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

/*
 * 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;
unsigned long highest_memmap_pfn __read_mostly;
int percpu_pagelist_fraction;

#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;

unsigned long __meminitdata nr_kernel_pages;
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];
#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
  static unsigned long __meminitdata node_boundary_start_pfn[MAX_NUMNODES];
  static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
  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;
EXPORT_SYMBOL(nr_node_ids);
#endif

int page_group_by_mobility_disabled __read_mostly;

static void set_pageblock_migratetype(struct page *page, int migratetype)
{
	set_pageblock_flags_group(page, (unsigned long)migratetype,
					PB_migrate, PB_migrate_end);
}

#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;

	/*
	 * 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));
	printk(KERN_ALERT
		"page:%p flags:%p count:%d mapcount:%d mapping:%p index:%lx\n",
		page, (void *)page->flags, page_count(page),
		page_mapcount(page), page->mapping, page->index);

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

#ifdef CONFIG_HUGETLBFS
void prep_compound_gigantic_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;
	struct page *p = page + 1;

	set_compound_page_dtor(page, free_compound_page);
	set_compound_order(page, order);
	__SetPageHead(page);
	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
		__SetPageTail(p);
		p->first_page = page;
	}
}
#endif

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 struct page *
__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order)
{
	unsigned long buddy_idx = page_idx ^ (1 << order);

	return page + (buddy_idx - page_idx);
}

static inline unsigned long
__find_combined_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 use PG_buddy.
 * Setting, clearing, and testing PG_buddy 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) {
		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 PG_buddy. 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)
{
	unsigned long page_idx;
	int order_size = 1 << order;
	int migratetype = get_pageblock_migratetype(page);

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

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

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

	__mod_zone_page_state(zone, NR_FREE_PAGES, order_size);
	while (order < MAX_ORDER-1) {
		unsigned long combined_idx;
		struct page *buddy;

		buddy = __page_find_buddy(page, page_idx, order);
		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 = __find_combined_index(page_idx, order);
		page = page + (combined_idx - page_idx);
		page_idx = combined_idx;
		order++;
	}
	set_page_order(page, order);
	list_add(&page->lru,
		&zone->free_area[order].free_list[migratetype]);
	zone->free_area[order].nr_free++;
}

static inline int free_pages_check(struct page *page)
{
	free_page_mlock(page);
	if (unlikely(page_mapcount(page) |
		(page->mapping != NULL)  |
		(page_count(page) != 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 list of pages. 
 * 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_pages_bulk(struct zone *zone, int count,
					struct list_head *list, int order)
{
	spin_lock(&zone->lock);
	zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
	zone->pages_scanned = 0;
	while (count--) {
		struct page *page;

		VM_BUG_ON(list_empty(list));
		page = list_entry(list->prev, struct page, lru);
		/* have to delete it as __free_one_page list manipulates */
		list_del(&page->lru);
		__free_one_page(page, zone, order);
	}
	spin_unlock(&zone->lock);
}

static void free_one_page(struct zone *zone, struct page *page, int order)
{
	spin_lock(&zone->lock);
	zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
	zone->pages_scanned = 0;
	__free_one_page(page, zone, order);
	spin_unlock(&zone->lock);
}

static void __free_pages_ok(struct page *page, unsigned int order)
{
	unsigned long flags;
	int i;
	int bad = 0;

	for (i = 0 ; i < (1 << order) ; ++i)
		bad += free_pages_check(page + i);
	if (bad)
		return;

	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);

	local_irq_save(flags);
	__count_vm_events(PGFREE, 1 << order);
	free_one_page(page_zone(page), page, order);
	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 int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
{
	if (unlikely(page_mapcount(page) |
		(page->mapping != NULL)  |
		(page_count(page) != 0)  |
		(page->flags & PAGE_FLAGS_CHECK_AT_PREP))) {
		bad_page(page);
		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 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--;
		__mod_zone_page_state(zone, NR_FREE_PAGES, - (1UL << order));
		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);
}

/* Remove an element from the buddy allocator from the fallback list */
static 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) {
				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)))
					set_pageblock_migratetype(page,
								start_migratetype);

				migratetype = start_migratetype;
			}

			/* Remove the page from the freelists */
			list_del(&page->lru);
			rmv_page_order(page);
			__mod_zone_page_state(zone, NR_FREE_PAGES,
							-(1UL << order));

			if (current_order == pageblock_order)
				set_pageblock_migratetype(page,
							start_migratetype);

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

	/* Use MIGRATE_RESERVE rather than fail an allocation */
	return __rmqueue_smallest(zone, order, MIGRATE_RESERVE);
}

/*
 * 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;

	page = __rmqueue_smallest(zone, order, migratetype);

	if (unlikely(!page))
		page = __rmqueue_fallback(zone, 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 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.
		 */
		list_add(&page->lru, list);
		set_page_private(page, migratetype);
		list = &page->lru;
	}
	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_pages_bulk(zone, to_drain, &pcp->list, 0);
	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_zone(zone) {
		struct per_cpu_pageset *pset;
		struct per_cpu_pages *pcp;

		if (!populated_zone(zone))
			continue;

		pset = zone_pcp(zone, cpu);

		pcp = &pset->pcp;
		local_irq_save(flags);
		free_pages_bulk(zone, pcp->count, &pcp->list, 0);
		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
 */
static void free_hot_cold_page(struct page *page, int cold)
{
	struct zone *zone = page_zone(page);
	struct per_cpu_pages *pcp;