lowmem_reserve[j] = 0;

			idx = j;
			while (idx) {
				struct zone *lower_zone;

				idx--;

				if (sysctl_lowmem_reserve_ratio[idx] < 1)
					sysctl_lowmem_reserve_ratio[idx] = 1;

				lower_zone = pgdat->node_zones + idx;
				lower_zone->lowmem_reserve[j] = present_pages /
					sysctl_lowmem_reserve_ratio[idx];
				present_pages += lower_zone->present_pages;
			}
		}
	}

	/* update totalreserve_pages */
	calculate_totalreserve_pages();
}

/**
 * setup_per_zone_wmarks - called when min_free_kbytes changes
 * or when memory is hot-{added|removed}
 *
 * Ensures that the watermark[min,low,high] values for each zone are set
 * correctly with respect to min_free_kbytes.
 */
void setup_per_zone_wmarks(void)
{
	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
	unsigned long lowmem_pages = 0;
	struct zone *zone;
	unsigned long flags;

	/* Calculate total number of !ZONE_HIGHMEM pages */
	for_each_zone(zone) {
		if (!is_highmem(zone))
			lowmem_pages += zone->present_pages;
	}

	for_each_zone(zone) {
		u64 tmp;

		spin_lock_irqsave(&zone->lock, flags);
		tmp = (u64)pages_min * zone->present_pages;
		do_div(tmp, lowmem_pages);
		if (is_highmem(zone)) {
			/*
			 * __GFP_HIGH and PF_MEMALLOC allocations usually don't
			 * need highmem pages, so cap pages_min to a small
			 * value here.
			 *
			 * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
			 * deltas controls asynch page reclaim, and so should
			 * not be capped for highmem.
			 */
			int min_pages;

			min_pages = zone->present_pages / 1024;
			if (min_pages < SWAP_CLUSTER_MAX)
				min_pages = SWAP_CLUSTER_MAX;
			if (min_pages > 128)
				min_pages = 128;
			zone->watermark[WMARK_MIN] = min_pages;
		} else {
			/*
			 * If it's a lowmem zone, reserve a number of pages
			 * proportionate to the zone's size.
			 */
			zone->watermark[WMARK_MIN] = tmp;
		}

		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
		setup_zone_migrate_reserve(zone);
		spin_unlock_irqrestore(&zone->lock, flags);
	}

	/* update totalreserve_pages */
	calculate_totalreserve_pages();
}

/*
 * The inactive anon list should be small enough that the VM never has to
 * do too much work, but large enough that each inactive page has a chance
 * to be referenced again before it is swapped out.
 *
 * The inactive_anon ratio is the target ratio of ACTIVE_ANON to
 * INACTIVE_ANON pages on this zone's LRU, maintained by the
 * pageout code. A zone->inactive_ratio of 3 means 3:1 or 25% of
 * the anonymous pages are kept on the inactive list.
 *
 * total     target    max
 * memory    ratio     inactive anon
 * -------------------------------------
 *   10MB       1         5MB
 *  100MB       1        50MB
 *    1GB       3       250MB
 *   10GB      10       0.9GB
 *  100GB      31         3GB
 *    1TB     101        10GB
 *   10TB     320        32GB
 */
void calculate_zone_inactive_ratio(struct zone *zone)
{
	unsigned int gb, ratio;

	/* Zone size in gigabytes */
	gb = zone->present_pages >> (30 - PAGE_SHIFT);
	if (gb)
		ratio = int_sqrt(10 * gb);
	else
		ratio = 1;

	zone->inactive_ratio = ratio;
}

static void __init setup_per_zone_inactive_ratio(void)
{
	struct zone *zone;

	for_each_zone(zone)
		calculate_zone_inactive_ratio(zone);
}

/*
 * Initialise min_free_kbytes.
 *
 * For small machines we want it small (128k min).  For large machines
 * we want it large (64MB max).  But it is not linear, because network
 * bandwidth does not increase linearly with machine size.  We use
 *
 * 	min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
 *	min_free_kbytes = sqrt(lowmem_kbytes * 16)
 *
 * which yields
 *
 * 16MB:	512k
 * 32MB:	724k
 * 64MB:	1024k
 * 128MB:	1448k
 * 256MB:	2048k
 * 512MB:	2896k
 * 1024MB:	4096k
 * 2048MB:	5792k
 * 4096MB:	8192k
 * 8192MB:	11584k
 * 16384MB:	16384k
 */
static int __init init_per_zone_wmark_min(void)
{
	unsigned long lowmem_kbytes;

	lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);

	min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
	if (min_free_kbytes < 128)
		min_free_kbytes = 128;
	if (min_free_kbytes > 65536)
		min_free_kbytes = 65536;
	setup_per_zone_wmarks();
	setup_per_zone_lowmem_reserve();
	setup_per_zone_inactive_ratio();
	return 0;
}
module_init(init_per_zone_wmark_min)

/*
 * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so 
 *	that we can call two helper functions whenever min_free_kbytes
 *	changes.
 */
int min_free_kbytes_sysctl_handler(ctl_table *table, int write, 
	void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec(table, write, buffer, length, ppos);
	if (write)
		setup_per_zone_wmarks();
	return 0;
}

#ifdef CONFIG_NUMA
int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	struct zone *zone;
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	for_each_zone(zone)
		zone->min_unmapped_pages = (zone->present_pages *
				sysctl_min_unmapped_ratio) / 100;
	return 0;
}

int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	struct zone *zone;
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	for_each_zone(zone)
		zone->min_slab_pages = (zone->present_pages *
				sysctl_min_slab_ratio) / 100;
	return 0;
}
#endif

/*
 * lowmem_reserve_ratio_sysctl_handler - just a wrapper around
 *	proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
 *	whenever sysctl_lowmem_reserve_ratio changes.
 *
 * The reserve ratio obviously has absolutely no relation with the
 * minimum watermarks. The lowmem reserve ratio can only make sense
 * if in function of the boot time zone sizes.
 */
int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec_minmax(table, write, buffer, length, ppos);
	setup_per_zone_lowmem_reserve();
	return 0;
}

/*
 * percpu_pagelist_fraction - changes the pcp->high for each zone on each
 * cpu.  It is the fraction of total pages in each zone that a hot per cpu pagelist
 * can have before it gets flushed back to buddy allocator.
 */

int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	struct zone *zone;
	unsigned int cpu;
	int ret;

	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (!write || (ret == -EINVAL))
		return ret;
	for_each_populated_zone(zone) {
		for_each_possible_cpu(cpu) {
			unsigned long  high;
			high = zone->present_pages / percpu_pagelist_fraction;
			setup_pagelist_highmark(
				per_cpu_ptr(zone->pageset, cpu), high);
		}
	}
	return 0;
}

int hashdist = HASHDIST_DEFAULT;

#ifdef CONFIG_NUMA
static int __init set_hashdist(char *str)
{
	if (!str)
		return 0;
	hashdist = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("hashdist=", set_hashdist);
#endif

/*
 * allocate a large system hash table from bootmem
 * - it is assumed that the hash table must contain an exact power-of-2
 *   quantity of entries
 * - limit is the number of hash buckets, not the total allocation size
 */
void *__init alloc_large_system_hash(const char *tablename,
				     unsigned long bucketsize,
				     unsigned long numentries,
				     int scale,
				     int flags,
				     unsigned int *_hash_shift,
				     unsigned int *_hash_mask,
				     unsigned long limit)
{
	unsigned long long max = limit;
	unsigned long log2qty, size;
	void *table = NULL;

	/* allow the kernel cmdline to have a say */
	if (!numentries) {
		/* round applicable memory size up to nearest megabyte */
		numentries = nr_kernel_pages;
		numentries += (1UL << (20 - PAGE_SHIFT)) - 1;
		numentries >>= 20 - PAGE_SHIFT;
		numentries <<= 20 - PAGE_SHIFT;

		/* limit to 1 bucket per 2^scale bytes of low memory */
		if (scale > PAGE_SHIFT)
			numentries >>= (scale - PAGE_SHIFT);
		else
			numentries <<= (PAGE_SHIFT - scale);

		/* Make sure we've got at least a 0-order allocation.. */
		if (unlikely(flags & HASH_SMALL)) {
			/* Makes no sense without HASH_EARLY */
			WARN_ON(!(flags & HASH_EARLY));
			if (!(numentries >> *_hash_shift)) {
				numentries = 1UL << *_hash_shift;
				BUG_ON(!numentries);
			}
		} else if (unlikely((numentries * bucketsize) < PAGE_SIZE))
			numentries = PAGE_SIZE / bucketsize;
	}
	numentries = roundup_pow_of_two(numentries);

	/* limit allocation size to 1/16 total memory by default */
	if (max == 0) {
		max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
		do_div(max, bucketsize);
	}

	if (numentries > max)
		numentries = max;

	log2qty = ilog2(numentries);

	do {
		size = bucketsize << log2qty;
		if (flags & HASH_EARLY)
			table = alloc_bootmem_nopanic(size);
		else if (hashdist)
			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
		else {
			/*
			 * If bucketsize is not a power-of-two, we may free
			 * some pages at the end of hash table which
			 * alloc_pages_exact() automatically does
			 */
			if (get_order(size) < MAX_ORDER) {
				table = alloc_pages_exact(size, GFP_ATOMIC);
				kmemleak_alloc(table, size, 1, GFP_ATOMIC);
			}
		}
	} while (!table && size > PAGE_SIZE && --log2qty);

	if (!table)
		panic("Failed to allocate %s hash table\n", tablename);

	printk(KERN_INFO "%s hash table entries: %ld (order: %d, %lu bytes)\n",
	       tablename,
	       (1UL << log2qty),
	       ilog2(size) - PAGE_SHIFT,
	       size);

	if (_hash_shift)
		*_hash_shift = log2qty;
	if (_hash_mask)
		*_hash_mask = (1 << log2qty) - 1;

	return table;
}

/* Return a pointer to the bitmap storing bits affecting a block of pages */
static inline unsigned long *get_pageblock_bitmap(struct zone *zone,
							unsigned long pfn)
{
#ifdef CONFIG_SPARSEMEM
	return __pfn_to_section(pfn)->pageblock_flags;
#else
	return zone->pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
}

static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
{
#ifdef CONFIG_SPARSEMEM
	pfn &= (PAGES_PER_SECTION-1);
	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#else
	pfn = pfn - zone->zone_start_pfn;
	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#endif /* CONFIG_SPARSEMEM */
}

/**
 * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages
 * @page: The page within the block of interest
 * @start_bitidx: The first bit of interest to retrieve
 * @end_bitidx: The last bit of interest
 * returns pageblock_bits flags
 */
unsigned long get_pageblock_flags_group(struct page *page,
					int start_bitidx, int end_bitidx)
{
	struct zone *zone;
	unsigned long *bitmap;
	unsigned long pfn, bitidx;
	unsigned long flags = 0;
	unsigned long value = 1;

	zone = page_zone(page);
	pfn = page_to_pfn(page);
	bitmap = get_pageblock_bitmap(zone, pfn);
	bitidx = pfn_to_bitidx(zone, pfn);

	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
		if (test_bit(bitidx + start_bitidx, bitmap))
			flags |= value;

	return flags;
}

/**
 * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages
 * @page: The page within the block of interest
 * @start_bitidx: The first bit of interest
 * @end_bitidx: The last bit of interest
 * @flags: The flags to set
 */
void set_pageblock_flags_group(struct page *page, unsigned long flags,
					int start_bitidx, int end_bitidx)
{
	struct zone *zone;
	unsigned long *bitmap;
	unsigned long pfn, bitidx;
	unsigned long value = 1;

	zone = page_zone(page);
	pfn = page_to_pfn(page);
	bitmap = get_pageblock_bitmap(zone, pfn);
	bitidx = pfn_to_bitidx(zone, pfn);
	VM_BUG_ON(pfn < zone->zone_start_pfn);
	VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages);

	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
		if (flags & value)
			__set_bit(bitidx + start_bitidx, bitmap);
		else
			__clear_bit(bitidx + start_bitidx, bitmap);
}

/*
 * This is designed as sub function...plz see page_isolation.c also.
 * set/clear page block's type to be ISOLATE.
 * page allocater never alloc memory from ISOLATE block.
 */

static int
__count_immobile_pages(struct zone *zone, struct page *page, int count)
{
	unsigned long pfn, iter, found;
	/*
	 * For avoiding noise data, lru_add_drain_all() should be called
	 * If ZONE_MOVABLE, the zone never contains immobile pages
	 */
	if (zone_idx(zone) == ZONE_MOVABLE)
		return true;

	if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE)
		return true;

	pfn = page_to_pfn(page);
	for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
		unsigned long check = pfn + iter;

		if (!pfn_valid_within(check))
			continue;

		page = pfn_to_page(check);
		if (!page_count(page)) {
			if (PageBuddy(page))
				iter += (1 << page_order(page)) - 1;
			continue;
		}
		if (!PageLRU(page))
			found++;
		/*
		 * If there are RECLAIMABLE pages, we need to check it.
		 * But now, memory offline itself doesn't call shrink_slab()
		 * and it still to be fixed.
		 */
		/*
		 * If the page is not RAM, page_count()should be 0.
		 * we don't need more check. This is an _used_ not-movable page.
		 *
		 * The problematic thing here is PG_reserved pages. PG_reserved
		 * is set to both of a memory hole page and a _used_ kernel
		 * page at boot.
		 */
		if (found > count)
			return false;
	}
	return true;
}

bool is_pageblock_removable_nolock(struct page *page)
{
	struct zone *zone = page_zone(page);
	return __count_immobile_pages(zone, page, 0);
}

int set_migratetype_isolate(struct page *page)
{
	struct zone *zone;
	unsigned long flags, pfn;
	struct memory_isolate_notify arg;
	int notifier_ret;
	int ret = -EBUSY;
	int zone_idx;

	zone = page_zone(page);
	zone_idx = zone_idx(zone);

	spin_lock_irqsave(&zone->lock, flags);

	pfn = page_to_pfn(page);
	arg.start_pfn = pfn;
	arg.nr_pages = pageblock_nr_pages;
	arg.pages_found = 0;

	/*
	 * It may be possible to isolate a pageblock even if the
	 * migratetype is not MIGRATE_MOVABLE. The memory isolation
	 * notifier chain is used by balloon drivers to return the
	 * number of pages in a range that are held by the balloon
	 * driver to shrink memory. If all the pages are accounted for
	 * by balloons, are free, or on the LRU, isolation can continue.
	 * Later, for example, when memory hotplug notifier runs, these
	 * pages reported as "can be isolated" should be isolated(freed)
	 * by the balloon driver through the memory notifier chain.
	 */
	notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
	notifier_ret = notifier_to_errno(notifier_ret);
	if (notifier_ret)
		goto out;
	/*
	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
	 * We just check MOVABLE pages.
	 */
	if (__count_immobile_pages(zone, page, arg.pages_found))
		ret = 0;

	/*
	 * immobile means "not-on-lru" paes. If immobile is larger than
	 * removable-by-driver pages reported by notifier, we'll fail.
	 */

out:
	if (!ret) {
		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
		move_freepages_block(zone, page, MIGRATE_ISOLATE);
	}

	spin_unlock_irqrestore(&zone->lock, flags);
	if (!ret)
		drain_all_pages();
	return ret;
}

void unset_migratetype_isolate(struct page *page)
{
	struct zone *zone;
	unsigned long flags;
	zone = page_zone(page);
	spin_lock_irqsave(&zone->lock, flags);
	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
		goto out;
	set_pageblock_migratetype(page, MIGRATE_MOVABLE);
	move_freepages_block(zone, page, MIGRATE_MOVABLE);
out:
	spin_unlock_irqrestore(&zone->lock, flags);
}

#ifdef CONFIG_MEMORY_HOTREMOVE
/*
 * All pages in the range must be isolated before calling this.
 */
void
__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
	struct page *page;
	struct zone *zone;
	int order, i;
	unsigned long pfn;
	unsigned long flags;
	/* find the first valid pfn */
	for (pfn = start_pfn; pfn < end_pfn; pfn++)
		if (pfn_valid(pfn))
			break;
	if (pfn == end_pfn)
		return;
	zone = page_zone(pfn_to_page(pfn));
	spin_lock_irqsave(&zone->lock, flags);
	pfn = start_pfn;
	while (pfn < end_pfn) {
		if (!pfn_valid(pfn)) {
			pfn++;
			continue;
		}
		page = pfn_to_page(pfn);
		BUG_ON(page_count(page));
		BUG_ON(!PageBuddy(page));
		order = page_order(page);
#ifdef CONFIG_DEBUG_VM
		printk(KERN_INFO "remove from free list %lx %d %lx\n",
		       pfn, 1 << order, end_pfn);
#endif
		list_del(&page->lru);
		rmv_page_order(page);
		zone->free_area[order].nr_free--;
		__mod_zone_page_state(zone, NR_FREE_PAGES,
				      - (1UL << order));
		for (i = 0; i < (1 << order); i++)
			SetPageReserved((page+i));
		pfn += (1 << order);
	}
	spin_unlock_irqrestore(&zone->lock, flags);
}
#endif

#ifdef CONFIG_MEMORY_FAILURE
bool is_free_buddy_page(struct page *page)
{
	struct zone *zone = page_zone(page);
	unsigned long pfn = page_to_pfn(page);
	unsigned long flags;
	int order;

	spin_lock_irqsave(&zone->lock, flags);
	for (order = 0; order < MAX_ORDER; order++) {
		struct page *page_head = page - (pfn & ((1 << order) - 1));

		if (PageBuddy(page_head) && page_order(page_head) >= order)
			break;
	}
	spin_unlock_irqrestore(&zone->lock, flags);

	return order < MAX_ORDER;
}
#endif

static struct trace_print_flags pageflag_names[] = {
	{1UL << PG_locked,		"locked"	},
	{1UL << PG_error,		"error"		},
	{1UL << PG_referenced,		"referenced"	},
	{1UL << PG_uptodate,		"uptodate"	},
	{1UL << PG_dirty,		"dirty"		},
	{1UL << PG_lru,			"lru"		},
	{1UL << PG_active,		"active"	},
	{1UL << PG_slab,		"slab"		},
	{1UL << PG_owner_priv_1,	"owner_priv_1"	},
	{1UL << PG_arch_1,		"arch_1"	},
	{1UL << PG_reserved,		"reserved"	},
	{1UL << PG_private,		"private"	},
	{1UL << PG_private_2,		"private_2"	},
	{1UL << PG_writeback,		"writeback"	},
#ifdef CONFIG_PAGEFLAGS_EXTENDED
	{1UL << PG_head,		"head"		},
	{1UL << PG_tail,		"tail"		},
#else
	{1UL << PG_compound,		"compound"	},
#endif
	{1UL << PG_swapcache,		"swapcache"	},
	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
	{1UL << PG_reclaim,		"reclaim"	},
	{1UL << PG_swapbacked,		"swapbacked"	},
	{1UL << PG_unevictable,		"unevictable"	},
#ifdef CONFIG_MMU
	{1UL << PG_mlocked,		"mlocked"	},
#endif
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
	{1UL << PG_uncached,		"uncached"	},
#endif
#ifdef CONFIG_MEMORY_FAILURE
	{1UL << PG_hwpoison,		"hwpoison"	},
#endif
	{-1UL,				NULL		},
};

static void dump_page_flags(unsigned long flags)
{
	const char *delim = "";
	unsigned long mask;
	int i;

	printk(KERN_ALERT "page flags: %#lx(", flags);

	/* remove zone id */
	flags &= (1UL << NR_PAGEFLAGS) - 1;

	for (i = 0; pageflag_names[i].name && flags; i++) {

		mask = pageflag_names[i].mask;
		if ((flags & mask) != mask)
			continue;

		flags &= ~mask;
		printk("%s%s", delim, pageflag_names[i].name);
		delim = "|";
	}

	/* check for left over flags */
	if (flags)
		printk("%s%#lx", delim, flags);

	printk(")\n");
}

void dump_page(struct page *page)
{
	printk(KERN_ALERT
	       "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
		page, atomic_read(&page->_count), page_mapcount(page),
		page->mapping, page->index);
	dump_page_flags(page->flags);
}