mm: define memblock_virt_alloc_try_nid_raw

[sfrench/cifs-2.6.git] / mm / page_alloc.c

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

#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/jiffies.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/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/notifier.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>
#include <linux/vmstat.h>
#include <linux/mempolicy.h>
#include <linux/memremap.h>
#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <linux/pfn.h>
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
#include <linux/page-isolation.h>
#include <linux/page_ext.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/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 <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"

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

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

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

/* work_structs for global per-cpu drains */
DEFINE_MUTEX(pcpu_drain_mutex);
DEFINE_PER_CPU(struct work_struct, 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);

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

unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
unsigned long totalcma_pages __read_mostly;

int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;

/*
 * 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 pm_mutex held (gfp_allowed_mask also should
 * only be modified with pm_mutex held, unless the suspend/hibernate code is
 * guaranteed not to run in parallel with that modification).
 */

static gfp_t saved_gfp_mask;

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

void pm_restrict_gfp_mask(void)
{
        WARN_ON(!mutex_is_locked(&pm_mutex));
        WARN_ON(saved_gfp_mask);
        saved_gfp_mask = gfp_allowed_mask;
        gfp_allowed_mask &= ~(__GFP_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);

/*
 * 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-1] = {
#ifdef CONFIG_ZONE_DMA
         256,
#endif
#ifdef CONFIG_ZONE_DMA32
         256,
#endif
#ifdef CONFIG_HIGHMEM
         32,
#endif
         32,
};

EXPORT_SYMBOL(totalram_pages);

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

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[] = {
        NULL,
        free_compound_page,
#ifdef CONFIG_HUGETLB_PAGE
        free_huge_page,
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
        free_transhuge_page,
#endif
};

int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
int watermark_scale_factor = 10;

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

#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
static unsigned long __initdata required_kernelcore;
static unsigned long __initdata required_movablecore;
static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
static bool mirrored_kernelcore;

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

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

int page_group_by_mobility_disabled __read_mostly;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static inline void reset_deferred_meminit(pg_data_t *pgdat)
{
        unsigned long max_initialise;
        unsigned long reserved_lowmem;

        /*
         * Initialise at least 2G of a node but also take into account that
         * two large system hashes that can take up 1GB for 0.25TB/node.
         */
        max_initialise = max(2UL << (30 - PAGE_SHIFT),
                (pgdat->node_spanned_pages >> 8));

        /*
         * Compensate the all the memblock reservations (e.g. crash kernel)
         * from the initial estimation to make sure we will initialize enough
         * memory to boot.
         */
        reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
                        pgdat->node_start_pfn + max_initialise);
        max_initialise += reserved_lowmem;

        pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
        pgdat->first_deferred_pfn = ULONG_MAX;
}

/* 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 false when the remaining initialisation should be deferred until
 * later in the boot cycle when it can be parallelised.
 */
static inline bool update_defer_init(pg_data_t *pgdat,
                                unsigned long pfn, unsigned long zone_end,
                                unsigned long *nr_initialised)
{
        /* Always populate low zones for address-contrained allocations */
        if (zone_end < pgdat_end_pfn(pgdat))
                return true;
        (*nr_initialised)++;
        if ((*nr_initialised > pgdat->static_init_size) &&
            (pfn & (PAGES_PER_SECTION - 1)) == 0) {
                pgdat->first_deferred_pfn = pfn;
                return false;
        }

        return true;
}
#else
static inline void reset_deferred_meminit(pg_data_t *pgdat)
{
}

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

static inline bool update_defer_init(pg_data_t *pgdat,
                                unsigned long pfn, unsigned long zone_end,
                                unsigned long *nr_initialised)
{
        return true;
}
#endif

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

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

/**
 * 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
 * @end_bitidx: The last bit of interest to retrieve
 * @mask: mask of bits that the caller is interested in
 *
 * Return: pageblock_bits flags
 */
static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page,
                                        unsigned long pfn,
                                        unsigned long end_bitidx,
                                        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];
        bitidx += end_bitidx;
        return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
}

unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
                                        unsigned long end_bitidx,
                                        unsigned long mask)
{
        return __get_pfnblock_flags_mask(page, pfn, end_bitidx, mask);
}

static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn)
{
        return __get_pfnblock_flags_mask(page, pfn, PB_migrate_end, 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
 * @end_bitidx: The last bit of interest
 * @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 end_bitidx,
                                        unsigned long mask)
{
        unsigned long *bitmap;
        unsigned long bitidx, word_bitidx;
        unsigned long old_word, word;

        BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);

        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);

        bitidx += end_bitidx;
        mask <<= (BITS_PER_LONG - bitidx - 1);
        flags <<= (BITS_PER_LONG - bitidx - 1);

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

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

        return 1;
}
/*
 * Temporary debugging check for pages not lying within a given zone.
 */
static int __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,
                unsigned long bad_flags)
{
        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);
        bad_flags &= page->flags;
        if (bad_flags)
                pr_alert("bad because of flags: %#lx(%pGp)\n",
                                                bad_flags, &bad_flags);
        dump_page_owner(page);

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

/*
 * Higher-order pages are called "compound pages".  They are structured thusly:
 *
 * The first PAGE_SIZE page is called the "head page" 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)
{
        __free_pages_ok(page, compound_order(page));
}

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

        set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
        set_compound_order(page, order);
        __SetPageHead(page);
        for (i = 1; i < nr_pages; i++) {
                struct page *p = page + i;
                set_page_count(p, 0);
                p->mapping = TAIL_MAPPING;
                set_compound_head(p, page);
        }
        atomic_set(compound_mapcount_ptr(page), -1);
}

#ifdef CONFIG_DEBUG_PAGEALLOC
unsigned int _debug_guardpage_minorder;
bool _debug_pagealloc_enabled __read_mostly
                        = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
EXPORT_SYMBOL(_debug_pagealloc_enabled);
bool _debug_guardpage_enabled __read_mostly;

static int __init early_debug_pagealloc(char *buf)
{
        if (!buf)
                return -EINVAL;
        return kstrtobool(buf, &_debug_pagealloc_enabled);
}
early_param("debug_pagealloc", early_debug_pagealloc);

static bool need_debug_guardpage(void)
{
        /* If we don't use debug_pagealloc, we don't need guard page */
        if (!debug_pagealloc_enabled())
                return false;

        if (!debug_guardpage_minorder())
                return false;

        return true;
}

static void init_debug_guardpage(void)
{
        if (!debug_pagealloc_enabled())
                return;

        if (!debug_guardpage_minorder())
                return;

        _debug_guardpage_enabled = true;
}

struct page_ext_operations debug_guardpage_ops = {
        .need = need_debug_guardpage,
        .init = init_debug_guardpage,
};

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)
{
        struct page_ext *page_ext;

        if (!debug_guardpage_enabled())
                return false;

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

        page_ext = lookup_page_ext(page);
        if (unlikely(!page_ext))
                return false;

        __set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);

        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)
{
        struct page_ext *page_ext;

        if (!debug_guardpage_enabled())
                return;

        page_ext = lookup_page_ext(page);
        if (unlikely(!page_ext))
                return;

        __clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);

        set_page_private(page, 0);
        if (!is_migrate_isolate(migratetype))
                __mod_zone_freepage_state(zone, (1 << order), migratetype);
}
#else
struct page_ext_operations debug_guardpage_ops;
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

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

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

/*
 * This function checks whether a page is free && is the buddy
 * we can do coalesce a page and its buddy if
 * (a) the buddy is not in a hole (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 ->_mapcount
 * PAGE_BUDDY_MAPCOUNT_VALUE.
 * Setting, clearing, and testing _mapcount PAGE_BUDDY_MAPCOUNT_VALUE is
 * serialized by zone->lock.
 *
 * For recording page's order, we use page_private(page).
 */
static inline int page_is_buddy(struct page *page, struct page *buddy,
                                                        unsigned int order)
{
        if (page_is_guard(buddy) && page_order(buddy) == order) {
                if (page_zone_id(page) != page_zone_id(buddy))
                        return 0;

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

                return 1;
        }

        if (PageBuddy(buddy) && page_order(buddy) == order) {
                /*
                 * 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 0;

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

                return 1;
        }
        return 0;
}

/*
 * Freeing function for a buddy system allocator.
 *
 * The concept of a buddy system is to maintain direct-mapped table
 * (containing bit values) for memory blocks of various "orders".
 * The bottom level table contains the map for the smallest allocatable
 * units of memory (here, pages), and each level above it describes
 * pairs of units from the levels below, hence, "buddies".
 * At a high level, all that happens here is marking the table entry
 * at the bottom level available, and propagating the changes upward
 * as necessary, plus some accounting needed to play nicely with other
 * parts of the VM system.
 * At each level, we keep a list of pages, which are heads of continuous
 * free pages of length of (1 << order) and marked with _mapcount
 * PAGE_BUDDY_MAPCOUNT_VALUE. 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)
{
        unsigned long combined_pfn;
        unsigned long uninitialized_var(buddy_pfn);
        struct page *buddy;
        unsigned int max_order;

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

        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 - 1) {
                buddy_pfn = __find_buddy_pfn(pfn, order);
                buddy = page + (buddy_pfn - pfn);

                if (!pfn_valid_within(buddy_pfn))
                        goto done_merging;
                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 {
                        list_del(&buddy->lru);
                        zone->free_area[order].nr_free--;
                        rmv_page_order(buddy);
                }
                combined_pfn = buddy_pfn & pfn;
                page = page + (combined_pfn - pfn);
                pfn = combined_pfn;
                order++;
        }
        if (max_order < MAX_ORDER) {
                /* 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++;
                goto continue_merging;
        }

done_merging:
        set_page_order(page, order);

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

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

/*
 * 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
                        (unsigned long)page->mem_cgroup |
#endif
                        (page->flags & check_flags)))
                return false;

        return true;
}

static void free_pages_check_bad(struct page *page)
{
        const char *bad_reason;
        unsigned long bad_flags;

        bad_reason = NULL;
        bad_flags = 0;

        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 & PAGE_FLAGS_CHECK_AT_FREE)) {
                bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
                bad_flags = PAGE_FLAGS_CHECK_AT_FREE;
        }
#ifdef CONFIG_MEMCG
        if (unlikely(page->mem_cgroup))
                bad_reason = "page still charged to cgroup";
#endif
        bad_page(page, bad_reason, bad_flags);
}

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

        /* Something has gone sideways, find it */
        free_pages_check_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 is compound_mapcount() */
                if (unlikely(compound_mapcount(page))) {
                        bad_page(page, "nonzero compound_mapcount", 0);
                        goto out;
                }
                break;
        case 2:
                /*
                 * the second tail page: ->mapping is
                 * page_deferred_list().next -- ignore value.
                 */
                break;
        default:
                if (page->mapping != TAIL_MAPPING) {
                        bad_page(page, "corrupted mapping in tail page", 0);
                        goto out;
                }
                break;
        }
        if (unlikely(!PageTail(page))) {
                bad_page(page, "PageTail not set", 0);
                goto out;
        }
        if (unlikely(compound_head(page) != head_page)) {
                bad_page(page, "compound_head not consistent", 0);
                goto out;
        }
        ret = 0;
out:
        page->mapping = NULL;
        clear_compound_head(page);
        return ret;
}

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

        VM_BUG_ON_PAGE(PageTail(page), page);

        trace_mm_page_free(page, order);

        /*
         * 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);
                for (i = 1; i < (1 << order); i++) {
                        if (compound)
                                bad += free_tail_pages_check(page, page + i);
                        if (unlikely(free_pages_check(page + i))) {
                                bad++;
                                continue;
                        }
                        (page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
                }
        }
        if (PageMappingFlags(page))
                page->mapping = NULL;
        if (memcg_kmem_enabled() && PageKmemcg(page))
                memcg_kmem_uncharge(page, order);
        if (check_free)
                bad += free_pages_check(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);
        }
        arch_free_page(page, order);
        kernel_poison_pages(page, 1 << order, 0);
        kernel_map_pages(page, 1 << order, 0);
        kasan_free_pages(page, order);

        return true;
}

#ifdef CONFIG_DEBUG_VM
static inline bool free_pcp_prepare(struct page *page)
{
        return free_pages_prepare(page, 0, true);
}

static inline bool bulkfree_pcp_prepare(struct page *page)
{
        return false;
}
#else
static bool free_pcp_prepare(struct page *page)
{
        return free_pages_prepare(page, 0, false);
}

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

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

        spin_lock(&zone->lock);
        isolated_pageblocks = has_isolate_pageblock(zone);

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

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

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

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

                        page = list_last_entry(list, struct page, lru);
                        /* must delete as __free_one_page list manipulates */
                        list_del(&page->lru);

                        mt = get_pcppage_migratetype(page);
                        /* 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);

                        if (bulkfree_pcp_prepare(page))
                                continue;

                        __free_one_page(page, page_to_pfn(page), zone, 0, mt);
                        trace_mm_page_pcpu_drain(page, 0, mt);
                } while (--count && --batch_free && !list_empty(list));
        }
        spin_unlock(&zone->lock);
}

static void free_one_page(struct zone *zone,
                                struct page *page, unsigned long pfn,
                                unsigned int order,
                                int migratetype)
{
        spin_lock(&zone->lock);
        if (unlikely(has_isolate_pageblock(zone) ||
                is_migrate_isolate(migratetype))) {
                migratetype = get_pfnblock_migratetype(page, pfn);
        }
        __free_one_page(page, pfn, zone, order, migratetype);
        spin_unlock(&zone->lock);
}

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

static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone,
                                        int nid)
{
        return __init_single_page(pfn_to_page(pfn), pfn, zone, nid);
}

#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_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);

                        SetPageReserved(page);
                }
        }
}

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

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

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

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

        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);

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

#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
        defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)

static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;

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

#ifdef CONFIG_NODES_SPAN_OTHER_NODES
static inline bool __meminit __maybe_unused
meminit_pfn_in_nid(unsigned long pfn, int node,
                   struct mminit_pfnnid_cache *state)
{
        int nid;

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

/* Only safe to use early in boot when initialisation is single-threaded */
static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
        return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache);
}

#else

static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
        return true;
}
static inline bool __meminit  __maybe_unused
meminit_pfn_in_nid(unsigned long pfn, int node,
                   struct mminit_pfnnid_cache *state)
{
        return true;
}
#endif


void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
                                                        unsigned int order)
{
        if (early_page_uninitialised(pfn))
                return;
        return __free_pages_boot_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. The scanners then need to
 * use only pfn_valid_within() check for arches that allow holes within
 * pageblocks.
 *
 * 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;
        }

        /* 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_boot_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_boot_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);
}

/*
 * Helper for deferred_init_range, free the given range, reset the counters, and
 * return number of pages freed.
 */
static inline unsigned long __init __def_free(unsigned long *nr_free,
                                              unsigned long *free_base_pfn,
                                              struct page **page)
{
        unsigned long nr = *nr_free;

        deferred_free_range(*free_base_pfn, nr);
        *free_base_pfn = 0;
        *nr_free = 0;
        *page = NULL;

        return nr;
}

static unsigned long __init deferred_init_range(int nid, int zid,
                                                unsigned long start_pfn,
                                                unsigned long end_pfn)
{
        struct mminit_pfnnid_cache nid_init_state = { };
        unsigned long nr_pgmask = pageblock_nr_pages - 1;
        unsigned long free_base_pfn = 0;
        unsigned long nr_pages = 0;
        unsigned long nr_free = 0;
        struct page *page = NULL;
        unsigned long pfn;

        /*
         * 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.
         *
         * meminit_pfn_in_nid is checked on systems where pfns can interleave
         * within a node: a pfn is between start and end of a node, but does not
         * belong to this memory node.
         *
         * Finally, we minimize pfn page lookups and scheduler checks by
         * performing it only once every pageblock_nr_pages.
         *
         * We do it in two loops: first we initialize struct page, than free to
         * buddy allocator, becuse while we are freeing pages we can access
         * pages that are ahead (computing buddy page in __free_one_page()).
         */
        for (pfn = start_pfn; pfn < end_pfn; pfn++) {
                if (!pfn_valid_within(pfn))
                        continue;
                if ((pfn & nr_pgmask) || pfn_valid(pfn)) {
                        if (meminit_pfn_in_nid(pfn, nid, &nid_init_state)) {
                                if (page && (pfn & nr_pgmask))
                                        page++;
                                else
                                        page = pfn_to_page(pfn);
                                __init_single_page(page, pfn, zid, nid);
                                cond_resched();
                        }
                }
        }

        page = NULL;
        for (pfn = start_pfn; pfn < end_pfn; pfn++) {
                if (!pfn_valid_within(pfn)) {
                        nr_pages += __def_free(&nr_free, &free_base_pfn, &page);
                } else if (!(pfn & nr_pgmask) && !pfn_valid(pfn)) {
                        nr_pages += __def_free(&nr_free, &free_base_pfn, &page);
                } else if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) {
                        nr_pages += __def_free(&nr_free, &free_base_pfn, &page);
                } else if (page && (pfn & nr_pgmask)) {
                        page++;
                        nr_free++;
                } else {
                        nr_pages += __def_free(&nr_free, &free_base_pfn, &page);
                        page = pfn_to_page(pfn);
                        free_base_pfn = pfn;
                        nr_free = 1;
                        cond_resched();
                }
        }
        /* Free the last block of pages to allocator */
        nr_pages += __def_free(&nr_free, &free_base_pfn, &page);

        return nr_pages;
}

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

        if (first_init_pfn == ULONG_MAX) {
                pgdat_init_report_one_done();
                return 0;
        }

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

        /* 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;

        /* 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;
        }
        first_init_pfn = max(zone->zone_start_pfn, first_init_pfn);

        for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
                spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
                epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
                nr_pages += deferred_init_range(nid, zid, spfn, epfn);
        }

        /* Sanity check that the next zone really is unpopulated */
        WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));

        pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
                                        jiffies_to_msecs(jiffies - start));

        pgdat_init_report_one_done();
        return 0;
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */

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

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
        int nid;

        /* 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);

        /* Reinit limits that are based on free pages after the kernel is up */
        files_maxfiles_init();
#endif
#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
        /* Discard memblock private memory */
        memblock_discard();
#endif

        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);
}
#endif

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

        while (high > low) {
                area--;
                high--;
                size >>= 1;
                VM_BUG_ON_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;

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

static void check_new_page_bad(struct page *page)
{
        const char *bad_reason = NULL;
        unsigned long bad_flags = 0;

        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 _count";
        if (unlikely(page->flags & __PG_HWPOISON)) {
                bad_reason = "HWPoisoned (hardware-corrupted)";
                bad_flags = __PG_HWPOISON;
                /* Don't complain about hwpoisoned pages */
                page_mapcount_reset(page); /* remove PageBuddy */
                return;
        }
        if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
                bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
                bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
        }
#ifdef CONFIG_MEMCG
        if (unlikely(page->mem_cgroup))
                bad_reason = "page still charged to cgroup";
#endif
        bad_page(page, bad_reason, bad_flags);
}

/*
 * 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;
}

static inline bool free_pages_prezeroed(void)
{
        return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) &&
                page_poisoning_enabled();
}

#ifdef CONFIG_DEBUG_VM
static bool check_pcp_refill(struct page *page)
{
        return false;
}

static bool check_new_pcp(struct page *page)
{
        return check_new_page(page);
}
#else
static bool check_pcp_refill(struct page *page)
{
        return check_new_page(page);
}
static bool check_new_pcp(struct page *page)
{
        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);
        kernel_map_pages(page, 1 << order, 1);
        kernel_poison_pages(page, 1 << order, 1);
        kasan_alloc_pages(page, order);
        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)
{
        int i;

        post_alloc_hook(page, order, gfp_flags);

        if (!free_pages_prezeroed() && (gfp_flags & __GFP_ZERO))
                for (i = 0; i < (1 << order); i++)
                        clear_highpage(page + i);

        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 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 = list_first_entry_or_null(&area->free_list[migratetype],
                                                        struct page, lru);
                if (!page)
                        continue;
                list_del(&page->lru);
                rmv_page_order(page);
                area->nr_free--;
                expand(zone, page, order, current_order, area, 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][4] = {
        [MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,   MIGRATE_TYPES },
        [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,   MIGRATE_TYPES },
        [MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, 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 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 free lists of the requested type.
 * Note that start_page and end_pages are not aligned on a pageblock
 * boundary. If alignment is required, use move_freepages_block()
 */
static int move_freepages(struct zone *zone,
                          struct page *start_page, struct page *end_page,
                          int migratetype, int *num_movable)
{
        struct page *page;
        unsigned int order;
        int pages_moved = 0;

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

        if (num_movable)
                *num_movable = 0;

        for (page = start_page; page <= end_page;) {
                if (!pfn_valid_within(page_to_pfn(page))) {
                        page++;
                        continue;
                }

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

                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)++;

                        page++;
                        continue;
                }

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

        return pages_moved;
}

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

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

        /* Do not cross zone boundaries */
        if (!zone_spans_pfn(zone, start_pfn))
                start_page = page;
        if (!zone_spans_pfn(zone, end_pfn))
                return 0;

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

/*
 * 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,
                                        int start_type, bool whole_block)
{
        unsigned int current_order = page_order(page);
        struct free_area *area;
        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;
        }

        /* 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:
        area = &zone->free_area[current_order];
        list_move(&page->lru, &area->free_list[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 (list_empty(&area->free_list[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 / 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->high_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 = list_first_entry_or_null(
                                        &area->free_list[MIGRATE_HIGHATOMIC],
                                        struct page, lru);
                        if (!page)
                                continue;

                        /*
                         * In page freeing path, migratetype change is racy so
                         * we can counter several free pages in a pageblock
                         * in this loop althoug 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 inline bool
__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
{
        struct free_area *area;
        int current_order;
        struct page *page;
        int fallback_mt;
        bool can_steal;

        /*
         * 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 >= 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 = list_first_entry(&area->free_list[fallback_mt],
                                                        struct page, lru);

        steal_suitable_fallback(zone, page, 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 struct page *__rmqueue(struct zone *zone, unsigned int order,
                                int migratetype)
{
        struct page *page;

retry:
        page = __rmqueue_smallest(zone, order, migratetype);
        if (unlikely(!page)) {
                if (migratetype == MIGRATE_MOVABLE)
                        page = __rmqueue_cma_fallback(zone, order);

                if (!page && __rmqueue_fallback(zone, order, migratetype))
                        goto retry;
        }

        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, bool cold)
{
        int i, alloced = 0;

        spin_lock(&zone->lock);
        for (i = 0; i < count; ++i) {
                struct page *page = __rmqueue(zone, order, migratetype);
                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 callers and
                 * list and the list head then moves forward. From the callers
                 * perspective, the linked list is ordered by page number in
                 * some conditions. This is useful for IO devices that can
                 * merge IO requests if the physical pages are ordered
                 * properly.
                 */
                if (likely(!cold))
                        list_add(&page->lru, list);
                else
                        list_add_tail(&page->lru, list);
                list = &page->lru;
                alloced++;
                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 'alloced' 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 alloced;
}

#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_irq_save(flags);
        batch = READ_ONCE(pcp->batch);
        to_drain = min(pcp->count, batch);
        if (to_drain > 0) {
                free_pcppages_bulk(zone, to_drain, pcp);
                pcp->count -= to_drain;
        }
        local_irq_restore(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_pageset *pset;
        struct per_cpu_pages *pcp;

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

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

/*
 * 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)
{
        /*
         * 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 allright but we also have to make sure to not move to
         * a different one.
         */
        preempt_disable();
        drain_local_pages(NULL);
        preempt_enable();
}

/*
 * 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)
{
        int cpu;

        /*
         * Allocate in the BSS so we wont 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;

        /* Workqueues cannot recurse */
        if (current->flags & PF_WQ_WORKER)
                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_pageset *pcp;
                struct zone *z;
                bool has_pcps = false;

                if (zone) {
                        pcp = per_cpu_ptr(zone->pageset, cpu);
                        if (pcp->pcp.count)
                                has_pcps = true;
                } else {
                        for_each_populated_zone(z) {
                                pcp = per_cpu_ptr(z->pageset, cpu);
                                if (pcp->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 work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
                INIT_WORK(work, drain_local_pages_wq);
                queue_work_on(cpu, mm_percpu_wq, work);
        }
        for_each_cpu(cpu, &cpus_with_pcps)
                flush_work(per_cpu_ptr(&pcpu_drain, cpu));

        mutex_unlock(&pcpu_drain_mutex);
}

#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 */

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

        if (!free_pcp_prepare(page))
                return;

        migratetype = get_pfnblock_migratetype(page, pfn);
        set_pcppage_migratetype(page, migratetype);
        local_irq_save(flags);
        __count_vm_event(PGFREE);

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

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

out:
        local_irq_restore(flags);
}

/*
 * Free a list of 0-order pages
 */
void free_hot_cold_page_list(struct list_head *list, bool cold)
{
        struct page *page, *next;

        list_for_each_entry_safe(page, next, list, lru) {
                trace_mm_page_free_batched(page, cold);
                free_hot_cold_page(page, cold);
        }
}

/*
 * 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, 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 = min_wmark_pages(zone) + (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 */
        list_del(&page->lru);
        zone->free_area[order].nr_free--;
        rmv_page_order(page);

        /*
         * 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;
}

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

        if (z->node != numa_node_id())
                local_stat = NUMA_OTHER;

        if (z->node == preferred_zone->node)
                __inc_numa_state(z, NUMA_HIT);
        else {
                __inc_numa_state(z, NUMA_MISS);
                __inc_numa_state(preferred_zone, NUMA_FOREIGN);
        }
        __inc_numa_state(z, local_stat);
#endif
}

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

        do {
                if (list_empty(list)) {
                        pcp->count += rmqueue_bulk(zone, 0,
                                        pcp->batch, list,
                                        migratetype, cold);
                        if (unlikely(list_empty(list)))
                                return NULL;
                }

                if (cold)
                        page = list_last_entry(list, struct page, lru);
                else
                        page = list_first_entry(list, struct page, lru);

                list_del(&page->lru);
                pcp->count--;
        } 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)
{
        struct per_cpu_pages *pcp;
        struct list_head *list;
        bool cold = ((gfp_flags & __GFP_COLD) != 0);
        struct page *page;
        unsigned long flags;

        local_irq_save(flags);
        pcp = &this_cpu_ptr(zone->pageset)->pcp;
        list = &pcp->lists[migratetype];
        page = __rmqueue_pcplist(zone,  migratetype, cold, pcp, list);
        if (page) {
                __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
                zone_statistics(preferred_zone, zone);
        }
        local_irq_restore(flags);
        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(order == 0)) {
                page = rmqueue_pcplist(preferred_zone, zone, order,
                                gfp_flags, migratetype);
                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;
                if (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);
        } while (page && check_new_pages(page, order));
        spin_unlock(&zone->lock);
        if (!page)
                goto failed;
        __mod_zone_freepage_state(zone, -(1 << order),
                                  get_pcppage_migratetype(page));

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

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

failed:
        local_irq_restore(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 | S_IRUSR | S_IWUSR;
        struct dentry *dir;

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

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

        return 0;
fail:
        debugfs_remove_recursive(dir);

        return -ENOMEM;
}

late_initcall(fail_page_alloc_debugfs);

#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */

#else /* CONFIG_FAIL_PAGE_ALLOC */

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

#endif /* CONFIG_FAIL_PAGE_ALLOC */

/*
 * 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 classzone_idx, 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 -= (1 << order) - 1;

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

        /*
         * 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)) {
                free_pages -= z->nr_reserved_highatomic;
        } else {
                /*
                 * 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;
        }


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

        /*
         * 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[classzone_idx])
                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;

                if (alloc_harder)
                        return true;

                for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
                        if (!list_empty(&area->free_list[mt]))
                                return true;
                }

#ifdef CONFIG_CMA
                if ((alloc_flags & ALLOC_CMA) &&
                    !list_empty(&area->free_list[MIGRATE_CMA])) {
                        return true;
                }
#endif
        }
        return false;
}

bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
                      int classzone_idx, unsigned int alloc_flags)
{
        return __zone_watermark_ok(z, order, mark, classzone_idx, 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 classzone_idx, unsigned int alloc_flags)
{
        long free_pages = zone_page_state(z, NR_FREE_PAGES);
        long cma_pages = 0;

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

        /*
         * Fast check for order-0 only. If this fails then the reserves
         * need to be calculated. There is a corner case where the check
         * passes but only the high-order atomic reserve are free. If
         * the caller is !atomic then it'll uselessly search the free
         * list. That corner case is then slower but it is harmless.
         */
        if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
                return true;

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

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

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

        return __zone_watermark_ok(z, order, mark, classzone_idx, 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)) <=
                                RECLAIM_DISTANCE;
}
#else   /* CONFIG_NUMA */
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
        return true;
}
#endif  /* CONFIG_NUMA */

/*
 * get_page_from_freelist goes through the zonelist trying to allocate
 * a page.
 */
static struct page *
get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
                                                const struct alloc_context *ac)
{
        struct zoneref *z = ac->preferred_zoneref;
        struct zone *zone;
        struct pglist_data *last_pgdat_dirty_limit = NULL;

        /*
         * Scan zonelist, looking for a zone with enough free.
         * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
         */
        for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
                                                                ac->nodemask) {
                struct page *page;
                unsigned long mark;

                if (cpusets_enabled() &&
                        (alloc_flags & ALLOC_CPUSET) &&
                        !__cpuset_zone_allowed(zone, gfp_mask))
                                continue;
                /*
                 * When allocating a page cache page for writing, we
                 * want to get it from a node that is within its dirty
                 * limit, such that no single node holds more than its
                 * proportional share of globally allowed dirty pages.
                 * The dirty limits take into account the node's
                 * lowmem reserves and high watermark so that kswapd
                 * should be able to balance it without having to
                 * write pages from its LRU list.
                 *
                 * XXX: For now, allow allocations to potentially
                 * exceed the per-node dirty limit in the slowpath
                 * (spread_dirty_pages unset) before going into reclaim,
                 * which is important when on a NUMA setup the allowed
                 * nodes are together not big enough to reach the
                 * global limit.  The proper fix for these situations
                 * will require awareness of nodes in the
                 * dirty-throttling and the flusher threads.
                 */
                if (ac->spread_dirty_pages) {
                        if (last_pgdat_dirty_limit == zone->zone_pgdat)
                                continue;

                        if (!node_dirty_ok(zone->zone_pgdat)) {
                                last_pgdat_dirty_limit = zone->zone_pgdat;
                                continue;
                        }
                }

                mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
                if (!zone_watermark_fast(zone, order, mark,
                                       ac_classzone_idx(ac), alloc_flags)) {
                        int ret;

                        /* Checked here to keep the fast path fast */
                        BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
                        if (alloc_flags & ALLOC_NO_WATERMARKS)
                                goto try_this_zone;

                        if (node_reclaim_mode == 0 ||
                            !zone_allows_reclaim(ac->preferred_zoneref->zone, zone))
                                continue;

                        ret = node_reclaim(zone->zone_pgdat, gfp_mask, order);
                        switch (ret) {
                        case NODE_RECLAIM_NOSCAN:
                                /* did not scan */
                                continue;
                        case NODE_RECLAIM_FULL:
                                /* scanned but unreclaimable */
                                continue;
                        default:
                                /* did we reclaim enough */
                                if (zone_watermark_ok(zone, order, mark,
                                                ac_classzone_idx(ac), alloc_flags))
                                        goto try_this_zone;

                                continue;
                        }
                }

try_this_zone:
                page = rmqueue(ac->preferred_zoneref->zone, zone, order,
                                gfp_mask, alloc_flags, ac->migratetype);
                if (page) {
                        prep_new_page(page, order, gfp_mask, alloc_flags);

                        /*
                         * If this is a high-order atomic allocation then check
                         * if the pageblock should be reserved for the future
                         */
                        if (unlikely(order && (alloc_flags & ALLOC_HARDER)))
                                reserve_highatomic_pageblock(page, zone, order);

                        return page;
                }
        }

        return NULL;
}

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

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

static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
{
        unsigned int filter = SHOW_MEM_FILTER_NODES;
        static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1);

        if (should_suppress_show_mem() || !__ratelimit(&show_mem_rs))
                return;

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

        show_mem(filter, nodemask);
}

void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
{
        struct va_format vaf;
        va_list args;
        static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL,
                                      DEFAULT_RATELIMIT_BURST);

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

        pr_warn("%s: ", current->comm);

        va_start(args, fmt);
        vaf.fmt = fmt;
        vaf.va = &args;
        pr_cont("%pV", &vaf);
        va_end(args);

        pr_cont(", mode:%#x(%pGg), nodemask=", gfp_mask, &gfp_mask);
        if (nodemask)
                pr_cont("%*pbl\n", nodemask_pr_args(nodemask));
        else
                pr_cont("(null)\n");

        cpuset_print_current_mems_allowed();

        dump_stack();
        warn_alloc_show_mem(gfp_mask, nodemask);
}

static inline struct page *
__alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order,
                              unsigned int alloc_flags,
                              const struct alloc_context *ac)
{
        struct page *page;

        page = get_page_from_freelist(gfp_mask, order,
                        alloc_flags|ALLOC_CPUSET, ac);
        /*
         * fallback to ignore cpuset restriction if our nodes
         * are depleted
         */
        if (!page)
                page = get_page_from_freelist(gfp_mask, order,
                                alloc_flags, ac);

        return page;
}

static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
        const struct alloc_context *ac, unsigned long *did_some_progress)
{
        struct oom_control oc = {
                .zonelist = ac->zonelist,
                .nodemask = ac->nodemask,
                .memcg = NULL,
                .gfp_mask = gfp_mask,
                .order = order,
        };
        struct page *page;

        *did_some_progress = 0;

        /*
         * Acquire the oom lock.  If that fails, somebody else is
         * making progress for us.
         */
        if (!mutex_trylock(&oom_lock)) {
                *did_some_progress = 1;
                schedule_timeout_uninterruptible(1);
                return NULL;
        }

        /*
         * Go through the zonelist yet one more time, keep very high watermark
         * here, this is only to catch a parallel oom killing, we must fail if
         * we're still under heavy pressure. But make sure that this reclaim
         * attempt shall not depend on __GFP_DIRECT_RECLAIM && !__GFP_NORETRY
         * allocation which will never fail due to oom_lock already held.
         */
        page = get_page_from_freelist((gfp_mask | __GFP_HARDWALL) &
                                      ~__GFP_DIRECT_RECLAIM, order,
                                      ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);
        if (page)
                goto out;

        /* Coredumps can quickly deplete all memory reserves */
        if (current->flags & PF_DUMPCORE)
                goto out;
        /* The OOM killer will not help higher order allocs */
        if (order > PAGE_ALLOC_COSTLY_ORDER)
                goto out;
        /*
         * We have already exhausted all our reclaim opportunities without any
         * success so it is time to admit defeat. We will skip the OOM killer
         * because it is very likely that the caller has a more reasonable
         * fallback than shooting a random task.
         */
        if (gfp_mask & __GFP_RETRY_MAYFAIL)
                goto out;
        /* The OOM killer does not needlessly kill tasks for lowmem */
        if (ac->high_zoneidx < ZONE_NORMAL)
                goto out;
        if (pm_suspended_storage())
                goto out;
        /*
         * XXX: GFP_NOFS allocations should rather fail than rely on
         * other request to make a forward progress.
         * We are in an unfortunate situation where out_of_memory cannot
         * do much for this context but let's try it to at least get
         * access to memory reserved if the current task is killed (see
         * out_of_memory). Once filesystems are ready to handle allocation
         * failures more gracefully we should just bail out here.
         */

        /* The OOM killer may not free memory on a specific node */
        if (gfp_mask & __GFP_THISNODE)
                goto out;

        /* Exhausted what can be done so it's blamo time */
        if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {