// SPDX-License-Identifier: GPL-2.0-only
/*
 *  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/highmem.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/jiffies.h>
#include <linux/memblock.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/kasan.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/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/memremap.h>
#include <linux/stop_machine.h>
#include <linux/random.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/debugobjects.h>
#include <linux/kmemleak.h>
#include <linux/compaction.h>
#include <trace/events/kmem.h>
#include <trace/events/oom.h>
#include <linux/prefetch.h>
#include <linux/mm_inline.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/sched/rt.h>
#include <linux/sched/mm.h>
#include <linux/page_owner.h>
#include <linux/kthread.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
#include <linux/lockdep.h>
#include <linux/nmi.h>
#include <linux/psi.h>
#include <linux/padata.h>
#include <linux/khugepaged.h>
#include <linux/buffer_head.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
#include "shuffle.h"
#include "page_reporting.h"

/* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */
typedef int __bitwise fpi_t;

/* No special request */
#define FPI_NONE                ((__force fpi_t)0)

/*
 * Skip free page reporting notification for the (possibly merged) page.
 * This does not hinder free page reporting from grabbing the page,
 * reporting it and marking it "reported" -  it only skips notifying
 * the free page reporting infrastructure about a newly freed page. For
 * example, used when temporarily pulling a page from a freelist and
 * putting it back unmodified.
 */
#define FPI_SKIP_REPORT_NOTIFY  ((__force fpi_t)BIT(0))

/*
 * Place the (possibly merged) page to the tail of the freelist. Will ignore
 * page shuffling (relevant code - e.g., memory onlining - is expected to
 * shuffle the whole zone).
 *
 * Note: No code should rely on this flag for correctness - it's purely
 *       to allow for optimizations when handing back either fresh pages
 *       (memory onlining) or untouched pages (page isolation, free page
 *       reporting).
 */
#define FPI_TO_TAIL             ((__force fpi_t)BIT(1))

/*
 * Don't poison memory with KASAN (only for the tag-based modes).
 * During boot, all non-reserved memblock memory is exposed to page_alloc.
 * Poisoning all that memory lengthens boot time, especially on systems with
 * large amount of RAM. This flag is used to skip that poisoning.
 * This is only done for the tag-based KASAN modes, as those are able to
 * detect memory corruptions with the memory tags assigned by default.
 * All memory allocated normally after boot gets poisoned as usual.
 */
#define FPI_SKIP_KASAN_POISON   ((__force fpi_t)BIT(2))

/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
#define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8)

struct pagesets {
        local_lock_t lock;
};
static DEFINE_PER_CPU(struct pagesets, pagesets) = {
        .lock = INIT_LOCAL_LOCK(lock),
};

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

DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key);

#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

/* work_structs for global per-cpu drains */
struct pcpu_drain {
        struct zone *zone;
        struct work_struct work;
};
static DEFINE_MUTEX(pcpu_drain_mutex);
static DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);

#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
volatile unsigned long latent_entropy __latent_entropy;
EXPORT_SYMBOL(latent_entropy);
#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_MEMORY] = { { [0] = 1UL } },
        [N_CPU] = { { [0] = 1UL } },
#endif  /* NUMA */
};
EXPORT_SYMBOL(node_states);

atomic_long_t _totalram_pages __read_mostly;
EXPORT_SYMBOL(_totalram_pages);
unsigned long totalreserve_pages __read_mostly;
unsigned long totalcma_pages __read_mostly;

int percpu_pagelist_high_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
EXPORT_SYMBOL(init_on_alloc);

DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
EXPORT_SYMBOL(init_on_free);

static bool _init_on_alloc_enabled_early __read_mostly
                                = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON);
static int __init early_init_on_alloc(char *buf)
{

        return kstrtobool(buf, &_init_on_alloc_enabled_early);
}
early_param("init_on_alloc", early_init_on_alloc);

static bool _init_on_free_enabled_early __read_mostly
                                = IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON);
static int __init early_init_on_free(char *buf)
{
        return kstrtobool(buf, &_init_on_free_enabled_early);
}
early_param("init_on_free", early_init_on_free);

/*
 * A cached value of the page's pageblock's migratetype, used when the page is
 * put on a pcplist. Used to avoid the pageblock migratetype lookup when
 * freeing from pcplists in most cases, at the cost of possibly becoming stale.
 * Also the migratetype set in the page does not necessarily match the pcplist
 * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any
 * other index - this ensures that it will be put on the correct CMA freelist.
 */
static inline int get_pcppage_migratetype(struct page *page)
{
        return page->index;
}

static inline void set_pcppage_migratetype(struct page *page, int migratetype)
{
        page->index = migratetype;
}

#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 system_transition_mutex held
 * (gfp_allowed_mask also should only be modified with system_transition_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(&system_transition_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(&system_transition_mutex));
        WARN_ON(saved_gfp_mask);
        saved_gfp_mask = gfp_allowed_mask;
        gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
}

bool pm_suspended_storage(void)
{
        if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
                return false;
        return true;
}
#endif /* CONFIG_PM_SLEEP */

#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
unsigned int pageblock_order __read_mostly;
#endif

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

/*
 * 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 leave (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] = {
#ifdef CONFIG_ZONE_DMA
        [ZONE_DMA] = 256,
#endif
#ifdef CONFIG_ZONE_DMA32
        [ZONE_DMA32] = 256,
#endif
        [ZONE_NORMAL] = 32,
#ifdef CONFIG_HIGHMEM
        [ZONE_HIGHMEM] = 0,
#endif
        [ZONE_MOVABLE] = 0,
};

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",
#ifdef CONFIG_ZONE_DEVICE
         "Device",
#endif
};

const char * const migratetype_names[MIGRATE_TYPES] = {
        "Unmovable",
        "Movable",
        "Reclaimable",
        "HighAtomic",
#ifdef CONFIG_CMA
        "CMA",
#endif
#ifdef CONFIG_MEMORY_ISOLATION
        "Isolate",
#endif
};

compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = {
        [NULL_COMPOUND_DTOR] = NULL,
        [COMPOUND_PAGE_DTOR] = free_compound_page,
#ifdef CONFIG_HUGETLB_PAGE
        [HUGETLB_PAGE_DTOR] = free_huge_page,
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
        [TRANSHUGE_PAGE_DTOR] = free_transhuge_page,
#endif
};

int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
int watermark_boost_factor __read_mostly = 15000;
int watermark_scale_factor = 10;

static unsigned long nr_kernel_pages __initdata;
static unsigned long nr_all_pages __initdata;
static unsigned long dma_reserve __initdata;

static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata;
static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata;
static unsigned long required_kernelcore __initdata;
static unsigned long required_kernelcore_percent __initdata;
static unsigned long required_movablecore __initdata;
static unsigned long required_movablecore_percent __initdata;
static unsigned long zone_movable_pfn[MAX_NUMNODES] __initdata;
static bool mirrored_kernelcore __meminitdata;

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

#if MAX_NUMNODES > 1
unsigned int nr_node_ids __read_mostly = MAX_NUMNODES;
unsigned 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;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
 * During boot we initialize deferred pages on-demand, as needed, but once
 * page_alloc_init_late() has finished, the deferred pages are all initialized,
 * and we can permanently disable that path.
 */
static DEFINE_STATIC_KEY_TRUE(deferred_pages);

/*
 * Calling kasan_poison_pages() only after deferred memory initialization
 * has completed. Poisoning pages during deferred memory init will greatly
 * lengthen the process and cause problem in large memory systems as the
 * deferred pages initialization is done with interrupt disabled.
 *
 * Assuming that there will be no reference to those newly initialized
 * pages before they are ever allocated, this should have no effect on
 * KASAN memory tracking as the poison will be properly inserted at page
 * allocation time. The only corner case is when pages are allocated by
 * on-demand allocation and then freed again before the deferred pages
 * initialization is done, but this is not likely to happen.
 */
static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
{
        return static_branch_unlikely(&deferred_pages) ||
               (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
                (fpi_flags & FPI_SKIP_KASAN_POISON)) ||
               PageSkipKASanPoison(page);
}

/* Returns true if the struct page for the pfn is uninitialised */
static inline bool __meminit early_page_uninitialised(unsigned long pfn)
{
        int nid = early_pfn_to_nid(pfn);

        if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
                return true;

        return false;
}

/*
 * Returns true when the remaining initialisation should be deferred until
 * later in the boot cycle when it can be parallelised.
 */
static bool __meminit
defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
{
        static unsigned long prev_end_pfn, nr_initialised;

        /*
         * prev_end_pfn static that contains the end of previous zone
         * No need to protect because called very early in boot before smp_init.
         */
        if (prev_end_pfn != end_pfn) {
                prev_end_pfn = end_pfn;
                nr_initialised = 0;
        }

        /* Always populate low zones for address-constrained allocations */
        if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
                return false;

        if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
                return true;
        /*
         * We start only with one section of pages, more pages are added as
         * needed until the rest of deferred pages are initialized.
         */
        nr_initialised++;
        if ((nr_initialised > PAGES_PER_SECTION) &&
            (pfn & (PAGES_PER_SECTION - 1)) == 0) {
                NODE_DATA(nid)->first_deferred_pfn = pfn;
                return true;
        }
        return false;
}
#else
static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
{
        return (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
                (fpi_flags & FPI_SKIP_KASAN_POISON)) ||
               PageSkipKASanPoison(page);
}

static inline bool early_page_uninitialised(unsigned long pfn)
{
        return false;
}

static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
{
        return false;
}
#endif

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

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

static __always_inline
unsigned long __get_pfnblock_flags_mask(const struct page *page,
                                        unsigned long pfn,
                                        unsigned long mask)
{
        unsigned long *bitmap;
        unsigned long bitidx, word_bitidx;
        unsigned long word;

        bitmap = get_pageblock_bitmap(page, pfn);
        bitidx = pfn_to_bitidx(page, pfn);
        word_bitidx = bitidx / BITS_PER_LONG;
        bitidx &= (BITS_PER_LONG-1);

        word = bitmap[word_bitidx];
        return (word >> bitidx) & mask;
}

/**
 * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
 * @page: The page within the block of interest
 * @pfn: The target page frame number
 * @mask: mask of bits that the caller is interested in
 *
 * Return: pageblock_bits flags
 */
unsigned long get_pfnblock_flags_mask(const struct page *page,
                                        unsigned long pfn, unsigned long mask)
{
        return __get_pfnblock_flags_mask(page, pfn, mask);
}

static __always_inline int get_pfnblock_migratetype(const struct page *page,
                                        unsigned long pfn)
{
        return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK);
}

/**
 * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
 * @page: The page within the block of interest
 * @flags: The flags to set
 * @pfn: The target page frame number
 * @mask: mask of bits that the caller is interested in
 */
void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
                                        unsigned long pfn,
                                        unsigned long mask)
{
        unsigned long *bitmap;
        unsigned long bitidx, word_bitidx;
        unsigned long old_word, word;

        BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
        BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits));

        bitmap = get_pageblock_bitmap(page, pfn);
        bitidx = pfn_to_bitidx(page, pfn);
        word_bitidx = bitidx / BITS_PER_LONG;
        bitidx &= (BITS_PER_LONG-1);

        VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);

        mask <<= bitidx;
        flags <<= bitidx;

        word = READ_ONCE(bitmap[word_bitidx]);
        for (;;) {
                old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags);
                if (word == old_word)
                        break;
                word = old_word;
        }
}

void set_pageblock_migratetype(struct page *page, int migratetype)
{
        if (unlikely(page_group_by_mobility_disabled &&
                     migratetype < MIGRATE_PCPTYPES))
                migratetype = MIGRATE_UNMOVABLE;

        set_pfnblock_flags_mask(page, (unsigned long)migratetype,
                                page_to_pfn(page), MIGRATETYPE_MASK);
}

#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 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n",
                        pfn, zone_to_nid(zone), zone->name,
                        start_pfn, start_pfn + sp);

        return ret;
}

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

        return 1;
}
/*
 * Temporary debugging check for pages not lying within a given zone.
 */
static int __maybe_unused 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 __maybe_unused bad_range(struct zone *zone, struct page *page)
{
        return 0;
}
#endif

static void bad_page(struct page *page, const char *reason)
{
        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) {
                        pr_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;

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

        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);
}

static inline unsigned int order_to_pindex(int migratetype, int order)
{
        int base = order;

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
        if (order > PAGE_ALLOC_COSTLY_ORDER) {
                VM_BUG_ON(order != pageblock_order);
                base = PAGE_ALLOC_COSTLY_ORDER + 1;
        }
#else
        VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER);
#endif

        return (MIGRATE_PCPTYPES * base) + migratetype;
}

static inline int pindex_to_order(unsigned int pindex)
{
        int order = pindex / MIGRATE_PCPTYPES;

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
        if (order > PAGE_ALLOC_COSTLY_ORDER) {
                order = pageblock_order;
                VM_BUG_ON(order != pageblock_order);
        }
#else
        VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER);
#endif

        return order;
}

static inline bool pcp_allowed_order(unsigned int order)
{
        if (order <= PAGE_ALLOC_COSTLY_ORDER)
                return true;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
        if (order == pageblock_order)
                return true;
#endif
        return false;
}

static inline void free_the_page(struct page *page, unsigned int order)
{
        if (pcp_allowed_order(order))           /* Via pcp? */
                free_unref_page(page, order);
        else
                __free_pages_ok(page, order, FPI_NONE);
}

/*
 * Higher-order pages are called "compound pages".  They are structured thusly:
 *
 * The first PAGE_SIZE page is called the "head page" and have PG_head set.
 *
 * The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded
 * in bit 0 of page->compound_head. The rest of bits is pointer to head page.
 *
 * The first tail page's ->compound_dtor holds the offset in array of compound
 * page destructors. See compound_page_dtors.
 *
 * The first tail page's ->compound_order holds the order of allocation.
 * This usage means that zero-order pages may not be compound.
 */

void free_compound_page(struct page *page)
{
        mem_cgroup_uncharge(page);
        free_the_page(page, compound_order(page));
}

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

        __SetPageHead(page);
        for (i = 1; i < nr_pages; i++) {
                struct page *p = page + i;
                p->mapping = TAIL_MAPPING;
                set_compound_head(p, page);
        }

        set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
        set_compound_order(page, order);
        atomic_set(compound_mapcount_ptr(page), -1);
        if (hpage_pincount_available(page))
                atomic_set(compound_pincount_ptr(page), 0);
}

#ifdef CONFIG_DEBUG_PAGEALLOC
unsigned int _debug_guardpage_minorder;

bool _debug_pagealloc_enabled_early __read_mostly
                        = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
EXPORT_SYMBOL(_debug_pagealloc_enabled_early);
DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
EXPORT_SYMBOL(_debug_pagealloc_enabled);

DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled);

static int __init early_debug_pagealloc(char *buf)
{
        return kstrtobool(buf, &_debug_pagealloc_enabled_early);
}
early_param("debug_pagealloc", early_debug_pagealloc);

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

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

static inline bool set_page_guard(struct zone *zone, struct page *page,
                                unsigned int order, int migratetype)
{
        if (!debug_guardpage_enabled())
                return false;

        if (order >= debug_guardpage_minorder())
                return false;

        __SetPageGuard(page);
        INIT_LIST_HEAD(&page->lru);
        set_page_private(page, order);
        /* Guard pages are not available for any usage */
        __mod_zone_freepage_state(zone, -(1 << order), migratetype);

        return true;
}

static inline void clear_page_guard(struct zone *zone, struct page *page,
                                unsigned int order, int migratetype)
{
        if (!debug_guardpage_enabled())
                return;

        __ClearPageGuard(page);

        set_page_private(page, 0);
        if (!is_migrate_isolate(migratetype))
                __mod_zone_freepage_state(zone, (1 << order), migratetype);
}
#else
static inline bool set_page_guard(struct zone *zone, struct page *page,
                        unsigned int order, int migratetype) { return false; }
static inline void clear_page_guard(struct zone *zone, struct page *page,
                                unsigned int order, int migratetype) {}
#endif

/*
 * Enable static keys related to various memory debugging and hardening options.
 * Some override others, and depend on early params that are evaluated in the
 * order of appearance. So we need to first gather the full picture of what was
 * enabled, and then make decisions.
 */
void init_mem_debugging_and_hardening(void)
{
        bool page_poisoning_requested = false;

#ifdef CONFIG_PAGE_POISONING
        /*
         * Page poisoning is debug page alloc for some arches. If
         * either of those options are enabled, enable poisoning.
         */
        if (page_poisoning_enabled() ||
             (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) &&
              debug_pagealloc_enabled())) {
                static_branch_enable(&_page_poisoning_enabled);
                page_poisoning_requested = true;
        }
#endif

        if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) &&
            page_poisoning_requested) {
                pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
                        "will take precedence over init_on_alloc and init_on_free\n");
                _init_on_alloc_enabled_early = false;
                _init_on_free_enabled_early = false;
        }

        if (_init_on_alloc_enabled_early)
                static_branch_enable(&init_on_alloc);
        else
                static_branch_disable(&init_on_alloc);

        if (_init_on_free_enabled_early)
                static_branch_enable(&init_on_free);
        else
                static_branch_disable(&init_on_free);

#ifdef CONFIG_DEBUG_PAGEALLOC
        if (!debug_pagealloc_enabled())
                return;

        static_branch_enable(&_debug_pagealloc_enabled);

        if (!debug_guardpage_minorder())
                return;

        static_branch_enable(&_debug_guardpage_enabled);
#endif
}

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

/*
 * This function checks whether a page is free && is the buddy
 * we can coalesce a page and its buddy if
 * (a) the buddy is not in a hole (check before calling!) &&
 * (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 PageBuddy.
 * Setting, clearing, and testing PageBuddy is serialized by zone->lock.
 *
 * For recording page's order, we use page_private(page).
 */
static inline bool page_is_buddy(struct page *page, struct page *buddy,
                                                        unsigned int order)
{
        if (!page_is_guard(buddy) && !PageBuddy(buddy))
                return false;

        if (buddy_order(buddy) != order)
                return false;

        /*
         * zone check is done late to avoid uselessly calculating
         * zone/node ids for pages that could never merge.
         */
        if (page_zone_id(page) != page_zone_id(buddy))
                return false;

        VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);

        return true;
}

#ifdef CONFIG_COMPACTION
static inline struct capture_control *task_capc(struct zone *zone)
{
        struct capture_control *capc = current->capture_control;

        return unlikely(capc) &&
                !(current->flags & PF_KTHREAD) &&
                !capc->page &&
                capc->cc->zone == zone ? capc : NULL;
}

static inline bool
compaction_capture(struct capture_control *capc, struct page *page,
                   int order, int migratetype)
{
        if (!capc || order != capc->cc->order)
                return false;

        /* Do not accidentally pollute CMA or isolated regions*/
        if (is_migrate_cma(migratetype) ||
            is_migrate_isolate(migratetype))
                return false;

        /*
         * Do not let lower order allocations pollute a movable pageblock.
         * This might let an unmovable request use a reclaimable pageblock
         * and vice-versa but no more than normal fallback logic which can
         * have trouble finding a high-order free page.
         */
        if (order < pageblock_order && migratetype == MIGRATE_MOVABLE)
                return false;

        capc->page = page;
        return true;
}

#else
static inline struct capture_control *task_capc(struct zone *zone)
{
        return NULL;
}

static inline bool
compaction_capture(struct capture_control *capc, struct page *page,
                   int order, int migratetype)
{
        return false;
}
#endif /* CONFIG_COMPACTION */

/* Used for pages not on another list */
static inline void add_to_free_list(struct page *page, struct zone *zone,
                                    unsigned int order, int migratetype)
{
        struct free_area *area = &zone->free_area[order];

        list_add(&page->lru, &area->free_list[migratetype]);
        area->nr_free++;
}

/* Used for pages not on another list */
static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
                                         unsigned int order, int migratetype)
{
        struct free_area *area = &zone->free_area[order];

        list_add_tail(&page->lru, &area->free_list[migratetype]);
        area->nr_free++;
}

/*
 * Used for pages which are on another list. Move the pages to the tail
 * of the list - so the moved pages won't immediately be considered for
 * allocation again (e.g., optimization for memory onlining).
 */
static inline void move_to_free_list(struct page *page, struct zone *zone,
                                     unsigned int order, int migratetype)
{
        struct free_area *area = &zone->free_area[order];

        list_move_tail(&page->lru, &area->free_list[migratetype]);
}

static inline void del_page_from_free_list(struct page *page, struct zone *zone,
                                           unsigned int order)
{
        /* clear reported state and update reported page count */
        if (page_reported(page))
                __ClearPageReported(page);

        list_del(&page->lru);
        __ClearPageBuddy(page);
        set_page_private(page, 0);
        zone->free_area[order].nr_free--;
}

/*
 * 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
 */
static inline bool
buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
                   struct page *page, unsigned int order)
{
        struct page *higher_page, *higher_buddy;
        unsigned long combined_pfn;

        if (order >= MAX_ORDER - 2)
                return false;

        combined_pfn = buddy_pfn & pfn;
        higher_page = page + (combined_pfn - pfn);
        buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
        higher_buddy = higher_page + (buddy_pfn - combined_pfn);

        return page_is_buddy(higher_page, higher_buddy, order + 1);
}

/*
 * 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 PageBuddy.
 * 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,
                unsigned long pfn,
                struct zone *zone, unsigned int order,
                int migratetype, fpi_t fpi_flags)
{
        struct capture_control *capc = task_capc(zone);
        unsigned long buddy_pfn;
        unsigned long combined_pfn;
        unsigned int max_order;
        struct page *buddy;
        bool to_tail;

        max_order = min_t(unsigned int, MAX_ORDER - 1, pageblock_order);

        VM_BUG_ON(!zone_is_initialized(zone));
        VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);

        VM_BUG_ON(migratetype == -1);
        if (likely(!is_migrate_isolate(migratetype)))
                __mod_zone_freepage_state(zone, 1 << order, migratetype);

        VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
        VM_BUG_ON_PAGE(bad_range(zone, page), page);

continue_merging:
        while (order < max_order) {
                if (compaction_capture(capc, page, order, migratetype)) {
                        __mod_zone_freepage_state(zone, -(1 << order),
                                                                migratetype);
                        return;
                }
                buddy_pfn = __find_buddy_pfn(pfn, order);
                buddy = page + (buddy_pfn - pfn);

                if (!page_is_buddy(page, buddy, order))
                        goto done_merging;
                /*
                 * 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(zone, buddy, order, migratetype);
                else
                        del_page_from_free_list(buddy, zone, order);
                combined_pfn = buddy_pfn & pfn;
                page = page + (combined_pfn - pfn);
                pfn = combined_pfn;
                order++;
        }
        if (order < MAX_ORDER - 1) {
                /* If we are here, it means order is >= pageblock_order.
                 * We want to prevent merge between freepages on isolate
                 * pageblock and normal pageblock. Without this, pageblock
                 * isolation could cause incorrect freepage or CMA accounting.
                 *
                 * We don't want to hit this code for the more frequent
                 * low-order merging.
                 */
                if (unlikely(has_isolate_pageblock(zone))) {
                        int buddy_mt;

                        buddy_pfn = __find_buddy_pfn(pfn, order);
                        buddy = page + (buddy_pfn - pfn);
                        buddy_mt = get_pageblock_migratetype(buddy);

                        if (migratetype != buddy_mt
                                        && (is_migrate_isolate(migratetype) ||
                                                is_migrate_isolate(buddy_mt)))
                                goto done_merging;
                }
                max_order = order + 1;
                goto continue_merging;
        }

done_merging:
        set_buddy_order(page, order);

        if (fpi_flags & FPI_TO_TAIL)
                to_tail = true;
        else if (is_shuffle_order(order))
                to_tail = shuffle_pick_tail();
        else
                to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);

        if (to_tail)
                add_to_free_list_tail(page, zone, order, migratetype);
        else
                add_to_free_list(page, zone, order, migratetype);

        /* Notify page reporting subsystem of freed page */
        if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY))
                page_reporting_notify_free(order);
}

/*
 * A bad page could be due to a number of fields. Instead of multiple branches,
 * try and check multiple fields with one check. The caller must do a detailed
 * check if necessary.
 */
static inline bool page_expected_state(struct page *page,
                                        unsigned long check_flags)
{
        if (unlikely(atomic_read(&page->_mapcount) != -1))
                return false;

        if (unlikely((unsigned long)page->mapping |
                        page_ref_count(page) |
#ifdef CONFIG_MEMCG
                        page->memcg_data |
#endif
                        (page->flags & check_flags)))
                return false;

        return true;
}

static const char *page_bad_reason(struct page *page, unsigned long flags)
{
        const char *bad_reason = NULL;

        if (unlikely(atomic_read(&page->_mapcount) != -1))
                bad_reason = "nonzero mapcount";
        if (unlikely(page->mapping != NULL))
                bad_reason = "non-NULL mapping";
        if (unlikely(page_ref_count(page) != 0))
                bad_reason = "nonzero _refcount";
        if (unlikely(page->flags & flags)) {
                if (flags == PAGE_FLAGS_CHECK_AT_PREP)
                        bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag(s) set";
                else
                        bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
        }
#ifdef CONFIG_MEMCG
        if (unlikely(page->memcg_data))
                bad_reason = "page still charged to cgroup";
#endif
        return bad_reason;
}

static void check_free_page_bad(struct page *page)
{
        bad_page(page,
                 page_bad_reason(page, PAGE_FLAGS_CHECK_AT_FREE));
}

static inline int check_free_page(struct page *page)
{
        if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE)))
                return 0;

        /* Something has gone sideways, find it */
        check_free_page_bad(page);
        return 1;
}

static int free_tail_pages_check(struct page *head_page, struct page *page)
{
        int ret = 1;

        /*
         * We rely page->lru.next never has bit 0 set, unless the page
         * is PageTail(). Let's make sure that's true even for poisoned ->lru.
         */
        BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1);

        if (!IS_ENABLED(CONFIG_DEBUG_VM)) {
                ret = 0;
                goto out;
        }
        switch (page - head_page) {
        case 1:
                /* the first tail page: ->mapping may be compound_mapcount() */
                if (unlikely(compound_mapcount(page))) {
                        bad_page(page, "nonzero compound_mapcount");
                        goto out;
                }
                break;
        case 2:
                /*
                 * the second tail page: ->mapping is
                 * deferred_list.next -- ignore value.
                 */
                break;
        default:
                if (page->mapping != TAIL_MAPPING) {
                        bad_page(page, "corrupted mapping in tail page");
                        goto out;
                }
                break;
        }
        if (unlikely(!PageTail(page))) {
                bad_page(page, "PageTail not set");
                goto out;
        }
        if (unlikely(compound_head(page) != head_page)) {
                bad_page(page, "compound_head not consistent");
                goto out;
        }
        ret = 0;
out:
        page->mapping = NULL;
        clear_compound_head(page);
        return ret;
}

static void kernel_init_free_pages(struct page *page, int numpages, bool zero_tags)
{
        int i;

        if (zero_tags) {
                for (i = 0; i < numpages; i++)
                        tag_clear_highpage(page + i);
                return;
        }

        /* s390's use of memset() could override KASAN redzones. */
        kasan_disable_current();
        for (i = 0; i < numpages; i++) {
                u8 tag = page_kasan_tag(page + i);
                page_kasan_tag_reset(page + i);
                clear_highpage(page + i);
                page_kasan_tag_set(page + i, tag);
        }
        kasan_enable_current();
}

static __always_inline bool free_pages_prepare(struct page *page,
                        unsigned int order, bool check_free, fpi_t fpi_flags)
{
        int bad = 0;
        bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags);

        VM_BUG_ON_PAGE(PageTail(page), page);

        trace_mm_page_free(page, order);

        if (unlikely(PageHWPoison(page)) && !order) {
                /*
                 * Do not let hwpoison pages hit pcplists/buddy
                 * Untie memcg state and reset page's owner
                 */
                if (memcg_kmem_enabled() && PageMemcgKmem(page))
                        __memcg_kmem_uncharge_page(page, order);
                reset_page_owner(page, order);
                return false;
        }

        /*
         * Check tail pages before head page information is cleared to
         * avoid checking PageCompound for order-0 pages.
         */
        if (unlikely(order)) {
                bool compound = PageCompound(page);
                int i;

                VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);

                if (compound) {
                        ClearPageDoubleMap(page);
                        ClearPageHasHWPoisoned(page);
                }
                for (i = 1; i < (1 << order); i++) {
                        if (compound)
                                bad += free_tail_pages_check(page, page + i);
                        if (unlikely(check_free_page(page + i))) {
                                bad++;
                                continue;
                        }
                        (page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
                }
        }
        if (PageMappingFlags(page))
                page->mapping = NULL;
        if (memcg_kmem_enabled() && PageMemcgKmem(page))
                __memcg_kmem_uncharge_page(page, order);
        if (check_free)
                bad += check_free_page(page);
        if (bad)
                return false;

        page_cpupid_reset_last(page);
        page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
        reset_page_owner(page, order);

        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);
        }

        kernel_poison_pages(page, 1 << order);

        /*
         * As memory initialization might be integrated into KASAN,
         * kasan_free_pages and kernel_init_free_pages must be
         * kept together to avoid discrepancies in behavior.
         *
         * With hardware tag-based KASAN, memory tags must be set before the
         * page becomes unavailable via debug_pagealloc or arch_free_page.
         */
        if (kasan_has_integrated_init()) {
                if (!skip_kasan_poison)
                        kasan_free_pages(page, order);
        } else {
                bool init = want_init_on_free();

                if (init)
                        kernel_init_free_pages(page, 1 << order, false);
                if (!skip_kasan_poison)
                        kasan_poison_pages(page, order, init);
        }

        /*
         * arch_free_page() can make the page's contents inaccessible.  s390
         * does this.  So nothing which can access the page's contents should
         * happen after this.
         */
        arch_free_page(page, order);

        debug_pagealloc_unmap_pages(page, 1 << order);

        return true;
}

#ifdef CONFIG_DEBUG_VM
/*
 * With DEBUG_VM enabled, order-0 pages are checked immediately when being freed
 * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when
 * moved from pcp lists to free lists.
 */
static bool free_pcp_prepare(struct page *page, unsigned int order)
{
        return free_pages_prepare(page, order, true, FPI_NONE);
}

static bool bulkfree_pcp_prepare(struct page *page)
{
        if (debug_pagealloc_enabled_static())
                return check_free_page(page);
        else
                return false;
}
#else
/*
 * With DEBUG_VM disabled, order-0 pages being freed are checked only when
 * moving from pcp lists to free list in order to reduce overhead. With
 * debug_pagealloc enabled, they are checked also immediately when being freed
 * to the pcp lists.
 */
static bool free_pcp_prepare(struct page *page, unsigned int order)
{
        if (debug_pagealloc_enabled_static())
                return free_pages_prepare(page, order, true, FPI_NONE);
        else
                return free_pages_prepare(page, order, false, FPI_NONE);
}

static bool bulkfree_pcp_prepare(struct page *page)
{
        return check_free_page(page);
}
#endif /* CONFIG_DEBUG_VM */

static inline void prefetch_buddy(struct page *page)
{
        unsigned long pfn = page_to_pfn(page);
        unsigned long buddy_pfn = __find_buddy_pfn(pfn, 0);
        struct page *buddy = page + (buddy_pfn - pfn);

        prefetch(buddy);
}

/*
 * 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 pindex = 0;
        int batch_free = 0;
        int nr_freed = 0;
        unsigned int order;
        int prefetch_nr = READ_ONCE(pcp->batch);
        bool isolated_pageblocks;
        struct page *page, *tmp;
        LIST_HEAD(head);

        /*
         * Ensure proper count is passed which otherwise would stuck in the
         * below while (list_empty(list)) loop.
         */
        count = min(pcp->count, count);
        while (count > 0) {
                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 (++pindex == NR_PCP_LISTS)
                                pindex = 0;
                        list = &pcp->lists[pindex];
                } while (list_empty(list));

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

                order = pindex_to_order(pindex);
                BUILD_BUG_ON(MAX_ORDER >= (1<<NR_PCP_ORDER_WIDTH));
                do {
                        page = list_last_entry(list, struct page, lru);
                        /* must delete to avoid corrupting pcp list */
                        list_del(&page->lru);
                        nr_freed += 1 << order;
                        count -= 1 << order;

                        if (bulkfree_pcp_prepare(page))
                                continue;

                        /* Encode order with the migratetype */
                        page->index <<= NR_PCP_ORDER_WIDTH;
                        page->index |= order;

                        list_add_tail(&page->lru, &head);

                        /*
                         * We are going to put the page back to the global
                         * pool, prefetch its buddy to speed up later access
                         * under zone->lock. It is believed the overhead of
                         * an additional test and calculating buddy_pfn here
                         * can be offset by reduced memory latency later. To
                         * avoid excessive prefetching due to large count, only
                         * prefetch buddy for the first pcp->batch nr of pages.
                         */
                        if (prefetch_nr) {
                                prefetch_buddy(page);
                                prefetch_nr--;
                        }
                } while (count > 0 && --batch_free && !list_empty(list));
        }
        pcp->count -= nr_freed;

        /*
         * local_lock_irq held so equivalent to spin_lock_irqsave for
         * both PREEMPT_RT and non-PREEMPT_RT configurations.
         */
        spin_lock(&zone->lock);
        isolated_pageblocks = has_isolate_pageblock(zone);

        /*
         * Use safe version since after __free_one_page(),
         * page->lru.next will not point to original list.
         */
        list_for_each_entry_safe(page, tmp, &head, lru) {
                int mt = get_pcppage_migratetype(page);

                /* mt has been encoded with the order (see above) */
                order = mt & NR_PCP_ORDER_MASK;
                mt >>= NR_PCP_ORDER_WIDTH;

                /* MIGRATE_ISOLATE page should not go to pcplists */
                VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
                /* Pageblock could have been isolated meanwhile */
                if (unlikely(isolated_pageblocks))
                        mt = get_pageblock_migratetype(page);

                __free_one_page(page, page_to_pfn(page), zone, order, mt, FPI_NONE);
                trace_mm_page_pcpu_drain(page, order, mt);
        }
        spin_unlock(&zone->lock);
}

static void free_one_page(struct zone *zone,
                                struct page *page, unsigned long pfn,
                                unsigned int order,
                                int migratetype, fpi_t fpi_flags)
{
        unsigned long flags;

        spin_lock_irqsave(&zone->lock, flags);
        if (unlikely(has_isolate_pageblock(zone) ||
                is_migrate_isolate(migratetype))) {
                migratetype = get_pfnblock_migratetype(page, pfn);
        }
        __free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
        spin_unlock_irqrestore(&zone->lock, flags);
}

static void __meminit __init_single_page(struct page *page, unsigned long pfn,
                                unsigned long zone, int nid)
{
        mm_zero_struct_page(page);
        set_page_links(page, zone, nid, pfn);
        init_page_count(page);
        page_mapcount_reset(page);
        page_cpupid_reset_last(page);
        page_kasan_tag_reset(page);

        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
}

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __meminit init_reserved_page(unsigned long pfn)
{
        pg_data_t *pgdat;
        int nid, zid;

        if (!early_page_uninitialised(pfn))
                return;

        nid = early_pfn_to_nid(pfn);
        pgdat = NODE_DATA(nid);

        for (zid = 0; zid < MAX_NR_ZONES; zid++) {
                struct zone *zone = &pgdat->node_zones[zid];

                if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
                        break;
        }
        __init_single_page(pfn_to_page(pfn), pfn, zid, nid);
}
#else
static inline void init_reserved_page(unsigned long pfn)
{
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */

/*
 * Initialised pages do not have PageReserved set. This function is
 * called for each range allocated by the bootmem allocator and
 * marks the pages PageReserved. The remaining valid pages are later
 * sent to the buddy page allocator.
 */
void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
{
        unsigned long start_pfn = PFN_DOWN(start);
        unsigned long end_pfn = PFN_UP(end);

        for (; start_pfn < end_pfn; start_pfn++) {
                if (pfn_valid(start_pfn)) {
                        struct page *page = pfn_to_page(start_pfn);

                        init_reserved_page(start_pfn);

                        /* Avoid false-positive PageTail() */
                        INIT_LIST_HEAD(&page->lru);

                        /*
                         * no need for atomic set_bit because the struct
                         * page is not visible yet so nobody should
                         * access it yet.
                         */
                        __SetPageReserved(page);
                }
        }
}

static void __free_pages_ok(struct page *page, unsigned int order,
                            fpi_t fpi_flags)
{
        unsigned long flags;
        int migratetype;
        unsigned long pfn = page_to_pfn(page);
        struct zone *zone = page_zone(page);

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

        migratetype = get_pfnblock_migratetype(page, pfn);

        spin_lock_irqsave(&zone->lock, flags);
        if (unlikely(has_isolate_pageblock(zone) ||
                is_migrate_isolate(migratetype))) {
                migratetype = get_pfnblock_migratetype(page, pfn);
        }
        __free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
        spin_unlock_irqrestore(&zone->lock, flags);

        __count_vm_events(PGFREE, 1 << order);
}

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

        /*
         * When initializing the memmap, __init_single_page() sets the refcount
         * of all pages to 1 ("allocated"/"not free"). We have to set the
         * refcount of all involved pages to 0.
         */
        prefetchw(p);
        for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
                prefetchw(p + 1);
                __ClearPageReserved(p);
                set_page_count(p, 0);
        }
        __ClearPageReserved(p);
        set_page_count(p, 0);

        atomic_long_add(nr_pages, &page_zone(page)->managed_pages);

        /*
         * Bypass PCP and place fresh pages right to the tail, primarily
         * relevant for memory onlining.
         */
        __free_pages_ok(page, order, FPI_TO_TAIL | FPI_SKIP_KASAN_POISON);
}

#ifdef CONFIG_NUMA

/*
 * During memory init memblocks map pfns to nids. The search is expensive and
 * this caches recent lookups. The implementation of __early_pfn_to_nid
 * treats start/end as pfns.
 */
struct mminit_pfnnid_cache {
        unsigned long last_start;
        unsigned long last_end;
        int last_nid;
};

static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;

/*
 * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
 */
static int __meminit __early_pfn_to_nid(unsigned long pfn,
                                        struct mminit_pfnnid_cache *state)
{
        unsigned long start_pfn, end_pfn;
        int nid;

        if (state->last_start <= pfn && pfn < state->last_end)
                return state->last_nid;

        nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
        if (nid != NUMA_NO_NODE) {
                state->last_start = start_pfn;
                state->last_end = end_pfn;
                state->last_nid = nid;
        }

        return nid;
}

int __meminit early_pfn_to_nid(unsigned long pfn)
{
        static DEFINE_SPINLOCK(early_pfn_lock);
        int nid;

        spin_lock(&early_pfn_lock);
        nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
        if (nid < 0)
                nid = first_online_node;
        spin_unlock(&early_pfn_lock);

        return nid;
}
#endif /* CONFIG_NUMA */

void __init memblock_free_pages(struct page *page, unsigned long pfn,
                                                        unsigned int order)
{
        if (early_page_uninitialised(pfn))
                return;
        __free_pages_core(page, order);
}

/*
 * Check that the whole (or subset of) a pageblock given by the interval of
 * [start_pfn, end_pfn) is valid and within the same zone, before scanning it
 * with the migration of free compaction scanner.
 *
 * Return struct page pointer of start_pfn, or NULL if checks were not passed.
 *
 * It's possible on some configurations to have a setup like node0 node1 node0
 * i.e. it's possible that all pages within a zones range of pages do not
 * belong to a single zone. We assume that a border between node0 and node1
 * can occur within a single pageblock, but not a node0 node1 node0
 * interleaving within a single pageblock. It is therefore sufficient to check
 * the first and last page of a pageblock and avoid checking each individual
 * page in a pageblock.
 */
struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
                                     unsigned long end_pfn, struct zone *zone)
{
        struct page *start_page;
        struct page *end_page;

        /* end_pfn is one past the range we are checking */
        end_pfn--;

        if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
                return NULL;

        start_page = pfn_to_online_page(start_pfn);
        if (!start_page)
                return NULL;

        if (page_zone(start_page) != zone)
                return NULL;

        end_page = pfn_to_page(end_pfn);

        /* This gives a shorter code than deriving page_zone(end_page) */
        if (page_zone_id(start_page) != page_zone_id(end_page))
                return NULL;

        return start_page;
}

void set_zone_contiguous(struct zone *zone)
{
        unsigned long block_start_pfn = zone->zone_start_pfn;
        unsigned long block_end_pfn;

        block_end_pfn = ALIGN(block_start_pfn + 1, pageblock_nr_pages);
        for (; block_start_pfn < zone_end_pfn(zone);
                        block_start_pfn = block_end_pfn,
                         block_end_pfn += pageblock_nr_pages) {

                block_end_pfn = min(block_end_pfn, zone_end_pfn(zone));

                if (!__pageblock_pfn_to_page(block_start_pfn,
                                             block_end_pfn, zone))
                        return;
                cond_resched();
        }

        /* We confirm that there is no hole */
        zone->contiguous = true;
}

void clear_zone_contiguous(struct zone *zone)
{
        zone->contiguous = false;
}

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __init deferred_free_range(unsigned long pfn,
                                       unsigned long nr_pages)
{
        struct page *page;
        unsigned long i;

        if (!nr_pages)
                return;

        page = pfn_to_page(pfn);

        /* Free a large naturally-aligned chunk if possible */
        if (nr_pages == pageblock_nr_pages &&
            (pfn & (pageblock_nr_pages - 1)) == 0) {
                set_pageblock_migratetype(page, MIGRATE_MOVABLE);
                __free_pages_core(page, pageblock_order);
                return;
        }

        for (i = 0; i < nr_pages; i++, page++, pfn++) {
                if ((pfn & (pageblock_nr_pages - 1)) == 0)
                        set_pageblock_migratetype(page, MIGRATE_MOVABLE);
                __free_pages_core(page, 0);
        }
}

/* Completion tracking for deferred_init_memmap() threads */
static atomic_t pgdat_init_n_undone __initdata;
static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);

static inline void __init pgdat_init_report_one_done(void)
{
        if (atomic_dec_and_test(&pgdat_init_n_undone))
                complete(&pgdat_init_all_done_comp);
}

/*
 * Returns true if page needs to be initialized or freed to buddy allocator.
 *
 * First we check if pfn is valid on architectures where it is possible to have
 * holes within pageblock_nr_pages. On systems where it is not possible, this
 * function is optimized out.
 *
 * Then, we check if a current large page is valid by only checking the validity
 * of the head pfn.
 */
static inline bool __init deferred_pfn_valid(unsigned long pfn)
{
        if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
                return false;
        return true;
}

/*
 * Free pages to buddy allocator. Try to free aligned pages in
 * pageblock_nr_pages sizes.
 */
static void __init deferred_free_pages(unsigned long pfn,
                                       unsigned long end_pfn)
{
        unsigned long nr_pgmask = pageblock_nr_pages - 1;
        unsigned long nr_free = 0;

        for (; pfn < end_pfn; pfn++) {
                if (!deferred_pfn_valid(pfn)) {
                        deferred_free_range(pfn - nr_free, nr_free);
                        nr_free = 0;
                } else if (!(pfn & nr_pgmask)) {
                        deferred_free_range(pfn - nr_free, nr_free);
                        nr_free = 1;
                } else {
                        nr_free++;
                }
        }
        /* Free the last block of pages to allocator */
        deferred_free_range(pfn - nr_free, nr_free);
}

/*
 * Initialize struct pages.  We minimize pfn page lookups and scheduler checks
 * by performing it only once every pageblock_nr_pages.
 * Return number of pages initialized.
 */
static unsigned long  __init deferred_init_pages(struct zone *zone,
                                                 unsigned long pfn,
                                                 unsigned long end_pfn)
{
        unsigned long nr_pgmask = pageblock_nr_pages - 1;
        int nid = zone_to_nid(zone);
        unsigned long nr_pages = 0;
        int zid = zone_idx(zone);
        struct page *page = NULL;

        for (; pfn < end_pfn; pfn++) {
                if (!deferred_pfn_valid(pfn)) {
                        page = NULL;
                        continue;
                } else if (!page || !(pfn & nr_pgmask)) {
                        page = pfn_to_page(pfn);
                } else {
                        page++;
                }
                __init_single_page(page, pfn, zid, nid);
                nr_pages++;
        }
        return (nr_pages);
}

/*
 * This function is meant to pre-load the iterator for the zone init.
 * Specifically it walks through the ranges until we are caught up to the
 * first_init_pfn value and exits there. If we never encounter the value we
 * return false indicating there are no valid ranges left.
 */
static bool __init
deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone,
                                    unsigned long *spfn, unsigned long *epfn,
                                    unsigned long first_init_pfn)
{
        u64 j;

        /*
         * Start out by walking through the ranges in this zone that have
         * already been initialized. We don't need to do anything with them
         * so we just need to flush them out of the system.
         */
        for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) {
                if (*epfn <= first_init_pfn)
                        continue;
                if (*spfn < first_init_pfn)
                        *spfn = first_init_pfn;
                *i = j;
                return true;
        }

        return false;
}

/*
 * Initialize and free pages. We do it in two loops: first we initialize
 * struct page, then free to buddy allocator, because while we are
 * freeing pages we can access pages that are ahead (computing buddy
 * page in __free_one_page()).
 *
 * In order to try and keep some memory in the cache we have the loop
 * broken along max page order boundaries. This way we will not cause
 * any issues with the buddy page computation.
 */
static unsigned long __init
deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn,
                       unsigned long *end_pfn)
{
        unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES);
        unsigned long spfn = *start_pfn, epfn = *end_pfn;
        unsigned long nr_pages = 0;
        u64 j = *i;

        /* First we loop through and initialize the page values */
        for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) {
                unsigned long t;

                if (mo_pfn <= *start_pfn)
                        break;

                t = min(mo_pfn, *end_pfn);
                nr_pages += deferred_init_pages(zone, *start_pfn, t);

                if (mo_pfn < *end_pfn) {
                        *start_pfn = mo_pfn;
                        break;
                }
        }

        /* Reset values and now loop through freeing pages as needed */
        swap(j, *i);

        for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) {
                unsigned long t;

                if (mo_pfn <= spfn)
                        break;

                t = min(mo_pfn, epfn);
                deferred_free_pages(spfn, t);

                if (mo_pfn <= epfn)
                        break;
        }

        return nr_pages;
}

static void __init
deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
                           void *arg)
{
        unsigned long spfn, epfn;
        struct zone *zone = arg;
        u64 i;

        deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn);

        /*
         * Initialize and free pages in MAX_ORDER sized increments so that we
         * can avoid introducing any issues with the buddy allocator.
         */
        while (spfn < end_pfn) {
                deferred_init_maxorder(&i, zone, &spfn, &epfn);
                cond_resched();
        }
}

/* An arch may override for more concurrency. */
__weak int __init
deferred_page_init_max_threads(const struct cpumask *node_cpumask)
{
        return 1;
}

/* Initialise remaining memory on a node */
static int __init deferred_init_memmap(void *data)
{
        pg_data_t *pgdat = data;
        const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
        unsigned long spfn = 0, epfn = 0;
        unsigned long first_init_pfn, flags;
        unsigned long start = jiffies;
        struct zone *zone;
        int zid, max_threads;
        u64 i;

        /* Bind memory initialisation thread to a local node if possible */
        if (!cpumask_empty(cpumask))
                set_cpus_allowed_ptr(current, cpumask);

        pgdat_resize_lock(pgdat, &flags);
        first_init_pfn = pgdat->first_deferred_pfn;
        if (first_init_pfn == ULONG_MAX) {
                pgdat_resize_unlock(pgdat, &flags);
                pgdat_init_report_one_done();
                return 0;
        }

        /* Sanity check boundaries */
        BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
        BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
        pgdat->first_deferred_pfn = ULONG_MAX;

        /*
         * Once we unlock here, the zone cannot be grown anymore, thus if an
         * interrupt thread must allocate this early in boot, zone must be
         * pre-grown prior to start of deferred page initialization.
         */
        pgdat_resize_unlock(pgdat, &flags);

        /* Only the highest zone is deferred so find it */
        for (zid = 0; zid < MAX_NR_ZONES; zid++) {
                zone = pgdat->node_zones + zid;
                if (first_init_pfn < zone_end_pfn(zone))
                        break;
        }

        /* If the zone is empty somebody else may have cleared out the zone */
        if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
                                                 first_init_pfn))
                goto zone_empty;

        max_threads = deferred_page_init_max_threads(cpumask);

        while (spfn < epfn) {
                unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION);
                struct padata_mt_job job = {
                        .thread_fn   = deferred_init_memmap_chunk,
                        .fn_arg      = zone,
                        .start       = spfn,
                        .size        = epfn_align - spfn,
                        .align       = PAGES_PER_SECTION,
                        .min_chunk   = PAGES_PER_SECTION,
                        .max_threads = max_threads,
                };

                padata_do_multithreaded(&job);
                deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
                                                    epfn_align);
        }
zone_empty:
        /* Sanity check that the next zone really is unpopulated */
        WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));

        pr_info("node %d deferred pages initialised in %ums\n",
                pgdat->node_id, jiffies_to_msecs(jiffies - start));

        pgdat_init_report_one_done();
        return 0;
}

/*
 * If this zone has deferred pages, try to grow it by initializing enough
 * deferred pages to satisfy the allocation specified by order, rounded up to
 * the nearest PAGES_PER_SECTION boundary.  So we're adding memory in increments
 * of SECTION_SIZE bytes by initializing struct pages in increments of
 * PAGES_PER_SECTION * sizeof(struct page) bytes.
 *
 * Return true when zone was grown, otherwise return false. We return true even
 * when we grow less than requested, to let the caller decide if there are
 * enough pages to satisfy the allocation.
 *
 * Note: We use noinline because this function is needed only during boot, and
 * it is called from a __ref function _deferred_grow_zone. This way we are
 * making sure that it is not inlined into permanent text section.
 */
static noinline bool __init
deferred_grow_zone(struct zone *zone, unsigned int order)
{
        unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
        pg_data_t *pgdat = zone->zone_pgdat;
        unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
        unsigned long spfn, epfn, flags;
        unsigned long nr_pages = 0;
        u64 i;

        /* Only the last zone may have deferred pages */
        if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat))
                return false;

        pgdat_resize_lock(pgdat, &flags);

        /*
         * If someone grew this zone while we were waiting for spinlock, return
         * true, as there might be enough pages already.
         */
        if (first_deferred_pfn != pgdat->first_deferred_pfn) {
                pgdat_resize_unlock(pgdat, &flags);
                return true;
        }

        /* If the zone is empty somebody else may have cleared out the zone */
        if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
                                                 first_deferred_pfn)) {
                pgdat->first_deferred_pfn = ULONG_MAX;
                pgdat_resize_unlock(pgdat, &flags);
                /* Retry only once. */
                return first_deferred_pfn != ULONG_MAX;
        }

        /*
         * Initialize and free pages in MAX_ORDER sized increments so
         * that we can avoid introducing any issues with the buddy
         * allocator.
         */
        while (spfn < epfn) {
                /* update our first deferred PFN for this section */
                first_deferred_pfn = spfn;

                nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
                touch_nmi_watchdog();

                /* We should only stop along section boundaries */
                if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION)
                        continue;

                /* If our quota has been met we can stop here */
                if (nr_pages >= nr_pages_needed)
                        break;
        }

        pgdat->first_deferred_pfn = spfn;
        pgdat_resize_unlock(pgdat, &flags);

        return nr_pages > 0;
}

/*
 * deferred_grow_zone() is __init, but it is called from
 * get_page_from_freelist() during early boot until deferred_pages permanently
 * disables this call. This is why we have refdata wrapper to avoid warning,
 * and to ensure that the function body gets unloaded.
 */
static bool __ref
_deferred_grow_zone(struct zone *zone, unsigned int order)
{
        return deferred_grow_zone(zone, order);
}

#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */

void __init page_alloc_init_late(void)
{
        struct zone *zone;
        int nid;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT

        /* There will be num_node_state(N_MEMORY) threads */
        atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
        for_each_node_state(nid, N_MEMORY) {
                kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
        }

        /* Block until all are initialised */
        wait_for_completion(&pgdat_init_all_done_comp);

        /*
         * We initialized the rest of the deferred pages.  Permanently disable
         * on-demand struct page initialization.
         */
        static_branch_disable(&deferred_pages);

        /* Reinit limits that are based on free pages after the kernel is up */
        files_maxfiles_init();
#endif

        buffer_init();

        /* Discard memblock private memory */
        memblock_discard();

        for_each_node_state(nid, N_MEMORY)
                shuffle_free_memory(NODE_DATA(nid));

        for_each_populated_zone(zone)
                set_zone_contiguous(zone);
}

#ifdef CONFIG_CMA
/* Free whole pageblock and set its 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_pageblock_migratetype(page, MIGRATE_CMA);

        if (pageblock_order >= MAX_ORDER) {
                i = pageblock_nr_pages;
                p = page;
                do {
                        set_page_refcounted(p);
                        __free_pages(p, MAX_ORDER - 1);
                        p += MAX_ORDER_NR_PAGES;
                } while (i -= MAX_ORDER_NR_PAGES);
        } else {
                set_page_refcounted(page);
                __free_pages(page, pageblock_order);
        }

        adjust_managed_page_count(page, pageblock_nr_pages);
        page_zone(page)->cma_pages += 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, int migratetype)
{
        unsigned long size = 1 << high;

        while (high > low) {
                high--;
                size >>= 1;
                VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);

                /*
                 * 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
                 */
                if (set_page_guard(zone, &page[size], high, migratetype))
                        continue;

                add_to_free_list(&page[size], zone, high, migratetype);
                set_buddy_order(&page[size], high);
        }
}

static void check_new_page_bad(struct page *page)
{
        if (unlikely(page->flags & __PG_HWPOISON)) {
                /* Don't complain about hwpoisoned pages */
                page_mapcount_reset(page); /* remove PageBuddy */
                return;
        }

        bad_page(page,
                 page_bad_reason(page, PAGE_FLAGS_CHECK_AT_PREP));
}

/*
 * This page is about to be returned from the page allocator
 */
static inline int check_new_page(struct page *page)
{
        if (likely(page_expected_state(page,
                                PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON)))
                return 0;

        check_new_page_bad(page);
        return 1;
}

#ifdef CONFIG_DEBUG_VM
/*
 * With DEBUG_VM enabled, order-0 pages are checked for expected state when
 * being allocated from pcp lists. With debug_pagealloc also enabled, they are
 * also checked when pcp lists are refilled from the free lists.
 */
static inline bool check_pcp_refill(struct page *page)
{
        if (debug_pagealloc_enabled_static())
                return check_new_page(page);
        else
                return false;
}

static inline bool check_new_pcp(struct page *page)
{
        return check_new_page(page);
}
#else
/*
 * With DEBUG_VM disabled, free order-0 pages are checked for expected state
 * when pcp lists are being refilled from the free lists. With debug_pagealloc
 * enabled, they are also checked when being allocated from the pcp lists.
 */
static inline bool check_pcp_refill(struct page *page)
{
        return check_new_page(page);
}
static inline bool check_new_pcp(struct page *page)
{
        if (debug_pagealloc_enabled_static())
                return check_new_page(page);
        else
                return false;
}
#endif /* CONFIG_DEBUG_VM */

static bool check_new_pages(struct page *page, unsigned int order)
{
        int i;
        for (i = 0; i < (1 << order); i++) {
                struct page *p = page + i;

                if (unlikely(check_new_page(p)))
                        return true;
        }

        return false;
}

inline void post_alloc_hook(struct page *page, unsigned int order,
                                gfp_t gfp_flags)
{
        set_page_private(page, 0);
        set_page_refcounted(page);

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

        /*
         * Page unpoisoning must happen before memory initialization.
         * Otherwise, the poison pattern will be overwritten for __GFP_ZERO
         * allocations and the page unpoisoning code will complain.
         */
        kernel_unpoison_pages(page, 1 << order);

        /*
         * As memory initialization might be integrated into KASAN,
         * kasan_alloc_pages and kernel_init_free_pages must be
         * kept together to avoid discrepancies in behavior.
         */
        if (kasan_has_integrated_init()) {
                kasan_alloc_pages(page, order, gfp_flags);
        } else {
                bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags);

                kasan_unpoison_pages(page, order, init);
                if (init)
                        kernel_init_free_pages(page, 1 << order,
                                               gfp_flags & __GFP_ZEROTAGS);
        }

        set_page_owner(page, order, gfp_flags);
}

static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
                                                        unsigned int alloc_flags)
{
        post_alloc_hook(page, order, gfp_flags);

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

        /*
         * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to
         * allocate the page. The expectation is that the caller is taking
         * steps that will free more memory. The caller should avoid the page
         * being used for !PFMEMALLOC purposes.
         */
        if (alloc_flags & ALLOC_NO_WATERMARKS)
                set_page_pfmemalloc(page);
        else
                clear_page_pfmemalloc(page);
}

/*
 * Go through the free lists for the given migratetype and remove
 * the smallest available page from the freelists
 */
static __always_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]);
                page = get_page_from_free_area(area, migratetype);
                if (!page)
                        continue;
                del_page_from_free_list(page, zone, current_order);
                expand(zone, page, order, current_order, migratetype);
                set_pcppage_migratetype(page, 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][3] = {
        [MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,   MIGRATE_TYPES },
        [MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES },
        [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,   MIGRATE_TYPES },
#ifdef CONFIG_CMA
        [MIGRATE_CMA]         = { MIGRATE_TYPES }, /* Never used */
#endif
#ifdef CONFIG_MEMORY_ISOLATION
        [MIGRATE_ISOLATE]     = { MIGRATE_TYPES }, /* Never used */
#endif
};

#ifdef CONFIG_CMA
static __always_inline struct page *__rmqueue_cma_fallback(struct zone *zone,
                                        unsigned int order)
{
        return __rmqueue_smallest(zone, order, MIGRATE_CMA);
}
#else
static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
                                        unsigned int order) { return NULL; }
#endif

/*
 * Move the free pages in a range to the freelist tail 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,
                          unsigned long start_pfn, unsigned long end_pfn,
                          int migratetype, int *num_movable)
{
        struct page *page;
        unsigned long pfn;
        unsigned int order;
        int pages_moved = 0;

        for (pfn = start_pfn; pfn <= end_pfn;) {
                page = pfn_to_page(pfn);
                if (!PageBuddy(page)) {
                        /*
                         * We assume that pages that could be isolated for
                         * migration are movable. But we don't actually try
                         * isolating, as that would be expensive.
                         */
                        if (num_movable &&
                                        (PageLRU(page) || __PageMovable(page)))
                                (*num_movable)++;
                        pfn++;
                        continue;
                }

                /* Make sure we are not inadvertently changing nodes */
                VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
                VM_BUG_ON_PAGE(page_zone(page) != zone, page);

                order = buddy_order(page);
                move_to_free_list(page, zone, order, migratetype);
                pfn += 1 << order;
                pages_moved += 1 << order;
        }

        return pages_moved;
}

int move_freepages_block(struct zone *zone, struct page *page,
                                int migratetype, int *num_movable)
{
        unsigned long start_pfn, end_pfn, pfn;

        if (num_movable)
                *num_movable = 0;

        pfn = page_to_pfn(page);
        start_pfn = pfn & ~(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_pfn = pfn;
        if (!zone_spans_pfn(zone, end_pfn))
                return 0;

        return move_freepages(zone, start_pfn, end_pfn, migratetype,
                                                                num_movable);
}

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;
        }
}

/*
 * When we are falling back to another migratetype during allocation, try to
 * steal extra free pages from the same pageblocks to satisfy further
 * allocations, instead of polluting multiple pageblocks.
 *
 * If we are stealing a relatively large buddy page, it is likely there will
 * be more free pages in the pageblock, so try to steal them all. For
 * reclaimable and unmovable allocations, we steal regardless of page size,
 * as fragmentation caused by those allocations polluting movable pageblocks
 * is worse than movable allocations stealing from unmovable and reclaimable
 * pageblocks.
 */
static bool can_steal_fallback(unsigned int order, int start_mt)
{
        /*
         * Leaving this order check is intended, although there is
         * relaxed order check in next check. The reason is that
         * we can actually steal whole pageblock if this condition met,
         * but, below check doesn't guarantee it and that is just heuristic
         * so could be changed anytime.
         */
        if (order >= pageblock_order)
                return true;

        if (order >= pageblock_order / 2 ||
                start_mt == MIGRATE_RECLAIMABLE ||
                start_mt == MIGRATE_UNMOVABLE ||
                page_group_by_mobility_disabled)
                return true;

        return false;
}

static inline bool boost_watermark(struct zone *zone)
{
        unsigned long max_boost;

        if (!watermark_boost_factor)
                return false;
        /*
         * Don't bother in zones that are unlikely to produce results.
         * On small machines, including kdump capture kernels running
         * in a small area, boosting the watermark can cause an out of
         * memory situation immediately.
         */
        if ((pageblock_nr_pages * 4) > zone_managed_pages(zone))
                return false;

        max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
                        watermark_boost_factor, 10000);

        /*
         * high watermark may be uninitialised if fragmentation occurs
         * very early in boot so do not boost. We do not fall
         * through and boost by pageblock_nr_pages as failing
         * allocations that early means that reclaim is not going
         * to help and it may even be impossible to reclaim the
         * boosted watermark resulting in a hang.
         */
        if (!max_boost)
                return false;

        max_boost = max(pageblock_nr_pages, max_boost);

        zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
                max_boost);

        return true;
}

/*
 * This function implements actual steal behaviour. If order is large enough,
 * we can steal whole pageblock. If not, we first move freepages in this
 * pageblock to our migratetype and determine how many already-allocated pages
 * are there in the pageblock with a compatible migratetype. If at least half
 * of pages are free or compatible, we can change migratetype of the pageblock
 * itself, so pages freed in the future will be put on the correct free list.
 */
static void steal_suitable_fallback(struct zone *zone, struct page *page,
                unsigned int alloc_flags, int start_type, bool whole_block)
{
        unsigned int current_order = buddy_order(page);
        int free_pages, movable_pages, alike_pages;
        int old_block_type;

        old_block_type = get_pageblock_migratetype(page);

        /*
         * This can happen due to races and we want to prevent broken
         * highatomic accounting.
         */
        if (is_migrate_highatomic(old_block_type))
                goto single_page;

        /* Take ownership for orders >= pageblock_order */
        if (current_order >= pageblock_order) {
                change_pageblock_range(page, current_order, start_type);
                goto single_page;
        }

        /*
         * Boost watermarks to increase reclaim pressure to reduce the
         * likelihood of future fallbacks. Wake kswapd now as the node
         * may be balanced overall and kswapd will not wake naturally.
         */
        if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD))
                set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);

        /* We are not allowed to try stealing from the whole block */
        if (!whole_block)
                goto single_page;

        free_pages = move_freepages_block(zone, page, start_type,
                                                &movable_pages);
        /*
         * Determine how many pages are compatible with our allocation.
         * For movable allocation, it's the number of movable pages which
         * we just obtained. For other types it's a bit more tricky.
         */
        if (start_type == MIGRATE_MOVABLE) {
                alike_pages = movable_pages;
        } else {
                /*
                 * If we are falling back a RECLAIMABLE or UNMOVABLE allocation
                 * to MOVABLE pageblock, consider all non-movable pages as
                 * compatible. If it's UNMOVABLE falling back to RECLAIMABLE or
                 * vice versa, be conservative since we can't distinguish the
                 * exact migratetype of non-movable pages.
                 */
                if (old_block_type == MIGRATE_MOVABLE)
                        alike_pages = pageblock_nr_pages
                                                - (free_pages + movable_pages);
                else
                        alike_pages = 0;
        }

        /* moving whole block can fail due to zone boundary conditions */
        if (!free_pages)
                goto single_page;

        /*
         * If a sufficient number of pages in the block are either free or of
         * comparable migratability as our allocation, claim the whole block.
         */
        if (free_pages + alike_pages >= (1 << (pageblock_order-1)) ||
                        page_group_by_mobility_disabled)
                set_pageblock_migratetype(page, start_type);

        return;

single_page:
        move_to_free_list(page, zone, current_order, start_type);
}

/*
 * Check whether there is a suitable fallback freepage with requested order.
 * If only_stealable is true, this function returns fallback_mt only if
 * we can steal other freepages all together. This would help to reduce
 * fragmentation due to mixed migratetype pages in one pageblock.
 */
int find_suitable_fallback(struct free_area *area, unsigned int order,
                        int migratetype, bool only_stealable, bool *can_steal)
{
        int i;
        int fallback_mt;

        if (area->nr_free == 0)
                return -1;

        *can_steal = false;
        for (i = 0;; i++) {
                fallback_mt = fallbacks[migratetype][i];
                if (fallback_mt == MIGRATE_TYPES)
                        break;

                if (free_area_empty(area, fallback_mt))
                        continue;

                if (can_steal_fallback(order, migratetype))
                        *can_steal = true;

                if (!only_stealable)
                        return fallback_mt;

                if (*can_steal)
                        return fallback_mt;
        }

        return -1;
}

/*
 * Reserve a pageblock for exclusive use of high-order atomic allocations if
 * there are no empty page blocks that contain a page with a suitable order
 */
static void reserve_highatomic_pageblock(struct page *page, struct zone *zone,
                                unsigned int alloc_order)
{
        int mt;
        unsigned long max_managed, flags;

        /*
         * Limit the number reserved to 1 pageblock or roughly 1% of a zone.
         * Check is race-prone but harmless.
         */
        max_managed = (zone_managed_pages(zone) / 100) + pageblock_nr_pages;
        if (zone->nr_reserved_highatomic >= max_managed)
                return;

        spin_lock_irqsave(&zone->lock, flags);

        /* Recheck the nr_reserved_highatomic limit under the lock */
        if (zone->nr_reserved_highatomic >= max_managed)
                goto out_unlock;

        /* Yoink! */
        mt = get_pageblock_migratetype(page);
        if (!is_migrate_highatomic(mt) && !is_migrate_isolate(mt)
            && !is_migrate_cma(mt)) {
                zone->nr_reserved_highatomic += pageblock_nr_pages;
                set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC);
                move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL);
        }

out_unlock:
        spin_unlock_irqrestore(&zone->lock, flags);
}

/*
 * Used when an allocation is about to fail under memory pressure. This
 * potentially hurts the reliability of high-order allocations when under
 * intense memory pressure but failed atomic allocations should be easier
 * to recover from than an OOM.
 *
 * If @force is true, try to unreserve a pageblock even though highatomic
 * pageblock is exhausted.
 */
static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
                                                bool force)
{
        struct zonelist *zonelist = ac->zonelist;
        unsigned long flags;
        struct zoneref *z;
        struct zone *zone;
        struct page *page;
        int order;
        bool ret;

        for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx,
                                                                ac->nodemask) {
                /*
                 * Preserve at least one pageblock unless memory pressure
                 * is really high.
                 */
                if (!force && zone->nr_reserved_highatomic <=
                                        pageblock_nr_pages)
                        continue;

                spin_lock_irqsave(&zone->lock, flags);
                for (order = 0; order < MAX_ORDER; order++) {
                        struct free_area *area = &(zone->free_area[order]);

                        page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC);
                        if (!page)
                                continue;

                        /*
                         * In page freeing path, migratetype change is racy so
                         * we can counter several free pages in a pageblock
                         * in this loop although we changed the pageblock type
                         * from highatomic to ac->migratetype. So we should
                         * adjust the count once.
                         */
                        if (is_migrate_highatomic_page(page)) {
                                /*
                                 * It should never happen but changes to
                                 * locking could inadvertently allow a per-cpu
                                 * drain to add pages to MIGRATE_HIGHATOMIC
                                 * while unreserving so be safe and watch for
                                 * underflows.
                                 */
                                zone->nr_reserved_highatomic -= min(
                                                pageblock_nr_pages,
                                                zone->nr_reserved_highatomic);
                        }

                        /*
                         * Convert to ac->migratetype and avoid the normal
                         * pageblock stealing heuristics. Minimally, the caller
                         * is doing the work and needs the pages. More
                         * importantly, if the block was always converted to
                         * MIGRATE_UNMOVABLE or another type then the number
                         * of pageblocks that cannot be completely freed
                         * may increase.
                         */
                        set_pageblock_migratetype(page, ac->migratetype);
                        ret = move_freepages_block(zone, page, ac->migratetype,
                                                                        NULL);
                        if (ret) {
                                spin_unlock_irqrestore(&zone->lock, flags);
                                return ret;
                        }
                }
                spin_unlock_irqrestore(&zone->lock, flags);
        }

        return false;
}

/*
 * Try finding a free buddy page on the fallback list and put it on the free
 * list of requested migratetype, possibly along with other pages from the same
 * block, depending on fragmentation avoidance heuristics. Returns true if
 * fallback was found so that __rmqueue_smallest() can grab it.
 *
 * The use of signed ints for order and current_order is a deliberate
 * deviation from the rest of this file, to make the for loop
 * condition simpler.
 */
static __always_inline bool
__rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
                                                unsigned int alloc_flags)
{
        struct free_area *area;
        int current_order;
        int min_order = order;
        struct page *page;
        int fallback_mt;
        bool can_steal;

        /*
         * Do not steal pages from freelists belonging to other pageblocks
         * i.e. orders < pageblock_order. If there are no local zones free,
         * the zonelists will be reiterated without ALLOC_NOFRAGMENT.
         */
        if (alloc_flags & ALLOC_NOFRAGMENT)
                min_order = pageblock_order;

        /*
         * Find the largest available free page in the other list. This roughly
         * approximates finding the pageblock with the most free pages, which
         * would be too costly to do exactly.
         */
        for (current_order = MAX_ORDER - 1; current_order >= min_order;
                                --current_order) {
                area = &(zone->free_area[current_order]);
                fallback_mt = find_suitable_fallback(area, current_order,
                                start_migratetype, false, &can_steal);
                if (fallback_mt == -1)
                        continue;

                /*
                 * We cannot steal all free pages from the pageblock and the
                 * requested migratetype is movable. In that case it's better to
                 * steal and split the smallest available page instead of the
                 * largest available page, because even if the next movable
                 * allocation falls back into a different pageblock than this
                 * one, it won't cause permanent fragmentation.
                 */
                if (!can_steal && start_migratetype == MIGRATE_MOVABLE
                                        && current_order > order)
                        goto find_smallest;

                goto do_steal;
        }

        return false;

find_smallest:
        for (current_order = order; current_order < MAX_ORDER;
                                                        current_order++) {
                area = &(zone->free_area[current_order]);
                fallback_mt = find_suitable_fallback(area, current_order,
                                start_migratetype, false, &can_steal);
                if (fallback_mt != -1)
                        break;
        }

        /*
         * This should not happen - we already found a suitable fallback
         * when looking for the largest page.
         */
        VM_BUG_ON(current_order == MAX_ORDER);

do_steal:
        page = get_page_from_free_area(area, fallback_mt);

        steal_suitable_fallback(zone, page, alloc_flags, start_migratetype,
                                                                can_steal);

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

        return true;

}

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

        if (IS_ENABLED(CONFIG_CMA)) {
                /*
                 * Balance movable allocations between regular and CMA areas by
                 * allocating from CMA when over half of the zone's free memory
                 * is in the CMA area.
                 */
                if (alloc_flags & ALLOC_CMA &&
                    zone_page_state(zone, NR_FREE_CMA_PAGES) >
                    zone_page_state(zone, NR_FREE_PAGES) / 2) {
                        page = __rmqueue_cma_fallback(zone, order);
                        if (page)
                                goto out;
                }
        }
retry:
        page = __rmqueue_smallest(zone, order, migratetype);
        if (unlikely(!page)) {
                if (alloc_flags & ALLOC_CMA)
                        page = __rmqueue_cma_fallback(zone, order);

                if (!page && __rmqueue_fallback(zone, order, migratetype,

                                                                alloc_flags))
                        goto retry;
        }
out:
        if (page)
                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, unsigned int alloc_flags)
{
        int i, allocated = 0;

        /*
         * local_lock_irq held so equivalent to spin_lock_irqsave for
         * both PREEMPT_RT and non-PREEMPT_RT configurations.
         */
        spin_lock(&zone->lock);
        for (i = 0; i < count; ++i) {
                struct page *page = __rmqueue(zone, order, migratetype,
                                                                alloc_flags);
                if (unlikely(page == NULL))
                        break;

                if (unlikely(check_pcp_refill(page)))
                        continue;

                /*
                 * Split buddy pages returned by expand() are received here in
                 * physical page order. The page is added to the tail of
                 * caller's list. From the callers perspective, the linked list
                 * is ordered by page number under some conditions. This is
                 * useful for IO devices that can forward direction from the
                 * head, thus also in the physical page order. This is useful
                 * for IO devices that can merge IO requests if the physical
                 * pages are ordered properly.
                 */
                list_add_tail(&page->lru, list);
                allocated++;
                if (is_migrate_cma(get_pcppage_migratetype(page)))
                        __mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
                                              -(1 << order));
        }

        /*
         * i pages were removed from the buddy list even if some leak due
         * to check_pcp_refill failing so adjust NR_FREE_PAGES based
         * on i. Do not confuse with 'allocated' which is the number of
         * pages added to the pcp list.
         */
        __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
        spin_unlock(&zone->lock);
        return allocated;
}

#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, batch;

        local_lock_irqsave(&pagesets.lock, flags);
        batch = READ_ONCE(pcp->batch);
        to_drain = min(pcp->count, batch);
        if (to_drain > 0)
                free_pcppages_bulk(zone, to_drain, pcp);
        local_unlock_irqrestore(&pagesets.lock, flags);
}
#endif

/*
 * Drain pcplists of the indicated processor and zone.
 *
 * 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_zone(unsigned int cpu, struct zone *zone)
{
        unsigned long flags;
        struct per_cpu_pages *pcp;

        local_lock_irqsave(&pagesets.lock, flags);

        pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
        if (pcp->count)
                free_pcppages_bulk(zone, pcp->count, pcp);

        local_unlock_irqrestore(&pagesets.lock, flags);
}

/*
 * Drain pcplists of all zones on 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)
{
        struct zone *zone;

        for_each_populated_zone(zone) {
                drain_pages_zone(cpu, zone);
        }
}

/*
 * Spill all of this CPU's per-cpu pages back into the buddy allocator.
 *
 * The CPU has to be pinned. When zone parameter is non-NULL, spill just
 * the single zone's pages.
 */
void drain_local_pages(struct zone *zone)
{
        int cpu = smp_processor_id();

        if (zone)
                drain_pages_zone(cpu, zone);
        else
                drain_pages(cpu);
}

static void drain_local_pages_wq(struct work_struct *work)
{
        struct pcpu_drain *drain;

        drain = container_of(work, struct pcpu_drain, work);

        /*
         * drain_all_pages doesn't use proper cpu hotplug protection so
         * we can race with cpu offline when the WQ can move this from
         * a cpu pinned worker to an unbound one. We can operate on a different
         * cpu which is alright but we also have to make sure to not move to
         * a different one.
         */
        preempt_disable();
        drain_local_pages(drain->zone);
        preempt_enable();
}

/*
 * The implementation of drain_all_pages(), exposing an extra parameter to
 * drain on all cpus.
 *
 * drain_all_pages() is optimized to only execute on cpus where pcplists are
 * not empty. The check for non-emptiness can however race with a free to
 * pcplist that has not yet increased the pcp->count from 0 to 1. Callers
 * that need the guarantee that every CPU has drained can disable the
 * optimizing racy check.
 */
static void __drain_all_pages(struct zone *zone, bool force_all_cpus)
{
        int cpu;

        /*
         * Allocate in the BSS so we won't require allocation in
         * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
         */
        static cpumask_t cpus_with_pcps;

        /*
         * Make sure nobody triggers this path before mm_percpu_wq is fully
         * initialized.
         */
        if (WARN_ON_ONCE(!mm_percpu_wq))
                return;

        /*
         * Do not drain if one is already in progress unless it's specific to
         * a zone. Such callers are primarily CMA and memory hotplug and need
         * the drain to be complete when the call returns.
         */
        if (unlikely(!mutex_trylock(&pcpu_drain_mutex))) {
                if (!zone)
                        return;
                mutex_lock(&pcpu_drain_mutex);
        }

        /*
         * We don't care about racing with CPU hotplug event
         * as offline notification will cause the notified
         * cpu to drain that CPU pcps and on_each_cpu_mask
         * disables preemption as part of its processing
         */
        for_each_online_cpu(cpu) {
                struct per_cpu_pages *pcp;
                struct zone *z;
                bool has_pcps = false;

                if (force_all_cpus) {
                        /*
                         * The pcp.count check is racy, some callers need a
                         * guarantee that no cpu is missed.
                         */
                        has_pcps = true;
                } else if (zone) {
                        pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
                        if (pcp->count)
                                has_pcps = true;
                } else {
                        for_each_populated_zone(z) {
                                pcp = per_cpu_ptr(z->per_cpu_pageset, cpu);
                                if (pcp->count) {
                                        has_pcps = true;
                                        break;
                                }
                        }
                }

                if (has_pcps)
                        cpumask_set_cpu(cpu, &cpus_with_pcps);
                else
                        cpumask_clear_cpu(cpu, &cpus_with_pcps);
        }

        for_each_cpu(cpu, &cpus_with_pcps) {
                struct pcpu_drain *drain = per_cpu_ptr(&pcpu_drain, cpu);

                drain->zone = zone;
                INIT_WORK(&drain->work, drain_local_pages_wq);
                queue_work_on(cpu, mm_percpu_wq, &drain->work);
        }
        for_each_cpu(cpu, &cpus_with_pcps)
                flush_work(&per_cpu_ptr(&pcpu_drain, cpu)->work);

        mutex_unlock(&pcpu_drain_mutex);
}

/*
 * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
 *
 * When zone parameter is non-NULL, spill just the single zone's pages.
 *
 * Note that this can be extremely slow as the draining happens in a workqueue.
 */
void drain_all_pages(struct zone *zone)
{
        __drain_all_pages(zone, false);
}

#ifdef CONFIG_HIBERNATION

/*
 * Touch the watchdog for every WD_PAGE_COUNT pages.
 */
#define WD_PAGE_COUNT   (128*1024)

void mark_free_pages(struct zone *zone)
{
        unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT;
        unsigned long flags;
        unsigned int order, t;
        struct page *page;

        if (zone_is_empty(zone))
                return;

        spin_lock_irqsave(&zone->lock, flags);

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

                        if (!--page_count) {
                                touch_nmi_watchdog();
                                page_count = WD_PAGE_COUNT;
                        }

                        if (page_zone(page) != zone)
                                continue;

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

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

                        pfn = page_to_pfn(page);
                        for (i = 0; i < (1UL << order); i++) {
                                if (!--page_count) {
                                        touch_nmi_watchdog();
                                        page_count = WD_PAGE_COUNT;
                                }
                                swsusp_set_page_free(pfn_to_page(pfn + i));
                        }
                }
        }
        spin_unlock_irqrestore(&zone->lock, flags);
}
#endif /* CONFIG_PM */

static bool free_unref_page_prepare(struct page *page, unsigned long pfn,
                                                        unsigned int order)
{
        int migratetype;

        if (!free_pcp_prepare(page, order))
                return false;

        migratetype = get_pfnblock_migratetype(page, pfn);
        set_pcppage_migratetype(page, migratetype);
        return true;
}

static int nr_pcp_free(struct per_cpu_pages *pcp, int high, int batch)
{
        int min_nr_free, max_nr_free;

        /* Check for PCP disabled or boot pageset */
        if (unlikely(high < batch))
                return 1;

        /* Leave at least pcp->batch pages on the list */
        min_nr_free = batch;
        max_nr_free = high - batch;

        /*
         * Double the number of pages freed each time there is subsequent
         * freeing of pages without any allocation.
         */
        batch <<= pcp->free_factor;
        if (batch < max_nr_free)
                pcp->free_factor++;
        batch = clamp(batch, min_nr_free, max_nr_free);

        return batch;
}

static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone)
{
        int high = READ_ONCE(pcp->high);

        if (unlikely(!high))
                return 0;

        if (!test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags))
                return high;

        /*
         * If reclaim is active, limit the number of pages that can be
         * stored on pcp lists
         */
        return min(READ_ONCE(pcp->batch) << 2, high);
}

static void free_unref_page_commit(struct page *page, unsigned long pfn,
                                   int migratetype, unsigned int order)
{
        struct zone *zone = page_zone(page);
        struct per_cpu_pages *pcp;
        int high;
        int pindex;

        __count_vm_event(PGFREE);
        pcp = this_cpu_ptr(zone->per_cpu_pageset);
        pindex = order_to_pindex(migratetype, order);
        list_add(&page->lru, &pcp->lists[pindex]);
        pcp->count += 1 << order;
        high = nr_pcp_high(pcp, zone);
        if (pcp->count >= high) {
                int batch = READ_ONCE(pcp->batch);

                free_pcppages_bulk(zone, nr_pcp_free(pcp, high, batch), pcp);
        }
}

/*
 * Free a pcp page
 */
void free_unref_page(struct page *page, unsigned int order)
{
        unsigned long flags;
        unsigned long pfn = page_to_pfn(page);
        int migratetype;

        if (!free_unref_page_prepare(page, pfn, order))
                return;

        /*
         * We only track unmovable, reclaimable and movable on pcp lists.
         * Place ISOLATE pages on the isolated list because they are being
         * offlined but treat HIGHATOMIC as movable pages so we can get those
         * areas back if necessary. Otherwise, we may have to free
         * excessively into the page allocator
         */
        migratetype = get_pcppage_migratetype(page);
        if (unlikely(migratetype >= MIGRATE_PCPTYPES)) {
                if (unlikely(is_migrate_isolate(migratetype))) {
                        free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE);
                        return;
                }
                migratetype = MIGRATE_MOVABLE;
        }

        local_lock_irqsave(&pagesets.lock, flags);
        free_unref_page_commit(page, pfn, migratetype, order);
        local_unlock_irqrestore(&pagesets.lock, flags);
}

/*
 * Free a list of 0-order pages
 */
void free_unref_page_list(struct list_head *list)
{
        struct page *page, *next;
        unsigned long flags, pfn;
        int batch_count = 0;
        int migratetype;

        /* Prepare pages for freeing */
        list_for_each_entry_safe(page, next, list, lru) {
                pfn = page_to_pfn(page);
                if (!free_unref_page_prepare(page, pfn, 0)) {
                        list_del(&page->lru);
                        continue;
                }

                /*
                 * Free isolated pages directly to the allocator, see
                 * comment in free_unref_page.
                 */
                migratetype = get_pcppage_migratetype(page);
                if (unlikely(is_migrate_isolate(migratetype))) {
                        list_del(&page->lru);
                        free_one_page(page_zone(page), page, pfn, 0, migratetype, FPI_NONE);
                        continue;
                }

                set_page_private(page, pfn);
        }

        local_lock_irqsave(&pagesets.lock, flags);
        list_for_each_entry_safe(page, next, list, lru) {
                pfn = page_private(page);
                set_page_private(page, 0);

                /*
                 * Non-isolated types over MIGRATE_PCPTYPES get added
                 * to the MIGRATE_MOVABLE pcp list.
                 */
                migratetype = get_pcppage_migratetype(page);
                if (unlikely(migratetype >= MIGRATE_PCPTYPES))
                        migratetype = MIGRATE_MOVABLE;

                trace_mm_page_free_batched(page);
                free_unref_page_commit(page, pfn, migratetype, 0);

                /*
                 * Guard against excessive IRQ disabled times when we get
                 * a large list of pages to free.
                 */
                if (++batch_count == SWAP_CLUSTER_MAX) {
                        local_unlock_irqrestore(&pagesets.lock, flags);
                        batch_count = 0;
                        local_lock_irqsave(&pagesets.lock, flags);
                }
        }
        local_unlock_irqrestore(&pagesets.lock, 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_PAGE(PageCompound(page), page);
        VM_BUG_ON_PAGE(!page_count(page), page);

        for (i = 1; i < (1 << order); i++)
                set_page_refcounted(page + i);
        split_page_owner(page, 1 << order);
        split_page_memcg(page, 1 << order);
}
EXPORT_SYMBOL_GPL(split_page);

int __isolate_free_page(struct page *page, unsigned int order)
{
        unsigned long watermark;
        struct zone *zone;
        int mt;

        BUG_ON(!PageBuddy(page));

        zone = page_zone(page);
        mt = get_pageblock_migratetype(page);

        if (!is_migrate_isolate(mt)) {
                /*
                 * Obey watermarks as if the page was being allocated. We can
                 * emulate a high-order watermark check with a raised order-0
                 * watermark, because we already know our high-order page
                 * exists.
                 */
                watermark = zone->_watermark[WMARK_MIN] + (1UL << order);
                if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
                        return 0;

                __mod_zone_freepage_state(zone, -(1UL << order), mt);
        }

        /* Remove page from free list */

        del_page_from_free_list(page, zone, order);

        /*
         * Set the pageblock if the isolated page is at least half of a
         * pageblock
         */
        if (order >= pageblock_order - 1) {
                struct page *endpage = page + (1 << order) - 1;
                for (; page < endpage; page += pageblock_nr_pages) {
                        int mt = get_pageblock_migratetype(page);
                        if (!is_migrate_isolate(mt) && !is_migrate_cma(mt)
                            && !is_migrate_highatomic(mt))
                                set_pageblock_migratetype(page,
                                                          MIGRATE_MOVABLE);
                }
        }


        return 1UL << order;
}

/**
 * __putback_isolated_page - Return a now-isolated page back where we got it
 * @page: Page that was isolated
 * @order: Order of the isolated page
 * @mt: The page's pageblock's migratetype
 *
 * This function is meant to return a page pulled from the free lists via
 * __isolate_free_page back to the free lists they were pulled from.
 */
void __putback_isolated_page(struct page *page, unsigned int order, int mt)
{
        struct zone *zone = page_zone(page);

        /* zone lock should be held when this function is called */
        lockdep_assert_held(&zone->lock);

        /* Return isolated page to tail of freelist. */
        __free_one_page(page, page_to_pfn(page), zone, order, mt,
                        FPI_SKIP_REPORT_NOTIFY | FPI_TO_TAIL);
}

/*
 * Update NUMA hit/miss statistics
 *
 * Must be called with interrupts disabled.
 */
static inline void zone_statistics(struct zone *preferred_zone, struct zone *z,
                                   long nr_account)
{
#ifdef CONFIG_NUMA
        enum numa_stat_item local_stat = NUMA_LOCAL;

        /* skip numa counters update if numa stats is disabled */
        if (!static_branch_likely(&vm_numa_stat_key))
                return;

        if (zone_to_nid(z) != numa_node_id())
                local_stat = NUMA_OTHER;

        if (zone_to_nid(z) == zone_to_nid(preferred_zone))
                __count_numa_events(z, NUMA_HIT, nr_account);
        else {
                __count_numa_events(z, NUMA_MISS, nr_account);
                __count_numa_events(preferred_zone, NUMA_FOREIGN, nr_account);
        }
        __count_numa_events(z, local_stat, nr_account);
#endif
}

/* Remove page from the per-cpu list, caller must protect the list */
static inline
struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order,
                        int migratetype,
                        unsigned int alloc_flags,
                        struct per_cpu_pages *pcp,
                        struct list_head *list)
{
        struct page *page;

        do {
                if (list_empty(list)) {
                        int batch = READ_ONCE(pcp->batch);
                        int alloced;

                        /*
                         * Scale batch relative to order if batch implies
                         * free pages can be stored on the PCP. Batch can
                         * be 1 for small zones or for boot pagesets which
                         * should never store free pages as the pages may
                         * belong to arbitrary zones.
                         */
                        if (batch > 1)
                                batch = max(batch >> order, 2);
                        alloced = rmqueue_bulk(zone, order,
                                        batch, list,
                                        migratetype, alloc_flags);

                        pcp->count += alloced << order;
                        if (unlikely(list_empty(list)))
                                return NULL;
                }

                page = list_first_entry(list, struct page, lru);
                list_del(&page->lru);
                pcp->count -= 1 << order;
        } while (check_new_pcp(page));

        return page;
}

/* Lock and remove page from the per-cpu list */
static struct page *rmqueue_pcplist(struct zone *preferred_zone,
                        struct zone *zone, unsigned int order,
                        gfp_t gfp_flags, int migratetype,
                        unsigned int alloc_flags)
{
        struct per_cpu_pages *pcp;
        struct list_head *list;
        struct page *page;
        unsigned long flags;

        local_lock_irqsave(&pagesets.lock, flags);

        /*
         * On allocation, reduce the number of pages that are batch freed.
         * See nr_pcp_free() where free_factor is increased for subsequent
         * frees.
         */
        pcp = this_cpu_ptr(zone->per_cpu_pageset);
        pcp->free_factor >>= 1;
        list = &pcp->lists[order_to_pindex(migratetype, order)];
        page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list);
        local_unlock_irqrestore(&pagesets.lock, flags);
        if (page) {
                __count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
                zone_statistics(preferred_zone, zone, 1);
        }
        return page;
}

/*
 * Allocate a page from the given zone. Use pcplists for order-0 allocations.
 */
static inline
struct page *rmqueue(struct zone *preferred_zone,
                        struct zone *zone, unsigned int order,
                        gfp_t gfp_flags, unsigned int alloc_flags,
                        int migratetype)
{
        unsigned long flags;
        struct page *page;

        if (likely(pcp_allowed_order(order))) {
                /*
                 * MIGRATE_MOVABLE pcplist could have the pages on CMA area and
                 * we need to skip it when CMA area isn't allowed.
                 */
                if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA ||
                                migratetype != MIGRATE_MOVABLE) {
                        page = rmqueue_pcplist(preferred_zone, zone, order,
                                        gfp_flags, migratetype, alloc_flags);
                        goto out;
                }
        }

        /*
         * We most definitely don't want callers attempting to
         * allocate greater than order-1 page units with __GFP_NOFAIL.
         */
        WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
        spin_lock_irqsave(&zone->lock, flags);

        do {
                page = NULL;
                /*
                 * order-0 request can reach here when the pcplist is skipped
                 * due to non-CMA allocation context. HIGHATOMIC area is
                 * reserved for high-order atomic allocation, so order-0
                 * request should skip it.
                 */
                if (order > 0 && alloc_flags & ALLOC_HARDER) {
                        page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
                        if (page)
                                trace_mm_page_alloc_zone_locked(page, order, migratetype);
                }
                if (!page)
                        page = __rmqueue(zone, order, migratetype, alloc_flags);
        } while (page && check_new_pages(page, order));
        if (!page)
                goto failed;

        __mod_zone_freepage_state(zone, -(1 << order),
                                  get_pcppage_migratetype(page));
        spin_unlock_irqrestore(&zone->lock, flags);

        __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
        zone_statistics(preferred_zone, zone, 1);

out:
        /* Separate test+clear to avoid unnecessary atomics */
        if (test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags)) {
                clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);
                wakeup_kswapd(zone, 0, 0, zone_idx(zone));
        }

        VM_BUG_ON_PAGE(page && bad_range(zone, page), page);
        return page;

failed:
        spin_unlock_irqrestore(&zone->lock, flags);
        return NULL;
}

#ifdef CONFIG_FAIL_PAGE_ALLOC

static struct {
        struct fault_attr attr;

        bool ignore_gfp_highmem;
        bool ignore_gfp_reclaim;
        u32 min_order;
} fail_page_alloc = {
        .attr = FAULT_ATTR_INITIALIZER,
        .ignore_gfp_reclaim = true,
        .ignore_gfp_highmem = true,
        .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 bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
        if (order < fail_page_alloc.min_order)
                return false;
        if (gfp_mask & __GFP_NOFAIL)
                return false;
        if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
                return false;
        if (fail_page_alloc.ignore_gfp_reclaim &&
                        (gfp_mask & __GFP_DIRECT_RECLAIM))
                return false;

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

#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

static int __init fail_page_alloc_debugfs(void)
{
        umode_t mode = S_IFREG | 0600;
        struct dentry *dir;

        dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
                                        &fail_page_alloc.attr);

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

        return 0;
}

late_initcall(fail_page_alloc_debugfs);

#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */

#else /* CONFIG_FAIL_PAGE_ALLOC */

static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
        return false;
}

#endif /* CONFIG_FAIL_PAGE_ALLOC */

noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
        return __should_fail_alloc_page(gfp_mask, order);
}
ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);

static inline long __zone_watermark_unusable_free(struct zone *z,
                                unsigned int order, unsigned int alloc_flags)
{
        const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
        long unusable_free = (1 << order) - 1;

        /*
         * If the caller does not have rights to ALLOC_HARDER then subtract
         * the high-atomic reserves. This will over-estimate the size of the
         * atomic reserve but it avoids a search.
         */
        if (likely(!alloc_harder))
                unusable_free += z->nr_reserved_highatomic;

#ifdef CONFIG_CMA
        /* If allocation can't use CMA areas don't use free CMA pages */
        if (!(alloc_flags & ALLOC_CMA))
                unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
#endif

        return unusable_free;
}

/*
 * Return true if free base pages are above 'mark'. For high-order checks it
 * will return true of the order-0 watermark is reached and there is at least
 * one free page of a suitable size. Checking now avoids taking the zone lock
 * to check in the allocation paths if no pages are free.
 */
bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
                         int highest_zoneidx, unsigned int alloc_flags,
                         long free_pages)
{
        long min = mark;
        int o;
        const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));

        /* free_pages may go negative - that's OK */
        free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);

        if (alloc_flags & ALLOC_HIGH)
                min -= min / 2;

        if (unlikely(alloc_harder)) {
                /*
                 * OOM victims can try even harder than normal ALLOC_HARDER
                 * users on the grounds that it's definitely going to be in
                 * the exit path shortly and free memory. Any allocation it
                 * makes during the free path will be small and short-lived.
                 */
                if (alloc_flags & ALLOC_OOM)
                        min -= min / 2;
                else
                        min -= min / 4;
        }

        /*
         * Check watermarks for an order-0 allocation request. If these
         * are not met, then a high-order request also cannot go ahead
         * even if a suitable page happened to be free.
         */
        if (free_pages <= min + z->lowmem_reserve[highest_zoneidx])
                return false;

        /* If this is an order-0 request then the watermark is fine */
        if (!order)
                return true;

        /* For a high-order request, check at least one suitable page is free */
        for (o = order; o < MAX_ORDER; o++) {
                struct free_area *area = &z->free_area[o];
                int mt;

                if (!area->nr_free)
                        continue;

                for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
                        if (!free_area_empty(area, mt))
                                return true;
                }

#ifdef CONFIG_CMA
                if ((alloc_flags & ALLOC_CMA) &&
                    !free_area_empty(area, MIGRATE_CMA)) {
                        return true;
                }
#endif
                if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC))
                        return true;
        }
        return false;
}

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

static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
                                unsigned long mark, int highest_zoneidx,
                                unsigned int alloc_flags, gfp_t gfp_mask)
{
        long free_pages;

        free_pages = zone_page_state(z, NR_FREE_PAGES);

        /*
         * Fast check for order-0 only. If this fails then the reserves
         * need to be calculated.
         */
        if (!order) {
                long fast_free;

                fast_free = free_pages;
                fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
                if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
                        return true;
        }

        if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
                                        free_pages))
                return true;
        /*
         * Ignore watermark boosting for GFP_ATOMIC order-0 allocations
         * when checking the min watermark. The min watermark is the
         * point where boosting is ignored so that kswapd is woken up
         * when below the low watermark.
         */
        if (unlikely(!order && (gfp_mask & __GFP_ATOMIC) && z->watermark_boost
                && ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) {
                mark = z->_watermark[WMARK_MIN];
                return __zone_watermark_ok(z, order, mark, highest_zoneidx,
                                        alloc_flags, free_pages);
        }

        return false;
}

bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
                        unsigned long mark, int highest_zoneidx)
{
        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, highest_zoneidx, 0,
                                                                free_pages);
}

#ifdef CONFIG_NUMA
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
        return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
                                node_reclaim_distance;
}
#else   /* CONFIG_NUMA */
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
        return true;
}
#endif  /* CONFIG_NUMA */

/*
 * The restriction on ZONE_DMA32 as being a suitable zone to use to avoid
 * fragmentation is subtle. If the preferred zone was HIGHMEM then
 * premature use of a lower zone may cause lowmem pressure problems that
 * are worse than fragmentation. If the next zone is ZONE_DMA then it is
 * probably too small. It only makes sense to spread allocations to avoid
 * fragmentation between the Normal and DMA32 zones.
 */
static inline unsigned int
alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
{
        unsigned int alloc_flags;

        /*
         * __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
         * to save a branch.
         */
        alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM);