TOMOYO Linux Cross Reference
Linux/mm/page_alloc.c

   // SPDX-License-Identifier: GPL-2.0-only
   /*
    *  linux/mm/page_alloc.c
    *
    *  Manages the free list, the system allocates free pages here.
    *  Note that kmalloc() lives in slab.c
    *
    *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
    *  Swap reorganised 29.12.95, Stephen Tweedie
   *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
   *  Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
   *  Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
   *  Zone balancing, Kanoj Sarcar, SGI, Jan 2000
   *  Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
   *          (lots of bits borrowed from Ingo Molnar & Andrew Morton)
   */
  
  #include <linux/stddef.h>
  #include <linux/mm.h>
  #include <linux/highmem.h>
  #include <linux/swap.h>
  #include <linux/interrupt.h>
  #include <linux/pagemap.h>
  #include <linux/jiffies.h>
  #include <linux/memblock.h>
  #include <linux/compiler.h>
  #include <linux/kernel.h>
  #include <linux/kasan.h>
  #include <linux/module.h>
  #include <linux/suspend.h>
  #include <linux/pagevec.h>
  #include <linux/blkdev.h>
  #include <linux/slab.h>
  #include <linux/ratelimit.h>
  #include <linux/oom.h>
  #include <linux/topology.h>
  #include <linux/sysctl.h>
  #include <linux/cpu.h>
  #include <linux/cpuset.h>
  #include <linux/memory_hotplug.h>
  #include <linux/nodemask.h>
  #include <linux/vmalloc.h>
  #include <linux/vmstat.h>
  #include <linux/mempolicy.h>
  #include <linux/memremap.h>
  #include <linux/stop_machine.h>
  #include <linux/random.h>
  #include <linux/sort.h>
  #include <linux/pfn.h>
  #include <linux/backing-dev.h>
  #include <linux/fault-inject.h>
  #include <linux/page-isolation.h>
  #include <linux/debugobjects.h>
  #include <linux/kmemleak.h>
  #include <linux/compaction.h>
  #include <trace/events/kmem.h>
  #include <trace/events/oom.h>
  #include <linux/prefetch.h>
  #include <linux/mm_inline.h>
  #include <linux/mmu_notifier.h>
  #include <linux/migrate.h>
  #include <linux/hugetlb.h>
  #include <linux/sched/rt.h>
  #include <linux/sched/mm.h>
  #include <linux/page_owner.h>
  #include <linux/kthread.h>
  #include <linux/memcontrol.h>
  #include <linux/ftrace.h>
  #include <linux/lockdep.h>
  #include <linux/nmi.h>
  #include <linux/psi.h>
  #include <linux/padata.h>
  #include <linux/khugepaged.h>
  #include <linux/buffer_head.h>
  #include <asm/sections.h>
  #include <asm/tlbflush.h>
  #include <asm/div64.h>
  #include "internal.h"
  #include "shuffle.h"
  #include "page_reporting.h"
  
  /* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */
  typedef int __bitwise fpi_t;
  
  /* No special request */
  #define FPI_NONE                ((__force fpi_t)0)
  
  /*
   * Skip free page reporting notification for the (possibly merged) page.
   * This does not hinder free page reporting from grabbing the page,
   * reporting it and marking it "reported" -  it only skips notifying
   * the free page reporting infrastructure about a newly freed page. For
   * example, used when temporarily pulling a page from a freelist and
   * putting it back unmodified.
   */
  #define FPI_SKIP_REPORT_NOTIFY  ((__force fpi_t)BIT(0))
  
  /*
   * Place the (possibly merged) page to the tail of the freelist. Will ignore
  * page shuffling (relevant code - e.g., memory onlining - is expected to
  * shuffle the whole zone).
  *
  * Note: No code should rely on this flag for correctness - it's purely
  *       to allow for optimizations when handing back either fresh pages
  *       (memory onlining) or untouched pages (page isolation, free page
  *       reporting).
  */
 #define FPI_TO_TAIL             ((__force fpi_t)BIT(1))
 
 /*
  * Don't poison memory with KASAN (only for the tag-based modes).
  * During boot, all non-reserved memblock memory is exposed to page_alloc.
  * Poisoning all that memory lengthens boot time, especially on systems with
  * large amount of RAM. This flag is used to skip that poisoning.
  * This is only done for the tag-based KASAN modes, as those are able to
  * detect memory corruptions with the memory tags assigned by default.
  * All memory allocated normally after boot gets poisoned as usual.
  */
 #define FPI_SKIP_KASAN_POISON   ((__force fpi_t)BIT(2))
 
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
 #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8)
 
 struct pagesets {
         local_lock_t lock;
 };
 static DEFINE_PER_CPU(struct pagesets, pagesets) = {
         .lock = INIT_LOCAL_LOCK(lock),
 };
 
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
 EXPORT_PER_CPU_SYMBOL(numa_node);
 #endif
 
 DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key);
 
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
 /*
  * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
  * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
  * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem()
  * defined in <linux/topology.h>.
  */
 DEFINE_PER_CPU(int, _numa_mem_);                /* Kernel "local memory" node */
 EXPORT_PER_CPU_SYMBOL(_numa_mem_);
 #endif
 
 /* work_structs for global per-cpu drains */
 struct pcpu_drain {
         struct zone *zone;
         struct work_struct work;
 };
 static DEFINE_MUTEX(pcpu_drain_mutex);
 static DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);
 
 #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
 volatile unsigned long latent_entropy __latent_entropy;
 EXPORT_SYMBOL(latent_entropy);
 #endif
 
 /*
  * Array of node states.
  */
 nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
         [N_POSSIBLE] = NODE_MASK_ALL,
         [N_ONLINE] = { { [0] = 1UL } },
 #ifndef CONFIG_NUMA
         [N_NORMAL_MEMORY] = { { [0] = 1UL } },
 #ifdef CONFIG_HIGHMEM
         [N_HIGH_MEMORY] = { { [0] = 1UL } },
 #endif
         [N_MEMORY] = { { [0] = 1UL } },
         [N_CPU] = { { [0] = 1UL } },
 #endif  /* NUMA */
 };
 EXPORT_SYMBOL(node_states);
 
 atomic_long_t _totalram_pages __read_mostly;
 EXPORT_SYMBOL(_totalram_pages);
 unsigned long totalreserve_pages __read_mostly;
 unsigned long totalcma_pages __read_mostly;
 
 int percpu_pagelist_high_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
 DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
 EXPORT_SYMBOL(init_on_alloc);
 
 DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
 EXPORT_SYMBOL(init_on_free);
 
 static bool _init_on_alloc_enabled_early __read_mostly
                                 = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON);
 static int __init early_init_on_alloc(char *buf)
 {
 
         return kstrtobool(buf, &_init_on_alloc_enabled_early);
 }
 early_param("init_on_alloc", early_init_on_alloc);
 
 static bool _init_on_free_enabled_early __read_mostly
                                 = IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON);
 static int __init early_init_on_free(char *buf)
 {
         return kstrtobool(buf, &_init_on_free_enabled_early);
 }
 early_param("init_on_free", early_init_on_free);
 
 /*
  * A cached value of the page's pageblock's migratetype, used when the page is
  * put on a pcplist. Used to avoid the pageblock migratetype lookup when
  * freeing from pcplists in most cases, at the cost of possibly becoming stale.
  * Also the migratetype set in the page does not necessarily match the pcplist
  * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any
  * other index - this ensures that it will be put on the correct CMA freelist.
  */
 static inline int get_pcppage_migratetype(struct page *page)
 {
         return page->index;
 }
 
 static inline void set_pcppage_migratetype(struct page *page, int migratetype)
 {
         page->index = migratetype;
 }
 
 #ifdef CONFIG_PM_SLEEP
 /*
  * The following functions are used by the suspend/hibernate code to temporarily
  * change gfp_allowed_mask in order to avoid using I/O during memory allocations
  * while devices are suspended.  To avoid races with the suspend/hibernate code,
  * they should always be called with system_transition_mutex held
  * (gfp_allowed_mask also should only be modified with system_transition_mutex
  * held, unless the suspend/hibernate code is guaranteed not to run in parallel
  * with that modification).
  */
 
 static gfp_t saved_gfp_mask;
 
 void pm_restore_gfp_mask(void)
 {
         WARN_ON(!mutex_is_locked(&system_transition_mutex));
         if (saved_gfp_mask) {
                 gfp_allowed_mask = saved_gfp_mask;
                 saved_gfp_mask = 0;
         }
 }
 
 void pm_restrict_gfp_mask(void)
 {
         WARN_ON(!mutex_is_locked(&system_transition_mutex));
         WARN_ON(saved_gfp_mask);
         saved_gfp_mask = gfp_allowed_mask;
         gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
 }
 
 bool pm_suspended_storage(void)
 {
         if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
                 return false;
         return true;
 }
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 unsigned int pageblock_order __read_mostly;
 #endif
 
 static void __free_pages_ok(struct page *page, unsigned int order,
                             fpi_t fpi_flags);
 
 /*
  * results with 256, 32 in the lowmem_reserve sysctl:
  *      1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
  *      1G machine -> (16M dma, 784M normal, 224M high)
  *      NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
  *      HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
  *      HIGHMEM allocation will leave (224M+784M)/256 of ram reserved in ZONE_DMA
  *
  * TBD: should special case ZONE_DMA32 machines here - in those we normally
  * don't need any ZONE_NORMAL reservation
  */
 int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {
 #ifdef CONFIG_ZONE_DMA
         [ZONE_DMA] = 256,
 #endif
 #ifdef CONFIG_ZONE_DMA32
         [ZONE_DMA32] = 256,
 #endif
         [ZONE_NORMAL] = 32,
 #ifdef CONFIG_HIGHMEM
         [ZONE_HIGHMEM] = 0,
 #endif
         [ZONE_MOVABLE] = 0,
 };
 
 static char * const zone_names[MAX_NR_ZONES] = {
 #ifdef CONFIG_ZONE_DMA
          "DMA",
 #endif
 #ifdef CONFIG_ZONE_DMA32
          "DMA32",
 #endif
          "Normal",
 #ifdef CONFIG_HIGHMEM
          "HighMem",
 #endif
          "Movable",
 #ifdef CONFIG_ZONE_DEVICE
          "Device",
 #endif
 };
 
 const char * const migratetype_names[MIGRATE_TYPES] = {
         "Unmovable",
         "Movable",
         "Reclaimable",
         "HighAtomic",
 #ifdef CONFIG_CMA
         "CMA",
 #endif
 #ifdef CONFIG_MEMORY_ISOLATION
         "Isolate",
 #endif
 };
 
 compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = {
         [NULL_COMPOUND_DTOR] = NULL,
         [COMPOUND_PAGE_DTOR] = free_compound_page,
 #ifdef CONFIG_HUGETLB_PAGE
         [HUGETLB_PAGE_DTOR] = free_huge_page,
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
         [TRANSHUGE_PAGE_DTOR] = free_transhuge_page,
 #endif
 };
 
 int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
 int watermark_boost_factor __read_mostly = 15000;
 int watermark_scale_factor = 10;
 
 static unsigned long nr_kernel_pages __initdata;
 static unsigned long nr_all_pages __initdata;
 static unsigned long dma_reserve __initdata;
 
 static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata;
 static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata;
 static unsigned long required_kernelcore __initdata;
 static unsigned long required_kernelcore_percent __initdata;
 static unsigned long required_movablecore __initdata;
 static unsigned long required_movablecore_percent __initdata;
 static unsigned long zone_movable_pfn[MAX_NUMNODES] __initdata;
 static bool mirrored_kernelcore __meminitdata;
 
 /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
 int movable_zone;
 EXPORT_SYMBOL(movable_zone);
 
 #if MAX_NUMNODES > 1
 unsigned int nr_node_ids __read_mostly = MAX_NUMNODES;
 unsigned int nr_online_nodes __read_mostly = 1;
 EXPORT_SYMBOL(nr_node_ids);
 EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 /*
  * During boot we initialize deferred pages on-demand, as needed, but once
  * page_alloc_init_late() has finished, the deferred pages are all initialized,
  * and we can permanently disable that path.
  */
 static DEFINE_STATIC_KEY_TRUE(deferred_pages);
 
 /*
  * Calling kasan_poison_pages() only after deferred memory initialization
  * has completed. Poisoning pages during deferred memory init will greatly
  * lengthen the process and cause problem in large memory systems as the
  * deferred pages initialization is done with interrupt disabled.
  *
  * Assuming that there will be no reference to those newly initialized
  * pages before they are ever allocated, this should have no effect on
  * KASAN memory tracking as the poison will be properly inserted at page
  * allocation time. The only corner case is when pages are allocated by
  * on-demand allocation and then freed again before the deferred pages
  * initialization is done, but this is not likely to happen.
  */
 static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
 {
         return static_branch_unlikely(&deferred_pages) ||
                (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
                 (fpi_flags & FPI_SKIP_KASAN_POISON)) ||
                PageSkipKASanPoison(page);
 }
 
 /* Returns true if the struct page for the pfn is uninitialised */
 static inline bool __meminit early_page_uninitialised(unsigned long pfn)
 {
         int nid = early_pfn_to_nid(pfn);
 
         if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
                 return true;
 
         return false;
 }
 
 /*
  * Returns true when the remaining initialisation should be deferred until
  * later in the boot cycle when it can be parallelised.
  */
 static bool __meminit
 defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 {
         static unsigned long prev_end_pfn, nr_initialised;
 
         /*
          * prev_end_pfn static that contains the end of previous zone
          * No need to protect because called very early in boot before smp_init.
          */
         if (prev_end_pfn != end_pfn) {
                 prev_end_pfn = end_pfn;
                 nr_initialised = 0;
         }
 
         /* Always populate low zones for address-constrained allocations */
         if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
                 return false;
 
         if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
                 return true;
         /*
          * We start only with one section of pages, more pages are added as
          * needed until the rest of deferred pages are initialized.
          */
         nr_initialised++;
         if ((nr_initialised > PAGES_PER_SECTION) &&
             (pfn & (PAGES_PER_SECTION - 1)) == 0) {
                 NODE_DATA(nid)->first_deferred_pfn = pfn;
                 return true;
         }
         return false;
 }
 #else
 static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
 {
         return (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
                 (fpi_flags & FPI_SKIP_KASAN_POISON)) ||
                PageSkipKASanPoison(page);
 }
 
 static inline bool early_page_uninitialised(unsigned long pfn)
 {
         return false;
 }
 
 static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 {
         return false;
 }
 #endif
 
 /* Return a pointer to the bitmap storing bits affecting a block of pages */
 static inline unsigned long *get_pageblock_bitmap(const struct page *page,
                                                         unsigned long pfn)
 {
 #ifdef CONFIG_SPARSEMEM
         return section_to_usemap(__pfn_to_section(pfn));
 #else
         return page_zone(page)->pageblock_flags;
 #endif /* CONFIG_SPARSEMEM */
 }
 
 static inline int pfn_to_bitidx(const struct page *page, unsigned long pfn)
 {
 #ifdef CONFIG_SPARSEMEM
         pfn &= (PAGES_PER_SECTION-1);
 #else
         pfn = pfn - round_down(page_zone(page)->zone_start_pfn, pageblock_nr_pages);
 #endif /* CONFIG_SPARSEMEM */
         return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 }
 
 static __always_inline
 unsigned long __get_pfnblock_flags_mask(const struct page *page,
                                         unsigned long pfn,
                                         unsigned long mask)
 {
         unsigned long *bitmap;
         unsigned long bitidx, word_bitidx;
         unsigned long word;
 
         bitmap = get_pageblock_bitmap(page, pfn);
         bitidx = pfn_to_bitidx(page, pfn);
         word_bitidx = bitidx / BITS_PER_LONG;
         bitidx &= (BITS_PER_LONG-1);
 
         word = bitmap[word_bitidx];
         return (word >> bitidx) & mask;
 }
 
 /**
  * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
  * @page: The page within the block of interest
  * @pfn: The target page frame number
  * @mask: mask of bits that the caller is interested in
  *
  * Return: pageblock_bits flags
  */
 unsigned long get_pfnblock_flags_mask(const struct page *page,
                                         unsigned long pfn, unsigned long mask)
 {
         return __get_pfnblock_flags_mask(page, pfn, mask);
 }
 
 static __always_inline int get_pfnblock_migratetype(const struct page *page,
                                         unsigned long pfn)
 {
         return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK);
 }
 
 /**
  * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
  * @page: The page within the block of interest
  * @flags: The flags to set
  * @pfn: The target page frame number
  * @mask: mask of bits that the caller is interested in
  */
 void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
                                         unsigned long pfn,
                                         unsigned long mask)
 {
         unsigned long *bitmap;
         unsigned long bitidx, word_bitidx;
         unsigned long old_word, word;
 
         BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
         BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits));
 
         bitmap = get_pageblock_bitmap(page, pfn);
         bitidx = pfn_to_bitidx(page, pfn);
         word_bitidx = bitidx / BITS_PER_LONG;
         bitidx &= (BITS_PER_LONG-1);
 
         VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
 
         mask <<= bitidx;
         flags <<= bitidx;
 
         word = READ_ONCE(bitmap[word_bitidx]);
         for (;;) {
                 old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags);
                 if (word == old_word)
                         break;
                 word = old_word;
         }
 }
 
 void set_pageblock_migratetype(struct page *page, int migratetype)
 {
         if (unlikely(page_group_by_mobility_disabled &&
                      migratetype < MIGRATE_PCPTYPES))
                 migratetype = MIGRATE_UNMOVABLE;
 
         set_pfnblock_flags_mask(page, (unsigned long)migratetype,
                                 page_to_pfn(page), MIGRATETYPE_MASK);
 }
 
 #ifdef CONFIG_DEBUG_VM
 static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 {
         int ret = 0;
         unsigned seq;
         unsigned long pfn = page_to_pfn(page);
         unsigned long sp, start_pfn;
 
         do {
                 seq = zone_span_seqbegin(zone);
                 start_pfn = zone->zone_start_pfn;
                 sp = zone->spanned_pages;
                 if (!zone_spans_pfn(zone, pfn))
                         ret = 1;
         } while (zone_span_seqretry(zone, seq));
 
         if (ret)
                 pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n",
                         pfn, zone_to_nid(zone), zone->name,
                         start_pfn, start_pfn + sp);
 
         return ret;
 }
 
 static int page_is_consistent(struct zone *zone, struct page *page)
 {
         if (zone != page_zone(page))
                 return 0;
 
         return 1;
 }
 /*
  * Temporary debugging check for pages not lying within a given zone.
  */
 static int __maybe_unused bad_range(struct zone *zone, struct page *page)
 {
         if (page_outside_zone_boundaries(zone, page))
                 return 1;
         if (!page_is_consistent(zone, page))
                 return 1;
 
         return 0;
 }
 #else
 static inline int __maybe_unused bad_range(struct zone *zone, struct page *page)
 {
         return 0;
 }
 #endif
 
 static void bad_page(struct page *page, const char *reason)
 {
         static unsigned long resume;
         static unsigned long nr_shown;
         static unsigned long nr_unshown;
 
         /*
          * Allow a burst of 60 reports, then keep quiet for that minute;
          * or allow a steady drip of one report per second.
          */
         if (nr_shown == 60) {
                 if (time_before(jiffies, resume)) {
                         nr_unshown++;
                         goto out;
                 }
                 if (nr_unshown) {
                         pr_alert(
                               "BUG: Bad page state: %lu messages suppressed\n",
                                 nr_unshown);
                         nr_unshown = 0;
                 }
                 nr_shown = 0;
         }
         if (nr_shown++ == 0)
                 resume = jiffies + 60 * HZ;
 
         pr_alert("BUG: Bad page state in process %s  pfn:%05lx\n",
                 current->comm, page_to_pfn(page));
         dump_page(page, reason);
 
         print_modules();
         dump_stack();
 out:
         /* Leave bad fields for debug, except PageBuddy could make trouble */
         page_mapcount_reset(page); /* remove PageBuddy */
         add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 }
 
 static inline unsigned int order_to_pindex(int migratetype, int order)
 {
         int base = order;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
         if (order > PAGE_ALLOC_COSTLY_ORDER) {
                 VM_BUG_ON(order != pageblock_order);
                 base = PAGE_ALLOC_COSTLY_ORDER + 1;
         }
 #else
         VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER);
 #endif
 
         return (MIGRATE_PCPTYPES * base) + migratetype;
 }
 
 static inline int pindex_to_order(unsigned int pindex)
 {
         int order = pindex / MIGRATE_PCPTYPES;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
         if (order > PAGE_ALLOC_COSTLY_ORDER)
                 order = pageblock_order;
 #else
         VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER);
 #endif
 
         return order;
 }
 
 static inline bool pcp_allowed_order(unsigned int order)
 {
         if (order <= PAGE_ALLOC_COSTLY_ORDER)
                 return true;
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
         if (order == pageblock_order)
                 return true;
 #endif
         return false;
 }
 
 static inline void free_the_page(struct page *page, unsigned int order)
 {
         if (pcp_allowed_order(order))           /* Via pcp? */
                 free_unref_page(page, order);
         else
                 __free_pages_ok(page, order, FPI_NONE);
 }
 
 /*
  * Higher-order pages are called "compound pages".  They are structured thusly:
  *
  * The first PAGE_SIZE page is called the "head page" and have PG_head set.
  *
  * The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded
  * in bit 0 of page->compound_head. The rest of bits is pointer to head page.
  *
  * The first tail page's ->compound_dtor holds the offset in array of compound
  * page destructors. See compound_page_dtors.
  *
  * The first tail page's ->compound_order holds the order of allocation.
  * This usage means that zero-order pages may not be compound.
  */
 
 void free_compound_page(struct page *page)
 {
         mem_cgroup_uncharge(page_folio(page));
         free_the_page(page, compound_order(page));
 }
 
 void prep_compound_page(struct page *page, unsigned int order)
 {
         int i;
         int nr_pages = 1 << order;
 
         __SetPageHead(page);
         for (i = 1; i < nr_pages; i++) {
                 struct page *p = page + i;
                 p->mapping = TAIL_MAPPING;
                 set_compound_head(p, page);
         }
 
         set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
         set_compound_order(page, order);
         atomic_set(compound_mapcount_ptr(page), -1);
         if (hpage_pincount_available(page))
                 atomic_set(compound_pincount_ptr(page), 0);
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 unsigned int _debug_guardpage_minorder;
 
 bool _debug_pagealloc_enabled_early __read_mostly
                         = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
 EXPORT_SYMBOL(_debug_pagealloc_enabled_early);
 DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
 EXPORT_SYMBOL(_debug_pagealloc_enabled);
 
 DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
 
 static int __init early_debug_pagealloc(char *buf)
 {
         return kstrtobool(buf, &_debug_pagealloc_enabled_early);
 }
 early_param("debug_pagealloc", early_debug_pagealloc);
 
 static int __init debug_guardpage_minorder_setup(char *buf)
 {
         unsigned long res;
 
         if (kstrtoul(buf, 10, &res) < 0 ||  res > MAX_ORDER / 2) {
                 pr_err("Bad debug_guardpage_minorder value\n");
                 return 0;
         }
         _debug_guardpage_minorder = res;
         pr_info("Setting debug_guardpage_minorder to %lu\n", res);
         return 0;
 }
 early_param("debug_guardpage_minorder", debug_guardpage_minorder_setup);
 
 static inline bool set_page_guard(struct zone *zone, struct page *page,
                                 unsigned int order, int migratetype)
 {
         if (!debug_guardpage_enabled())
                 return false;
 
         if (order >= debug_guardpage_minorder())
                 return false;
 
         __SetPageGuard(page);
         INIT_LIST_HEAD(&page->lru);
         set_page_private(page, order);
         /* Guard pages are not available for any usage */
         __mod_zone_freepage_state(zone, -(1 << order), migratetype);
 
         return true;
 }
 
 static inline void clear_page_guard(struct zone *zone, struct page *page,
                                 unsigned int order, int migratetype)
 {
         if (!debug_guardpage_enabled())
                 return;
 
         __ClearPageGuard(page);
 
         set_page_private(page, 0);
         if (!is_migrate_isolate(migratetype))
                 __mod_zone_freepage_state(zone, (1 << order), migratetype);
 }
 #else
 static inline bool set_page_guard(struct zone *zone, struct page *page,
                         unsigned int order, int migratetype) { return false; }
 static inline void clear_page_guard(struct zone *zone, struct page *page,
                                 unsigned int order, int migratetype) {}
 #endif
 
 /*
  * Enable static keys related to various memory debugging and hardening options.
  * Some override others, and depend on early params that are evaluated in the
  * order of appearance. So we need to first gather the full picture of what was
  * enabled, and then make decisions.
  */
 void init_mem_debugging_and_hardening(void)
 {
         bool page_poisoning_requested = false;
 
 #ifdef CONFIG_PAGE_POISONING
         /*
          * Page poisoning is debug page alloc for some arches. If
          * either of those options are enabled, enable poisoning.
          */
         if (page_poisoning_enabled() ||
              (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) &&
               debug_pagealloc_enabled())) {
                 static_branch_enable(&_page_poisoning_enabled);
                 page_poisoning_requested = true;
         }
 #endif
 
         if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) &&
             page_poisoning_requested) {
                 pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
                         "will take precedence over init_on_alloc and init_on_free\n");
                 _init_on_alloc_enabled_early = false;
                 _init_on_free_enabled_early = false;
         }
 
         if (_init_on_alloc_enabled_early)
                 static_branch_enable(&init_on_alloc);
         else
                 static_branch_disable(&init_on_alloc);
 
         if (_init_on_free_enabled_early)
                 static_branch_enable(&init_on_free);
         else
                 static_branch_disable(&init_on_free);
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
         if (!debug_pagealloc_enabled())
                 return;
 
         static_branch_enable(&_debug_pagealloc_enabled);
 
         if (!debug_guardpage_minorder())
                 return;
 
         static_branch_enable(&_debug_guardpage_enabled);
 #endif
 }
 
 static inline void set_buddy_order(struct page *page, unsigned int order)
 {
         set_page_private(page, order);
         __SetPageBuddy(page);
 }
 
 /*
  * This function checks whether a page is free && is the buddy
  * we can coalesce a page and its buddy if
  * (a) the buddy is not in a hole (check before calling!) &&
  * (b) the buddy is in the buddy system &&
  * (c) a page and its buddy have the same order &&
  * (d) a page and its buddy are in the same zone.
  *
  * For recording whether a page is in the buddy system, we set PageBuddy.
  * Setting, clearing, and testing PageBuddy is serialized by zone->lock.
  *
  * For recording page's order, we use page_private(page).
  */
 static inline bool page_is_buddy(struct page *page, struct page *buddy,
                                                         unsigned int order)
 {
         if (!page_is_guard(buddy) && !PageBuddy(buddy))
                 return false;
 
         if (buddy_order(buddy) != order)
                 return false;
 
         /*
          * zone check is done late to avoid uselessly calculating
          * zone/node ids for pages that could never merge.
          */
         if (page_zone_id(page) != page_zone_id(buddy))
                 return false;
 
         VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
 
         return true;
 }
 
 #ifdef CONFIG_COMPACTION
 static inline struct capture_control *task_capc(struct zone *zone)
 {
         struct capture_control *capc = current->capture_control;
 
         return unlikely(capc) &&
                 !(current->flags & PF_KTHREAD) &&
                 !capc->page &&
                 capc->cc->zone == zone ? capc : NULL;
 }
 
 static inline bool
 compaction_capture(struct capture_control *capc, struct page *page,
                    int order, int migratetype)
 {
         if (!capc || order != capc->cc->order)
                 return false;
 
         /* Do not accidentally pollute CMA or isolated regions*/
         if (is_migrate_cma(migratetype) ||
             is_migrate_isolate(migratetype))
                 return false;
 
         /*
          * Do not let lower order allocations pollute a movable pageblock.
          * This might let an unmovable request use a reclaimable pageblock
          * and vice-versa but no more than normal fallback logic which can
          * have trouble finding a high-order free page.
          */
         if (order < pageblock_order && migratetype == MIGRATE_MOVABLE)
                 return false;
 
         capc->page = page;
         return true;
 }
 
 #else
 static inline struct capture_control *task_capc(struct zone *zone)
 {
         return NULL;
 }
 
 static inline bool
 compaction_capture(struct capture_control *capc, struct page *page,
                    int order, int migratetype)
 {
         return false;
 }
 #endif /* CONFIG_COMPACTION */
 
 /* Used for pages not on another list */
 static inline void add_to_free_list(struct page *page, struct zone *zone,
                                     unsigned int order, int migratetype)
 {
         struct free_area *area = &zone->free_area[order];
 
         list_add(&page->lru, &area->free_list[migratetype]);
         area->nr_free++;
 }
 
 /* Used for pages not on another list */
 static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
                                          unsigned int order, int migratetype)
 {
         struct free_area *area = &zone->free_area[order];
 
         list_add_tail(&page->lru, &area->free_list[migratetype]);
         area->nr_free++;
 }
 
 /*
  * Used for pages which are on another list. Move the pages to the tail
  * of the list - so the moved pages won't immediately be considered for
  * allocation again (e.g., optimization for memory onlining).
  */
 static inline void move_to_free_list(struct page *page, struct zone *zone,
                                      unsigned int order, int migratetype)
 {
         struct free_area *area = &zone->free_area[order];
 
         list_move_tail(&page->lru, &area->free_list[migratetype]);
 }
 
 static inline void del_page_from_free_list(struct page *page, struct zone *zone,
                                            unsigned int order)
 {
         /* clear reported state and update reported page count */
         if (page_reported(page))
                 __ClearPageReported(page);
 
         list_del(&page->lru);
         __ClearPageBuddy(page);
         set_page_private(page, 0);
         zone->free_area[order].nr_free--;
 }
 
 /*
  * If this is not the largest possible page, check if the buddy
  * of the next-highest order is free. If it is, it's possible
  * that pages are being freed that will coalesce soon. In case,
  * that is happening, add the free page to the tail of the list
  * so it's less likely to be used soon and more likely to be merged
  * as a higher order page
  */
 static inline bool
 buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
                    struct page *page, unsigned int order)
 {
         struct page *higher_page, *higher_buddy;
         unsigned long combined_pfn;
 
         if (order >= MAX_ORDER - 2)
                 return false;
 
         combined_pfn = buddy_pfn & pfn;
         higher_page = page + (combined_pfn - pfn);
         buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
         higher_buddy = higher_page + (buddy_pfn - combined_pfn);
 
         return page_is_buddy(higher_page, higher_buddy, order + 1);
 }
 
 /*
  * Freeing function for a buddy system allocator.
  *
  * The concept of a buddy system is to maintain direct-mapped table
  * (containing bit values) for memory blocks of various "orders".
  * The bottom level table contains the map for the smallest allocatable
  * units of memory (here, pages), and each level above it describes
  * pairs of units from the levels below, hence, "buddies".
  * At a high level, all that happens here is marking the table entry
  * at the bottom level available, and propagating the changes upward
  * as necessary, plus some accounting needed to play nicely with other
  * parts of the VM system.
  * At each level, we keep a list of pages, which are heads of continuous
  * free pages of length of (1 << order) and marked with PageBuddy.
  * Page's order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
  * other.  That is, if we allocate a small block, and both were
  * free, the remainder of the region must be split into blocks.
  * If a block is freed, and its buddy is also free, then this
  * triggers coalescing into a block of larger size.
  *
  * -- nyc
  */
 
 static inline void __free_one_page(struct page *page,
                 unsigned long pfn,
                 struct zone *zone, unsigned int order,
                 int migratetype, fpi_t fpi_flags)
 {
         struct capture_control *capc = task_capc(zone);
         unsigned long buddy_pfn;
         unsigned long combined_pfn;
         unsigned int max_order;
         struct page *buddy;
         bool to_tail;
 
         max_order = min_t(unsigned int, MAX_ORDER - 1, pageblock_order);
 
         VM_BUG_ON(!zone_is_initialized(zone));
         VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
 
         VM_BUG_ON(migratetype == -1);
         if (likely(!is_migrate_isolate(migratetype)))
                 __mod_zone_freepage_state(zone, 1 << order, migratetype);
 
         VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
         VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
 continue_merging:
         while (order < max_order) {
                 if (compaction_capture(capc, page, order, migratetype)) {
                         __mod_zone_freepage_state(zone, -(1 << order),
                                                                 migratetype);
                         return;
                 }
                 buddy_pfn = __find_buddy_pfn(pfn, order);
                 buddy = page + (buddy_pfn - pfn);
 
                 if (!page_is_buddy(page, buddy, order))
                         goto done_merging;
                 /*
                  * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
                  * merge with it and move up one order.
                  */
                 if (page_is_guard(buddy))
                         clear_page_guard(zone, buddy, order, migratetype);
                 else
                         del_page_from_free_list(buddy, zone, order);
                 combined_pfn = buddy_pfn & pfn;
                 page = page + (combined_pfn - pfn);
                 pfn = combined_pfn;
                 order++;
         }
         if (order < MAX_ORDER - 1) {
                 /* If we are here, it means order is >= pageblock_order.
                  * We want to prevent merge between freepages on isolate
                  * pageblock and normal pageblock. Without this, pageblock
                  * isolation could cause incorrect freepage or CMA accounting.
                  *
                  * We don't want to hit this code for the more frequent
                  * low-order merging.
                  */
                 if (unlikely(has_isolate_pageblock(zone))) {
                         int buddy_mt;
 
                         buddy_pfn = __find_buddy_pfn(pfn, order);
                         buddy = page + (buddy_pfn - pfn);
                         buddy_mt = get_pageblock_migratetype(buddy);
 
                         if (migratetype != buddy_mt
                                         && (is_migrate_isolate(migratetype) ||
                                                 is_migrate_isolate(buddy_mt)))
                                 goto done_merging;
                 }
                 max_order = order + 1;
                 goto continue_merging;
         }
 
 done_merging:
         set_buddy_order(page, order);
 
         if (fpi_flags & FPI_TO_TAIL)
                 to_tail = true;
         else if (is_shuffle_order(order))
                 to_tail = shuffle_pick_tail();
         else
                 to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);
 
         if (to_tail)
                 add_to_free_list_tail(page, zone, order, migratetype);
         else
                 add_to_free_list(page, zone, order, migratetype);
 
         /* Notify page reporting subsystem of freed page */
         if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY))
                 page_reporting_notify_free(order);
 }
 
 /*
  * A bad page could be due to a number of fields. Instead of multiple branches,
  * try and check multiple fields with one check. The caller must do a detailed
  * check if necessary.
  */
 static inline bool page_expected_state(struct page *page,
                                         unsigned long check_flags)
 {
         if (unlikely(atomic_read(&page->_mapcount) != -1))
                 return false;
 
         if (unlikely((unsigned long)page->mapping |
                         page_ref_count(page) |
 #ifdef CONFIG_MEMCG
                         page->memcg_data |
 #endif
                         (page->flags & check_flags)))
                 return false;
 
         return true;
 }
 
 static const char *page_bad_reason(struct page *page, unsigned long flags)
 {
         const char *bad_reason = NULL;
 
         if (unlikely(atomic_read(&page->_mapcount) != -1))
                 bad_reason = "nonzero mapcount";
         if (unlikely(page->mapping != NULL))
                 bad_reason = "non-NULL mapping";
         if (unlikely(page_ref_count(page) != 0))
                 bad_reason = "nonzero _refcount";
         if (unlikely(page->flags & flags)) {
                 if (flags == PAGE_FLAGS_CHECK_AT_PREP)
                         bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag(s) set";
                 else
                         bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
         }
 #ifdef CONFIG_MEMCG
         if (unlikely(page->memcg_data))
                 bad_reason = "page still charged to cgroup";
 #endif
         return bad_reason;
 }
 
 static void check_free_page_bad(struct page *page)
 {
         bad_page(page,
                  page_bad_reason(page, PAGE_FLAGS_CHECK_AT_FREE));
 }
 
 static inline int check_free_page(struct page *page)
 {
         if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE)))
                 return 0;
 
         /* Something has gone sideways, find it */
         check_free_page_bad(page);
         return 1;
 }
 
 static int free_tail_pages_check(struct page *head_page, struct page *page)
 {
         int ret = 1;
 
         /*
          * We rely page->lru.next never has bit 0 set, unless the page
          * is PageTail(). Let's make sure that's true even for poisoned ->lru.
          */
         BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1);
 
         if (!IS_ENABLED(CONFIG_DEBUG_VM)) {
                 ret = 0;
                 goto out;
         }
         switch (page - head_page) {
         case 1:
                 /* the first tail page: ->mapping may be compound_mapcount() */
                 if (unlikely(compound_mapcount(page))) {
                         bad_page(page, "nonzero compound_mapcount");
                         goto out;
                 }
                 break;
         case 2:
                 /*
                  * the second tail page: ->mapping is
                  * deferred_list.next -- ignore value.
                  */
                 break;
         default:
                 if (page->mapping != TAIL_MAPPING) {
                         bad_page(page, "corrupted mapping in tail page");
                         goto out;
                 }
                 break;
         }
         if (unlikely(!PageTail(page))) {
                 bad_page(page, "PageTail not set");
                 goto out;
         }
         if (unlikely(compound_head(page) != head_page)) {
                 bad_page(page, "compound_head not consistent");
                 goto out;
         }
         ret = 0;
 out:
         page->mapping = NULL;
         clear_compound_head(page);
         return ret;
 }
 
 static void kernel_init_free_pages(struct page *page, int numpages, bool zero_tags)
 {
         int i;
 
         if (zero_tags) {
                 for (i = 0; i < numpages; i++)
                         tag_clear_highpage(page + i);
                 return;
         }
 
         /* s390's use of memset() could override KASAN redzones. */
         kasan_disable_current();
         for (i = 0; i < numpages; i++) {
                 u8 tag = page_kasan_tag(page + i);
                 page_kasan_tag_reset(page + i);
                 clear_highpage(page + i);
                 page_kasan_tag_set(page + i, tag);
         }
         kasan_enable_current();
 }
 
 static __always_inline bool free_pages_prepare(struct page *page,
                         unsigned int order, bool check_free, fpi_t fpi_flags)
 {
         int bad = 0;
         bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags);
 
         VM_BUG_ON_PAGE(PageTail(page), page);
 
         trace_mm_page_free(page, order);
 
         if (unlikely(PageHWPoison(page)) && !order) {
                 /*
                  * Do not let hwpoison pages hit pcplists/buddy
                  * Untie memcg state and reset page's owner
                  */
                 if (memcg_kmem_enabled() && PageMemcgKmem(page))
                         __memcg_kmem_uncharge_page(page, order);
                 reset_page_owner(page, order);
                 return false;
         }
 
         /*
          * Check tail pages before head page information is cleared to
          * avoid checking PageCompound for order-0 pages.
          */
         if (unlikely(order)) {
                 bool compound = PageCompound(page);
                 int i;
 
                 VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);
 
                 if (compound) {
                         ClearPageDoubleMap(page);
                         ClearPageHasHWPoisoned(page);
                 }
                 for (i = 1; i < (1 << order); i++) {
                         if (compound)
                                 bad += free_tail_pages_check(page, page + i);
                         if (unlikely(check_free_page(page + i))) {
                                 bad++;
                                 continue;
                         }
                         (page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
                 }
         }
         if (PageMappingFlags(page))
                 page->mapping = NULL;
         if (memcg_kmem_enabled() && PageMemcgKmem(page))
                 __memcg_kmem_uncharge_page(page, order);
         if (check_free)
                 bad += check_free_page(page);
         if (bad)
                 return false;
 
         page_cpupid_reset_last(page);
         page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
         reset_page_owner(page, order);
 
         if (!PageHighMem(page)) {
                 debug_check_no_locks_freed(page_address(page),
                                            PAGE_SIZE << order);
                 debug_check_no_obj_freed(page_address(page),
                                            PAGE_SIZE << order);
         }
 
         kernel_poison_pages(page, 1 << order);
 
         /*
          * As memory initialization might be integrated into KASAN,
          * kasan_free_pages and kernel_init_free_pages must be
          * kept together to avoid discrepancies in behavior.
          *
          * With hardware tag-based KASAN, memory tags must be set before the
          * page becomes unavailable via debug_pagealloc or arch_free_page.
          */
         if (kasan_has_integrated_init()) {
                 if (!skip_kasan_poison)
                         kasan_free_pages(page, order);
         } else {
                 bool init = want_init_on_free();
 
                 if (init)
                         kernel_init_free_pages(page, 1 << order, false);
                 if (!skip_kasan_poison)
                         kasan_poison_pages(page, order, init);
         }
 
         /*
          * arch_free_page() can make the page's contents inaccessible.  s390
          * does this.  So nothing which can access the page's contents should
          * happen after this.
          */
         arch_free_page(page, order);
 
         debug_pagealloc_unmap_pages(page, 1 << order);
 
         return true;
 }
 
 #ifdef CONFIG_DEBUG_VM
 /*
  * With DEBUG_VM enabled, order-0 pages are checked immediately when being freed
  * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when
  * moved from pcp lists to free lists.
  */
 static bool free_pcp_prepare(struct page *page, unsigned int order)
 {
         return free_pages_prepare(page, order, true, FPI_NONE);
 }
 
 static bool bulkfree_pcp_prepare(struct page *page)
 {
         if (debug_pagealloc_enabled_static())
                 return check_free_page(page);
         else
                 return false;
 }
 #else
 /*
  * With DEBUG_VM disabled, order-0 pages being freed are checked only when
  * moving from pcp lists to free list in order to reduce overhead. With
  * debug_pagealloc enabled, they are checked also immediately when being freed
  * to the pcp lists.
  */
 static bool free_pcp_prepare(struct page *page, unsigned int order)
 {
         if (debug_pagealloc_enabled_static())
                 return free_pages_prepare(page, order, true, FPI_NONE);
         else
                 return free_pages_prepare(page, order, false, FPI_NONE);
 }
 
 static bool bulkfree_pcp_prepare(struct page *page)
 {
         return check_free_page(page);
 }
 #endif /* CONFIG_DEBUG_VM */
 
 static inline void prefetch_buddy(struct page *page)
 {
         unsigned long pfn = page_to_pfn(page);
         unsigned long buddy_pfn = __find_buddy_pfn(pfn, 0);
         struct page *buddy = page + (buddy_pfn - pfn);
 
         prefetch(buddy);
 }
 
 /*
  * Frees a number of pages from the PCP lists
  * Assumes all pages on list are in same zone.
  * count is the number of pages to free.
  */
 static void free_pcppages_bulk(struct zone *zone, int count,
                                         struct per_cpu_pages *pcp)
 {
         int pindex = 0;
         int batch_free = 0;
         int nr_freed = 0;
         unsigned int order;
         int prefetch_nr = READ_ONCE(pcp->batch);
         bool isolated_pageblocks;
         struct page *page, *tmp;
         LIST_HEAD(head);
 
         /*
          * Ensure proper count is passed which otherwise would stuck in the
          * below while (list_empty(list)) loop.
          */
         count = min(pcp->count, count);
         while (count > 0) {
                 struct list_head *list;
 
                 /*
                  * Remove pages from lists in a round-robin fashion. A
                  * batch_free count is maintained that is incremented when an
                  * empty list is encountered.  This is so more pages are freed
                  * off fuller lists instead of spinning excessively around empty
                  * lists
                  */
                 do {
                         batch_free++;
                         if (++pindex == NR_PCP_LISTS)
                                 pindex = 0;
                         list = &pcp->lists[pindex];
                 } while (list_empty(list));
 
                 /* This is the only non-empty list. Free them all. */
                 if (batch_free == NR_PCP_LISTS)
                         batch_free = count;
 
                 order = pindex_to_order(pindex);
                 BUILD_BUG_ON(MAX_ORDER >= (1<<NR_PCP_ORDER_WIDTH));
                 do {
                         page = list_last_entry(list, struct page, lru);
                         /* must delete to avoid corrupting pcp list */
                         list_del(&page->lru);
                         nr_freed += 1 << order;
                         count -= 1 << order;
 
                         if (bulkfree_pcp_prepare(page))
                                 continue;
 
                         /* Encode order with the migratetype */
                         page->index <<= NR_PCP_ORDER_WIDTH;
                         page->index |= order;
 
                         list_add_tail(&page->lru, &head);
 
                         /*
                          * We are going to put the page back to the global
                          * pool, prefetch its buddy to speed up later access
                          * under zone->lock. It is believed the overhead of
                          * an additional test and calculating buddy_pfn here
                          * can be offset by reduced memory latency later. To
                          * avoid excessive prefetching due to large count, only
                          * prefetch buddy for the first pcp->batch nr of pages.
                          */
                         if (prefetch_nr) {
                                 prefetch_buddy(page);
                                 prefetch_nr--;
                         }
                 } while (count > 0 && --batch_free && !list_empty(list));
         }
         pcp->count -= nr_freed;
 
         /*
          * local_lock_irq held so equivalent to spin_lock_irqsave for
          * both PREEMPT_RT and non-PREEMPT_RT configurations.
          */
         spin_lock(&zone->lock);
         isolated_pageblocks = has_isolate_pageblock(zone);
 
         /*
          * Use safe version since after __free_one_page(),
          * page->lru.next will not point to original list.
          */
         list_for_each_entry_safe(page, tmp, &head, lru) {
                 int mt = get_pcppage_migratetype(page);
 
                 /* mt has been encoded with the order (see above) */
                 order = mt & NR_PCP_ORDER_MASK;
                 mt >>= NR_PCP_ORDER_WIDTH;
 
                 /* MIGRATE_ISOLATE page should not go to pcplists */
                 VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
                 /* Pageblock could have been isolated meanwhile */
                 if (unlikely(isolated_pageblocks))
                         mt = get_pageblock_migratetype(page);
 
                 __free_one_page(page, page_to_pfn(page), zone, order, mt, FPI_NONE);
                 trace_mm_page_pcpu_drain(page, order, mt);
         }
         spin_unlock(&zone->lock);
 }
 
 static void free_one_page(struct zone *zone,
                                 struct page *page, unsigned long pfn,
                                 unsigned int order,
                                 int migratetype, fpi_t fpi_flags)
 {
         unsigned long flags;
 
         spin_lock_irqsave(&zone->lock, flags);
         if (unlikely(has_isolate_pageblock(zone) ||
                 is_migrate_isolate(migratetype))) {
                 migratetype = get_pfnblock_migratetype(page, pfn);
         }
         __free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
         spin_unlock_irqrestore(&zone->lock, flags);
 }
 
 static void __meminit __init_single_page(struct page *page, unsigned long pfn,
                                 unsigned long zone, int nid)
 {
         mm_zero_struct_page(page);
         set_page_links(page, zone, nid, pfn);
         init_page_count(page);
         page_mapcount_reset(page);
         page_cpupid_reset_last(page);
         page_kasan_tag_reset(page);
 
         INIT_LIST_HEAD(&page->lru);
 #ifdef WANT_PAGE_VIRTUAL
         /* The shift won't overflow because ZONE_NORMAL is below 4G. */
         if (!is_highmem_idx(zone))
                 set_page_address(page, __va(pfn << PAGE_SHIFT));
 #endif
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static void __meminit init_reserved_page(unsigned long pfn)
 {
         pg_data_t *pgdat;
         int nid, zid;
 
         if (!early_page_uninitialised(pfn))
                 return;
 
         nid = early_pfn_to_nid(pfn);
         pgdat = NODE_DATA(nid);
 
         for (zid = 0; zid < MAX_NR_ZONES; zid++) {
                 struct zone *zone = &pgdat->node_zones[zid];
 
                 if (zone_spans_pfn(zone, pfn))
                         break;
         }
         __init_single_page(pfn_to_page(pfn), pfn, zid, nid);
 }
 #else
 static inline void init_reserved_page(unsigned long pfn)
 {
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 /*
  * Initialised pages do not have PageReserved set. This function is
  * called for each range allocated by the bootmem allocator and
  * marks the pages PageReserved. The remaining valid pages are later
  * sent to the buddy page allocator.
  */
 void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
 {
         unsigned long start_pfn = PFN_DOWN(start);
         unsigned long end_pfn = PFN_UP(end);
 
         for (; start_pfn < end_pfn; start_pfn++) {
                 if (pfn_valid(start_pfn)) {
                         struct page *page = pfn_to_page(start_pfn);
 
                         init_reserved_page(start_pfn);
 
                         /* Avoid false-positive PageTail() */
                         INIT_LIST_HEAD(&page->lru);
 
                         /*
                          * no need for atomic set_bit because the struct
                          * page is not visible yet so nobody should
                          * access it yet.
                          */
                         __SetPageReserved(page);
                 }
         }
 }
 
 static void __free_pages_ok(struct page *page, unsigned int order,
                             fpi_t fpi_flags)
 {
         unsigned long flags;
         int migratetype;
         unsigned long pfn = page_to_pfn(page);
         struct zone *zone = page_zone(page);
 
         if (!free_pages_prepare(page, order, true, fpi_flags))
                 return;
 
         migratetype = get_pfnblock_migratetype(page, pfn);
 
         spin_lock_irqsave(&zone->lock, flags);
         if (unlikely(has_isolate_pageblock(zone) ||
                 is_migrate_isolate(migratetype))) {
                 migratetype = get_pfnblock_migratetype(page, pfn);
         }
         __free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
         spin_unlock_irqrestore(&zone->lock, flags);
 
         __count_vm_events(PGFREE, 1 << order);
 }
 
 void __free_pages_core(struct page *page, unsigned int order)
 {
         unsigned int nr_pages = 1 << order;
         struct page *p = page;
         unsigned int loop;
 
         /*
          * When initializing the memmap, __init_single_page() sets the refcount
          * of all pages to 1 ("allocated"/"not free"). We have to set the
          * refcount of all involved pages to 0.
          */
         prefetchw(p);
         for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
                 prefetchw(p + 1);
                 __ClearPageReserved(p);
                 set_page_count(p, 0);
         }
         __ClearPageReserved(p);
         set_page_count(p, 0);
 
         atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
 
         /*
          * Bypass PCP and place fresh pages right to the tail, primarily
          * relevant for memory onlining.
          */
         __free_pages_ok(page, order, FPI_TO_TAIL | FPI_SKIP_KASAN_POISON);
 }
 
 #ifdef CONFIG_NUMA
 
 /*
  * During memory init memblocks map pfns to nids. The search is expensive and
  * this caches recent lookups. The implementation of __early_pfn_to_nid
  * treats start/end as pfns.
  */
 struct mminit_pfnnid_cache {
         unsigned long last_start;
         unsigned long last_end;
         int last_nid;
 };
 
 static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
 
 /*
  * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
  */
 static int __meminit __early_pfn_to_nid(unsigned long pfn,
                                         struct mminit_pfnnid_cache *state)
 {
         unsigned long start_pfn, end_pfn;
         int nid;
 
         if (state->last_start <= pfn && pfn < state->last_end)
                 return state->last_nid;
 
         nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
         if (nid != NUMA_NO_NODE) {
                 state->last_start = start_pfn;
                 state->last_end = end_pfn;
                 state->last_nid = nid;
         }
 
         return nid;
 }
 
 int __meminit early_pfn_to_nid(unsigned long pfn)
 {
         static DEFINE_SPINLOCK(early_pfn_lock);
         int nid;
 
         spin_lock(&early_pfn_lock);
         nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
         if (nid < 0)
                 nid = first_online_node;
         spin_unlock(&early_pfn_lock);
 
         return nid;
 }
 #endif /* CONFIG_NUMA */
 
 void __init memblock_free_pages(struct page *page, unsigned long pfn,
                                                         unsigned int order)
 {
         if (early_page_uninitialised(pfn))
                 return;
         __free_pages_core(page, order);
 }
 
 /*
  * Check that the whole (or subset of) a pageblock given by the interval of
  * [start_pfn, end_pfn) is valid and within the same zone, before scanning it
  * with the migration of free compaction scanner.
  *
  * Return struct page pointer of start_pfn, or NULL if checks were not passed.
  *
  * It's possible on some configurations to have a setup like node0 node1 node0
  * i.e. it's possible that all pages within a zones range of pages do not
  * belong to a single zone. We assume that a border between node0 and node1
  * can occur within a single pageblock, but not a node0 node1 node0
  * interleaving within a single pageblock. It is therefore sufficient to check
  * the first and last page of a pageblock and avoid checking each individual
  * page in a pageblock.
  */
 struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
                                      unsigned long end_pfn, struct zone *zone)
 {
         struct page *start_page;
         struct page *end_page;
 
         /* end_pfn is one past the range we are checking */
         end_pfn--;
 
         if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
                 return NULL;
 
         start_page = pfn_to_online_page(start_pfn);
         if (!start_page)
                 return NULL;
 
         if (page_zone(start_page) != zone)
                 return NULL;
 
         end_page = pfn_to_page(end_pfn);
 
         /* This gives a shorter code than deriving page_zone(end_page) */
         if (page_zone_id(start_page) != page_zone_id(end_page))
                 return NULL;
 
         return start_page;
 }
 
 void set_zone_contiguous(struct zone *zone)
 {
         unsigned long block_start_pfn = zone->zone_start_pfn;
         unsigned long block_end_pfn;
 
         block_end_pfn = ALIGN(block_start_pfn + 1, pageblock_nr_pages);
         for (; block_start_pfn < zone_end_pfn(zone);
                         block_start_pfn = block_end_pfn,
                          block_end_pfn += pageblock_nr_pages) {
 
                 block_end_pfn = min(block_end_pfn, zone_end_pfn(zone));
 
                 if (!__pageblock_pfn_to_page(block_start_pfn,
                                              block_end_pfn, zone))
                         return;
                 cond_resched();
         }
 
         /* We confirm that there is no hole */
         zone->contiguous = true;
 }
 
 void clear_zone_contiguous(struct zone *zone)
 {
         zone->contiguous = false;
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static void __init deferred_free_range(unsigned long pfn,
                                        unsigned long nr_pages)
 {
         struct page *page;
         unsigned long i;
 
         if (!nr_pages)
                 return;
 
         page = pfn_to_page(pfn);
 
         /* Free a large naturally-aligned chunk if possible */
         if (nr_pages == pageblock_nr_pages &&
             (pfn & (pageblock_nr_pages - 1)) == 0) {
                 set_pageblock_migratetype(page, MIGRATE_MOVABLE);
                 __free_pages_core(page, pageblock_order);
                 return;
         }
 
         for (i = 0; i < nr_pages; i++, page++, pfn++) {
                 if ((pfn & (pageblock_nr_pages - 1)) == 0)
                         set_pageblock_migratetype(page, MIGRATE_MOVABLE);
                 __free_pages_core(page, 0);
         }
 }
 
 /* Completion tracking for deferred_init_memmap() threads */
 static atomic_t pgdat_init_n_undone __initdata;
 static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);
 
 static inline void __init pgdat_init_report_one_done(void)
 {
         if (atomic_dec_and_test(&pgdat_init_n_undone))
                 complete(&pgdat_init_all_done_comp);
 }
 
 /*
  * Returns true if page needs to be initialized or freed to buddy allocator.
  *
  * First we check if pfn is valid on architectures where it is possible to have
  * holes within pageblock_nr_pages. On systems where it is not possible, this
  * function is optimized out.
  *
  * Then, we check if a current large page is valid by only checking the validity
  * of the head pfn.
  */
 static inline bool __init deferred_pfn_valid(unsigned long pfn)
 {
         if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
                 return false;
         return true;
 }
 
 /*
  * Free pages to buddy allocator. Try to free aligned pages in
  * pageblock_nr_pages sizes.
  */
 static void __init deferred_free_pages(unsigned long pfn,
                                        unsigned long end_pfn)
 {
         unsigned long nr_pgmask = pageblock_nr_pages - 1;
         unsigned long nr_free = 0;
 
         for (; pfn < end_pfn; pfn++) {
                 if (!deferred_pfn_valid(pfn)) {
                         deferred_free_range(pfn - nr_free, nr_free);
                         nr_free = 0;
                 } else if (!(pfn & nr_pgmask)) {
                         deferred_free_range(pfn - nr_free, nr_free);
                         nr_free = 1;
                 } else {
                         nr_free++;
                 }
         }
         /* Free the last block of pages to allocator */
         deferred_free_range(pfn - nr_free, nr_free);
 }
 
 /*
  * Initialize struct pages.  We minimize pfn page lookups and scheduler checks
  * by performing it only once every pageblock_nr_pages.
  * Return number of pages initialized.
  */
 static unsigned long  __init deferred_init_pages(struct zone *zone,
                                                  unsigned long pfn,
                                                  unsigned long end_pfn)
 {
         unsigned long nr_pgmask = pageblock_nr_pages - 1;
         int nid = zone_to_nid(zone);
         unsigned long nr_pages = 0;
         int zid = zone_idx(zone);
         struct page *page = NULL;
 
         for (; pfn < end_pfn; pfn++) {
                 if (!deferred_pfn_valid(pfn)) {
                         page = NULL;
                         continue;
                 } else if (!page || !(pfn & nr_pgmask)) {
                         page = pfn_to_page(pfn);
                 } else {
                         page++;
                 }
                 __init_single_page(page, pfn, zid, nid);
                 nr_pages++;
         }
         return (nr_pages);
 }
 
 /*
  * This function is meant to pre-load the iterator for the zone init.
  * Specifically it walks through the ranges until we are caught up to the
  * first_init_pfn value and exits there. If we never encounter the value we
  * return false indicating there are no valid ranges left.
  */
 static bool __init
 deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone,
                                     unsigned long *spfn, unsigned long *epfn,
                                     unsigned long first_init_pfn)
 {
         u64 j;
 
         /*
          * Start out by walking through the ranges in this zone that have
          * already been initialized. We don't need to do anything with them
          * so we just need to flush them out of the system.
          */
         for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) {
                 if (*epfn <= first_init_pfn)
                         continue;
                 if (*spfn < first_init_pfn)
                         *spfn = first_init_pfn;
                 *i = j;
                 return true;
         }
 
         return false;
 }
 
 /*
  * Initialize and free pages. We do it in two loops: first we initialize
  * struct page, then free to buddy allocator, because while we are
  * freeing pages we can access pages that are ahead (computing buddy
  * page in __free_one_page()).
  *
  * In order to try and keep some memory in the cache we have the loop
  * broken along max page order boundaries. This way we will not cause
  * any issues with the buddy page computation.
  */
 static unsigned long __init
 deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn,
                        unsigned long *end_pfn)
 {
         unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES);
         unsigned long spfn = *start_pfn, epfn = *end_pfn;
         unsigned long nr_pages = 0;
         u64 j = *i;
 
         /* First we loop through and initialize the page values */
         for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) {
                 unsigned long t;
 
                 if (mo_pfn <= *start_pfn)
                         break;
 
                 t = min(mo_pfn, *end_pfn);
                 nr_pages += deferred_init_pages(zone, *start_pfn, t);
 
                 if (mo_pfn < *end_pfn) {
                         *start_pfn = mo_pfn;
                         break;
                 }
         }
 
         /* Reset values and now loop through freeing pages as needed */
         swap(j, *i);
 
         for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) {
                 unsigned long t;
 
                 if (mo_pfn <= spfn)
                         break;
 
                 t = min(mo_pfn, epfn);
                 deferred_free_pages(spfn, t);
 
                 if (mo_pfn <= epfn)
                         break;
         }
 
         return nr_pages;
 }
 
 static void __init
 deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
                            void *arg)
 {
         unsigned long spfn, epfn;
         struct zone *zone = arg;
         u64 i;
 
         deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn);
 
         /*
          * Initialize and free pages in MAX_ORDER sized increments so that we
          * can avoid introducing any issues with the buddy allocator.
          */
         while (spfn < end_pfn) {
                 deferred_init_maxorder(&i, zone, &spfn, &epfn);
                 cond_resched();
         }
 }
 
 /* An arch may override for more concurrency. */
 __weak int __init
 deferred_page_init_max_threads(const struct cpumask *node_cpumask)
 {
         return 1;
 }
 
 /* Initialise remaining memory on a node */
 static int __init deferred_init_memmap(void *data)
 {
         pg_data_t *pgdat = data;
         const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
         unsigned long spfn = 0, epfn = 0;
         unsigned long first_init_pfn, flags;
         unsigned long start = jiffies;
         struct zone *zone;
         int zid, max_threads;
         u64 i;
 
         /* Bind memory initialisation thread to a local node if possible */
         if (!cpumask_empty(cpumask))
                 set_cpus_allowed_ptr(current, cpumask);
 
         pgdat_resize_lock(pgdat, &flags);
         first_init_pfn = pgdat->first_deferred_pfn;
         if (first_init_pfn == ULONG_MAX) {
                 pgdat_resize_unlock(pgdat, &flags);
                 pgdat_init_report_one_done();
                 return 0;
         }
 
         /* Sanity check boundaries */
         BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
         BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
         pgdat->first_deferred_pfn = ULONG_MAX;
 
         /*
          * Once we unlock here, the zone cannot be grown anymore, thus if an
          * interrupt thread must allocate this early in boot, zone must be
          * pre-grown prior to start of deferred page initialization.
          */
         pgdat_resize_unlock(pgdat, &flags);
 
         /* Only the highest zone is deferred so find it */
         for (zid = 0; zid < MAX_NR_ZONES; zid++) {
                 zone = pgdat->node_zones + zid;
                 if (first_init_pfn < zone_end_pfn(zone))
                         break;
         }
 
         /* If the zone is empty somebody else may have cleared out the zone */
         if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
                                                  first_init_pfn))
                 goto zone_empty;
 
         max_threads = deferred_page_init_max_threads(cpumask);
 
         while (spfn < epfn) {
                 unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION);
                 struct padata_mt_job job = {
                         .thread_fn   = deferred_init_memmap_chunk,
                         .fn_arg      = zone,
                         .start       = spfn,
                         .size        = epfn_align - spfn,
                         .align       = PAGES_PER_SECTION,
                         .min_chunk   = PAGES_PER_SECTION,
                         .max_threads = max_threads,
                 };
 
                 padata_do_multithreaded(&job);
                 deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
                                                     epfn_align);
         }
 zone_empty:
         /* Sanity check that the next zone really is unpopulated */
         WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
 
         pr_info("node %d deferred pages initialised in %ums\n",
                 pgdat->node_id, jiffies_to_msecs(jiffies - start));
 
         pgdat_init_report_one_done();
         return 0;
 }
 
 /*
  * If this zone has deferred pages, try to grow it by initializing enough
  * deferred pages to satisfy the allocation specified by order, rounded up to
  * the nearest PAGES_PER_SECTION boundary.  So we're adding memory in increments
  * of SECTION_SIZE bytes by initializing struct pages in increments of
  * PAGES_PER_SECTION * sizeof(struct page) bytes.
  *
  * Return true when zone was grown, otherwise return false. We return true even
  * when we grow less than requested, to let the caller decide if there are
  * enough pages to satisfy the allocation.
  *
  * Note: We use noinline because this function is needed only during boot, and
  * it is called from a __ref function _deferred_grow_zone. This way we are
  * making sure that it is not inlined into permanent text section.
  */
 static noinline bool __init
 deferred_grow_zone(struct zone *zone, unsigned int order)
 {
         unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
         pg_data_t *pgdat = zone->zone_pgdat;
         unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
         unsigned long spfn, epfn, flags;
         unsigned long nr_pages = 0;
         u64 i;
 
         /* Only the last zone may have deferred pages */
         if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat))
                 return false;
 
         pgdat_resize_lock(pgdat, &flags);
 
         /*
          * If someone grew this zone while we were waiting for spinlock, return
          * true, as there might be enough pages already.
          */
         if (first_deferred_pfn != pgdat->first_deferred_pfn) {
                 pgdat_resize_unlock(pgdat, &flags);
                 return true;
         }
 
         /* If the zone is empty somebody else may have cleared out the zone */
         if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
                                                  first_deferred_pfn)) {
                 pgdat->first_deferred_pfn = ULONG_MAX;
                 pgdat_resize_unlock(pgdat, &flags);
                 /* Retry only once. */
                 return first_deferred_pfn != ULONG_MAX;
         }
 
         /*
          * Initialize and free pages in MAX_ORDER sized increments so
          * that we can avoid introducing any issues with the buddy
          * allocator.
          */
         while (spfn < epfn) {
                 /* update our first deferred PFN for this section */
                 first_deferred_pfn = spfn;
 
                 nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
                 touch_nmi_watchdog();
 
                 /* We should only stop along section boundaries */
                 if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION)
                         continue;
 
                 /* If our quota has been met we can stop here */
                 if (nr_pages >= nr_pages_needed)
                         break;
         }
 
         pgdat->first_deferred_pfn = spfn;
         pgdat_resize_unlock(pgdat, &flags);
 
         return nr_pages > 0;
 }
 
 /*
  * deferred_grow_zone() is __init, but it is called from
  * get_page_from_freelist() during early boot until deferred_pages permanently
  * disables this call. This is why we have refdata wrapper to avoid warning,
  * and to ensure that the function body gets unloaded.
  */
 static bool __ref
 _deferred_grow_zone(struct zone *zone, unsigned int order)
 {
         return deferred_grow_zone(zone, order);
 }
 
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 void __init page_alloc_init_late(void)
 {
         struct zone *zone;
         int nid;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 
         /* There will be num_node_state(N_MEMORY) threads */
         atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
         for_each_node_state(nid, N_MEMORY) {
                 kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
         }
 
         /* Block until all are initialised */
         wait_for_completion(&pgdat_init_all_done_comp);
 
         /*
          * We initialized the rest of the deferred pages.  Permanently disable
          * on-demand struct page initialization.
          */
         static_branch_disable(&deferred_pages);
 
         /* Reinit limits that are based on free pages after the kernel is up */
         files_maxfiles_init();
 #endif
 
         buffer_init();
 
         /* Discard memblock private memory */
         memblock_discard();
 
         for_each_node_state(nid, N_MEMORY)
                 shuffle_free_memory(NODE_DATA(nid));
 
         for_each_populated_zone(zone)
                 set_zone_contiguous(zone);
 }
 
 #ifdef CONFIG_CMA
 /* Free whole pageblock and set its migration type to MIGRATE_CMA. */
 void __init init_cma_reserved_pageblock(struct page *page)
 {
         unsigned i = pageblock_nr_pages;
         struct page *p = page;
 
         do {
                 __ClearPageReserved(p);
                 set_page_count(p, 0);
         } while (++p, --i);
 
         set_pageblock_migratetype(page, MIGRATE_CMA);
 
         if (pageblock_order >= MAX_ORDER) {
                 i = pageblock_nr_pages;
                 p = page;
                 do {
                         set_page_refcounted(p);
                         __free_pages(p, MAX_ORDER - 1);
                         p += MAX_ORDER_NR_PAGES;
                 } while (i -= MAX_ORDER_NR_PAGES);
         } else {
                 set_page_refcounted(page);
                 __free_pages(page, pageblock_order);
         }
 
         adjust_managed_page_count(page, pageblock_nr_pages);
         page_zone(page)->cma_pages += pageblock_nr_pages;
 }
 #endif
 
 /*
  * The order of subdivision here is critical for the IO subsystem.
  * Please do not alter this order without good reasons and regression
  * testing. Specifically, as large blocks of memory are subdivided,
  * the order in which smaller blocks are delivered depends on the order
  * they're subdivided in this function. This is the primary factor
  * influencing the order in which pages are delivered to the IO
  * subsystem according to empirical testing, and this is also justified
  * by considering the behavior of a buddy system containing a single
  * large block of memory acted on by a series of small allocations.
  * This behavior is a critical factor in sglist merging's success.
  *
  * -- nyc
  */
 static inline void expand(struct zone *zone, struct page *page,
         int low, int high, int migratetype)
 {
         unsigned long size = 1 << high;
 
         while (high > low) {
                 high--;
                 size >>= 1;
                 VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
 
                 /*
                  * Mark as guard pages (or page), that will allow to
                  * merge back to allocator when buddy will be freed.
                  * Corresponding page table entries will not be touched,
                  * pages will stay not present in virtual address space
                  */
                 if (set_page_guard(zone, &page[size], high, migratetype))
                         continue;
 
                 add_to_free_list(&page[size], zone, high, migratetype);
                 set_buddy_order(&page[size], high);
         }
 }
 
 static void check_new_page_bad(struct page *page)
 {
         if (unlikely(page->flags & __PG_HWPOISON)) {
                 /* Don't complain about hwpoisoned pages */
                 page_mapcount_reset(page); /* remove PageBuddy */
                 return;
         }
 
         bad_page(page,
                  page_bad_reason(page, PAGE_FLAGS_CHECK_AT_PREP));
 }
 
 /*
  * This page is about to be returned from the page allocator
  */
 static inline int check_new_page(struct page *page)
 {
         if (likely(page_expected_state(page,
                                 PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON)))
                 return 0;
 
         check_new_page_bad(page);
         return 1;
 }
 
 #ifdef CONFIG_DEBUG_VM
 /*
  * With DEBUG_VM enabled, order-0 pages are checked for expected state when
  * being allocated from pcp lists. With debug_pagealloc also enabled, they are
  * also checked when pcp lists are refilled from the free lists.
  */
 static inline bool check_pcp_refill(struct page *page)
 {
         if (debug_pagealloc_enabled_static())
                 return check_new_page(page);
         else
                 return false;
 }
 
 static inline bool check_new_pcp(struct page *page)
 {
         return check_new_page(page);
 }
 #else
 /*
  * With DEBUG_VM disabled, free order-0 pages are checked for expected state
  * when pcp lists are being refilled from the free lists. With debug_pagealloc
  * enabled, they are also checked when being allocated from the pcp lists.
  */
 static inline bool check_pcp_refill(struct page *page)
 {
         return check_new_page(page);
 }
 static inline bool check_new_pcp(struct page *page)
 {
         if (debug_pagealloc_enabled_static())
                 return check_new_page(page);
         else
                 return false;
 }
 #endif /* CONFIG_DEBUG_VM */
 
 static bool check_new_pages(struct page *page, unsigned int order)
 {
         int i;
         for (i = 0; i < (1 << order); i++) {
                 struct page *p = page + i;
 
                 if (unlikely(check_new_page(p)))
                         return true;
         }
 
         return false;
 }
 
 inline void post_alloc_hook(struct page *page, unsigned int order,
                                 gfp_t gfp_flags)
 {
         set_page_private(page, 0);
         set_page_refcounted(page);
 
         arch_alloc_page(page, order);
         debug_pagealloc_map_pages(page, 1 << order);
 
         /*
          * Page unpoisoning must happen before memory initialization.
          * Otherwise, the poison pattern will be overwritten for __GFP_ZERO
          * allocations and the page unpoisoning code will complain.
          */
         kernel_unpoison_pages(page, 1 << order);
 
         /*
          * As memory initialization might be integrated into KASAN,
          * kasan_alloc_pages and kernel_init_free_pages must be
          * kept together to avoid discrepancies in behavior.
          */
         if (kasan_has_integrated_init()) {
                 kasan_alloc_pages(page, order, gfp_flags);
         } else {
                 bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags);
 
                 kasan_unpoison_pages(page, order, init);
                 if (init)
                         kernel_init_free_pages(page, 1 << order,
                                                gfp_flags & __GFP_ZEROTAGS);
         }
 
         set_page_owner(page, order, gfp_flags);
 }
 
 static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
                                                         unsigned int alloc_flags)
 {
         post_alloc_hook(page, order, gfp_flags);
 
         if (order && (gfp_flags & __GFP_COMP))
                 prep_compound_page(page, order);
 
         /*
          * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to
          * allocate the page. The expectation is that the caller is taking
          * steps that will free more memory. The caller should avoid the page
          * being used for !PFMEMALLOC purposes.
          */
         if (alloc_flags & ALLOC_NO_WATERMARKS)
                 set_page_pfmemalloc(page);
         else
                 clear_page_pfmemalloc(page);
 }
 
 /*
  * Go through the free lists for the given migratetype and remove
  * the smallest available page from the freelists
  */
 static __always_inline
 struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
                                                 int migratetype)
 {
         unsigned int current_order;
         struct free_area *area;
         struct page *page;
 
         /* Find a page of the appropriate size in the preferred list */
         for (current_order = order; current_order < MAX_ORDER; ++current_order) {
                 area = &(zone->free_area[current_order]);
                 page = get_page_from_free_area(area, migratetype);
                 if (!page)
                         continue;
                 del_page_from_free_list(page, zone, current_order);
                 expand(zone, page, order, current_order, migratetype);
                 set_pcppage_migratetype(page, migratetype);
                 return page;
         }
 
         return NULL;
 }
 
 
 /*
  * This array describes the order lists are fallen back to when
  * the free lists for the desirable migrate type are depleted
  */
 static int fallbacks[MIGRATE_TYPES][3] = {
         [MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,   MIGRATE_TYPES },
         [MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES },
         [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,   MIGRATE_TYPES },
 #ifdef CONFIG_CMA
         [MIGRATE_CMA]         = { MIGRATE_TYPES }, /* Never used */
 #endif
 #ifdef CONFIG_MEMORY_ISOLATION
         [MIGRATE_ISOLATE]     = { MIGRATE_TYPES }, /* Never used */
 #endif
 };
 
 #ifdef CONFIG_CMA
 static __always_inline struct page *__rmqueue_cma_fallback(struct zone *zone,
                                         unsigned int order)
 {
         return __rmqueue_smallest(zone, order, MIGRATE_CMA);
 }
 #else
 static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
                                         unsigned int order) { return NULL; }
 #endif
 
 /*
  * Move the free pages in a range to the freelist tail of the requested type.
  * Note that start_page and end_pages are not aligned on a pageblock
  * boundary. If alignment is required, use move_freepages_block()
  */
 static int move_freepages(struct zone *zone,
                           unsigned long start_pfn, unsigned long end_pfn,
                           int migratetype, int *num_movable)
 {
         struct page *page;
         unsigned long pfn;
         unsigned int order;
         int pages_moved = 0;
 
         for (pfn = start_pfn; pfn <= end_pfn;) {
                 page = pfn_to_page(pfn);
                 if (!PageBuddy(page)) {
                         /*
                          * We assume that pages that could be isolated for
                          * migration are movable. But we don't actually try
                          * isolating, as that would be expensive.
                          */
                         if (num_movable &&
                                         (PageLRU(page) || __PageMovable(page)))
                                 (*num_movable)++;
                         pfn++;
                         continue;
                 }
 
                 /* Make sure we are not inadvertently changing nodes */
                 VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
                 VM_BUG_ON_PAGE(page_zone(page) != zone, page);
 
                 order = buddy_order(page);
                 move_to_free_list(page, zone, order, migratetype);
                 pfn += 1 << order;
                 pages_moved += 1 << order;
         }
 
         return pages_moved;
 }
 
 int move_freepages_block(struct zone *zone, struct page *page,
                                 int migratetype, int *num_movable)
 {
         unsigned long start_pfn, end_pfn, pfn;
 
         if (num_movable)
                 *num_movable = 0;
 
         pfn = page_to_pfn(page);
         start_pfn = pfn & ~(pageblock_nr_pages - 1);
         end_pfn = start_pfn + pageblock_nr_pages - 1;
 
         /* Do not cross zone boundaries */
         if (!zone_spans_pfn(zone, start_pfn))
                 start_pfn = pfn;
         if (!zone_spans_pfn(zone, end_pfn))
                 return 0;
 
         return move_freepages(zone, start_pfn, end_pfn, migratetype,
                                                                 num_movable);
 }
 
 static void change_pageblock_range(struct page *pageblock_page,
                                         int start_order, int migratetype)
 {
         int nr_pageblocks = 1 << (start_order - pageblock_order);
 
         while (nr_pageblocks--) {
                 set_pageblock_migratetype(pageblock_page, migratetype);
                 pageblock_page += pageblock_nr_pages;
         }
 }
 
 /*
  * When we are falling back to another migratetype during allocation, try to
  * steal extra free pages from the same pageblocks to satisfy further
  * allocations, instead of polluting multiple pageblocks.
  *
  * If we are stealing a relatively large buddy page, it is likely there will
  * be more free pages in the pageblock, so try to steal them all. For
  * reclaimable and unmovable allocations, we steal regardless of page size,
  * as fragmentation caused by those allocations polluting movable pageblocks
  * is worse than movable allocations stealing from unmovable and reclaimable
  * pageblocks.
  */
 static bool can_steal_fallback(unsigned int order, int start_mt)
 {
         /*
          * Leaving this order check is intended, although there is
          * relaxed order check in next check. The reason is that
          * we can actually steal whole pageblock if this condition met,
          * but, below check doesn't guarantee it and that is just heuristic
          * so could be changed anytime.
          */
         if (order >= pageblock_order)
                 return true;
 
         if (order >= pageblock_order / 2 ||
                 start_mt == MIGRATE_RECLAIMABLE ||
                 start_mt == MIGRATE_UNMOVABLE ||
                 page_group_by_mobility_disabled)
                 return true;
 
         return false;
 }
 
 static inline bool boost_watermark(struct zone *zone)
 {
         unsigned long max_boost;
 
         if (!watermark_boost_factor)
                 return false;
         /*
          * Don't bother in zones that are unlikely to produce results.
          * On small machines, including kdump capture kernels running
          * in a small area, boosting the watermark can cause an out of
          * memory situation immediately.
          */
         if ((pageblock_nr_pages * 4) > zone_managed_pages(zone))
                 return false;
 
         max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
                         watermark_boost_factor, 10000);
 
         /*
          * high watermark may be uninitialised if fragmentation occurs
          * very early in boot so do not boost. We do not fall
          * through and boost by pageblock_nr_pages as failing
          * allocations that early means that reclaim is not going
          * to help and it may even be impossible to reclaim the
          * boosted watermark resulting in a hang.
          */
         if (!max_boost)
                 return false;
 
         max_boost = max(pageblock_nr_pages, max_boost);
 
         zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
                 max_boost);
 
         return true;
 }
 
 /*
  * This function implements actual steal behaviour. If order is large enough,
  * we can steal whole pageblock. If not, we first move freepages in this
  * pageblock to our migratetype and determine how many already-allocated pages
  * are there in the pageblock with a compatible migratetype. If at least half
  * of pages are free or compatible, we can change migratetype of the pageblock
  * itself, so pages freed in the future will be put on the correct free list.
  */
 static void steal_suitable_fallback(struct zone *zone, struct page *page,
                 unsigned int alloc_flags, int start_type, bool whole_block)
 {
         unsigned int current_order = buddy_order(page);
         int free_pages, movable_pages, alike_pages;
         int old_block_type;
 
         old_block_type = get_pageblock_migratetype(page);
 
         /*
          * This can happen due to races and we want to prevent broken
          * highatomic accounting.
          */
         if (is_migrate_highatomic(old_block_type))
                 goto single_page;
 
         /* Take ownership for orders >= pageblock_order */
         if (current_order >= pageblock_order) {
                 change_pageblock_range(page, current_order, start_type);
                 goto single_page;
         }
 
         /*
          * Boost watermarks to increase reclaim pressure to reduce the
          * likelihood of future fallbacks. Wake kswapd now as the node
          * may be balanced overall and kswapd will not wake naturally.
          */
         if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD))
                 set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);
 
         /* We are not allowed to try stealing from the whole block */
         if (!whole_block)
                 goto single_page;
 
         free_pages = move_freepages_block(zone, page, start_type,
                                                 &movable_pages);
         /*
          * Determine how many pages are compatible with our allocation.
          * For movable allocation, it's the number of movable pages which
          * we just obtained. For other types it's a bit more tricky.
          */
         if (start_type == MIGRATE_MOVABLE) {
                 alike_pages = movable_pages;
         } else {
                 /*
                  * If we are falling back a RECLAIMABLE or UNMOVABLE allocation
                  * to MOVABLE pageblock, consider all non-movable pages as
                  * compatible. If it's UNMOVABLE falling back to RECLAIMABLE or
                  * vice versa, be conservative since we can't distinguish the
                  * exact migratetype of non-movable pages.
                  */
                 if (old_block_type == MIGRATE_MOVABLE)
                         alike_pages = pageblock_nr_pages
                                                 - (free_pages + movable_pages);
                 else
                         alike_pages = 0;
         }
 
         /* moving whole block can fail due to zone boundary conditions */
         if (!free_pages)
                 goto single_page;
 
         /*
          * If a sufficient number of pages in the block are either free or of
          * comparable migratability as our allocation, claim the whole block.
          */
         if (free_pages + alike_pages >= (1 << (pageblock_order-1)) ||
                         page_group_by_mobility_disabled)
                 set_pageblock_migratetype(page, start_type);
 
         return;
 
 single_page:
         move_to_free_list(page, zone, current_order, start_type);
 }
 
 /*
  * Check whether there is a suitable fallback freepage with requested order.
  * If only_stealable is true, this function returns fallback_mt only if
  * we can steal other freepages all together. This would help to reduce
  * fragmentation due to mixed migratetype pages in one pageblock.
  */
 int find_suitable_fallback(struct free_area *area, unsigned int order,
                         int migratetype, bool only_stealable, bool *can_steal)
 {
         int i;
         int fallback_mt;
 
         if (area->nr_free == 0)
                 return -1;
 
         *can_steal = false;
         for (i = 0;; i++) {
                 fallback_mt = fallbacks[migratetype][i];
                 if (fallback_mt == MIGRATE_TYPES)
                         break;
 
                 if (free_area_empty(area, fallback_mt))
                         continue;
 
                 if (can_steal_fallback(order, migratetype))
                         *can_steal = true;
 
                 if (!only_stealable)
                         return fallback_mt;
 
                 if (*can_steal)
                         return fallback_mt;
         }
 
         return -1;
 }
 
 /*
  * Reserve a pageblock for exclusive use of high-order atomic allocations if
  * there are no empty page blocks that contain a page with a suitable order
  */
 static void reserve_highatomic_pageblock(struct page *page, struct zone *zone,
                                 unsigned int alloc_order)
 {
         int mt;
         unsigned long max_managed, flags;
 
         /*
          * Limit the number reserved to 1 pageblock or roughly 1% of a zone.
          * Check is race-prone but harmless.
          */
         max_managed = (zone_managed_pages(zone) / 100) + pageblock_nr_pages;
         if (zone->nr_reserved_highatomic >= max_managed)
                 return;
 
         spin_lock_irqsave(&zone->lock, flags);
 
         /* Recheck the nr_reserved_highatomic limit under the lock */
         if (zone->nr_reserved_highatomic >= max_managed)
                 goto out_unlock;
 
         /* Yoink! */
         mt = get_pageblock_migratetype(page);
         if (!is_migrate_highatomic(mt) && !is_migrate_isolate(mt)
             && !is_migrate_cma(mt)) {
                 zone->nr_reserved_highatomic += pageblock_nr_pages;
                 set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC);
                 move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL);
         }
 
 out_unlock:
         spin_unlock_irqrestore(&zone->lock, flags);
 }
 
 /*
  * Used when an allocation is about to fail under memory pressure. This
  * potentially hurts the reliability of high-order allocations when under
  * intense memory pressure but failed atomic allocations should be easier
  * to recover from than an OOM.
  *
  * If @force is true, try to unreserve a pageblock even though highatomic
  * pageblock is exhausted.
  */
 static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
                                                 bool force)
 {
         struct zonelist *zonelist = ac->zonelist;
         unsigned long flags;
         struct zoneref *z;
         struct zone *zone;
         struct page *page;
         int order;
         bool ret;
 
         for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx,
                                                                 ac->nodemask) {
                 /*
                  * Preserve at least one pageblock unless memory pressure
                  * is really high.
                  */
                 if (!force && zone->nr_reserved_highatomic <=
                                         pageblock_nr_pages)
                         continue;
 
                 spin_lock_irqsave(&zone->lock, flags);
                 for (order = 0; order < MAX_ORDER; order++) {
                         struct free_area *area = &(zone->free_area[order]);
 
                         page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC);
                         if (!page)
                                 continue;
 
                         /*
                          * In page freeing path, migratetype change is racy so
                          * we can counter several free pages in a pageblock
                          * in this loop although we changed the pageblock type
                          * from highatomic to ac->migratetype. So we should
                          * adjust the count once.
                          */
                         if (is_migrate_highatomic_page(page)) {
                                 /*
                                  * It should never happen but changes to
                                  * locking could inadvertently allow a per-cpu
                                  * drain to add pages to MIGRATE_HIGHATOMIC
                                  * while unreserving so be safe and watch for
                                  * underflows.
                                  */
                                 zone->nr_reserved_highatomic -= min(
                                                 pageblock_nr_pages,
                                                 zone->nr_reserved_highatomic);
                         }
 
                         /*
                          * Convert to ac->migratetype and avoid the normal
                          * pageblock stealing heuristics. Minimally, the caller
                          * is doing the work and needs the pages. More
                          * importantly, if the block was always converted to
                          * MIGRATE_UNMOVABLE or another type then the number
                          * of pageblocks that cannot be completely freed
                          * may increase.
                          */
                         set_pageblock_migratetype(page, ac->migratetype);
                         ret = move_freepages_block(zone, page, ac->migratetype,
                                                                         NULL);
                         if (ret) {
                                 spin_unlock_irqrestore(&zone->lock, flags);
                                 return ret;
                         }
                 }
                 spin_unlock_irqrestore(&zone->lock, flags);
         }
 
         return false;
 }
 
 /*
  * Try finding a free buddy page on the fallback list and put it on the free
  * list of requested migratetype, possibly along with other pages from the same
  * block, depending on fragmentation avoidance heuristics. Returns true if
  * fallback was found so that __rmqueue_smallest() can grab it.
  *
  * The use of signed ints for order and current_order is a deliberate
  * deviation from the rest of this file, to make the for loop
  * condition simpler.
  */
 static __always_inline bool
 __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
                                                 unsigned int alloc_flags)
 {
         struct free_area *area;
         int current_order;
         int min_order = order;
         struct page *page;
         int fallback_mt;
         bool can_steal;
 
         /*
          * Do not steal pages from freelists belonging to other pageblocks
          * i.e. orders < pageblock_order. If there are no local zones free,
          * the zonelists will be reiterated without ALLOC_NOFRAGMENT.
          */
         if (alloc_flags & ALLOC_NOFRAGMENT)
                 min_order = pageblock_order;
 
         /*
          * Find the largest available free page in the other list. This roughly
          * approximates finding the pageblock with the most free pages, which
          * would be too costly to do exactly.
          */
         for (current_order = MAX_ORDER - 1; current_order >= min_order;
                                 --current_order) {
                 area = &(zone->free_area[current_order]);
                 fallback_mt = find_suitable_fallback(area, current_order,
                                 start_migratetype, false, &can_steal);
                 if (fallback_mt == -1)
                         continue;
 
                 /*
                  * We cannot steal all free pages from the pageblock and the
                  * requested migratetype is movable. In that case it's better to
                  * steal and split the smallest available page instead of the
                  * largest available page, because even if the next movable
                  * allocation falls back into a different pageblock than this
                  * one, it won't cause permanent fragmentation.
                  */
                 if (!can_steal && start_migratetype == MIGRATE_MOVABLE
                                         && current_order > order)
                         goto find_smallest;
 
                 goto do_steal;
         }
 
         return false;
 
 find_smallest:
         for (current_order = order; current_order < MAX_ORDER;
                                                         current_order++) {
                 area = &(zone->free_area[current_order]);
                 fallback_mt = find_suitable_fallback(area, current_order,
                                 start_migratetype, false, &can_steal);
                 if (fallback_mt != -1)
                         break;
         }
 
         /*
          * This should not happen - we already found a suitable fallback
          * when looking for the largest page.
          */
         VM_BUG_ON(current_order == MAX_ORDER);
 
 do_steal:
         page = get_page_from_free_area(area, fallback_mt);
 
         steal_suitable_fallback(zone, page, alloc_flags, start_migratetype,
                                                                 can_steal);
 
         trace_mm_page_alloc_extfrag(page, order, current_order,
                 start_migratetype, fallback_mt);
 
         return true;
 
 }
 
 /*
  * Do the hard work of removing an element from the buddy allocator.
  * Call me with the zone->lock already held.
  */
 static __always_inline struct page *
 __rmqueue(struct zone *zone, unsigned int order, int migratetype,
                                                 unsigned int alloc_flags)
 {
         struct page *page;
 
         if (IS_ENABLED(CONFIG_CMA)) {
                 /*
                  * Balance movable allocations between regular and CMA areas by
                  * allocating from CMA when over half of the zone's free memory
                  * is in the CMA area.
                  */
                 if (alloc_flags & ALLOC_CMA &&
                     zone_page_state(zone, NR_FREE_CMA_PAGES) >
                     zone_page_state(zone, NR_FREE_PAGES) / 2) {
                         page = __rmqueue_cma_fallback(zone, order);
                         if (page)
                                 goto out;
                 }
         }
 retry:
         page = __rmqueue_smallest(zone, order, migratetype);
         if (unlikely(!page)) {
                 if (alloc_flags & ALLOC_CMA)
                         page = __rmqueue_cma_fallback(zone, order);
 
                 if (!page && __rmqueue_fallback(zone, order, migratetype,
                                                                 alloc_flags))
                         goto retry;
         }
 out:
         if (page)
                 trace_mm_page_alloc_zone_locked(page, order, migratetype);
         return page;
 }
 
 /*
  * Obtain a specified number of elements from the buddy allocator, all under
  * a single hold of the lock, for efficiency.  Add them to the supplied list.
  * Returns the number of new pages which were placed at *list.
  */
 static int rmqueue_bulk(struct zone *zone, unsigned int order,
                         unsigned long count, struct list_head *list,
                         int migratetype, unsigned int alloc_flags)
 {
         int i, allocated = 0;
 
         /*
          * local_lock_irq held so equivalent to spin_lock_irqsave for
          * both PREEMPT_RT and non-PREEMPT_RT configurations.
          */
         spin_lock(&zone->lock);
         for (i = 0; i < count; ++i) {
                 struct page *page = __rmqueue(zone, order, migratetype,
                                                                 alloc_flags);
                 if (unlikely(page == NULL))
                         break;
 
                 if (unlikely(check_pcp_refill(page)))
                         continue;
 
                 /*
                  * Split buddy pages returned by expand() are received here in
                  * physical page order. The page is added to the tail of
                  * caller's list. From the callers perspective, the linked list
                  * is ordered by page number under some conditions. This is
                  * useful for IO devices that can forward direction from the
                  * head, thus also in the physical page order. This is useful
                  * for IO devices that can merge IO requests if the physical
                  * pages are ordered properly.
                  */
                 list_add_tail(&page->lru, list);
                 allocated++;
                 if (is_migrate_cma(get_pcppage_migratetype(page)))
                         __mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
                                               -(1 << order));
         }
 
         /*
          * i pages were removed from the buddy list even if some leak due
          * to check_pcp_refill failing so adjust NR_FREE_PAGES based
          * on i. Do not confuse with 'allocated' which is the number of
          * pages added to the pcp list.
          */
         __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
         spin_unlock(&zone->lock);
         return allocated;
 }
 
 #ifdef CONFIG_NUMA
 /*
  * Called from the vmstat counter updater to drain pagesets of this
  * currently executing processor on remote nodes after they have
  * expired.
  *
  * Note that this function must be called with the thread pinned to
  * a single processor.
  */
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 {
         unsigned long flags;
         int to_drain, batch;
 
         local_lock_irqsave(&pagesets.lock, flags);
         batch = READ_ONCE(pcp->batch);
         to_drain = min(pcp->count, batch);
         if (to_drain > 0)
                 free_pcppages_bulk(zone, to_drain, pcp);
         local_unlock_irqrestore(&pagesets.lock, flags);
 }
 #endif
 
 /*
  * Drain pcplists of the indicated processor and zone.
  *
  * The processor must either be the current processor and the
  * thread pinned to the current processor or a processor that
  * is not online.
  */
 static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
         unsigned long flags;
         struct per_cpu_pages *pcp;
 
         local_lock_irqsave(&pagesets.lock, flags);
 
         pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
         if (pcp->count)
                 free_pcppages_bulk(zone, pcp->count, pcp);
 
         local_unlock_irqrestore(&pagesets.lock, flags);
 }
 
 /*
  * Drain pcplists of all zones on the indicated processor.
  *
  * The processor must either be the current processor and the
  * thread pinned to the current processor or a processor that
  * is not online.
  */
 static void drain_pages(unsigned int cpu)
 {
         struct zone *zone;
 
         for_each_populated_zone(zone) {
                 drain_pages_zone(cpu, zone);
         }
 }
 
 /*
  * Spill all of this CPU's per-cpu pages back into the buddy allocator.
  *
  * The CPU has to be pinned. When zone parameter is non-NULL, spill just
  * the single zone's pages.
  */
 void drain_local_pages(struct zone *zone)
 {
         int cpu = smp_processor_id();
 
         if (zone)
                 drain_pages_zone(cpu, zone);
         else
                 drain_pages(cpu);
 }
 
 static void drain_local_pages_wq(struct work_struct *work)
 {
         struct pcpu_drain *drain;
 
         drain = container_of(work, struct pcpu_drain, work);
 
         /*
          * drain_all_pages doesn't use proper cpu hotplug protection so
          * we can race with cpu offline when the WQ can move this from
          * a cpu pinned worker to an unbound one. We can operate on a different
          * cpu which is alright but we also have to make sure to not move to
          * a different one.
          */
         migrate_disable();
         drain_local_pages(drain->zone);
         migrate_enable();
 }
 
 /*
  * The implementation of drain_all_pages(), exposing an extra parameter to
  * drain on all cpus.
  *
  * drain_all_pages() is optimized to only execute on cpus where pcplists are
  * not empty. The check for non-emptiness can however race with a free to
  * pcplist that has not yet increased the pcp->count from 0 to 1. Callers
  * that need the guarantee that every CPU has drained can disable the
  * optimizing racy check.
  */
 static void __drain_all_pages(struct zone *zone, bool force_all_cpus)
 {
         int cpu;
 
         /*
          * Allocate in the BSS so we won't require allocation in
          * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
          */
         static cpumask_t cpus_with_pcps;
 
         /*
          * Make sure nobody triggers this path before mm_percpu_wq is fully
          * initialized.
          */
         if (WARN_ON_ONCE(!mm_percpu_wq))
                 return;
 
         /*
          * Do not drain if one is already in progress unless it's specific to
          * a zone. Such callers are primarily CMA and memory hotplug and need
          * the drain to be complete when the call returns.
          */
         if (unlikely(!mutex_trylock(&pcpu_drain_mutex))) {
                 if (!zone)
                         return;
                 mutex_lock(&pcpu_drain_mutex);
         }
 
         /*
          * We don't care about racing with CPU hotplug event
          * as offline notification will cause the notified
          * cpu to drain that CPU pcps and on_each_cpu_mask
          * disables preemption as part of its processing
          */
         for_each_online_cpu(cpu) {
                 struct per_cpu_pages *pcp;
                 struct zone *z;
                 bool has_pcps = false;
 
                 if (force_all_cpus) {
                         /*
                          * The pcp.count check is racy, some callers need a
                          * guarantee that no cpu is missed.
                          */
                         has_pcps = true;
                 } else if (zone) {
                         pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
                         if (pcp->count)
                                 has_pcps = true;
                 } else {
                         for_each_populated_zone(z) {
                                 pcp = per_cpu_ptr(z->per_cpu_pageset, cpu);
                                 if (pcp->count) {
                                         has_pcps = true;
                                         break;
                                 }
                         }
                 }
 
                 if (has_pcps)
                         cpumask_set_cpu(cpu, &cpus_with_pcps);
                 else
                         cpumask_clear_cpu(cpu, &cpus_with_pcps);
         }
 
         for_each_cpu(cpu, &cpus_with_pcps) {
                 struct pcpu_drain *drain = per_cpu_ptr(&pcpu_drain, cpu);
 
                 drain->zone = zone;
                 INIT_WORK(&drain->work, drain_local_pages_wq);
                 queue_work_on(cpu, mm_percpu_wq, &drain->work);
         }
         for_each_cpu(cpu, &cpus_with_pcps)
                 flush_work(&per_cpu_ptr(&pcpu_drain, cpu)->work);
 
         mutex_unlock(&pcpu_drain_mutex);
 }
 
 /*
  * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
  *
  * When zone parameter is non-NULL, spill just the single zone's pages.
  *
  * Note that this can be extremely slow as the draining happens in a workqueue.
  */
 void drain_all_pages(struct zone *zone)
 {
         __drain_all_pages(zone, false);
 }
 
 #ifdef CONFIG_HIBERNATION
 
 /*
  * Touch the watchdog for every WD_PAGE_COUNT pages.
  */
 #define WD_PAGE_COUNT   (128*1024)
 
 void mark_free_pages(struct zone *zone)
 {
         unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT;
         unsigned long flags;
         unsigned int order, t;
         struct page *page;
 
         if (zone_is_empty(zone))
                 return;
 
         spin_lock_irqsave(&zone->lock, flags);
 
         max_zone_pfn = zone_end_pfn(zone);
         for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
                 if (pfn_valid(pfn)) {
                         page = pfn_to_page(pfn);
 
                         if (!--page_count) {
                                 touch_nmi_watchdog();
                                 page_count = WD_PAGE_COUNT;
                         }
 
                         if (page_zone(page) != zone)
                                 continue;
 
                         if (!swsusp_page_is_forbidden(page))
                                 swsusp_unset_page_free(page);
                 }
 
         for_each_migratetype_order(order, t) {
                 list_for_each_entry(page,
                                 &zone->free_area[order].free_list[t], lru) {
                         unsigned long i;
 
                         pfn = page_to_pfn(page);
                         for (i = 0; i < (1UL << order); i++) {
                                 if (!--page_count) {
                                         touch_nmi_watchdog();
                                         page_count = WD_PAGE_COUNT;
                                 }
                                 swsusp_set_page_free(pfn_to_page(pfn + i));
                         }
                 }
         }
         spin_unlock_irqrestore(&zone->lock, flags);
 }
 #endif /* CONFIG_PM */
 
 static bool free_unref_page_prepare(struct page *page, unsigned long pfn,
                                                         unsigned int order)
 {
         int migratetype;
 
         if (!free_pcp_prepare(page, order))
                 return false;
 
         migratetype = get_pfnblock_migratetype(page, pfn);
         set_pcppage_migratetype(page, migratetype);
         return true;
 }
 
 static int nr_pcp_free(struct per_cpu_pages *pcp, int high, int batch)
 {
         int min_nr_free, max_nr_free;
 
         /* Check for PCP disabled or boot pageset */
         if (unlikely(high < batch))
                 return 1;
 
         /* Leave at least pcp->batch pages on the list */
         min_nr_free = batch;
         max_nr_free = high - batch;
 
         /*
          * Double the number of pages freed each time there is subsequent
          * freeing of pages without any allocation.
          */
         batch <<= pcp->free_factor;
         if (batch < max_nr_free)
                 pcp->free_factor++;
         batch = clamp(batch, min_nr_free, max_nr_free);
 
         return batch;
 }
 
 static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone)
 {
         int high = READ_ONCE(pcp->high);
 
         if (unlikely(!high))
                 return 0;
 
         if (!test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags))
                 return high;
 
         /*
          * If reclaim is active, limit the number of pages that can be
          * stored on pcp lists
          */
         return min(READ_ONCE(pcp->batch) << 2, high);
 }
 
 static void free_unref_page_commit(struct page *page, unsigned long pfn,
                                    int migratetype, unsigned int order)
 {
         struct zone *zone = page_zone(page);
         struct per_cpu_pages *pcp;
         int high;
         int pindex;
 
         __count_vm_event(PGFREE);
         pcp = this_cpu_ptr(zone->per_cpu_pageset);
         pindex = order_to_pindex(migratetype, order);
         list_add(&page->lru, &pcp->lists[pindex]);
         pcp->count += 1 << order;
         high = nr_pcp_high(pcp, zone);
         if (pcp->count >= high) {
                 int batch = READ_ONCE(pcp->batch);
 
                 free_pcppages_bulk(zone, nr_pcp_free(pcp, high, batch), pcp);
         }
 }
 
 /*
  * Free a pcp page
  */
 void free_unref_page(struct page *page, unsigned int order)
 {
         unsigned long flags;
         unsigned long pfn = page_to_pfn(page);
         int migratetype;
 
         if (!free_unref_page_prepare(page, pfn, order))
                 return;
 
         /*
          * We only track unmovable, reclaimable and movable on pcp lists.
          * Place ISOLATE pages on the isolated list because they are being
          * offlined but treat HIGHATOMIC as movable pages so we can get those
          * areas back if necessary. Otherwise, we may have to free
          * excessively into the page allocator
          */
         migratetype = get_pcppage_migratetype(page);
         if (unlikely(migratetype >= MIGRATE_PCPTYPES)) {
                 if (unlikely(is_migrate_isolate(migratetype))) {
                         free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE);
                         return;
                 }
                 migratetype = MIGRATE_MOVABLE;
         }
 
         local_lock_irqsave(&pagesets.lock, flags);
         free_unref_page_commit(page, pfn, migratetype, order);
         local_unlock_irqrestore(&pagesets.lock, flags);
 }
 
 /*
  * Free a list of 0-order pages
  */
 void free_unref_page_list(struct list_head *list)
 {
         struct page *page, *next;
         unsigned long flags, pfn;
         int batch_count = 0;
         int migratetype;
 
         /* Prepare pages for freeing */
         list_for_each_entry_safe(page, next, list, lru) {
                 pfn = page_to_pfn(page);
                 if (!free_unref_page_prepare(page, pfn, 0)) {
                         list_del(&page->lru);
                         continue;
                 }
 
                 /*
                  * Free isolated pages directly to the allocator, see
                  * comment in free_unref_page.
                  */
                 migratetype = get_pcppage_migratetype(page);
                 if (unlikely(is_migrate_isolate(migratetype))) {
                         list_del(&page->lru);
                         free_one_page(page_zone(page), page, pfn, 0, migratetype, FPI_NONE);
                         continue;
                 }
 
                 set_page_private(page, pfn);
         }
 
         local_lock_irqsave(&pagesets.lock, flags);
         list_for_each_entry_safe(page, next, list, lru) {
                 pfn = page_private(page);
                 set_page_private(page, 0);
 
                 /*
                  * Non-isolated types over MIGRATE_PCPTYPES get added
                  * to the MIGRATE_MOVABLE pcp list.
                  */
                 migratetype = get_pcppage_migratetype(page);
                 if (unlikely(migratetype >= MIGRATE_PCPTYPES))
                         migratetype = MIGRATE_MOVABLE;
 
                 trace_mm_page_free_batched(page);
                 free_unref_page_commit(page, pfn, migratetype, 0);
 
                 /*
                  * Guard against excessive IRQ disabled times when we get
                  * a large list of pages to free.
                  */
                 if (++batch_count == SWAP_CLUSTER_MAX) {
                         local_unlock_irqrestore(&pagesets.lock, flags);
                         batch_count = 0;
                         local_lock_irqsave(&pagesets.lock, flags);
                 }
         }
         local_unlock_irqrestore(&pagesets.lock, flags);
 }
 
 /*
  * split_page takes a non-compound higher-order page, and splits it into
  * n (1<<order) sub-pages: page[0..n]
  * Each sub-page must be freed individually.
  *
  * Note: this is probably too low level an operation for use in drivers.
  * Please consult with lkml before using this in your driver.
  */
 void split_page(struct page *page, unsigned int order)
 {
         int i;
 
         VM_BUG_ON_PAGE(PageCompound(page), page);
         VM_BUG_ON_PAGE(!page_count(page), page);
 
         for (i = 1; i < (1 << order); i++)
                 set_page_refcounted(page + i);
         split_page_owner(page, 1 << order);
         split_page_memcg(page, 1 << order);
 }
 EXPORT_SYMBOL_GPL(split_page);
 
 int __isolate_free_page(struct page *page, unsigned int order)
 {
         unsigned long watermark;
         struct zone *zone;
         int mt;
 
         BUG_ON(!PageBuddy(page));
 
         zone = page_zone(page);
         mt = get_pageblock_migratetype(page);
 
         if (!is_migrate_isolate(mt)) {
                 /*
                  * Obey watermarks as if the page was being allocated. We can
                  * emulate a high-order watermark check with a raised order-0
                  * watermark, because we already know our high-order page
                  * exists.
                  */
                 watermark = zone->_watermark[WMARK_MIN] + (1UL << order);
                 if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
                         return 0;
 
                 __mod_zone_freepage_state(zone, -(1UL << order), mt);
         }
 
         /* Remove page from free list */
 
         del_page_from_free_list(page, zone, order);
 
         /*
          * Set the pageblock if the isolated page is at least half of a
          * pageblock
          */
         if (order >= pageblock_order - 1) {
                 struct page *endpage = page + (1 << order) - 1;
                 for (; page < endpage; page += pageblock_nr_pages) {
                         int mt = get_pageblock_migratetype(page);
                         if (!is_migrate_isolate(mt) && !is_migrate_cma(mt)
                             && !is_migrate_highatomic(mt))
                                 set_pageblock_migratetype(page,
                                                           MIGRATE_MOVABLE);
                 }
         }
 
 
         return 1UL << order;
 }
 
 /**
  * __putback_isolated_page - Return a now-isolated page back where we got it
  * @page: Page that was isolated
  * @order: Order of the isolated page
  * @mt: The page's pageblock's migratetype
  *
  * This function is meant to return a page pulled from the free lists via
  * __isolate_free_page back to the free lists they were pulled from.
  */
 void __putback_isolated_page(struct page *page, unsigned int order, int mt)
 {
         struct zone *zone = page_zone(page);
 
         /* zone lock should be held when this function is called */
         lockdep_assert_held(&zone->lock);
 
         /* Return isolated page to tail of freelist. */
         __free_one_page(page, page_to_pfn(page), zone, order, mt,
                         FPI_SKIP_REPORT_NOTIFY | FPI_TO_TAIL);
 }
 
 /*
  * Update NUMA hit/miss statistics
  *
  * Must be called with interrupts disabled.
  */
 static inline void zone_statistics(struct zone *preferred_zone, struct zone *z,
                                    long nr_account)
 {
 #ifdef CONFIG_NUMA
         enum numa_stat_item local_stat = NUMA_LOCAL;
 
         /* skip numa counters update if numa stats is disabled */
         if (!static_branch_likely(&vm_numa_stat_key))
                 return;
 
         if (zone_to_nid(z) != numa_node_id())
                 local_stat = NUMA_OTHER;
 
         if (zone_to_nid(z) == zone_to_nid(preferred_zone))
                 __count_numa_events(z, NUMA_HIT, nr_account);
         else {
                 __count_numa_events(z, NUMA_MISS, nr_account);
                 __count_numa_events(preferred_zone, NUMA_FOREIGN, nr_account);
         }
         __count_numa_events(z, local_stat, nr_account);
 #endif
 }
 
 /* Remove page from the per-cpu list, caller must protect the list */
 static inline
 struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order,
                         int migratetype,
                         unsigned int alloc_flags,
                         struct per_cpu_pages *pcp,
                         struct list_head *list)
 {
         struct page *page;
 
         do {
                 if (list_empty(list)) {
                         int batch = READ_ONCE(pcp->batch);
                         int alloced;
 
                         /*
                          * Scale batch relative to order if batch implies
                          * free pages can be stored on the PCP. Batch can
                          * be 1 for small zones or for boot pagesets which
                          * should never store free pages as the pages may
                          * belong to arbitrary zones.
                          */
                         if (batch > 1)
                                 batch = max(batch >> order, 2);
                         alloced = rmqueue_bulk(zone, order,
                                         batch, list,
                                         migratetype, alloc_flags);
 
                         pcp->count += alloced << order;
                         if (unlikely(list_empty(list)))
                                 return NULL;
                 }
 
                 page = list_first_entry(list, struct page, lru);
                 list_del(&page->lru);
                 pcp->count -= 1 << order;
         } while (check_new_pcp(page));
 
         return page;
 }
 
 /* Lock and remove page from the per-cpu list */
 static struct page *rmqueue_pcplist(struct zone *preferred_zone,
                         struct zone *zone, unsigned int order,
                         gfp_t gfp_flags, int migratetype,
                         unsigned int alloc_flags)
 {
         struct per_cpu_pages *pcp;
         struct list_head *list;
         struct page *page;
         unsigned long flags;
 
         local_lock_irqsave(&pagesets.lock, flags);
 
         /*
          * On allocation, reduce the number of pages that are batch freed.
          * See nr_pcp_free() where free_factor is increased for subsequent
          * frees.
          */
         pcp = this_cpu_ptr(zone->per_cpu_pageset);
         pcp->free_factor >>= 1;
         list = &pcp->lists[order_to_pindex(migratetype, order)];
         page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list);
         local_unlock_irqrestore(&pagesets.lock, flags);
         if (page) {
                 __count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
                 zone_statistics(preferred_zone, zone, 1);
         }
         return page;
 }
 
 /*
  * Allocate a page from the given zone. Use pcplists for order-0 allocations.
  */
 static inline
 struct page *rmqueue(struct zone *preferred_zone,
                         struct zone *zone, unsigned int order,
                         gfp_t gfp_flags, unsigned int alloc_flags,
                         int migratetype)
 {
         unsigned long flags;
         struct page *page;
 
         if (likely(pcp_allowed_order(order))) {
                 /*
                  * MIGRATE_MOVABLE pcplist could have the pages on CMA area and
                  * we need to skip it when CMA area isn't allowed.
                  */
                 if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA ||
                                 migratetype != MIGRATE_MOVABLE) {
                         page = rmqueue_pcplist(preferred_zone, zone, order,
                                         gfp_flags, migratetype, alloc_flags);
                         goto out;
                 }
         }
 
         /*
          * We most definitely don't want callers attempting to
          * allocate greater than order-1 page units with __GFP_NOFAIL.
          */
         WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
         spin_lock_irqsave(&zone->lock, flags);
 
         do {
                 page = NULL;
                 /*
                  * order-0 request can reach here when the pcplist is skipped
                  * due to non-CMA allocation context. HIGHATOMIC area is
                  * reserved for high-order atomic allocation, so order-0
                  * request should skip it.
                  */
                 if (order > 0 && alloc_flags & ALLOC_HARDER) {
                         page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
                         if (page)
                                 trace_mm_page_alloc_zone_locked(page, order, migratetype);
                 }
                 if (!page)
                         page = __rmqueue(zone, order, migratetype, alloc_flags);
         } while (page && check_new_pages(page, order));
         if (!page)
                 goto failed;
 
         __mod_zone_freepage_state(zone, -(1 << order),
                                   get_pcppage_migratetype(page));
         spin_unlock_irqrestore(&zone->lock, flags);
 
         __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
         zone_statistics(preferred_zone, zone, 1);
 
 out:
         /* Separate test+clear to avoid unnecessary atomics */
         if (test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags)) {
                 clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);
                 wakeup_kswapd(zone, 0, 0, zone_idx(zone));
         }
 
         VM_BUG_ON_PAGE(page && bad_range(zone, page), page);
         return page;
 
 failed:
         spin_unlock_irqrestore(&zone->lock, flags);
         return NULL;
 }
 
 #ifdef CONFIG_FAIL_PAGE_ALLOC
 
 static struct {
         struct fault_attr attr;
 
         bool ignore_gfp_highmem;
         bool ignore_gfp_reclaim;
         u32 min_order;
 } fail_page_alloc = {
         .attr = FAULT_ATTR_INITIALIZER,
         .ignore_gfp_reclaim = true,
         .ignore_gfp_highmem = true,
         .min_order = 1,
 };
 
 static int __init setup_fail_page_alloc(char *str)
 {
         return setup_fault_attr(&fail_page_alloc.attr, str);
 }
 __setup("fail_page_alloc=", setup_fail_page_alloc);
 
 static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
         if (order < fail_page_alloc.min_order)
                 return false;
         if (gfp_mask & __GFP_NOFAIL)
                 return false;
         if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
                 return false;
         if (fail_page_alloc.ignore_gfp_reclaim &&
                         (gfp_mask & __GFP_DIRECT_RECLAIM))
                 return false;
 
         return should_fail(&fail_page_alloc.attr, 1 << order);
 }
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
 
 static int __init fail_page_alloc_debugfs(void)
 {
         umode_t mode = S_IFREG | 0600;
         struct dentry *dir;
 
         dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
                                         &fail_page_alloc.attr);
 
         debugfs_create_bool("ignore-gfp-wait", mode, dir,
                             &fail_page_alloc.ignore_gfp_reclaim);
         debugfs_create_bool("ignore-gfp-highmem", mode, dir,
                             &fail_page_alloc.ignore_gfp_highmem);
         debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order);
 
         return 0;
 }
 
 late_initcall(fail_page_alloc_debugfs);
 
 #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
 
 #else /* CONFIG_FAIL_PAGE_ALLOC */
 
 static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
         return false;
 }
 
 #endif /* CONFIG_FAIL_PAGE_ALLOC */
 
 noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
         return __should_fail_alloc_page(gfp_mask, order);
 }
 ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
 
 static inline long __zone_watermark_unusable_free(struct zone *z,
                                 unsigned int order, unsigned int alloc_flags)
 {
         const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
         long unusable_free = (1 << order) - 1;
 
         /*
          * If the caller does not have rights to ALLOC_HARDER then subtract
          * the high-atomic reserves. This will over-estimate the size of the
          * atomic reserve but it avoids a search.
          */
         if (likely(!alloc_harder))
                 unusable_free += z->nr_reserved_highatomic;
 
 #ifdef CONFIG_CMA
         /* If allocation can't use CMA areas don't use free CMA pages */
         if (!(alloc_flags & ALLOC_CMA))
                 unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
 #endif
 
         return unusable_free;
 }
 
 /*
  * Return true if free base pages are above 'mark'. For high-order checks it
  * will return true of the order-0 watermark is reached and there is at least
  * one free page of a suitable size. Checking now avoids taking the zone lock
  * to check in the allocation paths if no pages are free.
  */
 bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
                          int highest_zoneidx, unsigned int alloc_flags,
                          long free_pages)
 {
         long min = mark;
         int o;
         const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
 
         /* free_pages may go negative - that's OK */
         free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
 
         if (alloc_flags & ALLOC_HIGH)
                 min -= min / 2;
 
         if (unlikely(alloc_harder)) {
                 /*
                  * OOM victims can try even harder than normal ALLOC_HARDER
                  * users on the grounds that it's definitely going to be in
                  * the exit path shortly and free memory. Any allocation it
                  * makes during the free path will be small and short-lived.
                  */
                 if (alloc_flags & ALLOC_OOM)
                         min -= min / 2;
                 else
                         min -= min / 4;
         }
 
         /*
          * Check watermarks for an order-0 allocation request. If these
          * are not met, then a high-order request also cannot go ahead
          * even if a suitable page happened to be free.
          */
         if (free_pages <= min + z->lowmem_reserve[highest_zoneidx])
                 return false;
 
         /* If this is an order-0 request then the watermark is fine */
         if (!order)
                 return true;
 
         /* For a high-order request, check at least one suitable page is free */
         for (o = order; o < MAX_ORDER; o++) {
                 struct free_area *area = &z->free_area[o];
                 int mt;
 
                 if (!area->nr_free)
                         continue;
 
                 for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
                         if (!free_area_empty(area, mt))
                                 return true;
                 }
 
 #ifdef CONFIG_CMA
                 if ((alloc_flags & ALLOC_CMA) &&
                     !free_area_empty(area, MIGRATE_CMA)) {
                         return true;
                 }
 #endif
                 if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC))
                         return true;
         }
         return false;
 }
 
 bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
                       int highest_zoneidx, unsigned int alloc_flags)
 {
         return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
                                         zone_page_state(z, NR_FREE_PAGES));
 }
 
 static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
                                 unsigned long mark, int highest_zoneidx,
                                 unsigned int alloc_flags, gfp_t gfp_mask)
 {
         long free_pages;
 
         free_pages = zone_page_state(z, NR_FREE_PAGES);
 
         /*
          * Fast check for order-0 only. If this fails then the reserves
          * need to be calculated.
          */
         if (!order) {
                 long fast_free;
 
                 fast_free = free_pages;
                 fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
                 if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
                         return true;
         }
 
         if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
                                         free_pages))
                 return true;
         /*
          * Ignore watermark boosting for GFP_ATOMIC order-0 allocations
          * when checking the min watermark. The min watermark is the
          * point where boosting is ignored so that kswapd is woken up
          * when below the low watermark.
          */
         if (unlikely(!order && (gfp_mask & __GFP_ATOMIC) && z->watermark_boost
                 && ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) {
                 mark = z->_watermark[WMARK_MIN];
                 return __zone_watermark_ok(z, order, mark, highest_zoneidx,
                                         alloc_flags, free_pages);
         }
 
         return false;
 }
 
 bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
                         unsigned long mark, int highest_zoneidx)
 {
         long free_pages = zone_page_state(z, NR_FREE_PAGES);
 
         if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
                 free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
 
         return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0,
                                                                 free_pages);
 }
 
 #ifdef CONFIG_NUMA
 int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
 
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 {
         return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
                                 node_reclaim_distance;
 }
 #else   /* CONFIG_NUMA */
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 {
         return true;
 }
 #endif  /* CONFIG_NUMA */
 
 /*
  * The restriction on ZONE_DMA32 as being a suitable zone to use to avoid
  * fragmentation is subtle. If the preferred zone was HIGHMEM then
  * premature use of a lower zone may cause lowmem pressure problems that
  * are worse than fragmentation. If the next zone is ZONE_DMA then it is
  * probably too small. It only makes sense to spread allocations to avoid
  * fragmentation between the Normal and DMA32 zones.
  */
 static inline unsigned int
 alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 {
         unsigned int alloc_flags;
 
         /*
          * __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
          * to save a branch.
          */
         alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM);
 
 #ifdef CONFIG_ZONE_DMA32
         if (!zone)
                 return alloc_flags;
 
         if (zone_idx(zone) != ZONE_NORMAL)
                 return alloc_flags;
 
         /*
          * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and
          * the pointer is within zone->zone_pgdat->node_zones[]. Also assume
          * on UMA that if Normal is populated then so is DMA32.
          */
         BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1);
         if (nr_online_nodes > 1 && !populated_zone(--zone))
                 return alloc_flags;
 
         alloc_flags |= ALLOC_NOFRAGMENT;
 #endif /* CONFIG_ZONE_DMA32 */
         return alloc_flags;
 }
 
 /* Must be called after current_gfp_context() which can change gfp_mask */
 static inline unsigned int gfp_to_alloc_flags_cma(gfp_t gfp_mask,
                                                   unsigned int alloc_flags)
 {
 #ifdef CONFIG_CMA
         if (gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE)
                 alloc_flags |= ALLOC_CMA;
 #endif
         return alloc_flags;
 }
 
 /*
  * 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;
         struct zone *zone;
         struct pglist_data *last_pgdat_dirty_limit = NULL;
         bool no_fallback;
 
 retry:
         /*
          * Scan zonelist, looking for a zone with enough free.
          * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
          */
         no_fallback = alloc_flags & ALLOC_NOFRAGMENT;
         z = ac->preferred_zoneref;
         for_next_zone_zonelist_nodemask(zone, z, ac->highest_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;
                         }
                 }
 
                 if (no_fallback && nr_online_nodes > 1 &&
                     zone != ac->preferred_zoneref->zone) {
                         int local_nid;
 
                         /*
                          * If moving to a remote node, retry but allow
                          * fragmenting fallbacks. Locality is more important
                          * than fragmentation avoidance.
                          */
                         local_nid = zone_to_nid(ac->preferred_zoneref->zone);
                         if (zone_to_nid(zone) != local_nid) {
                                 alloc_flags &= ~ALLOC_NOFRAGMENT;
                                 goto retry;
                         }
                 }
 
                 mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
                 if (!zone_watermark_fast(zone, order, mark,
                                        ac->highest_zoneidx, alloc_flags,
                                        gfp_mask)) {
                         int ret;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
                         /*
                          * Watermark failed for this zone, but see if we can
                          * grow this zone if it contains deferred pages.
                          */
                         if (static_branch_unlikely(&deferred_pages)) {
                                 if (_deferred_grow_zone(zone, order))
                                         goto try_this_zone;
                         }
 #endif
                         /* 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_enabled() ||
                             !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->highest_zoneidx, 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;
                 } else {
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
                         /* Try again if zone has deferred pages */
                         if (static_branch_unlikely(&deferred_pages)) {
                                 if (_deferred_grow_zone(zone, order))
                                         goto try_this_zone;
                         }
 #endif
                 }
         }
 
         /*
          * It's possible on a UMA machine to get through all zones that are
          * fragmented. If avoiding fragmentation, reset and try again.
          */
         if (no_fallback) {
                 alloc_flags &= ~ALLOC_NOFRAGMENT;
                 goto retry;
         }
 
         return NULL;
 }
 
 static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
 {
         unsigned int filter = SHOW_MEM_FILTER_NODES;
 
         /*
          * 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_task() || !(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, 10*HZ, 1);
 
         if ((gfp_mask & __GFP_NOWARN) ||
              !__ratelimit(&nopage_rs) ||
              ((gfp_mask & __GFP_DMA) && !has_managed_dma()))
                 return;
 
         va_start(args, fmt);
         vaf.fmt = fmt;
         vaf.va = &args;
         pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl",
                         current->comm, &vaf, gfp_mask, &gfp_mask,
                         nodemask_pr_args(nodemask));
         va_end(args);
 
         cpuset_print_current_mems_allowed();
         pr_cont("\n");
         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.
          *
          * The OOM killer may not free memory on a specific node.
          */
         if (gfp_mask & (__GFP_RETRY_MAYFAIL | __GFP_THISNODE))
                 goto out;
         /* The OOM killer does not needlessly kill tasks for lowmem */
         if (ac->highest_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.
          */
 
         /* Exhausted what can be done so it's blame time */
         if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
                 *did_some_progress = 1;
 
                 /*
                  * Help non-failing allocations by giving them access to memory
                  * reserves
                  */
                 if (gfp_mask & __GFP_NOFAIL)
                         page = __alloc_pages_cpuset_fallback(gfp_mask, order,
                                         ALLOC_NO_WATERMARKS, ac);
         }
 out:
         mutex_unlock(&oom_lock);
         return page;
 }
 
 /*
  * Maximum number of compaction retries with a progress before OOM
  * killer is consider as the only way to move forward.
  */
 #define MAX_COMPACT_RETRIES 16
 
 #ifdef CONFIG_COMPACTION
 /* Try memory compaction for high-order allocations before reclaim */
 static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
                 unsigned int alloc_flags, const struct alloc_context *ac,
                 enum compact_priority prio, enum compact_result *compact_result)
 {
         struct page *page = NULL;
         unsigned long pflags;
         unsigned int noreclaim_flag;
 
         if (!order)
                 return NULL;
 
         psi_memstall_enter(&pflags);
         noreclaim_flag = memalloc_noreclaim_save();
 
         *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
                                                                 prio, &page);
 
         memalloc_noreclaim_restore(noreclaim_flag);
         psi_memstall_leave(&pflags);
 
         if (*compact_result == COMPACT_SKIPPED)
                 return NULL;
         /*
          * At least in one zone compaction wasn't deferred or skipped, so let's
          * count a compaction stall
          */
         count_vm_event(COMPACTSTALL);
 
         /* Prep a captured page if available */
         if (page)
                 prep_new_page(page, order, gfp_mask, alloc_flags);
 
         /* Try get a page from the freelist if available */
         if (!page)
                 page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
 
         if (page) {
                 struct zone *zone = page_zone(page);
 
                 zone->compact_blockskip_flush = false;
                 compaction_defer_reset(zone, order, true);
                 count_vm_event(COMPACTSUCCESS);
                 return page;
         }
 
         /*
          * It's bad if compaction run occurs and fails. The most likely reason
          * is that pages exist, but not enough to satisfy watermarks.
          */
         count_vm_event(COMPACTFAIL);
 
         cond_resched();
 
         return NULL;
 }
 
 static inline bool
 should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
                      enum compact_result compact_result,
                      enum compact_priority *compact_priority,
                      int *compaction_retries)
 {
         int max_retries = MAX_COMPACT_RETRIES;
         int min_priority;
         bool ret = false;
         int retries = *compaction_retries;
         enum compact_priority priority = *compact_priority;
 
         if (!order)
                 return false;
 
         if (fatal_signal_pending(current))
                 return false;
 
         if (compaction_made_progress(compact_result))
                 (*compaction_retries)++;
 
         /*
          * compaction considers all the zone as desperately out of memory
          * so it doesn't really make much sense to retry except when the
          * failure could be caused by insufficient priority
          */
         if (compaction_failed(compact_result))
                 goto check_priority;
 
         /*
          * compaction was skipped because there are not enough order-0 pages
          * to work with, so we retry only if it looks like reclaim can help.
          */
         if (compaction_needs_reclaim(compact_result)) {
                 ret = compaction_zonelist_suitable(ac, order, alloc_flags);
                 goto out;
         }
 
         /*
          * make sure the compaction wasn't deferred or didn't bail out early
          * due to locks contention before we declare that we should give up.
          * But the next retry should use a higher priority if allowed, so
          * we don't just keep bailing out endlessly.
          */
         if (compaction_withdrawn(compact_result)) {
                 goto check_priority;
         }
 
         /*
          * !costly requests are much more important than __GFP_RETRY_MAYFAIL
          * costly ones because they are de facto nofail and invoke OOM
          * killer to move on while costly can fail and users are ready
          * to cope with that. 1/4 retries is rather arbitrary but we
          * would need much more detailed feedback from compaction to
          * make a better decision.
          */
         if (order > PAGE_ALLOC_COSTLY_ORDER)
                 max_retries /= 4;
         if (*compaction_retries <= max_retries) {
                 ret = true;
                 goto out;
         }
 
         /*
          * Make sure there are attempts at the highest priority if we exhausted
          * all retries or failed at the lower priorities.
          */
 check_priority:
         min_priority = (order > PAGE_ALLOC_COSTLY_ORDER) ?
                         MIN_COMPACT_COSTLY_PRIORITY : MIN_COMPACT_PRIORITY;
 
         if (*compact_priority > min_priority) {
                 (*compact_priority)--;
                 *compaction_retries = 0;
                 ret = true;
         }
 out:
         trace_compact_retry(order, priority, compact_result, retries, max_retries, ret);
         return ret;
 }
 #else
 static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
                 unsigned int alloc_flags, const struct alloc_context *ac,
                 enum compact_priority prio, enum compact_result *compact_result)
 {
         *compact_result = COMPACT_SKIPPED;
         return NULL;
 }
 
 static inline bool
 should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags,
                      enum compact_result compact_result,
                      enum compact_priority *compact_priority,
                      int *compaction_retries)
 {
         struct zone *zone;
         struct zoneref *z;
 
         if (!order || order > PAGE_ALLOC_COSTLY_ORDER)
                 return false;
 
         /*
          * There are setups with compaction disabled which would prefer to loop
          * inside the allocator rather than hit the oom killer prematurely.
          * Let's give them a good hope and keep retrying while the order-0
          * watermarks are OK.
          */
         for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
                                 ac->highest_zoneidx, ac->nodemask) {
                 if (zone_watermark_ok(zone, 0, min_wmark_pages(zone),
                                         ac->highest_zoneidx, alloc_flags))
                         return true;
         }
         return false;
 }
 #endif /* CONFIG_COMPACTION */
 
 #ifdef CONFIG_LOCKDEP
 static struct lockdep_map __fs_reclaim_map =
         STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
 
 static bool __need_reclaim(gfp_t gfp_mask)
 {
         /* no reclaim without waiting on it */
         if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
                 return false;
 
         /* this guy won't enter reclaim */
         if (current->flags & PF_MEMALLOC)
                 return false;
 
         if (gfp_mask & __GFP_NOLOCKDEP)
                 return false;
 
         return true;
 }
 
 void __fs_reclaim_acquire(unsigned long ip)
 {
         lock_acquire_exclusive(&__fs_reclaim_map, 0, 0, NULL, ip);
 }
 
 void __fs_reclaim_release(unsigned long ip)
 {
         lock_release(&__fs_reclaim_map, ip);
 }
 
 void fs_reclaim_acquire(gfp_t gfp_mask)
 {
         gfp_mask = current_gfp_context(gfp_mask);
 
         if (__need_reclaim(gfp_mask)) {
                 if (gfp_mask & __GFP_FS)
                         __fs_reclaim_acquire(_RET_IP_);
 
 #ifdef CONFIG_MMU_NOTIFIER
                 lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
                 lock_map_release(&__mmu_notifier_invalidate_range_start_map);
 #endif
 
         }
 }
 EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
 
 void fs_reclaim_release(gfp_t gfp_mask)
 {
         gfp_mask = current_gfp_context(gfp_mask);
 
         if (__need_reclaim(gfp_mask)) {
                 if (gfp_mask & __GFP_FS)
                         __fs_reclaim_release(_RET_IP_);
         }
 }
 EXPORT_SYMBOL_GPL(fs_reclaim_release);
 #endif
 
 /* Perform direct synchronous page reclaim */
 static unsigned long
 __perform_reclaim(gfp_t gfp_mask, unsigned int order,
                                         const struct alloc_context *ac)
 {
         unsigned int noreclaim_flag;
         unsigned long pflags, progress;
 
         cond_resched();
 
         /* We now go into synchronous reclaim */
         cpuset_memory_pressure_bump();
         psi_memstall_enter(&pflags);
         fs_reclaim_acquire(gfp_mask);
         noreclaim_flag = memalloc_noreclaim_save();
 
         progress = try_to_free_pages(ac->zonelist, order, gfp_mask,
                                                                 ac->nodemask);
 
         memalloc_noreclaim_restore(noreclaim_flag);
         fs_reclaim_release(gfp_mask);
         psi_memstall_leave(&pflags);
 
         cond_resched();
 
         return progress;
 }
 
 /* The really slow allocator path where we enter direct reclaim */
 static inline struct page *
 __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
                 unsigned int alloc_flags, const struct alloc_context *ac,
                 unsigned long *did_some_progress)
 {
         struct page *page = NULL;
         bool drained = false;
 
         *did_some_progress = __perform_reclaim(gfp_mask, order, ac);
         if (unlikely(!(*did_some_progress)))
                 return NULL;
 
 retry:
         page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
 
         /*
          * If an allocation failed after direct reclaim, it could be because
          * pages are pinned on the per-cpu lists or in high alloc reserves.
          * Shrink them and try again
          */
         if (!page && !drained) {
                 unreserve_highatomic_pageblock(ac, false);
                 drain_all_pages(NULL);
                 drained = true;
                 goto retry;
         }
 
         return page;
 }
 
 static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
                              const struct alloc_context *ac)
 {
         struct zoneref *z;
         struct zone *zone;
         pg_data_t *last_pgdat = NULL;
         enum zone_type highest_zoneidx = ac->highest_zoneidx;
 
         for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx,
                                         ac->nodemask) {
                 if (last_pgdat != zone->zone_pgdat)
                         wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx);
                 last_pgdat = zone->zone_pgdat;
         }
 }
 
 static inline unsigned int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
         unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
 
         /*
          * __GFP_HIGH is assumed to be the same as ALLOC_HIGH
          * and __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
          * to save two branches.
          */
         BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
         BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD);
 
         /*
          * The caller may dip into page reserves a bit more if the caller
          * cannot run direct reclaim, or if the caller has realtime scheduling
          * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
          * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH).
          */
         alloc_flags |= (__force int)
                 (gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM));
 
         if (gfp_mask & __GFP_ATOMIC) {
                 /*
                  * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
                  * if it can't schedule.
                  */
                 if (!(gfp_mask & __GFP_NOMEMALLOC))
                         alloc_flags |= ALLOC_HARDER;
                 /*
                  * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
                  * comment for __cpuset_node_allowed().
                  */
                 alloc_flags &= ~ALLOC_CPUSET;
         } else if (unlikely(rt_task(current)) && in_task())
                 alloc_flags |= ALLOC_HARDER;
 
         alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags);
 
         return alloc_flags;
 }
 
 static bool oom_reserves_allowed(struct task_struct *tsk)
 {
         if (!tsk_is_oom_victim(tsk))
                 return false;
 
         /*
          * !MMU doesn't have oom reaper so give access to memory reserves
          * only to the thread with TIF_MEMDIE set
          */
         if (!IS_ENABLED(CONFIG_MMU) && !test_thread_flag(TIF_MEMDIE))
                 return false;
 
         return true;
 }
 
 /*
  * Distinguish requests which really need access to full memory
  * reserves from oom victims which can live with a portion of it
  */
 static inline int __gfp_pfmemalloc_flags(gfp_t gfp_mask)
 {
         if (unlikely(gfp_mask & __GFP_NOMEMALLOC))
                 return 0;
         if (gfp_mask & __GFP_MEMALLOC)
                 return ALLOC_NO_WATERMARKS;
         if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
                 return ALLOC_NO_WATERMARKS;
         if (!in_interrupt()) {
                 if (current->flags & PF_MEMALLOC)
                         return ALLOC_NO_WATERMARKS;
                 else if (oom_reserves_allowed(current))
                         return ALLOC_OOM;
         }
 
         return 0;
 }
 
 bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
 {
         return !!__gfp_pfmemalloc_flags(gfp_mask);
 }
 
 /*
  * Checks whether it makes sense to retry the reclaim to make a forward progress
  * for the given allocation request.
  *
  * We give up when we either have tried MAX_RECLAIM_RETRIES in a row
  * without success, or when we couldn't even meet the watermark if we
  * reclaimed all remaining pages on the LRU lists.
  *
  * Returns true if a retry is viable or false to enter the oom path.
  */
 static inline bool
 should_reclaim_retry(gfp_t gfp_mask, unsigned order,
                      struct alloc_context *ac, int alloc_flags,
                      bool did_some_progress, int *no_progress_loops)
 {
         struct zone *zone;
         struct zoneref *z;
         bool ret = false;
 
         /*
          * Costly allocations might have made a progress but this doesn't mean
          * their order will become available due to high fragmentation so
          * always increment the no progress counter for them
          */
         if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER)
                 *no_progress_loops = 0;
         else
                 (*no_progress_loops)++;
 
         /*
          * Make sure we converge to OOM if we cannot make any progress
          * several times in the row.
          */
         if (*no_progress_loops > MAX_RECLAIM_RETRIES) {
                 /* Before OOM, exhaust highatomic_reserve */
                 return unreserve_highatomic_pageblock(ac, true);
         }
 
         /*
          * Keep reclaiming pages while there is a chance this will lead
          * somewhere.  If none of the target zones can satisfy our allocation
          * request even if all reclaimable pages are considered then we are
          * screwed and have to go OOM.
          */
         for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
                                 ac->highest_zoneidx, ac->nodemask) {
                 unsigned long available;
                 unsigned long reclaimable;
                 unsigned long min_wmark = min_wmark_pages(zone);
                 bool wmark;
 
                 available = reclaimable = zone_reclaimable_pages(zone);
                 available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
 
                 /*
                  * Would the allocation succeed if we reclaimed all
                  * reclaimable pages?
                  */
                 wmark = __zone_watermark_ok(zone, order, min_wmark,
                                 ac->highest_zoneidx, alloc_flags, available);
                 trace_reclaim_retry_zone(z, order, reclaimable,
                                 available, min_wmark, *no_progress_loops, wmark);
                 if (wmark) {
                         ret = true;
                         break;
                 }
         }
 
         /*
          * Memory allocation/reclaim might be called from a WQ context and the
          * current implementation of the WQ concurrency control doesn't
          * recognize that a particular WQ is congested if the worker thread is
          * looping without ever sleeping. Therefore we have to do a short sleep
          * here rather than calling cond_resched().
          */
         if (current->flags & PF_WQ_WORKER)
                 schedule_timeout_uninterruptible(1);
         else
                 cond_resched();
         return ret;
 }
 
 static inline bool
 check_retry_cpuset(int cpuset_mems_cookie, struct alloc_context *ac)
 {
         /*
          * It's possible that cpuset's mems_allowed and the nodemask from
          * mempolicy don't intersect. This should be normally dealt with by
          * policy_nodemask(), but it's possible to race with cpuset update in
          * such a way the check therein was true, and then it became false
          * before we got our cpuset_mems_cookie here.
          * This assumes that for all allocations, ac->nodemask can come only
          * from MPOL_BIND mempolicy (whose documented semantics is to be ignored
          * when it does not intersect with the cpuset restrictions) or the
          * caller can deal with a violated nodemask.
          */
         if (cpusets_enabled() && ac->nodemask &&
                         !cpuset_nodemask_valid_mems_allowed(ac->nodemask)) {
                 ac->nodemask = NULL;
                 return true;
         }
 
         /*
          * When updating a task's mems_allowed or mempolicy nodemask, it is
          * possible to race with parallel threads in such a way that our
          * allocation can fail while the mask is being updated. If we are about
          * to fail, check if the cpuset changed during allocation and if so,
          * retry.
          */
         if (read_mems_allowed_retry(cpuset_mems_cookie))
                 return true;
 
         return false;
 }
 
 static inline struct page *
 __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
                                                 struct alloc_context *ac)
 {
         bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
         const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
         struct page *page = NULL;
         unsigned int alloc_flags;
         unsigned long did_some_progress;
         enum compact_priority compact_priority;
         enum compact_result compact_result;
         int compaction_retries;
         int no_progress_loops;
         unsigned int cpuset_mems_cookie;
         int reserve_flags;
 
         /*
          * We also sanity check to catch abuse of atomic reserves being used by
          * callers that are not in atomic context.
          */
         if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) ==
                                 (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
                 gfp_mask &= ~__GFP_ATOMIC;
 
 retry_cpuset:
         compaction_retries = 0;
         no_progress_loops = 0;
         compact_priority = DEF_COMPACT_PRIORITY;
         cpuset_mems_cookie = read_mems_allowed_begin();
 
         /*
          * The fast path uses conservative alloc_flags to succeed only until
          * kswapd needs to be woken up, and to avoid the cost of setting up
          * alloc_flags precisely. So we do that now.
          */
         alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
         /*
          * We need to recalculate the starting point for the zonelist iterator
          * because we might have used different nodemask in the fast path, or
          * there was a cpuset modification and we are retrying - otherwise we
          * could end up iterating over non-eligible zones endlessly.
          */
         ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
                                         ac->highest_zoneidx, ac->nodemask);
         if (!ac->preferred_zoneref->zone)
                 goto nopage;
 
         /*
          * Check for insane configurations where the cpuset doesn't contain
          * any suitable zone to satisfy the request - e.g. non-movable
          * GFP_HIGHUSER allocations from MOVABLE nodes only.
          */
         if (cpusets_insane_config() && (gfp_mask & __GFP_HARDWALL)) {
                 struct zoneref *z = first_zones_zonelist(ac->zonelist,
                                         ac->highest_zoneidx,
                                         &cpuset_current_mems_allowed);
                 if (!z->zone)
                         goto nopage;
         }
 
         if (alloc_flags & ALLOC_KSWAPD)
                 wake_all_kswapds(order, gfp_mask, ac);
 
         /*
          * The adjusted alloc_flags might result in immediate success, so try
          * that first
          */
         page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
         if (page)
                 goto got_pg;
 
         /*
          * For costly allocations, try direct compaction first, as it's likely
          * that we have enough base pages and don't need to reclaim. For non-
          * movable high-order allocations, do that as well, as compaction will
          * try prevent permanent fragmentation by migrating from blocks of the
          * same migratetype.
          * Don't try this for allocations that are allowed to ignore
          * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen.
          */
         if (can_direct_reclaim &&
                         (costly_order ||
                            (order > 0 && ac->migratetype != MIGRATE_MOVABLE))
                         && !gfp_pfmemalloc_allowed(gfp_mask)) {
                 page = __alloc_pages_direct_compact(gfp_mask, order,
                                                 alloc_flags, ac,
                                                 INIT_COMPACT_PRIORITY,
                                                 &compact_result);
                 if (page)
                         goto got_pg;
 
                 /*
                  * Checks for costly allocations with __GFP_NORETRY, which
                  * includes some THP page fault allocations
                  */
                 if (costly_order && (gfp_mask & __GFP_NORETRY)) {
                         /*
                          * If allocating entire pageblock(s) and compaction
                          * failed because all zones are below low watermarks
                          * or is prohibited because it recently failed at this
                          * order, fail immediately unless the allocator has
                          * requested compaction and reclaim retry.
                          *
                          * Reclaim is
                          *  - potentially very expensive because zones are far
                          *    below their low watermarks or this is part of very
                          *    bursty high order allocations,
                          *  - not guaranteed to help because isolate_freepages()
                          *    may not iterate over freed pages as part of its
                          *    linear scan, and
                          *  - unlikely to make entire pageblocks free on its
                          *    own.
                          */
                         if (compact_result == COMPACT_SKIPPED ||
                             compact_result == COMPACT_DEFERRED)
                                 goto nopage;
 
                         /*
                          * Looks like reclaim/compaction is worth trying, but
                          * sync compaction could be very expensive, so keep
                          * using async compaction.
                          */
                         compact_priority = INIT_COMPACT_PRIORITY;
                 }
         }
 
 retry:
         /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
         if (alloc_flags & ALLOC_KSWAPD)
                 wake_all_kswapds(order, gfp_mask, ac);
 
         reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
         if (reserve_flags)
                 alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, reserve_flags);
 
         /*
          * Reset the nodemask and zonelist iterators if memory policies can be
          * ignored. These allocations are high priority and system rather than
          * user oriented.
          */
         if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
                 ac->nodemask = NULL;
                 ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
                                         ac->highest_zoneidx, ac->nodemask);
         }
 
         /* Attempt with potentially adjusted zonelist and alloc_flags */
         page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
         if (page)
                 goto got_pg;
 
         /* Caller is not willing to reclaim, we can't balance anything */
         if (!can_direct_reclaim)
                 goto nopage;
 
         /* Avoid recursion of direct reclaim */
         if (current->flags & PF_MEMALLOC)
                 goto nopage;
 
         /* Try direct reclaim and then allocating */
         page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
                                                         &did_some_progress);
         if (page)
                 goto got_pg;
 
         /* Try direct compaction and then allocating */
         page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac,
                                         compact_priority, &compact_result);
         if (page)
                 goto got_pg;
 
         /* Do not loop if specifically requested */
         if (gfp_mask & __GFP_NORETRY)
                 goto nopage;
 
         /*
          * Do not retry costly high order allocations unless they are
          * __GFP_RETRY_MAYFAIL
          */
         if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
                 goto nopage;
 
         if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
                                  did_some_progress > 0, &no_progress_loops))
                 goto retry;
 
         /*
          * It doesn't make any sense to retry for the compaction if the order-0
          * reclaim is not able to make any progress because the current
          * implementation of the compaction depends on the sufficient amount
          * of free memory (see __compaction_suitable)
          */
         if (did_some_progress > 0 &&
                         should_compact_retry(ac, order, alloc_flags,
                                 compact_result, &compact_priority,
                                 &compaction_retries))
                 goto retry;
 
 
         /* Deal with possible cpuset update races before we start OOM killing */
         if (check_retry_cpuset(cpuset_mems_cookie, ac))
                 goto retry_cpuset;
 
         /* Reclaim has failed us, start killing things */
         page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
         if (page)
                 goto got_pg;
 
         /* Avoid allocations with no watermarks from looping endlessly */
         if (tsk_is_oom_victim(current) &&
             (alloc_flags & ALLOC_OOM ||
              (gfp_mask & __GFP_NOMEMALLOC)))
                 goto nopage;
 
         /* Retry as long as the OOM killer is making progress */
         if (did_some_progress) {
                 no_progress_loops = 0;
                 goto retry;
         }
 
 nopage:
         /* Deal with possible cpuset update races before we fail */
         if (check_retry_cpuset(cpuset_mems_cookie, ac))
                 goto retry_cpuset;
 
         /*
          * Make sure that __GFP_NOFAIL request doesn't leak out and make sure
          * we always retry
          */
         if (gfp_mask & __GFP_NOFAIL) {
                 /*
                  * All existing users of the __GFP_NOFAIL are blockable, so warn
                  * of any new users that actually require GFP_NOWAIT
                  */
                 if (WARN_ON_ONCE(!can_direct_reclaim))
                         goto fail;
 
                 /*
                  * PF_MEMALLOC request from this context is rather bizarre
                  * because we cannot reclaim anything and only can loop waiting
                  * for somebody to do a work for us
                  */
                 WARN_ON_ONCE(current->flags & PF_MEMALLOC);
 
                 /*
                  * non failing costly orders are a hard requirement which we
                  * are not prepared for much so let's warn about these users
                  * so that we can identify them and convert them to something
                  * else.
                  */
                 WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER);
 
                 /*
                  * Help non-failing allocations by giving them access to memory
                  * reserves but do not use ALLOC_NO_WATERMARKS because this
                  * could deplete whole memory reserves which would just make
                  * the situation worse
                  */
                 page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
                 if (page)
                         goto got_pg;
 
                 cond_resched();
                 goto retry;
         }
 fail:
         warn_alloc(gfp_mask, ac->nodemask,
                         "page allocation failure: order:%u", order);
 got_pg:
         return page;
 }
 
 static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
                 int preferred_nid, nodemask_t *nodemask,
                 struct alloc_context *ac, gfp_t *alloc_gfp,
                 unsigned int *alloc_flags)
 {
         ac->highest_zoneidx = gfp_zone(gfp_mask);
         ac->zonelist = node_zonelist(preferred_nid, gfp_mask);
         ac->nodemask = nodemask;
         ac->migratetype = gfp_migratetype(gfp_mask);
 
         if (cpusets_enabled()) {
                 *alloc_gfp |= __GFP_HARDWALL;
                 /*
                  * When we are in the interrupt context, it is irrelevant
                  * to the current task context. It means that any node ok.
                  */
                 if (in_task() && !ac->nodemask)
                         ac->nodemask = &cpuset_current_mems_allowed;
                 else
                         *alloc_flags |= ALLOC_CPUSET;
         }
 
         fs_reclaim_acquire(gfp_mask);
         fs_reclaim_release(gfp_mask);
 
         might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
 
         if (should_fail_alloc_page(gfp_mask, order))
                 return false;
 
         *alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, *alloc_flags);
 
         /* Dirty zone balancing only done in the fast path */
         ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
         /*
          * The preferred zone is used for statistics but crucially it is
          * also used as the starting point for the zonelist iterator. It
          * may get reset for allocations that ignore memory policies.
          */
         ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
                                         ac->highest_zoneidx, ac->nodemask);
 
         return true;
 }
 
 /*
  * __alloc_pages_bulk - Allocate a number of order-0 pages to a list or array
  * @gfp: GFP flags for the allocation
  * @preferred_nid: The preferred NUMA node ID to allocate from
  * @nodemask: Set of nodes to allocate from, may be NULL
  * @nr_pages: The number of pages desired on the list or array
  * @page_list: Optional list to store the allocated pages
  * @page_array: Optional array to store the pages
  *
  * This is a batched version of the page allocator that attempts to
  * allocate nr_pages quickly. Pages are added to page_list if page_list
  * is not NULL, otherwise it is assumed that the page_array is valid.
  *
  * For lists, nr_pages is the number of pages that should be allocated.
  *
  * For arrays, only NULL elements are populated with pages and nr_pages
  * is the maximum number of pages that will be stored in the array.
  *
  * Returns the number of pages on the list or array.
  */
 unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
                         nodemask_t *nodemask, int nr_pages,
                         struct list_head *page_list,
                         struct page **page_array)
 {
         struct page *page;
         unsigned long flags;
         struct zone *zone;
         struct zoneref *z;
         struct per_cpu_pages *pcp;
         struct list_head *pcp_list;
         struct alloc_context ac;
         gfp_t alloc_gfp;
         unsigned int alloc_flags = ALLOC_WMARK_LOW;
         int nr_populated = 0, nr_account = 0;
 
         /*
          * Skip populated array elements to determine if any pages need
          * to be allocated before disabling IRQs.
          */
         while (page_array && nr_populated < nr_pages && page_array[nr_populated])
                 nr_populated++;
 
         /* No pages requested? */
         if (unlikely(nr_pages <= 0))
                 goto out;
 
         /* Already populated array? */
         if (unlikely(page_array && nr_pages - nr_populated == 0))
                 goto out;
 
         /* Bulk allocator does not support memcg accounting. */
         if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT))
                 goto failed;
 
         /* Use the single page allocator for one page. */
         if (nr_pages - nr_populated == 1)
                 goto failed;
 
 #ifdef CONFIG_PAGE_OWNER
         /*
          * PAGE_OWNER may recurse into the allocator to allocate space to
          * save the stack with pagesets.lock held. Releasing/reacquiring
          * removes much of the performance benefit of bulk allocation so
          * force the caller to allocate one page at a time as it'll have
          * similar performance to added complexity to the bulk allocator.
          */
         if (static_branch_unlikely(&page_owner_inited))
                 goto failed;
 #endif
 
         /* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
         gfp &= gfp_allowed_mask;
         alloc_gfp = gfp;
         if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags))
                 goto out;
         gfp = alloc_gfp;
 
         /* Find an allowed local zone that meets the low watermark. */
         for_each_zone_zonelist_nodemask(zone, z, ac.zonelist, ac.highest_zoneidx, ac.nodemask) {
                 unsigned long mark;
 
                 if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) &&
                     !__cpuset_zone_allowed(zone, gfp)) {
                         continue;
                 }
 
                 if (nr_online_nodes > 1 && zone != ac.preferred_zoneref->zone &&
                     zone_to_nid(zone) != zone_to_nid(ac.preferred_zoneref->zone)) {
                         goto failed;
                 }
 
                 mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages;
                 if (zone_watermark_fast(zone, 0,  mark,
                                 zonelist_zone_idx(ac.preferred_zoneref),
                                 alloc_flags, gfp)) {
                         break;
                 }
         }
 
         /*
          * If there are no allowed local zones that meets the watermarks then
          * try to allocate a single page and reclaim if necessary.
          */
         if (unlikely(!zone))
                 goto failed;
 
         /* Attempt the batch allocation */
         local_lock_irqsave(&pagesets.lock, flags);
         pcp = this_cpu_ptr(zone->per_cpu_pageset);
         pcp_list = &pcp->lists[order_to_pindex(ac.migratetype, 0)];
 
         while (nr_populated < nr_pages) {
 
                 /* Skip existing pages */
                 if (page_array && page_array[nr_populated]) {
                         nr_populated++;
                         continue;
                 }
 
                 page = __rmqueue_pcplist(zone, 0, ac.migratetype, alloc_flags,
                                                                 pcp, pcp_list);
                 if (unlikely(!page)) {
                         /* Try and get at least one page */
                         if (!nr_populated)
                                 goto failed_irq;
                         break;
                 }
                 nr_account++;
 
                 prep_new_page(page, 0, gfp, 0);
                 if (page_list)
                         list_add(&page->lru, page_list);
                 else
                         page_array[nr_populated] = page;
                 nr_populated++;
         }
 
         local_unlock_irqrestore(&pagesets.lock, flags);
 
         __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account);
         zone_statistics(ac.preferred_zoneref->zone, zone, nr_account);
 
 out:
         return nr_populated;
 
 failed_irq:
         local_unlock_irqrestore(&pagesets.lock, flags);
 
 failed:
         page = __alloc_pages(gfp, 0, preferred_nid, nodemask);
         if (page) {
                 if (page_list)
                         list_add(&page->lru, page_list);
                 else
                         page_array[nr_populated] = page;
                 nr_populated++;
         }
 
         goto out;
 }
 EXPORT_SYMBOL_GPL(__alloc_pages_bulk);
 
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */
 struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
                                                         nodemask_t *nodemask)
 {
         struct page *page;
         unsigned int alloc_flags = ALLOC_WMARK_LOW;
         gfp_t alloc_gfp; /* The gfp_t that was actually used for allocation */
         struct alloc_context ac = { };
 
         /*
          * There are several places where we assume that the order value is sane
          * so bail out early if the request is out of bound.
          */
         if (unlikely(order >= MAX_ORDER)) {
                 WARN_ON_ONCE(!(gfp & __GFP_NOWARN));
                 return NULL;
         }
 
         gfp &= gfp_allowed_mask;
         /*
          * Apply scoped allocation constraints. This is mainly about GFP_NOFS
          * resp. GFP_NOIO which has to be inherited for all allocation requests
          * from a particular context which has been marked by
          * memalloc_no{fs,io}_{save,restore}. And PF_MEMALLOC_PIN which ensures
          * movable zones are not used during allocation.
          */
         gfp = current_gfp_context(gfp);
         alloc_gfp = gfp;
         if (!prepare_alloc_pages(gfp, order, preferred_nid, nodemask, &ac,
                         &alloc_gfp, &alloc_flags))
                 return NULL;
 
         /*
          * Forbid the first pass from falling back to types that fragment
          * memory until all local zones are considered.
          */
         alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp);
 
         /* First allocation attempt */
         page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac);
         if (likely(page))
                 goto out;
 
         alloc_gfp = gfp;
         ac.spread_dirty_pages = false;
 
         /*
          * Restore the original nodemask if it was potentially replaced with
          * &cpuset_current_mems_allowed to optimize the fast-path attempt.
          */
         ac.nodemask = nodemask;
 
         page = __alloc_pages_slowpath(alloc_gfp, order, &ac);
 
 out:
         if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT) && page &&
             unlikely(__memcg_kmem_charge_page(page, gfp, order) != 0)) {
                 __free_pages(page, order);
                 page = NULL;
         }
 
         trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype);
 
         return page;
 }
 EXPORT_SYMBOL(__alloc_pages);
 
 struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
                 nodemask_t *nodemask)
 {
         struct page *page = __alloc_pages(gfp | __GFP_COMP, order,
                         preferred_nid, nodemask);
 
         if (page && order > 1)
                 prep_transhuge_page(page);
         return (struct folio *)page;
 }
 EXPORT_SYMBOL(__folio_alloc);
 
 /*
  * Common helper functions. Never use with __GFP_HIGHMEM because the returned
  * address cannot represent highmem pages. Use alloc_pages and then kmap if
  * you need to access high mem.
  */
 unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
 {
         struct page *page;
 
         page = alloc_pages(gfp_mask & ~__GFP_HIGHMEM, order);
         if (!page)
                 return 0;
         return (unsigned long) page_address(page);
 }
 EXPORT_SYMBOL(__get_free_pages);
 
 unsigned long get_zeroed_page(gfp_t gfp_mask)
 {
         return __get_free_pages(gfp_mask | __GFP_ZERO, 0);
 }
 EXPORT_SYMBOL(get_zeroed_page);
 
 /**
  * __free_pages - Free pages allocated with alloc_pages().
  * @page: The page pointer returned from alloc_pages().
  * @order: The order of the allocation.
  *
  * This function can free multi-page allocations that are not compound
  * pages.  It does not check that the @order passed in matches that of
  * the allocation, so it is easy to leak memory.  Freeing more memory
  * than was allocated will probably emit a warning.
  *
  * If the last reference to this page is speculative, it will be released
  * by put_page() which only frees the first page of a non-compound
  * allocation.  To prevent the remaining pages from being leaked, we free
  * the subsequent pages here.  If you want to use the page's reference
  * count to decide when to free the allocation, you should allocate a
  * compound page, and use put_page() instead of __free_pages().
  *
  * Context: May be called in interrupt context or while holding a normal
  * spinlock, but not in NMI context or while holding a raw spinlock.
  */
 void __free_pages(struct page *page, unsigned int order)
 {
         if (put_page_testzero(page))
                 free_the_page(page, order);
         else if (!PageHead(page))
                 while (order-- > 0)
                         free_the_page(page + (1 << order), order);
 }
 EXPORT_SYMBOL(__free_pages);
 
 void free_pages(unsigned long addr, unsigned int order)
 {
         if (addr != 0) {
                 VM_BUG_ON(!virt_addr_valid((void *)addr));
                 __free_pages(virt_to_page((void *)addr), order);
         }
 }
 
 EXPORT_SYMBOL(free_pages);
 
 /*
  * Page Fragment:
  *  An arbitrary-length arbitrary-offset area of memory which resides
  *  within a 0 or higher order page.  Multiple fragments within that page
  *  are individually refcounted, in the page's reference counter.
  *
  * The page_frag functions below provide a simple allocation framework for
  * page fragments.  This is used by the network stack and network device
  * drivers to provide a backing region of memory for use as either an
  * sk_buff->head, or to be used in the "frags" portion of skb_shared_info.
  */
 static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
                                              gfp_t gfp_mask)
 {
         struct page *page = NULL;
         gfp_t gfp = gfp_mask;
 
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
         gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
                     __GFP_NOMEMALLOC;
         page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
                                 PAGE_FRAG_CACHE_MAX_ORDER);
         nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
 #endif
         if (unlikely(!page))
                 page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
 
         nc->va = page ? page_address(page) : NULL;
 
         return page;
 }
 
 void __page_frag_cache_drain(struct page *page, unsigned int count)
 {
         VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
 
         if (page_ref_sub_and_test(page, count))
                 free_the_page(page, compound_order(page));
 }
 EXPORT_SYMBOL(__page_frag_cache_drain);
 
 void *page_frag_alloc_align(struct page_frag_cache *nc,
                       unsigned int fragsz, gfp_t gfp_mask,
                       unsigned int align_mask)
 {
         unsigned int size = PAGE_SIZE;
         struct page *page;
         int offset;
 
         if (unlikely(!nc->va)) {
 refill:
                 page = __page_frag_cache_refill(nc, gfp_mask);
                 if (!page)
                         return NULL;
 
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
                 /* if size can vary use size else just use PAGE_SIZE */
                 size = nc->size;
 #endif
                 /* Even if we own the page, we do not use atomic_set().
                  * This would break get_page_unless_zero() users.
                  */
                 page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
 
                 /* reset page count bias and offset to start of new frag */
                 nc->pfmemalloc = page_is_pfmemalloc(page);
                 nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
                 nc->offset = size;
         }
 
         offset = nc->offset - fragsz;
         if (unlikely(offset < 0)) {
                 page = virt_to_page(nc->va);
 
                 if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
                         goto refill;
 
                 if (unlikely(nc->pfmemalloc)) {
                         free_the_page(page, compound_order(page));
                         goto refill;
                 }
 
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
                 /* if size can vary use size else just use PAGE_SIZE */
                 size = nc->size;
 #endif
                 /* OK, page count is 0, we can safely set it */
                 set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
 
                 /* reset page count bias and offset to start of new frag */
                 nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
                 offset = size - fragsz;
         }
 
         nc->pagecnt_bias--;
         offset &= align_mask;
         nc->offset = offset;
 
         return nc->va + offset;
 }
 EXPORT_SYMBOL(page_frag_alloc_align);
 
 /*
  * Frees a page fragment allocated out of either a compound or order 0 page.
  */
 void page_frag_free(void *addr)
 {
         struct page *page = virt_to_head_page(addr);
 
         if (unlikely(put_page_testzero(page)))
                 free_the_page(page, compound_order(page));
 }
 EXPORT_SYMBOL(page_frag_free);
 
 static void *make_alloc_exact(unsigned long addr, unsigned int order,
                 size_t size)
 {
         if (addr) {
                 unsigned long alloc_end = addr + (PAGE_SIZE << order);
                 unsigned long used = addr + PAGE_ALIGN(size);
 
                 split_page(virt_to_page((void *)addr), order);
                 while (used < alloc_end) {
                         free_page(used);
                         used += PAGE_SIZE;
                 }
         }
         return (void *)addr;
 }
 
 /**
  * alloc_pages_exact - allocate an exact number physically-contiguous pages.
  * @size: the number of bytes to allocate
  * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP
  *
  * This function is similar to alloc_pages(), except that it allocates the
  * minimum number of pages to satisfy the request.  alloc_pages() can only
  * allocate memory in power-of-two pages.
  *
  * This function is also limited by MAX_ORDER.
  *
  * Memory allocated by this function must be released by free_pages_exact().
  *
  * Return: pointer to the allocated area or %NULL in case of error.
  */
 void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
 {
         unsigned int order = get_order(size);
         unsigned long addr;
 
         if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM)))
                 gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM);
 
         addr = __get_free_pages(gfp_mask, order);
         return make_alloc_exact(addr, order, size);
 }
 EXPORT_SYMBOL(alloc_pages_exact);
 
 /**
  * alloc_pages_exact_nid - allocate an exact number of physically-contiguous
  *                         pages on a node.
  * @nid: the preferred node ID where memory should be allocated
  * @size: the number of bytes to allocate
  * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP
  *
  * Like alloc_pages_exact(), but try to allocate on node nid first before falling
  * back.
  *
  * Return: pointer to the allocated area or %NULL in case of error.
  */
 void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
 {
         unsigned int order = get_order(size);
         struct page *p;
 
         if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM)))
                 gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM);
 
         p = alloc_pages_node(nid, gfp_mask, order);
         if (!p)
                 return NULL;
         return make_alloc_exact((unsigned long)page_address(p), order, size);
 }
 
 /**
  * free_pages_exact - release memory allocated via alloc_pages_exact()
  * @virt: the value returned by alloc_pages_exact.
  * @size: size of allocation, same value as passed to alloc_pages_exact().
  *
  * Release the memory allocated by a previous call to alloc_pages_exact.
  */
 void free_pages_exact(void *virt, size_t size)
 {
         unsigned long addr = (unsigned long)virt;
         unsigned long end = addr + PAGE_ALIGN(size);
 
         while (addr < end) {
                 free_page(addr);
                 addr += PAGE_SIZE;
         }
 }
 EXPORT_SYMBOL(free_pages_exact);
 
 /**
  * nr_free_zone_pages - count number of pages beyond high watermark
  * @offset: The zone index of the highest zone
  *
  * nr_free_zone_pages() counts the number of pages which are beyond the
  * high watermark within all zones at or below a given zone index.  For each
  * zone, the number of pages is calculated as:
  *
  *     nr_free_zone_pages = managed_pages - high_pages
  *
  * Return: number of pages beyond high watermark.
  */
 static unsigned long nr_free_zone_pages(int offset)
 {
         struct zoneref *z;
         struct zone *zone;
 
         /* Just pick one node, since fallback list is circular */
         unsigned long sum = 0;
 
         struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
 
         for_each_zone_zonelist(zone, z, zonelist, offset) {
                 unsigned long size = zone_managed_pages(zone);
                 unsigned long high = high_wmark_pages(zone);
                 if (size > high)
                         sum += size - high;
         }
 
         return sum;
 }
 
 /**
  * nr_free_buffer_pages - count number of pages beyond high watermark
  *
  * nr_free_buffer_pages() counts the number of pages which are beyond the high
  * watermark within ZONE_DMA and ZONE_NORMAL.
  *
  * Return: number of pages beyond high watermark within ZONE_DMA and
  * ZONE_NORMAL.
  */
 unsigned long nr_free_buffer_pages(void)
 {
         return nr_free_zone_pages(gfp_zone(GFP_USER));
 }
 EXPORT_SYMBOL_GPL(nr_free_buffer_pages);
 
 static inline void show_node(struct zone *zone)
 {
         if (IS_ENABLED(CONFIG_NUMA))
                 printk("Node %d ", zone_to_nid(zone));
 }
 
 long si_mem_available(void)
 {
         long available;
         unsigned long pagecache;
         unsigned long wmark_low = 0;
         unsigned long pages[NR_LRU_LISTS];
         unsigned long reclaimable;
         struct zone *zone;
         int lru;
 
         for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
                 pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
 
         for_each_zone(zone)
                 wmark_low += low_wmark_pages(zone);
 
         /*
          * Estimate the amount of memory available for userspace allocations,
          * without causing swapping.
          */
         available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages;
 
         /*
          * Not all the page cache can be freed, otherwise the system will
          * start swapping. Assume at least half of the page cache, or the
          * low watermark worth of cache, needs to stay.
          */
         pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
         pagecache -= min(pagecache / 2, wmark_low);
         available += pagecache;
 
         /*
          * Part of the reclaimable slab and other kernel memory consists of
          * items that are in use, and cannot be freed. Cap this estimate at the
          * low watermark.
          */
         reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) +
                 global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
         available += reclaimable - min(reclaimable / 2, wmark_low);
 
         if (available < 0)
                 available = 0;
         return available;
 }
 EXPORT_SYMBOL_GPL(si_mem_available);
 
 void si_meminfo(struct sysinfo *val)
 {
         val->totalram = totalram_pages();
         val->sharedram = global_node_page_state(NR_SHMEM);
         val->freeram = global_zone_page_state(NR_FREE_PAGES);
         val->bufferram = nr_blockdev_pages();
         val->totalhigh = totalhigh_pages();
         val->freehigh = nr_free_highpages();
         val->mem_unit = PAGE_SIZE;
 }
 
 EXPORT_SYMBOL(si_meminfo);
 
 #ifdef CONFIG_NUMA
 void si_meminfo_node(struct sysinfo *val, int nid)
 {
         int zone_type;          /* needs to be signed */
         unsigned long managed_pages = 0;
         unsigned long managed_highpages = 0;
         unsigned long free_highpages = 0;
         pg_data_t *pgdat = NODE_DATA(nid);
 
         for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
                 managed_pages += zone_managed_pages(&pgdat->node_zones[zone_type]);
         val->totalram = managed_pages;
         val->sharedram = node_page_state(pgdat, NR_SHMEM);
         val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES);
 #ifdef CONFIG_HIGHMEM
         for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
                 struct zone *zone = &pgdat->node_zones[zone_type];
 
                 if (is_highmem(zone)) {
                         managed_highpages += zone_managed_pages(zone);
                         free_highpages += zone_page_state(zone, NR_FREE_PAGES);
                 }
         }
         val->totalhigh = managed_highpages;
         val->freehigh = free_highpages;
 #else
         val->totalhigh = managed_highpages;
         val->freehigh = free_highpages;
 #endif
         val->mem_unit = PAGE_SIZE;
 }
 #endif
 
 /*
  * Determine whether the node should be displayed or not, depending on whether
  * SHOW_MEM_FILTER_NODES was passed to show_free_areas().
  */
 static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask)
 {
         if (!(flags & SHOW_MEM_FILTER_NODES))
                 return false;
 
         /*
          * no node mask - aka implicit memory numa policy. Do not bother with
          * the synchronization - read_mems_allowed_begin - because we do not
          * have to be precise here.
          */
         if (!nodemask)
                 nodemask = &cpuset_current_mems_allowed;
 
         return !node_isset(nid, *nodemask);
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
 
 static void show_migration_types(unsigned char type)
 {
         static const char types[MIGRATE_TYPES] = {
                 [MIGRATE_UNMOVABLE]     = 'U',
                 [MIGRATE_MOVABLE]       = 'M',
                 [MIGRATE_RECLAIMABLE]   = 'E',
                 [MIGRATE_HIGHATOMIC]    = 'H',
 #ifdef CONFIG_CMA
                 [MIGRATE_CMA]           = 'C',
 #endif
 #ifdef CONFIG_MEMORY_ISOLATION
                 [MIGRATE_ISOLATE]       = 'I',
 #endif
         };
         char tmp[MIGRATE_TYPES + 1];
         char *p = tmp;
         int i;
 
         for (i = 0; i < MIGRATE_TYPES; i++) {
                 if (type & (1 << i))
                         *p++ = types[i];
         }
 
         *p = '\0';
         printk(KERN_CONT "(%s) ", tmp);
 }
 
 /*
  * Show free area list (used inside shift_scroll-lock stuff)
  * We also calculate the percentage fragmentation. We do this by counting the
  * memory on each free list with the exception of the first item on the list.
  *
  * Bits in @filter:
  * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's
  *   cpuset.
  */
 void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 {
         unsigned long free_pcp = 0;
         int cpu;
         struct zone *zone;
         pg_data_t *pgdat;
 
         for_each_populated_zone(zone) {
                 if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
                         continue;
 
                 for_each_online_cpu(cpu)
                         free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count;
         }
 
         printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
                 " active_file:%lu inactive_file:%lu isolated_file:%lu\n"
                 " unevictable:%lu dirty:%lu writeback:%lu\n"
                 " slab_reclaimable:%lu slab_unreclaimable:%lu\n"
                 " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
                 " kernel_misc_reclaimable:%lu\n"
                 " free:%lu free_pcp:%lu free_cma:%lu\n",
                 global_node_page_state(NR_ACTIVE_ANON),
                 global_node_page_state(NR_INACTIVE_ANON),
                 global_node_page_state(NR_ISOLATED_ANON),
                 global_node_page_state(NR_ACTIVE_FILE),
                 global_node_page_state(NR_INACTIVE_FILE),
                 global_node_page_state(NR_ISOLATED_FILE),
                 global_node_page_state(NR_UNEVICTABLE),
                 global_node_page_state(NR_FILE_DIRTY),
                 global_node_page_state(NR_WRITEBACK),
                 global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B),
                 global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B),
                 global_node_page_state(NR_FILE_MAPPED),
                 global_node_page_state(NR_SHMEM),
                 global_node_page_state(NR_PAGETABLE),
                 global_zone_page_state(NR_BOUNCE),
                 global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE),
                 global_zone_page_state(NR_FREE_PAGES),
                 free_pcp,
                 global_zone_page_state(NR_FREE_CMA_PAGES));
 
         for_each_online_pgdat(pgdat) {
                 if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
                         continue;
 
                 printk("Node %d"
                         " active_anon:%lukB"
                         " inactive_anon:%lukB"
                         " active_file:%lukB"
                         " inactive_file:%lukB"
                         " unevictable:%lukB"
                         " isolated(anon):%lukB"
                         " isolated(file):%lukB"
                         " mapped:%lukB"
                         " dirty:%lukB"
                         " writeback:%lukB"
                         " shmem:%lukB"
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
                         " shmem_thp: %lukB"
                         " shmem_pmdmapped: %lukB"
                         " anon_thp: %lukB"
 #endif
                         " writeback_tmp:%lukB"
                         " kernel_stack:%lukB"
 #ifdef CONFIG_SHADOW_CALL_STACK
                         " shadow_call_stack:%lukB"
 #endif
                         " pagetables:%lukB"
                         " all_unreclaimable? %s"
                         "\n",
                         pgdat->node_id,
                         K(node_page_state(pgdat, NR_ACTIVE_ANON)),
                         K(node_page_state(pgdat, NR_INACTIVE_ANON)),
                         K(node_page_state(pgdat, NR_ACTIVE_FILE)),
                         K(node_page_state(pgdat, NR_INACTIVE_FILE)),
                         K(node_page_state(pgdat, NR_UNEVICTABLE)),
                         K(node_page_state(pgdat, NR_ISOLATED_ANON)),
                         K(node_page_state(pgdat, NR_ISOLATED_FILE)),
                         K(node_page_state(pgdat, NR_FILE_MAPPED)),
                         K(node_page_state(pgdat, NR_FILE_DIRTY)),
                         K(node_page_state(pgdat, NR_WRITEBACK)),
                         K(node_page_state(pgdat, NR_SHMEM)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
                         K(node_page_state(pgdat, NR_SHMEM_THPS)),
                         K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)),
                         K(node_page_state(pgdat, NR_ANON_THPS)),
 #endif
                         K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
                         node_page_state(pgdat, NR_KERNEL_STACK_KB),
 #ifdef CONFIG_SHADOW_CALL_STACK
                         node_page_state(pgdat, NR_KERNEL_SCS_KB),
 #endif
                         K(node_page_state(pgdat, NR_PAGETABLE)),
                         pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
                                 "yes" : "no");
         }
 
         for_each_populated_zone(zone) {
                 int i;
 
                 if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
                         continue;
 
                 free_pcp = 0;
                 for_each_online_cpu(cpu)
                         free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count;
 
                 show_node(zone);
                 printk(KERN_CONT
                         "%s"
                         " free:%lukB"
                         " boost:%lukB"
                         " min:%lukB"
                         " low:%lukB"
                         " high:%lukB"
                         " reserved_highatomic:%luKB"
                         " active_anon:%lukB"
                         " inactive_anon:%lukB"
                         " active_file:%lukB"
                         " inactive_file:%lukB"
                         " unevictable:%lukB"
                         " writepending:%lukB"
                         " present:%lukB"
                         " managed:%lukB"
                         " mlocked:%lukB"
                         " bounce:%lukB"
                         " free_pcp:%lukB"
                         " local_pcp:%ukB"
                         " free_cma:%lukB"
                         "\n",
                         zone->name,
                         K(zone_page_state(zone, NR_FREE_PAGES)),
                         K(zone->watermark_boost),
                         K(min_wmark_pages(zone)),
                         K(low_wmark_pages(zone)),
                         K(high_wmark_pages(zone)),
                         K(zone->nr_reserved_highatomic),
                         K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)),
                         K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)),
                         K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)),
                         K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)),
                         K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)),
                         K(zone_page_state(zone, NR_ZONE_WRITE_PENDING)),
                         K(zone->present_pages),
                         K(zone_managed_pages(zone)),
                         K(zone_page_state(zone, NR_MLOCK)),
                         K(zone_page_state(zone, NR_BOUNCE)),
                         K(free_pcp),
                         K(this_cpu_read(zone->per_cpu_pageset->count)),
                         K(zone_page_state(zone, NR_FREE_CMA_PAGES)));
                 printk("lowmem_reserve[]:");
                 for (i = 0; i < MAX_NR_ZONES; i++)
                         printk(KERN_CONT " %ld", zone->lowmem_reserve[i]);
                 printk(KERN_CONT "\n");
         }
 
         for_each_populated_zone(zone) {
                 unsigned int order;
                 unsigned long nr[MAX_ORDER], flags, total = 0;
                 unsigned char types[MAX_ORDER];
 
                 if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
                         continue;
                 show_node(zone);
                 printk(KERN_CONT "%s: ", zone->name);
 
                 spin_lock_irqsave(&zone->lock, flags);
                 for (order = 0; order < MAX_ORDER; order++) {
                         struct free_area *area = &zone->free_area[order];
                         int type;
 
                         nr[order] = area->nr_free;
                         total += nr[order] << order;
 
                         types[order] = 0;
                         for (type = 0; type < MIGRATE_TYPES; type++) {
                                 if (!free_area_empty(area, type))
                                         types[order] |= 1 << type;
                         }
                 }
                 spin_unlock_irqrestore(&zone->lock, flags);
                 for (order = 0; order < MAX_ORDER; order++) {
                         printk(KERN_CONT "%lu*%lukB ",
                                nr[order], K(1UL) << order);
                         if (nr[order])
                                 show_migration_types(types[order]);
                 }
                 printk(KERN_CONT "= %lukB\n", K(total));
         }
 
         hugetlb_show_meminfo();
 
         printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES));
 
         show_swap_cache_info();
 }
 
 static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
 {
         zoneref->zone = zone;
         zoneref->zone_idx = zone_idx(zone);
 }
 
 /*
  * Builds allocation fallback zone lists.
  *
  * Add all populated zones of a node to the zonelist.
  */
 static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs)
 {
         struct zone *zone;
         enum zone_type zone_type = MAX_NR_ZONES;
         int nr_zones = 0;
 
         do {
                 zone_type--;
                 zone = pgdat->node_zones + zone_type;
                 if (managed_zone(zone)) {
                         zoneref_set_zone(zone, &zonerefs[nr_zones++]);
                         check_highest_zone(zone_type);
                 }
         } while (zone_type);
 
         return nr_zones;
 }
 
 #ifdef CONFIG_NUMA
 
 static int __parse_numa_zonelist_order(char *s)
 {
         /*
          * We used to support different zonelists modes but they turned
          * out to be just not useful. Let's keep the warning in place
          * if somebody still use the cmd line parameter so that we do
          * not fail it silently
          */
         if (!(*s == 'd' || *s == 'D' || *s == 'n' || *s == 'N')) {
                 pr_warn("Ignoring unsupported numa_zonelist_order value:  %s\n", s);
                 return -EINVAL;
         }
         return 0;
 }
 
 char numa_zonelist_order[] = "Node";
 
 /*
  * sysctl handler for numa_zonelist_order
  */
 int numa_zonelist_order_handler(struct ctl_table *table, int write,
                 void *buffer, size_t *length, loff_t *ppos)
 {
         if (write)
                 return __parse_numa_zonelist_order(buffer);
         return proc_dostring(table, write, buffer, length, ppos);
 }
 
 
 #define MAX_NODE_LOAD (nr_online_nodes)
 static int node_load[MAX_NUMNODES];
 
 /**
  * find_next_best_node - find the next node that should appear in a given node's fallback list
  * @node: node whose fallback list we're appending
  * @used_node_mask: nodemask_t of already used nodes
  *
  * We use a number of factors to determine which is the next node that should
  * appear on a given node's fallback list.  The node should not have appeared
  * already in @node's fallback list, and it should be the next closest node
  * according to the distance array (which contains arbitrary distance values
  * from each node to each node in the system), and should also prefer nodes
  * with no CPUs, since presumably they'll have very little allocation pressure
  * on them otherwise.
  *
  * Return: node id of the found node or %NUMA_NO_NODE if no node is found.
  */
 int find_next_best_node(int node, nodemask_t *used_node_mask)
 {
         int n, val;
         int min_val = INT_MAX;
         int best_node = NUMA_NO_NODE;
 
         /* Use the local node if we haven't already */
         if (!node_isset(node, *used_node_mask)) {
                 node_set(node, *used_node_mask);
                 return node;
         }
 
         for_each_node_state(n, N_MEMORY) {
 
                 /* Don't want a node to appear more than once */
                 if (node_isset(n, *used_node_mask))
                         continue;
 
                 /* Use the distance array to find the distance */
                 val = node_distance(node, n);
 
                 /* Penalize nodes under us ("prefer the next node") */
                 val += (n < node);
 
                 /* Give preference to headless and unused nodes */
                 if (!cpumask_empty(cpumask_of_node(n)))
                         val += PENALTY_FOR_NODE_WITH_CPUS;
 
                 /* Slight preference for less loaded node */
                 val *= (MAX_NODE_LOAD*MAX_NUMNODES);
                 val += node_load[n];
 
                 if (val < min_val) {
                         min_val = val;
                         best_node = n;
                 }
         }
 
         if (best_node >= 0)
                 node_set(best_node, *used_node_mask);
 
         return best_node;
 }
 
 
 /*
  * Build zonelists ordered by node and zones within node.
  * This results in maximum locality--normal zone overflows into local
  * DMA zone, if any--but risks exhausting DMA zone.
  */
 static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order,
                 unsigned nr_nodes)
 {
         struct zoneref *zonerefs;
         int i;
 
         zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
 
         for (i = 0; i < nr_nodes; i++) {
                 int nr_zones;
 
                 pg_data_t *node = NODE_DATA(node_order[i]);
 
                 nr_zones = build_zonerefs_node(node, zonerefs);
                 zonerefs += nr_zones;
         }
         zonerefs->zone = NULL;
         zonerefs->zone_idx = 0;
 }
 
 /*
  * Build gfp_thisnode zonelists
  */
 static void build_thisnode_zonelists(pg_data_t *pgdat)
 {
         struct zoneref *zonerefs;
         int nr_zones;
 
         zonerefs = pgdat->node_zonelists[ZONELIST_NOFALLBACK]._zonerefs;
         nr_zones = build_zonerefs_node(pgdat, zonerefs);
         zonerefs += nr_zones;
         zonerefs->zone = NULL;
         zonerefs->zone_idx = 0;
 }
 
 /*
  * Build zonelists ordered by zone and nodes within zones.
  * This results in conserving DMA zone[s] until all Normal memory is
  * exhausted, but results in overflowing to remote node while memory
  * may still exist in local DMA zone.
  */
 
 static void build_zonelists(pg_data_t *pgdat)
 {
         static int node_order[MAX_NUMNODES];
         int node, load, nr_nodes = 0;
         nodemask_t used_mask = NODE_MASK_NONE;
         int local_node, prev_node;
 
         /* NUMA-aware ordering of nodes */
         local_node = pgdat->node_id;
         load = nr_online_nodes;
         prev_node = local_node;
 
         memset(node_order, 0, sizeof(node_order));
         while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
                 /*
                  * We don't want to pressure a particular node.
                  * So adding penalty to the first node in same
                  * distance group to make it round-robin.
                  */
                 if (node_distance(local_node, node) !=
                     node_distance(local_node, prev_node))
                         node_load[node] += load;
 
                 node_order[nr_nodes++] = node;
                 prev_node = node;
                 load--;
         }
 
         build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
         build_thisnode_zonelists(pgdat);
         pr_info("Fallback order for Node %d: ", local_node);
         for (node = 0; node < nr_nodes; node++)
                 pr_cont("%d ", node_order[node]);
         pr_cont("\n");
 }
 
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
 /*
  * Return node id of node used for "local" allocations.
  * I.e., first node id of first zone in arg node's generic zonelist.
  * Used for initializing percpu 'numa_mem', which is used primarily
  * for kernel allocations, so use GFP_KERNEL flags to locate zonelist.
  */
 int local_memory_node(int node)
 {
         struct zoneref *z;
 
         z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
                                    gfp_zone(GFP_KERNEL),
                                    NULL);
         return zone_to_nid(z->zone);
 }
 #endif
 
 static void setup_min_unmapped_ratio(void);
 static void setup_min_slab_ratio(void);
 #else   /* CONFIG_NUMA */
 
 static void build_zonelists(pg_data_t *pgdat)
 {
         int node, local_node;
         struct zoneref *zonerefs;
         int nr_zones;
 
         local_node = pgdat->node_id;
 
         zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
         nr_zones = build_zonerefs_node(pgdat, zonerefs);
         zonerefs += nr_zones;
 
         /*
          * Now we build the zonelist so that it contains the zones
          * of all the other nodes.
          * We don't want to pressure a particular node, so when
          * building the zones for node N, we make sure that the
          * zones coming right after the local ones are those from
          * node N+1 (modulo N)
          */
         for (node = local_node + 1; node < MAX_NUMNODES; node++) {
                 if (!node_online(node))
                         continue;
                 nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
                 zonerefs += nr_zones;
         }
         for (node = 0; node < local_node; node++) {
                 if (!node_online(node))
                         continue;
                 nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
                 zonerefs += nr_zones;
         }
 
         zonerefs->zone = NULL;
         zonerefs->zone_idx = 0;
 }
 
 #endif  /* CONFIG_NUMA */
 
 /*
  * Boot pageset table. One per cpu which is going to be used for all
  * zones and all nodes. The parameters will be set in such a way
  * that an item put on a list will immediately be handed over to
  * the buddy list. This is safe since pageset manipulation is done
  * with interrupts disabled.
  *
  * The boot_pagesets must be kept even after bootup is complete for
  * unused processors and/or zones. They do play a role for bootstrapping
  * hotplugged processors.
  *
  * zoneinfo_show() and maybe other functions do
  * not check if the processor is online before following the pageset pointer.
  * Other parts of the kernel may not check if the zone is available.
  */
 static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats);
 /* These effectively disable the pcplists in the boot pageset completely */
 #define BOOT_PAGESET_HIGH       0
 #define BOOT_PAGESET_BATCH      1
 static DEFINE_PER_CPU(struct per_cpu_pages, boot_pageset);
 static DEFINE_PER_CPU(struct per_cpu_zonestat, boot_zonestats);
 static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);
 
 static void __build_all_zonelists(void *data)
 {
         int nid;
         int __maybe_unused cpu;
         pg_data_t *self = data;
         static DEFINE_SPINLOCK(lock);
 
         spin_lock(&lock);
 
 #ifdef CONFIG_NUMA
         memset(node_load, 0, sizeof(node_load));
 #endif
 
         /*
          * This node is hotadded and no memory is yet present.   So just
          * building zonelists is fine - no need to touch other nodes.
          */
         if (self && !node_online(self->node_id)) {
                 build_zonelists(self);
         } else {
                 for_each_online_node(nid) {
                         pg_data_t *pgdat = NODE_DATA(nid);
 
                         build_zonelists(pgdat);
                 }
 
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
                 /*
                  * We now know the "local memory node" for each node--
                  * i.e., the node of the first zone in the generic zonelist.
                  * Set up numa_mem percpu variable for on-line cpus.  During
                  * boot, only the boot cpu should be on-line;  we'll init the
                  * secondary cpus' numa_mem as they come on-line.  During
                  * node/memory hotplug, we'll fixup all on-line cpus.
                  */
                 for_each_online_cpu(cpu)
                         set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
 #endif
         }
 
         spin_unlock(&am