Merge with http://www.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git

[linux-2.6] / include / linux / mmzone.h

#ifndef _LINUX_MMZONE_H
#define _LINUX_MMZONE_H

#ifdef __KERNEL__
#ifndef __ASSEMBLY__

#include <linux/config.h>
#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 <asm/atomic.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

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_maxaligned_in_smp;
#define ZONE_PADDING(name)      struct zone_padding name;
#else
#define ZONE_PADDING(name)
#endif

struct per_cpu_pages {
        int count;              /* number of pages in the list */
        int low;                /* low watermark, refill needed */
        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
        unsigned long numa_hit;         /* allocated in intended node */
        unsigned long numa_miss;        /* allocated in non intended node */
        unsigned long numa_foreign;     /* was intended here, hit elsewhere */
        unsigned long interleave_hit;   /* interleaver prefered this zone */
        unsigned long local_node;       /* allocation from local node */
        unsigned long other_node;       /* allocation from other node */
#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

#define ZONE_DMA                0
#define ZONE_NORMAL             1
#define ZONE_HIGHMEM            2

#define MAX_NR_ZONES            3       /* Sync this with ZONES_SHIFT */
#define ZONES_SHIFT             2       /* ceil(log2(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.  GFP_ZONEMASK defines which bits within
 * the gfp_mask should be considered as zone modifiers.  Each valid
 * combination of the zone modifier bits has a corresponding list
 * of zones (in node_zonelists).  Thus for two zone modifiers there
 * will be a maximum of 4 (2 ** 2) zonelists, for 3 modifiers there will
 * be 8 (2 ** 3) zonelists.  GFP_ZONETYPES defines the number of possible
 * combinations of zone modifiers in "zone modifier space".
 */
#define GFP_ZONEMASK    0x03
/*
 * As an optimisation any zone modifier bits which are only valid when
 * no other zone modifier bits are set (loners) should be placed in
 * the highest order bits of this field.  This allows us to reduce the
 * extent of the zonelists thus saving space.  For example in the case
 * of three zone modifier bits, we could require up to eight zonelists.
 * If the left most zone modifier is a "loner" then the highest valid
 * zonelist would be four allowing us to allocate only five zonelists.
 * Use the first form when the left most bit is not a "loner", otherwise
 * use the second.
 */
/* #define GFP_ZONETYPES        (GFP_ZONEMASK + 1) */           /* Non-loner */
#define GFP_ZONETYPES   ((GFP_ZONEMASK + 1) / 2 + 1)            /* Loner */

/*
 * On machines where it is needed (eg PCs) we divide physical memory
 * into multiple physical zones. On a PC we have 3 zones:
 *
 * ZONE_DMA       < 16 MB       ISA DMA capable memory
 * ZONE_NORMAL  16-896 MB       direct mapped by the kernel
 * ZONE_HIGHMEM  > 896 MB       only page cache and user processes
 */

struct zone {
        /* Fields commonly accessed by the page allocator */
        unsigned long           free_pages;
        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
        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           nr_active;
        unsigned long           nr_inactive;
        unsigned long           pages_scanned;     /* since last reclaim */
        int                     all_unreclaimable; /* All pages pinned */

        /*
         * Does the allocator try to reclaim pages from the zone as soon
         * as it fails a watermark_ok() in __alloc_pages?
         */
        int                     reclaim_pages;
        /* A count of how many reclaimers are scanning this zone */
        atomic_t                reclaim_in_progress;

        /*
         * 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.
         *
         * temp_priority is used to remember the scanning priority at which
         * this zone was successfully refilled to free_pages == pages_high.
         *
         * Access to both these fields is quite racy even on uniprocessor.  But
         * it is expected to average out OK.
         */
        int temp_priority;
        int prev_priority;


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

        /*
         * wait_table           -- the array holding the hash table
         * wait_table_size      -- 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_size;
        unsigned long           wait_table_bits;

        /*
         * Discontig memory support fields.
         */
        struct pglist_data      *zone_pgdat;
        struct page             *zone_mem_map;
        /* 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:
         */
        char                    *name;
} ____cacheline_maxaligned_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

/*
 * 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.
 *
 * Right now a zonelist takes up less than a cacheline. We never
 * modify it apart from boot-up, and only a few indices are used,
 * so despite the zonelist table being relatively big, the cache
 * footprint of this construct is very small.
 */
struct zonelist {
        struct zone *zones[MAX_NUMNODES * MAX_NR_ZONES + 1]; // NULL delimited
};


/*
 * 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[GFP_ZONETYPES];
        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;
        struct pglist_data *pgdat_next;
        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>

extern struct pglist_data *pgdat_list;

void __get_zone_counts(unsigned long *active, unsigned long *inactive,
                        unsigned long *free, struct pglist_data *pgdat);
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 alloc_type, int can_try_harder, gfp_t gfp_high);

#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)

/**
 * for_each_pgdat - helper macro to iterate over all nodes
 * @pgdat - pointer to a pg_data_t variable
 *
 * Meant to help with common loops of the form
 * pgdat = pgdat_list;
 * while(pgdat) {
 *      ...
 *      pgdat = pgdat->pgdat_next;
 * }
 */
#define for_each_pgdat(pgdat) \
        for (pgdat = pgdat_list; pgdat; pgdat = pgdat->pgdat_next)

/*
 * next_zone - helper magic for for_each_zone()
 * Thanks to William Lee Irwin III for this piece of ingenuity.
 */
static inline struct zone *next_zone(struct zone *zone)
{
        pg_data_t *pgdat = zone->zone_pgdat;

        if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
                zone++;
        else if (pgdat->pgdat_next) {
                pgdat = pgdat->pgdat_next;
                zone = pgdat->node_zones;
        } else
                zone = NULL;

        return zone;
}

/**
 * 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. This basically means for_each_zone() is an
 * easier to read version of this piece of code:
 *
 * for (pgdat = pgdat_list; pgdat; pgdat = pgdat->node_next)
 *      for (i = 0; i < MAX_NR_ZONES; ++i) {
 *              struct zone * z = pgdat->node_zones + i;
 *              ...
 *      }
 * }
 */
#define for_each_zone(zone) \
        for (zone = pgdat_list->node_zones; zone; zone = next_zone(zone))

static inline int is_highmem_idx(int idx)
{
        return (idx == ZONE_HIGHMEM);
}

static inline int is_normal_idx(int 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)
{
        return zone == zone->zone_pgdat->node_zones + ZONE_HIGHMEM;
}

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

/* 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 *);

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

#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
#define pfn_to_nid(pfn)         (0)

#else /* CONFIG_NEED_MULTIPLE_NODES */

#include <asm/mmzone.h>

#endif /* !CONFIG_NEED_MULTIPLE_NODES */

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

#if BITS_PER_LONG == 32 || defined(ARCH_HAS_ATOMIC_UNSIGNED)
/*
 * with 32 bit page->flags field, we reserve 8 bits for node/zone info.
 * there are 3 zones (2 bits) and this leaves 8-2=6 bits for nodes.
 */
#define FLAGS_RESERVED          8

#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

#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
#define early_pfn_to_nid(nid)  (0UL)
#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())
         *
         * 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))

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));
}

/*
 * Given a kernel address, find the home node of the underlying memory.
 */
#define kvaddr_to_nid(kaddr)    pfn_to_nid(__pa(kaddr) >> PAGE_SHIFT)

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

#define pfn_to_page(pfn)                                                \
({                                                                      \
        unsigned long __pfn = (pfn);                                    \
        __section_mem_map_addr(__pfn_to_section(__pfn)) + __pfn;        \
})
#define page_to_pfn(page)                                               \
({                                                                      \
        page - __section_mem_map_addr(__nr_to_section(                  \
                page_to_section(page)));                                \
})

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              early_pfn_to_nid
#endif

#define pfn_to_pgdat(pfn)                                               \
({                                                                      \
        NODE_DATA(pfn_to_nid(pfn));                                     \
})

#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);

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