page_alloc.c

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

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

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

/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);

#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
#ifdef CONFIG_MOVABLE_NODE
	[N_MEMORY] = { { [0] = 1UL } },
#endif
	[N_CPU] = { { [0] = 1UL } },
#endif	/* NUMA */
};
EXPORT_SYMBOL(node_states);

/* Protect totalram_pages and zone->managed_pages */
static DEFINE_SPINLOCK(managed_page_count_lock);

unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
/*
 * When calculating the number of globally allowed dirty pages, there
 * is a certain number of per-zone reserves that should not be
 * considered dirtyable memory.  This is the sum of those reserves
 * over all existing zones that contribute dirtyable memory.
 */
unsigned long dirty_balance_reserve __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;
}

bool pm_suspended_storage(void)
{
	if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
		return false;
	return true;
}
#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_HAVE_MEMBLOCK_NODE_MAP
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_HAVE_MEMBLOCK_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;

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);
	unsigned long sp, start_pfn;

	do {
		seq = zone_span_seqbegin(zone);
		start_pfn = zone->zone_start_pfn;
		sp = zone->spanned_pages;
		if (!zone_spans_pfn(zone, pfn))
			ret = 1;
	} while (zone_span_seqretry(zone, seq));

	if (ret)
		pr_err("page %lu outside zone [ %lu - %lu ]\n",
			pfn, start_pfn, start_pfn + sp);

	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)) {
		page_mapcount_reset(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);

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

/*
 * 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 tail pages have their ->first_page
 * pointing at the head page.
 *
 * 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);
		set_page_count(p, 0);
		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)) {
		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);
}

#ifdef CONFIG_DEBUG_PAGEALLOC
unsigned int _debug_guardpage_minorder;

static int __init debug_guardpage_minorder_setup(char *buf)
{
	unsigned long res;

	if (kstrtoul(buf, 10, &res) < 0 ||  res > MAX_ORDER / 2) {
		printk(KERN_ERR "Bad debug_guardpage_minorder value\n");
		return 0;
	}
	_debug_guardpage_minorder = res;
	printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res);
	return 0;
}
__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);

static inline void set_page_guard_flag(struct page *page)
{
	__set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
}

static inline void clear_page_guard_flag(struct page *page)
{
	__clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
}
#else
static inline void set_page_guard_flag(struct page *page) { }
static inline void clear_page_guard_flag(struct page *page) { }
#endif

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

	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.
 *
 * -- nyc
 */

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;

	VM_BUG_ON(!zone_is_initialized(zone));

	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 or it is CONFIG_DEBUG_PAGEALLOC guard page,
		 * merge with it and move up one order.
		 */
		if (page_is_guard(buddy)) {
			clear_page_guard_flag(buddy);
			set_page_private(page, 0);
			__mod_zone_freepage_state(zone, 1 << order,
						  migratetype);
		} else {
			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 = higher_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++;
}

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

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

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

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

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

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

		do {
			int mt;	/* migratetype of the to-be-freed page */

			page = list_entry(list->prev, struct page, lru);
			/* must delete as __free_one_page list manipulates */
			list_del(&page->lru);
			mt = get_freepage_migratetype(page);
			/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
			__free_one_page(page, zone, 0, mt);
			trace_mm_page_pcpu_drain(page, 0, mt);
			if (likely(!is_migrate_isolate_page(page))) {
				__mod_zone_page_state(zone, NR_FREE_PAGES, 1);
				if (is_migrate_cma(mt))
					__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1);
			}
		} while (--to_free && --batch_free && !list_empty(list));
	}
	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);
	if (unlikely(!is_migrate_isolate(migratetype)))
		__mod_zone_freepage_state(zone, 1 << order, migratetype);
	spin_unlock(&zone->lock);
}

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

	trace_mm_page_free(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 migratetype;

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

	local_irq_save(flags);
	__count_vm_events(PGFREE, 1 << order);
	migratetype = get_pageblock_migratetype(page);
	set_freepage_migratetype(page, migratetype);
	free_one_page(page_zone(page), page, order, migratetype);
	local_irq_restore(flags);
}

void __init __free_pages_bootmem(struct page *page, unsigned int order)
{
	unsigned int nr_pages = 1 << order;
	unsigned int loop;

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

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

	page_zone(page)->managed_pages += 1 << order;
	set_page_refcounted(page);
	__free_pages(page, order);
}

#ifdef CONFIG_CMA
/* Free whole pageblock and set it's migration type to MIGRATE_CMA. */
void __init init_cma_reserved_pageblock(struct page *page)
{
	unsigned i = pageblock_nr_pages;
	struct page *p = page;

	do {
		__ClearPageReserved(p);
		set_page_count(p, 0);
	} while (++p, --i);

	set_page_refcounted(page);
	set_pageblock_migratetype(page, MIGRATE_CMA);
	__free_pages(page, pageblock_order);
	adjust_managed_page_count(page, pageblock_nr_pages);
}
#endif

/*
 * 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.
 *
 * -- nyc
 */
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]));

#ifdef CONFIG_DEBUG_PAGEALLOC
		if (high < debug_guardpage_minorder()) {
			/*
			 * Mark as guard pages (or page), that will allow to
			 * merge back to allocator when buddy will be freed.
			 * Corresponding page table entries will not be touched,
			 * pages will stay not present in virtual address space
			 */
			INIT_LIST_HEAD(&page[size].lru);
			set_page_guard_flag(&page[size]);
			set_page_private(&page[size], high);
			/* Guard pages are not available for any usage */
			__mod_zone_freepage_state(zone, -(1 << high),
						  migratetype);
			continue;
		}
#endif
		list_add(&page[size].lru, &area->free_list[migratetype]);
		area->nr_free++;
		set_page_order(&page[size], high);
	}
}

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

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

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

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

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

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

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

	return 0;
}

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

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

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

	return NULL;
}


/*
 * This array describes the order lists are fallen back to when
 * the free lists for the desirable migrate type are depleted
 */
static int fallbacks[MIGRATE_TYPES][4] = {
	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,     MIGRATE_RESERVE },
	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,     MIGRATE_RESERVE },
#ifdef CONFIG_CMA
	[MIGRATE_MOVABLE]     = { MIGRATE_CMA,         MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
	[MIGRATE_CMA]         = { MIGRATE_RESERVE }, /* Never used */
#else
	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE,   MIGRATE_RESERVE },
#endif
	[MIGRATE_RESERVE]     = { MIGRATE_RESERVE }, /* Never used */
#ifdef CONFIG_MEMORY_ISOLATION
	[MIGRATE_ISOLATE]     = { MIGRATE_RESERVE }, /* Never used */
#endif
};

/*
 * 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()
 */
int move_freepages(struct zone *zone,
			  struct page *start_page, struct page *end_page,
			  int migratetype)
{
	struct page *page;
	unsigned long order;
	int pages_moved = 0;

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

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

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

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

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

	return pages_moved;
}

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 (!zone_spans_pfn(zone, start_pfn))
		start_page = page;
	if (!zone_spans_pfn(zone, end_pfn))
		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);