内存管理相关数据结构之内存域zone

承接内存管理相关概念讲解相关数据结构。
主要有

• pg_data_t: 表示节点；
• zone： 内存域；
• page: 页帧；

struct zone {
    /* Read-mostly fields */
    unsigned long watermark[NR_WMARK];
    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
    /*
     * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
     * this zone's LRU.  Maintained by the pageout code.
     */
    unsigned int inactive_ratio;
    struct pglist_data  *zone_pgdat;
    struct per_cpu_pageset __percpu *pageset;
    /*
     * This is a per-zone reserve of pages that should not be
     * considered dirtyable memory.
     */
    unsigned long       dirty_balance_reserve;
#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 */
#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 */
    /* 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.
     *
     * Read access to managed_pages should be safe because it's unsigned
     * long. Write access to zone->managed_pages and totalram_pages are
     * protected by managed_page_count_lock at runtime. Idealy only
     * adjust_managed_page_count() should be used instead of directly
     * touching zone->managed_pages and totalram_pages.
     */
    unsigned long       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
    /*
     * 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;
    ZONE_PADDING(_pad1_)
    /* free areas of different sizes */
    struct free_area    free_area[MAX_ORDER];
    /* zone flags, see below */
    unsigned long       flags;
    /* Write-intensive fields used from the page allocator */
    spinlock_t      lock;
    ZONE_PADDING(_pad2_)
    /* Write-intensive fields used by page reclaim */
    /* Fields commonly accessed by the page reclaim scanner */
    spinlock_t      lru_lock;
    struct lruvec       lruvec;
    /* Evictions & activations on the inactive file list */
    atomic_long_t       inactive_age;
    /*
     * 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];
#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
    ZONE_PADDING(_pad3_)
    /* Zone statistics */
    atomic_long_t       vm_stat[NR_VM_ZONE_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;

该结构由ZONE_PADDING分割成了四部分，这是由于在多cpu系统上，通常会有多个cpu同时访问结构成员，使用锁分段从而提高性能(span_seqlock, lock, lru_lock)。
ZONE_PADDING用于填充缓冲行，保证各段在不同的高速缓冲行中互不干扰，确保了每个自旋锁都处于自身的缓冲行中。

• watermark是换出时使用的水印值，影响交换守护进程的行为，分为三部分，定义如下：

enum zone_watermarks {
    WMARK_MIN,
    WMARK_LOW,
    WMARK_HIGH,
    NR_WMARK
};
// 若空闲内存页数目小于该值，页回收工作的压力就比较大。
#define min_wmark_pages(z) (z->watermark[WMARK_MIN])
// 若内存空闲页数目低于该值，内存开始将页换出到磁盘
#define low_wmark_pages(z) (z->watermark[WMARK_LOW])
// 若空闲页数目多于high_wmark_pages，则内存域的状态是理想的。
#define high_wmark_pages(z) (z->watermark[WMARK_HIGH])

• lowmem_reserve分别为各种内存域指定了若干页，用于一些无论如何都不能失败的关键性内存分配；

• pageset用于实现每个cpu的冷热页帧列表。(ps: 页帧在高速缓存中叫热的，否则叫冷的);

• free_area用于实现伙伴系统，每个数组元素都表示某种固定长度的一些连续内存区。