mmzone.h

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MMZONE_H
#define _LINUX_MMZONE_H

#ifndef __ASSEMBLY__
#ifndef __GENERATING_BOUNDS_H

#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/bitops.h>
#include <linux/cache.h>
#include <linux/threads.h>
#include <linux/numa.h>
#include <linux/init.h>
#include <linux/seqlock.h>
#include <linux/nodemask.h>
#include <linux/pageblock-flags.h>
#include <linux/page-flags-layout.h>
#include <linux/atomic.h>
#include <asm/page.h>

/* Free memory management - zoned buddy allocator.  */
#ifndef CONFIG_FORCE_MAX_ZONEORDER
#define MAX_ORDER 11
#else
#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER
#endif
#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1))

/*
 * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
 * costly to service.  That is between allocation orders which should
 * coalesce naturally under reasonable reclaim pressure and those which
 * will not.
 */
#define PAGE_ALLOC_COSTLY_ORDER 3

enum migratetype {
	MIGRATE_UNMOVABLE,
	MIGRATE_MOVABLE,
	MIGRATE_RECLAIMABLE,
	MIGRATE_PCPTYPES,	/* the number of types on the pcp lists */
	MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES,
#ifdef CONFIG_CMA
	/*
	 * MIGRATE_CMA migration type is designed to mimic the way
	 * ZONE_MOVABLE works.  Only movable pages can be allocated
	 * from MIGRATE_CMA pageblocks and page allocator never
	 * implicitly change migration type of MIGRATE_CMA pageblock.
	 *
	 * The way to use it is to change migratetype of a range of
	 * pageblocks to MIGRATE_CMA which can be done by
	 * __free_pageblock_cma() function.  What is important though
	 * is that a range of pageblocks must be aligned to
	 * MAX_ORDER_NR_PAGES should biggest page be bigger then
	 * a single pageblock.
	 */
	MIGRATE_CMA,
#endif
#ifdef CONFIG_MEMORY_ISOLATION
	MIGRATE_ISOLATE,	/* can't allocate from here */
#endif
	MIGRATE_TYPES
};

/* In mm/page_alloc.c; keep in sync also with show_migration_types() there */
extern const char * const migratetype_names[MIGRATE_TYPES];

#ifdef CONFIG_CMA
#  define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
#  define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA)
#else
#  define is_migrate_cma(migratetype) false
#  define is_migrate_cma_page(_page) false
#endif

static inline bool is_migrate_movable(int mt)
{
	return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE;
}

#define for_each_migratetype_order(order, type) \
	for (order = 0; order < MAX_ORDER; order++) \
		for (type = 0; type < MIGRATE_TYPES; type++)

extern int page_group_by_mobility_disabled;

#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1)
#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1)

#define get_pageblock_migratetype(page)					\
	get_pfnblock_flags_mask(page, page_to_pfn(page),		\
			PB_migrate_end, MIGRATETYPE_MASK)

struct free_area {
	struct list_head	free_list[MIGRATE_TYPES];
	unsigned long		nr_free;
};

struct pglist_data;

/*
 * zone->lock and the zone lru_lock are two of the hottest locks in the kernel.
 * So add a wild amount of padding here to ensure that they fall into separate
 * cachelines.  There are very few zone structures in the machine, so space
 * consumption is not a concern here.
 */
#if defined(CONFIG_SMP)
struct zone_padding {
	char x[0];
} ____cacheline_internodealigned_in_smp;
#define ZONE_PADDING(name)	struct zone_padding name;
#else
#define ZONE_PADDING(name)
#endif

#ifdef CONFIG_NUMA
enum numa_stat_item {
	NUMA_HIT,		/* allocated in intended node */
	NUMA_MISS,		/* allocated in non intended node */
	NUMA_FOREIGN,		/* was intended here, hit elsewhere */
	NUMA_INTERLEAVE_HIT,	/* interleaver preferred this zone */
	NUMA_LOCAL,		/* allocation from local node */
	NUMA_OTHER,		/* allocation from other node */
	NR_VM_NUMA_STAT_ITEMS
};
#else
#define NR_VM_NUMA_STAT_ITEMS 0
#endif

enum zone_stat_item {
	/* First 128 byte cacheline (assuming 64 bit words) */
	NR_FREE_PAGES,
	NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
	NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE,
	NR_ZONE_ACTIVE_ANON,
	NR_ZONE_INACTIVE_FILE,
	NR_ZONE_ACTIVE_FILE,
	NR_ZONE_UNEVICTABLE,
	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
	NR_PAGETABLE,		/* used for pagetables */
	NR_KERNEL_STACK_KB,	/* measured in KiB */
	/* Second 128 byte cacheline */
	NR_BOUNCE,
#if IS_ENABLED(CONFIG_ZSMALLOC)
	NR_ZSPAGES,		/* allocated in zsmalloc */
#endif
	NR_FREE_CMA_PAGES,
	NR_VM_ZONE_STAT_ITEMS };

enum node_stat_item {
	NR_LRU_BASE,
	NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
	NR_SLAB_RECLAIMABLE,
	NR_SLAB_UNRECLAIMABLE,
	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
	WORKINGSET_NODES,
	WORKINGSET_REFAULT,
	WORKINGSET_ACTIVATE,
	WORKINGSET_RESTORE,
	WORKINGSET_NODERECLAIM,
	NR_ANON_MAPPED,	/* Mapped anonymous pages */
	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
			   only modified from process context */
	NR_FILE_PAGES,
	NR_FILE_DIRTY,
	NR_WRITEBACK,
	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
	NR_SHMEM_THPS,
	NR_SHMEM_PMDMAPPED,
	NR_ANON_THPS,
	NR_UNSTABLE_NFS,	/* NFS unstable pages */
	NR_VMSCAN_WRITE,
	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
	NR_DIRTIED,		/* page dirtyings since bootup */
	NR_WRITTEN,		/* page writings since bootup */
	NR_KERNEL_MISC_RECLAIMABLE,	/* reclaimable non-slab kernel pages */
	NR_VM_NODE_STAT_ITEMS
};

/*
 * We do arithmetic on the LRU lists in various places in the code,
 * so it is important to keep the active lists LRU_ACTIVE higher in
 * the array than the corresponding inactive lists, and to keep
 * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists.
 *
 * This has to be kept in sync with the statistics in zone_stat_item
 * above and the descriptions in vmstat_text in mm/vmstat.c
 */
#define LRU_BASE 0
#define LRU_ACTIVE 1
#define LRU_FILE 2

enum lru_list {
	LRU_INACTIVE_ANON = LRU_BASE,
	LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE,
	LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE,
	LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE,
	LRU_UNEVICTABLE,
	NR_LRU_LISTS
};

#define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++)

#define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++)

static inline int is_file_lru(enum lru_list lru)
{
	return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE);
}

static inline int is_active_lru(enum lru_list lru)
{
	return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
}

struct zone_reclaim_stat {
	/*
	 * The pageout code in vmscan.c keeps track of how many of the
	 * mem/swap backed and file backed pages are referenced.
	 * The higher the rotated/scanned ratio, the more valuable
	 * that cache is.
	 *
	 * The anon LRU stats live in [0], file LRU stats in [1]
	 */
	unsigned long		recent_rotated[2];
	unsigned long		recent_scanned[2];
};

struct lruvec {
	struct list_head		lists[NR_LRU_LISTS];
	struct zone_reclaim_stat	reclaim_stat;
	/* Evictions & activations on the inactive file list */
	atomic_long_t			inactive_age;
	/* Refaults at the time of last reclaim cycle */
	unsigned long			refaults;
#ifdef CONFIG_MEMCG
	struct pglist_data *pgdat;
#endif
};

/* Mask used at gathering information at once (see memcontrol.c) */
#define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE))
#define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON))
#define LRU_ALL	     ((1 << NR_LRU_LISTS) - 1)

/* Isolate unmapped file */
#define ISOLATE_UNMAPPED	((__force isolate_mode_t)0x2)
/* Isolate for asynchronous migration */
#define ISOLATE_ASYNC_MIGRATE	((__force isolate_mode_t)0x4)
/* Isolate unevictable pages */
#define ISOLATE_UNEVICTABLE	((__force isolate_mode_t)0x8)

/* LRU Isolation modes. */
typedef unsigned __bitwise isolate_mode_t;

enum zone_watermarks {
	WMARK_MIN,
	WMARK_LOW,
	WMARK_HIGH,
	NR_WMARK
};

#define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost)
#define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost)
#define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost)
#define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost)

struct per_cpu_pages {
	int count;		/* number of pages in the list */
	int high;		/* high watermark, emptying needed */
	int batch;		/* chunk size for buddy add/remove */

	/* Lists of pages, one per migrate type stored on the pcp-lists */
	struct list_head lists[MIGRATE_PCPTYPES];
};

struct per_cpu_pageset {
	struct per_cpu_pages pcp;
#ifdef CONFIG_NUMA
	s8 expire;
	u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS];
#endif
#ifdef CONFIG_SMP
	s8 stat_threshold;
	s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
#endif
};

struct per_cpu_nodestat {
	s8 stat_threshold;
	s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
};

#endif /* !__GENERATING_BOUNDS.H */

enum zone_type {
#ifdef CONFIG_ZONE_DMA
	/*
	 * ZONE_DMA is used when there are devices that are not able
	 * to do DMA to all of addressable memory (ZONE_NORMAL). Then we
	 * carve out the portion of memory that is needed for these devices.
	 * The range is arch specific.
	 *
	 * Some examples
	 *
	 * Architecture		Limit
	 * ---------------------------
	 * parisc, ia64, sparc	<4G
	 * s390, powerpc	<2G
	 * arm			Various
	 * alpha		Unlimited or 0-16MB.
	 *
	 * i386, x86_64 and multiple other arches
	 * 			<16M.
	 */
	ZONE_DMA,
#endif
#ifdef CONFIG_ZONE_DMA32
	/*
	 * x86_64 needs two ZONE_DMAs because it supports devices that are
	 * only able to do DMA to the lower 16M but also 32 bit devices that
	 * can only do DMA areas below 4G.
	 */
	ZONE_DMA32,
#endif
	/*
	 * Normal addressable memory is in ZONE_NORMAL. DMA operations can be
	 * performed on pages in ZONE_NORMAL if the DMA devices support
	 * transfers to all addressable memory.
	 */
	ZONE_NORMAL,
#ifdef CONFIG_HIGHMEM
	/*
	 * A memory area that is only addressable by the kernel through
	 * mapping portions into its own address space. This is for example
	 * used by i386 to allow the kernel to address the memory beyond
	 * 900MB. The kernel will set up special mappings (page
	 * table entries on i386) for each page that the kernel needs to
	 * access.
	 */
	ZONE_HIGHMEM,
#endif
	ZONE_MOVABLE,
#ifdef CONFIG_ZONE_DEVICE
	ZONE_DEVICE,
#endif
	__MAX_NR_ZONES

};

#ifndef __GENERATING_BOUNDS_H

struct zone {
	/* Read-mostly fields */

	/* zone watermarks, access with *_wmark_pages(zone) macros */
	unsigned long _watermark[NR_WMARK];
	unsigned long watermark_boost;

	unsigned long nr_reserved_highatomic;

	/*
	 * We don't know if the memory that we're going to allocate will be
	 * freeable or/and it will be released eventually, so to avoid totally
	 * wasting several GB of ram we must reserve some of the lower zone
	 * memory (otherwise we risk to run OOM on the lower zones despite
	 * there being tons of freeable ram on the higher zones).  This array is
	 * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl
	 * changes.
	 */
	long lowmem_reserve[MAX_NR_ZONES];

#ifdef CONFIG_NUMA
	int node;
#endif
	struct pglist_data	*zone_pgdat;
	struct per_cpu_pageset __percpu *pageset;

#ifndef CONFIG_SPARSEMEM
	/*
	 * Flags for a pageblock_nr_pages block. See pageblock-flags.h.
	 * In SPARSEMEM, this map is stored in struct mem_section
	 */
	unsigned long		*pageblock_flags;
#endif /* CONFIG_SPARSEMEM */

	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
	unsigned long		zone_start_pfn;

	/*
	 * spanned_pages is the total pages spanned by the zone, including
	 * holes, which is calculated as:
	 * 	spanned_pages = zone_end_pfn - zone_start_pfn;
	 *
	 * present_pages is physical pages existing within the zone, which
	 * is calculated as:
	 *	present_pages = spanned_pages - absent_pages(pages in holes);
	 *
	 * managed_pages is present pages managed by the buddy system, which
	 * is calculated as (reserved_pages includes pages allocated by the
	 * bootmem allocator):
	 *	managed_pages = present_pages - reserved_pages;
	 *
	 * So present_pages may be used by memory hotplug or memory power
	 * management logic to figure out unmanaged pages by checking
	 * (present_pages - managed_pages). And managed_pages should be used
	 * by page allocator and vm scanner to calculate all kinds of watermarks
	 * and thresholds.
	 *
	 * Locking rules:
	 *
	 * zone_start_pfn and spanned_pages are protected by span_seqlock.
	 * It is a seqlock because it has to be read outside of zone->lock,
	 * and it is done in the main allocator path.  But, it is written
	 * quite infrequently.
	 *
	 * The span_seq lock is declared along with zone->lock because it is
	 * frequently read in proximity to zone->lock.  It's good to
	 * give them a chance of being in the same cacheline.
	 *
	 * Write access to present_pages at runtime should be protected by
	 * mem_hotplug_begin/end(). Any reader who can't tolerant drift of
	 * present_pages should get_online_mems() to get a stable value.
	 */
	atomic_long_t		managed_pages;
	unsigned long		spanned_pages;
	unsigned long		present_pages;

	const char		*name;

#ifdef CONFIG_MEMORY_ISOLATION
	/*
	 * Number of isolated pageblock. It is used to solve incorrect
	 * freepage counting problem due to racy retrieving migratetype
	 * of pageblock. Protected by zone->lock.
	 */
	unsigned long		nr_isolate_pageblock;
#endif

#ifdef CONFIG_MEMORY_HOTPLUG
	/* see spanned/present_pages for more description */
	seqlock_t		span_seqlock;
#endif

	int initialized;

	/* Write-intensive fields used from the page allocator */
	ZONE_PADDING(_pad1_)

	/* free areas of different sizes */
	struct free_area	free_area[MAX_ORDER];

	/* zone flags, see below */
	unsigned long		flags;

	/* Primarily protects free_area */
	spinlock_t		lock;

	/* Write-intensive fields used by compaction and vmstats. */
	ZONE_PADDING(_pad2_)

	/*
	 * When free pages are below this point, additional steps are taken
	 * when reading the number of free pages to avoid per-cpu counter
	 * drift allowing watermarks to be breached
	 */
	unsigned long percpu_drift_mark;

#if defined CONFIG_COMPACTION || defined CONFIG_CMA
	/* pfn where compaction free scanner should start */
	unsigned long		compact_cached_free_pfn;
	/* pfn where async and sync compaction migration scanner should start */
	unsigned long		compact_cached_migrate_pfn[2];
	unsigned long		compact_init_migrate_pfn;
	unsigned long		compact_init_free_pfn;
#endif

#ifdef CONFIG_COMPACTION
	/*
	 * On compaction failure, 1<<compact_defer_shift compactions
	 * are skipped before trying again. The number attempted since
	 * last failure is tracked with compact_considered.
	 */
	unsigned int		compact_considered;
	unsigned int		compact_defer_shift;
	int			compact_order_failed;
#endif

#if defined CONFIG_COMPACTION || defined CONFIG_CMA
	/* Set to true when the PG_migrate_skip bits should be cleared */
	bool			compact_blockskip_flush;
#endif

	bool			contiguous;

	ZONE_PADDING(_pad3_)
	/* Zone statistics */
	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
	atomic_long_t		vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;

enum pgdat_flags {
	PGDAT_CONGESTED,		/* pgdat has many dirty pages backed by
					 * a congested BDI
					 */
	PGDAT_DIRTY,			/* reclaim scanning has recently found
					 * many dirty file pages at the tail
					 * of the LRU.
					 */
	PGDAT_WRITEBACK,		/* reclaim scanning has recently found
					 * many pages under writeback
					 */
	PGDAT_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
};

enum zone_flags {
	ZONE_BOOSTED_WATERMARK,		/* zone recently boosted watermarks.
					 * Cleared when kswapd is woken.
					 */
};

static inline unsigned long zone_managed_pages(struct zone *zone)
{
	return (unsigned long)atomic_long_read(&zone->managed_pages);
}

static inline unsigned long zone_end_pfn(const struct zone *zone)
{
	return zone->zone_start_pfn + zone->spanned_pages;
}

static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn)
{
	return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone);
}

static inline bool zone_is_initialized(struct zone *zone)
{
	return zone->initialized;
}

static inline bool zone_is_empty(struct zone *zone)
{
	return zone->spanned_pages == 0;
}

/*
 * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty
 * intersection with the given zone
 */
static inline bool zone_intersects(struct zone *zone,
		unsigned long start_pfn, unsigned long nr_pages)
{
	if (zone_is_empty(zone))
		return false;
	if (start_pfn >= zone_end_pfn(zone) ||
	    start_pfn + nr_pages <= zone->zone_start_pfn)
		return false;

	return true;
}

/*
 * The "priority" of VM scanning is how much of the queues we will scan in one
 * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the
 * queues ("queue_length >> 12") during an aging round.
 */
#define DEF_PRIORITY 12

/* Maximum number of zones on a zonelist */
#define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES)

enum {
	ZONELIST_FALLBACK,	/* zonelist with fallback */
#ifdef CONFIG_NUMA
	/*
	 * The NUMA zonelists are doubled because we need zonelists that
	 * restrict the allocations to a single node for __GFP_THISNODE.
	 */
	ZONELIST_NOFALLBACK,	/* zonelist without fallback (__GFP_THISNODE) */
#endif
	MAX_ZONELISTS
};

/*
 * This struct contains information about a zone in a zonelist. It is stored
 * here to avoid dereferences into large structures and lookups of tables
 */
struct zoneref {
	struct zone *zone;	/* Pointer to actual zone */
	int zone_idx;		/* zone_idx(zoneref->zone) */
};

/*
 * One allocation request operates on a zonelist. A zonelist
 * is a list of zones, the first one is the 'goal' of the
 * allocation, the other zones are fallback zones, in decreasing
 * priority.
 *
 * To speed the reading of the zonelist, the zonerefs contain the zone index
 * of the entry being read. Helper functions to access information given
 * a struct zoneref are
 *
 * zonelist_zone()	- Return the struct zone * for an entry in _zonerefs
 * zonelist_zone_idx()	- Return the index of the zone for an entry
 * zonelist_node_idx()	- Return the index of the node for an entry
 */
struct zonelist {
	struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1];
};

#ifndef CONFIG_DISCONTIGMEM
/* The array of struct pages - for discontigmem use pgdat->lmem_map */
extern struct page *mem_map;
#endif

/*
 * On NUMA machines, each NUMA node would have a pg_data_t to describe
 * it's memory layout. On UMA machines there is a single pglist_data which
 * describes the whole memory.
 *
 * Memory statistics and page replacement data structures are maintained on a
 * per-zone basis.
 */
struct bootmem_data;
typedef struct pglist_data {
	struct zone node_zones[MAX_NR_ZONES];
	struct zonelist node_zonelists[MAX_ZONELISTS];
	int nr_zones;
#ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
	struct page *node_mem_map;
#ifdef CONFIG_PAGE_EXTENSION
	struct page_ext *node_page_ext;
#endif
#endif
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
	/*
	 * Must be held any time you expect node_start_pfn,
	 * node_present_pages, node_spanned_pages or nr_zones to stay constant.
	 *
	 * pgdat_resize_lock() and pgdat_resize_unlock() are provided to
	 * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
	 * or CONFIG_DEFERRED_STRUCT_PAGE_INIT.
	 *
	 * Nests above zone->lock and zone->span_seqlock
	 */
	spinlock_t node_size_lock;
#endif
	unsigned long node_start_pfn;
	unsigned long node_present_pages; /* total number of physical pages */
	unsigned long node_spanned_pages; /* total size of physical page
					     range, including holes */
	int node_id;
	wait_queue_head_t kswapd_wait;
	wait_queue_head_t pfmemalloc_wait;
	struct task_struct *kswapd;	/* Protected by
					   mem_hotplug_begin/end() */
	int kswapd_order;
	enum zone_type kswapd_classzone_idx;

	int kswapd_failures;		/* Number of 'reclaimed == 0' runs */

#ifdef CONFIG_COMPACTION
	int kcompactd_max_order;
	enum zone_type kcompactd_classzone_idx;
	wait_queue_head_t kcompactd_wait;
	struct task_struct *kcompactd;
#endif
	/*
	 * This is a per-node reserve of pages that are not available
	 * to userspace allocations.
	 */
	unsigned long		totalreserve_pages;

#ifdef CONFIG_NUMA
	/*
	 * zone reclaim becomes active if more unmapped pages exist.
	 */
	unsigned long		min_unmapped_pages;
	unsigned long		min_slab_pages;
#endif /* CONFIG_NUMA */

	/* Write-intensive fields used by page reclaim */
	ZONE_PADDING(_pad1_)
	spinlock_t		lru_lock;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
	/*
	 * If memory initialisation on large machines is deferred then this
	 * is the first PFN that needs to be initialised.
	 */
	unsigned long first_deferred_pfn;
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	spinlock_t split_queue_lock;
	struct list_head split_queue;
	unsigned long split_queue_len;
#endif

	/* Fields commonly accessed by the page reclaim scanner */
	struct lruvec		lruvec;

	unsigned long		flags;

	ZONE_PADDING(_pad2_)

	/* Per-node vmstats */
	struct per_cpu_nodestat __percpu *per_cpu_nodestats;
	atomic_long_t		vm_stat[NR_VM_NODE_STAT_ITEMS];
} pg_data_t;

#define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
#define node_spanned_pages(nid)	(NODE_DATA(nid)->node_spanned_pages)
#ifdef CONFIG_FLAT_NODE_MEM_MAP
#define pgdat_page_nr(pgdat, pagenr)	((pgdat)->node_mem_map + (pagenr))
#else
#define pgdat_page_nr(pgdat, pagenr)	pfn_to_page((pgdat)->node_start_pfn + (pagenr))
#endif
#define nid_page_nr(nid, pagenr) 	pgdat_page_nr(NODE_DATA(nid),(pagenr))

#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
#define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
static inline spinlock_t *zone_lru_lock(struct zone *zone)
{
	return &zone->zone_pgdat->lru_lock;
}

static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
{
	return &pgdat->lruvec;
}

static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
{
	return pgdat->node_start_pfn + pgdat->node_spanned_pages;
}

static inline bool pgdat_is_empty(pg_data_t *pgdat)
{
	return !pgdat->node_start_pfn && !pgdat->node_spanned_pages;
}

#include <linux/memory_hotplug.h>

void build_all_zonelists(pg_data_t *pgdat);
void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order,
		   enum zone_type classzone_idx);
bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
			 int classzone_idx, unsigned int alloc_flags,
			 long free_pages);
bool zone_watermark_ok(struct zone *z, unsigned int order,
		unsigned long mark, int classzone_idx,
		unsigned int alloc_flags);
bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
		unsigned long mark, int classzone_idx);
enum memmap_context {
	MEMMAP_EARLY,
	MEMMAP_HOTPLUG,
};
extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
				     unsigned long size);

extern void lruvec_init(struct lruvec *lruvec);

static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
{
#ifdef CONFIG_MEMCG
	return lruvec->pgdat;
#else
	return container_of(lruvec, struct pglist_data, lruvec);
#endif
}

extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx);

#ifdef CONFIG_HAVE_MEMORY_PRESENT
void memory_present(int nid, unsigned long start, unsigned long end);
#else
static inline void memory_present(int nid, unsigned long start, unsigned long end) {}
#endif

#if defined(CONFIG_SPARSEMEM)
void memblocks_present(void);
#else
static inline void memblocks_present(void) {}
#endif

#ifdef CONFIG_HAVE_MEMORYLESS_NODES
int local_memory_node(int node_id);
#else
static inline int local_memory_node(int node_id) { return node_id; };
#endif

/*
 * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc.
 */
#define zone_idx(zone)		((zone) - (zone)->zone_pgdat->node_zones)

#ifdef CONFIG_ZONE_DEVICE
static inline bool is_dev_zone(const struct zone *zone)
{
	return zone_idx(zone) == ZONE_DEVICE;
}
#else
static inline bool is_dev_zone(const struct zone *zone)
{
	return false;
}
#endif

/*
 * Returns true if a zone has pages managed by the buddy allocator.
 * All the reclaim decisions have to use this function rather than
 * populated_zone(). If the whole zone is reserved then we can easily
 * end up with populated_zone() && !managed_zone().
 */
static inline bool managed_zone(struct zone *zone)
{
	return zone_managed_pages(zone);
}

/* Returns true if a zone has memory */
static inline bool populated_zone(struct zone *zone)
{
	return zone->present_pages;
}

#ifdef CONFIG_NUMA
static inline int zone_to_nid(struct zone *zone)
{
	return zone->node;
}

static inline void zone_set_nid(struct zone *zone, int nid)
{
	zone->node = nid;
}
#else
static inline int zone_to_nid(struct zone *zone)
{
	return 0;
}

static inline void zone_set_nid(struct zone *zone, int nid) {}
#endif

extern int movable_zone;

#ifdef CONFIG_HIGHMEM
static inline int zone_movable_is_highmem(void)
{
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
	return movable_zone == ZONE_HIGHMEM;
#else
	return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM;
#endif
}
#endif

static inline int is_highmem_idx(enum zone_type idx)
{
#ifdef CONFIG_HIGHMEM
	return (idx == ZONE_HIGHMEM ||
		(idx == ZONE_MOVABLE && zone_movable_is_highmem()));
#else
	return 0;
#endif
}

/**
 * is_highmem - helper function to quickly check if a struct zone is a
 *              highmem zone or not.  This is an attempt to keep references
 *              to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum.
 * @zone - pointer to struct zone variable
 */
static inline int is_highmem(struct zone *zone)
{
#ifdef CONFIG_HIGHMEM
	return is_highmem_idx(zone_idx(zone));
#else
	return 0;
#endif
}

/* These two functions are used to setup the per zone pages min values */
struct ctl_table;
int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
					void __user *, size_t *, loff_t *);
int watermark_boost_factor_sysctl_handler(struct ctl_table *, int,
					void __user *, size_t *, loff_t *);
int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
					void __user *, size_t *, loff_t *);
extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
					void __user *, size_t *, loff_t *);
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,
					void __user *, size_t *, loff_t *);
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
			void __user *, size_t *, loff_t *);
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
			void __user *, size_t *, loff_t *);

extern int numa_zonelist_order_handler(struct ctl_table *, int,
			void __user *, size_t *, loff_t *);
extern char numa_zonelist_order[];
#define NUMA_ZONELIST_ORDER_LEN	16

#ifndef CONFIG_NEED_MULTIPLE_NODES

extern struct pglist_data contig_page_data;
#define NODE_DATA(nid)		(&contig_page_data)
#define NODE_MEM_MAP(nid)	mem_map

#else /* CONFIG_NEED_MULTIPLE_NODES */

#include <asm/mmzone.h>

#endif /* !CONFIG_NEED_MULTIPLE_NODES */

extern struct pglist_data *first_online_pgdat(void);
extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat);
extern struct zone *next_zone(struct zone *zone);

/**
 * for_each_online_pgdat - helper macro to iterate over all online nodes
 * @pgdat - pointer to a pg_data_t variable
 */
#define for_each_online_pgdat(pgdat)			\
	for (pgdat = first_online_pgdat();		\
	     pgdat;					\
	     pgdat = next_online_pgdat(pgdat))
/**
 * for_each_zone - helper macro to iterate over all memory zones
 * @zone - pointer to struct zone variable
 *
 * The user only needs to declare the zone variable, for_each_zone
 * fills it in.
 */
#define for_each_zone(zone)			        \
	for (zone = (first_online_pgdat())->node_zones; \
	     zone;					\
	     zone = next_zone(zone))

#define for_each_populated_zone(zone)		        \
	for (zone = (first_online_pgdat())->node_zones; \
	     zone;					\
	     zone = next_zone(zone))			\
		if (!populated_zone(zone))		\
			; /* do nothing */		\
		else

static inline struct zone *zonelist_zone(struct zoneref *zoneref)
{
	return zoneref->zone;
}

static inline int zonelist_zone_idx(struct zoneref *zoneref)
{
	return zoneref->zone_idx;
}

static inline int zonelist_node_idx(struct zoneref *zoneref)
{
	return zone_to_nid(zoneref->zone);
}

struct zoneref *__next_zones_zonelist(struct zoneref *z,
					enum zone_type highest_zoneidx,
					nodemask_t *nodes);

/**
 * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point
 * @z - The cursor used as a starting point for the search
 * @highest_zoneidx - The zone index of the highest zone to return
 * @nodes - An optional nodemask to filter the zonelist with
 *
 * This function returns the next zone at or below a given zone index that is
 * within the allowed nodemask using a cursor as the starting point for the
 * search. The zoneref returned is a cursor that represents the current zone
 * being examined. It should be advanced by one before calling
 * next_zones_zonelist again.
 */
static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z,
					enum zone_type highest_zoneidx,
					nodemask_t *nodes)
{
	if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx))
		return z;
	return __next_zones_zonelist(z, highest_zoneidx, nodes);
}