change zonelist order: zonelist order selection logic

[mirror_ubuntu-bionic-kernel.git] / include / linux / mmzone.h

#ifndef _LINUX_MMZONE_H
#define _LINUX_MMZONE_H

#ifdef __KERNEL__
#ifndef __ASSEMBLY__

#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/wait.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 <asm/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))

struct free_area {
        struct list_head        free_list;
        unsigned long           nr_free;
};

struct pglist_data;

/*
 * zone->lock and 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

enum zone_stat_item {
        /* First 128 byte cacheline (assuming 64 bit words) */
        NR_FREE_PAGES,
        NR_INACTIVE,
        NR_ACTIVE,
        NR_ANON_PAGES,  /* Mapped anonymous pages */
        NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
                           only modified from process context */
        NR_FILE_PAGES,
        NR_FILE_DIRTY,
        NR_WRITEBACK,
        /* Second 128 byte cacheline */
        NR_SLAB_RECLAIMABLE,
        NR_SLAB_UNRECLAIMABLE,
        NR_PAGETABLE,           /* used for pagetables */
        NR_UNSTABLE_NFS,        /* NFS unstable pages */
        NR_BOUNCE,
        NR_VMSCAN_WRITE,
#ifdef CONFIG_NUMA
        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 */
#endif
        NR_VM_ZONE_STAT_ITEMS };

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 */
        struct list_head list;  /* the list of pages */
};

struct per_cpu_pageset {
        struct per_cpu_pages pcp[2];    /* 0: hot.  1: cold */
#ifdef CONFIG_NUMA
        s8 expire;
#endif
#ifdef CONFIG_SMP
        s8 stat_threshold;
        s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
#endif
} ____cacheline_aligned_in_smp;

#ifdef CONFIG_NUMA
#define zone_pcp(__z, __cpu) ((__z)->pageset[(__cpu)])
#else
#define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
#endif

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                 <2G
         * arm26                <48M
         * 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
        MAX_NR_ZONES
};

/*
 * When a memory allocation must conform to specific limitations (such
 * as being suitable for DMA) the caller will pass in hints to the
 * allocator in the gfp_mask, in the zone modifier bits.  These bits
 * are used to select a priority ordered list of memory zones which
 * match the requested limits. See gfp_zone() in include/linux/gfp.h
 */

/*
 * Count the active zones.  Note that the use of defined(X) outside
 * #if and family is not necessarily defined so ensure we cannot use
 * it later.  Use __ZONE_COUNT to work out how many shift bits we need.
 */
#define __ZONE_COUNT (                  \
          defined(CONFIG_ZONE_DMA)      \
        + defined(CONFIG_ZONE_DMA32)    \
        + 1                             \
        + defined(CONFIG_HIGHMEM)       \
)
#if __ZONE_COUNT < 2
#define ZONES_SHIFT 0
#elif __ZONE_COUNT <= 2
#define ZONES_SHIFT 1
#elif __ZONE_COUNT <= 4
#define ZONES_SHIFT 2
#else
#error ZONES_SHIFT -- too many zones configured adjust calculation
#endif
#undef __ZONE_COUNT

struct zone {
        /* Fields commonly accessed by the page allocator */
        unsigned long           pages_min, pages_low, pages_high;
        /*
         * 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's tons of freeable ram
         * on the higher zones). This array is recalculated at runtime if the
         * sysctl_lowmem_reserve_ratio sysctl changes.
         */
        unsigned long           lowmem_reserve[MAX_NR_ZONES];

#ifdef CONFIG_NUMA
        int node;
        /*
         * zone reclaim becomes active if more unmapped pages exist.
         */
        unsigned long           min_unmapped_pages;
        unsigned long           min_slab_pages;
        struct per_cpu_pageset  *pageset[NR_CPUS];
#else
        struct per_cpu_pageset  pageset[NR_CPUS];
#endif
        /*
         * free areas of different sizes
         */
        spinlock_t              lock;
#ifdef CONFIG_MEMORY_HOTPLUG
        /* see spanned/present_pages for more description */
        seqlock_t               span_seqlock;
#endif
        struct free_area        free_area[MAX_ORDER];


        ZONE_PADDING(_pad1_)

        /* Fields commonly accessed by the page reclaim scanner */
        spinlock_t              lru_lock;       
        struct list_head        active_list;
        struct list_head        inactive_list;
        unsigned long           nr_scan_active;
        unsigned long           nr_scan_inactive;
        unsigned long           pages_scanned;     /* since last reclaim */
        int                     all_unreclaimable; /* All pages pinned */

        /* A count of how many reclaimers are scanning this zone */
        atomic_t                reclaim_in_progress;

        /* Zone statistics */
        atomic_long_t           vm_stat[NR_VM_ZONE_STAT_ITEMS];

        /*
         * prev_priority holds the scanning priority for this zone.  It is
         * defined as the scanning priority at which we achieved our reclaim
         * target at the previous try_to_free_pages() or balance_pgdat()
         * invokation.
         *
         * We use prev_priority as a measure of how much stress page reclaim is
         * under - it drives the swappiness decision: whether to unmap mapped
         * pages.
         *
         * Access to both this field is quite racy even on uniprocessor.  But
         * it is expected to average out OK.
         */
        int prev_priority;


        ZONE_PADDING(_pad2_)
        /* Rarely used or read-mostly fields */

        /*
         * wait_table           -- the array holding the hash table
         * wait_table_hash_nr_entries   -- the size of the hash table array
         * wait_table_bits      -- wait_table_size == (1 << wait_table_bits)
         *
         * The purpose of all these is to keep track of the people
         * waiting for a page to become available and make them
         * runnable again when possible. The trouble is that this
         * consumes a lot of space, especially when so few things
         * wait on pages at a given time. So instead of using
         * per-page waitqueues, we use a waitqueue hash table.
         *
         * The bucket discipline is to sleep on the same queue when
         * colliding and wake all in that wait queue when removing.
         * When something wakes, it must check to be sure its page is
         * truly available, a la thundering herd. The cost of a
         * collision is great, but given the expected load of the
         * table, they should be so rare as to be outweighed by the
         * benefits from the saved space.
         *
         * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
         * primary users of these fields, and in mm/page_alloc.c
         * free_area_init_core() performs the initialization of them.
         */
        wait_queue_head_t       * wait_table;
        unsigned long           wait_table_hash_nr_entries;
        unsigned long           wait_table_bits;

        /*
         * Discontig memory support fields.
         */
        struct pglist_data      *zone_pgdat;
        /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
        unsigned long           zone_start_pfn;

        /*
         * zone_start_pfn, spanned_pages and present_pages are all
         * 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 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.
         */
        unsigned long           spanned_pages;  /* total size, including holes */
        unsigned long           present_pages;  /* amount of memory (excluding holes) */

        /*
         * rarely used fields:
         */
        const char              *name;
} ____cacheline_internodealigned_in_smp;

/*
 * 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)

#ifdef CONFIG_NUMA
/*
 * We cache key information from each zonelist for smaller cache
 * footprint when scanning for free pages in get_page_from_freelist().
 *
 * 1) The BITMAP fullzones tracks which zones in a zonelist have come
 *    up short of free memory since the last time (last_fullzone_zap)
 *    we zero'd fullzones.
 * 2) The array z_to_n[] maps each zone in the zonelist to its node
 *    id, so that we can efficiently evaluate whether that node is
 *    set in the current tasks mems_allowed.
 *
 * Both fullzones and z_to_n[] are one-to-one with the zonelist,
 * indexed by a zones offset in the zonelist zones[] array.
 *
 * The get_page_from_freelist() routine does two scans.  During the
 * first scan, we skip zones whose corresponding bit in 'fullzones'
 * is set or whose corresponding node in current->mems_allowed (which
 * comes from cpusets) is not set.  During the second scan, we bypass
 * this zonelist_cache, to ensure we look methodically at each zone.
 *
 * Once per second, we zero out (zap) fullzones, forcing us to
 * reconsider nodes that might have regained more free memory.
 * The field last_full_zap is the time we last zapped fullzones.
 *
 * This mechanism reduces the amount of time we waste repeatedly
 * reexaming zones for free memory when they just came up low on
 * memory momentarilly ago.
 *
 * The zonelist_cache struct members logically belong in struct
 * zonelist.  However, the mempolicy zonelists constructed for
 * MPOL_BIND are intentionally variable length (and usually much
 * shorter).  A general purpose mechanism for handling structs with
 * multiple variable length members is more mechanism than we want
 * here.  We resort to some special case hackery instead.
 *
 * The MPOL_BIND zonelists don't need this zonelist_cache (in good
 * part because they are shorter), so we put the fixed length stuff
 * at the front of the zonelist struct, ending in a variable length
 * zones[], as is needed by MPOL_BIND.
 *
 * Then we put the optional zonelist cache on the end of the zonelist
 * struct.  This optional stuff is found by a 'zlcache_ptr' pointer in
 * the fixed length portion at the front of the struct.  This pointer
 * both enables us to find the zonelist cache, and in the case of
 * MPOL_BIND zonelists, (which will just set the zlcache_ptr to NULL)
 * to know that the zonelist cache is not there.
 *
 * The end result is that struct zonelists come in two flavors:
 *  1) The full, fixed length version, shown below, and
 *  2) The custom zonelists for MPOL_BIND.
 * The custom MPOL_BIND zonelists have a NULL zlcache_ptr and no zlcache.
 *
 * Even though there may be multiple CPU cores on a node modifying
 * fullzones or last_full_zap in the same zonelist_cache at the same
 * time, we don't lock it.  This is just hint data - if it is wrong now
 * and then, the allocator will still function, perhaps a bit slower.
 */


struct zonelist_cache {
        unsigned short z_to_n[MAX_ZONES_PER_ZONELIST];          /* zone->nid */
        DECLARE_BITMAP(fullzones, MAX_ZONES_PER_ZONELIST);      /* zone full? */
        unsigned long last_full_zap;            /* when last zap'd (jiffies) */
};
#else
struct zonelist_cache;
#endif

/*
 * 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.
 *
 * If zlcache_ptr is not NULL, then it is just the address of zlcache,
 * as explained above.  If zlcache_ptr is NULL, there is no zlcache.
 */

struct zonelist {
        struct zonelist_cache *zlcache_ptr;                  // NULL or &zlcache
        struct zone *zones[MAX_ZONES_PER_ZONELIST + 1];      // NULL delimited
#ifdef CONFIG_NUMA
        struct zonelist_cache zlcache;                       // optional ...
#endif
};

#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
struct node_active_region {
        unsigned long start_pfn;
        unsigned long end_pfn;
        int nid;
};
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */

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

/*
 * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM
 * (mostly NUMA machines?) to denote a higher-level memory zone than the
 * zone denotes.
 *
 * On NUMA machines, each NUMA node would have a pg_data_t to describe
 * it's memory layout.
 *
 * 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_NR_ZONES];
        int nr_zones;
#ifdef CONFIG_FLAT_NODE_MEM_MAP
        struct page *node_mem_map;
#endif
        struct bootmem_data *bdata;
#ifdef CONFIG_MEMORY_HOTPLUG
        /*
         * Must be held any time you expect node_start_pfn, node_present_pages
         * or node_spanned_pages stay constant.  Holding this will also
         * guarantee that any pfn_valid() stays that way.
         *
         * Nests above zone->lock and zone->size_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;
        struct task_struct *kswapd;
        int kswapd_max_order;
} 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))

#include <linux/memory_hotplug.h>

void get_zone_counts(unsigned long *active, unsigned long *inactive,
                        unsigned long *free);
void build_all_zonelists(void);
void wakeup_kswapd(struct zone *zone, int order);
int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
                int classzone_idx, int alloc_flags);
enum memmap_context {
        MEMMAP_EARLY,
        MEMMAP_HOTPLUG,
};
extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
                                     unsigned long size,
                                     enum memmap_context context);

#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

#ifdef CONFIG_NEED_NODE_MEMMAP_SIZE
unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
#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)

static inline int populated_zone(struct zone *zone)
{
        return (!!zone->present_pages);
}

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

static inline int is_normal_idx(enum zone_type idx)
{
        return (idx == ZONE_NORMAL);
}

/**
 * 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 zone == zone->zone_pgdat->node_zones + ZONE_HIGHMEM;
#else
        return 0;
#endif
}

static inline int is_normal(struct zone *zone)
{
        return zone == zone->zone_pgdat->node_zones + ZONE_NORMAL;
}

static inline int is_dma32(struct zone *zone)
{
#ifdef CONFIG_ZONE_DMA32
        return zone == zone->zone_pgdat->node_zones + ZONE_DMA32;
#else
        return 0;
#endif
}

static inline int is_dma(struct zone *zone)
{
#ifdef CONFIG_ZONE_DMA
        return zone == zone->zone_pgdat->node_zones + ZONE_DMA;
#else
        return 0;
#endif
}

/* These two functions are used to setup the per zone pages min values */
struct ctl_table;
struct file;
int min_free_kbytes_sysctl_handler(struct ctl_table *, int, struct file *, 
                                        void __user *, size_t *, loff_t *);
extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1];
int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *,
                                        void __user *, size_t *, loff_t *);
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *,
                                        void __user *, size_t *, loff_t *);
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
                        struct file *, void __user *, size_t *, loff_t *);
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
                        struct file *, void __user *, size_t *, loff_t *);

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

#include <linux/topology.h>
/* Returns the number of the current Node. */
#ifndef numa_node_id
#define numa_node_id()          (cpu_to_node(raw_smp_processor_id()))
#endif

#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
#define MAX_NODES_SHIFT         1

#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_pgdat - helper macro to iterate over all 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))

#ifdef CONFIG_SPARSEMEM
#include <asm/sparsemem.h>
#endif

#if BITS_PER_LONG == 32
/*
 * with 32 bit page->flags field, we reserve 9 bits for node/zone info.
 * there are 4 zones (3 bits) and this leaves 9-3=6 bits for nodes.
 */
#define FLAGS_RESERVED          9

#elif BITS_PER_LONG == 64
/*
 * with 64 bit flags field, there's plenty of room.
 */
#define FLAGS_RESERVED          32

#else

#error BITS_PER_LONG not defined

#endif

#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
        !defined(CONFIG_ARCH_POPULATES_NODE_MAP)
#define early_pfn_to_nid(nid)  (0UL)
#endif

#ifdef CONFIG_FLATMEM
#define pfn_to_nid(pfn)         (0)
#endif

#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT)
#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT)

#ifdef CONFIG_SPARSEMEM

/*
 * SECTION_SHIFT                #bits space required to store a section #
 *
 * PA_SECTION_SHIFT             physical address to/from section number
 * PFN_SECTION_SHIFT            pfn to/from section number
 */
#define SECTIONS_SHIFT          (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS)

#define PA_SECTION_SHIFT        (SECTION_SIZE_BITS)
#define PFN_SECTION_SHIFT       (SECTION_SIZE_BITS - PAGE_SHIFT)

#define NR_MEM_SECTIONS         (1UL << SECTIONS_SHIFT)

#define PAGES_PER_SECTION       (1UL << PFN_SECTION_SHIFT)
#define PAGE_SECTION_MASK       (~(PAGES_PER_SECTION-1))

#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS
#error Allocator MAX_ORDER exceeds SECTION_SIZE
#endif

struct page;
struct mem_section {
        /*
         * This is, logically, a pointer to an array of struct
         * pages.  However, it is stored with some other magic.
         * (see sparse.c::sparse_init_one_section())
         *
         * Additionally during early boot we encode node id of
         * the location of the section here to guide allocation.
         * (see sparse.c::memory_present())
         *
         * Making it a UL at least makes someone do a cast
         * before using it wrong.
         */
        unsigned long section_mem_map;
};

#ifdef CONFIG_SPARSEMEM_EXTREME
#define SECTIONS_PER_ROOT       (PAGE_SIZE / sizeof (struct mem_section))
#else
#define SECTIONS_PER_ROOT       1
#endif

#define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT)
#define NR_SECTION_ROOTS        (NR_MEM_SECTIONS / SECTIONS_PER_ROOT)
#define SECTION_ROOT_MASK       (SECTIONS_PER_ROOT - 1)

#ifdef CONFIG_SPARSEMEM_EXTREME
extern struct mem_section *mem_section[NR_SECTION_ROOTS];
#else
extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
#endif

static inline struct mem_section *__nr_to_section(unsigned long nr)
{
        if (!mem_section[SECTION_NR_TO_ROOT(nr)])
                return NULL;
        return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
}
extern int __section_nr(struct mem_section* ms);

/*
 * We use the lower bits of the mem_map pointer to store
 * a little bit of information.  There should be at least
 * 3 bits here due to 32-bit alignment.
 */
#define SECTION_MARKED_PRESENT  (1UL<<0)
#define SECTION_HAS_MEM_MAP     (1UL<<1)
#define SECTION_MAP_LAST_BIT    (1UL<<2)
#define SECTION_MAP_MASK        (~(SECTION_MAP_LAST_BIT-1))
#define SECTION_NID_SHIFT       2

static inline struct page *__section_mem_map_addr(struct mem_section *section)
{
        unsigned long map = section->section_mem_map;
        map &= SECTION_MAP_MASK;
        return (struct page *)map;
}

static inline int valid_section(struct mem_section *section)
{
        return (section && (section->section_mem_map & SECTION_MARKED_PRESENT));
}

static inline int section_has_mem_map(struct mem_section *section)
{
        return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP));
}

static inline int valid_section_nr(unsigned long nr)
{
        return valid_section(__nr_to_section(nr));
}

static inline struct mem_section *__pfn_to_section(unsigned long pfn)
{
        return __nr_to_section(pfn_to_section_nr(pfn));
}

static inline int pfn_valid(unsigned long pfn)
{
        if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
                return 0;
        return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
}

/*
 * These are _only_ used during initialisation, therefore they
 * can use __initdata ...  They could have names to indicate
 * this restriction.
 */
#ifdef CONFIG_NUMA
#define pfn_to_nid(pfn)                                                 \
({                                                                      \
        unsigned long __pfn_to_nid_pfn = (pfn);                         \
        page_to_nid(pfn_to_page(__pfn_to_nid_pfn));                     \
})
#else
#define pfn_to_nid(pfn)         (0)
#endif

#define early_pfn_valid(pfn)    pfn_valid(pfn)
void sparse_init(void);
#else
#define sparse_init()   do {} while (0)
#define sparse_index_init(_sec, _nid)  do {} while (0)
#endif /* CONFIG_SPARSEMEM */

#ifdef CONFIG_NODES_SPAN_OTHER_NODES
#define early_pfn_in_nid(pfn, nid)      (early_pfn_to_nid(pfn) == (nid))
#else
#define early_pfn_in_nid(pfn, nid)      (1)
#endif

#ifndef early_pfn_valid
#define early_pfn_valid(pfn)    (1)
#endif

void memory_present(int nid, unsigned long start, unsigned long end);
unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);

/*
 * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
 * need to check pfn validility within that MAX_ORDER_NR_PAGES block.
 * pfn_valid_within() should be used in this case; we optimise this away
 * when we have no holes within a MAX_ORDER_NR_PAGES block.
 */
#ifdef CONFIG_HOLES_IN_ZONE
#define pfn_valid_within(pfn) pfn_valid(pfn)
#else
#define pfn_valid_within(pfn) (1)
#endif

#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _LINUX_MMZONE_H */