Linux-3.14.12内存管理笔记【构建内存管理框架（5）】

前面已经分析了内存管理框架的构建实现过程，有部分内容未完全呈现出来，这里主要做个补充。

如下图，这是前面已经看到过的linux物理内存管理框架的层次关系。

现着重分析一下各个管理结构体的成员功能作用。

【file：/include/linux/mmzone.h】
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_MEMCG
    struct page_cgroup *node_page_cgroup;
#endif
#endif
#ifndef CONFIG_NO_BOOTMEM
    struct bootmem_data *bdata;
#endif
#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.
     *
     * pgdat_resize_lock() and pgdat_resize_unlock() are provided to
     * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG.
     *
     * 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;
    nodemask_t reclaim_nodes; /* Nodes allowed to reclaim from */
    wait_queue_head_t kswapd_wait;
    wait_queue_head_t pfmemalloc_wait;
    struct task_struct *kswapd; /* Protected by lock_memory_hotplug() */
    int kswapd_max_order;
    enum zone_type classzone_idx;
#ifdef CONFIG_NUMA_BALANCING
    /* Lock serializing the migrate rate limiting window */
    spinlock_t numabalancing_migrate_lock;
 
    /* Rate limiting time interval */
    unsigned long numabalancing_migrate_next_window;
 
    /* Number of pages migrated during the rate limiting time interval */
    unsigned long numabalancing_migrate_nr_pages;
#endif
} pg_data_t;

• struct zone node_zones[MAX_NR_ZONES];

——存放该pg_data_t里面的zone；

• struct zonelist node_zonelists[MAX_ZONELISTS];

——其指向一个page结构的数组，数组中的每个成员为该节点中的一个物理页面，于是整个数组就对应了该节点中所有的物理页面；

• struct page_cgroup *node_page_cgroup;

——用于管理page_cgroup，原来的page_cgroup是page页面管理结构的一个成员，现在移到这里了，它将会在初始化时所有的page_cgroup都将申请下来；

• struct bootmem_data *bdata;

——该数据指向bootmem_node_data，可以通过system.map查到。原是用于bootmem内存分配器的信息存储，当前改用memblock算法，则不存在该成员；

• unsigned long node_start_pfn;

——指向当前pg_data_t结构管理的物理起始页面；

• unsigned long node_present_pages;

——记录物理页面数总量，除开内存空洞的物理页面数；

• unsigned long node_spanned_pages;

——最大和最小页面号的差值，包括内存空洞的总的物理页面大小；

• int node_id;

——pg_data_t对应的索引号，非NUMA架构下该值为0；

• nodemask_t reclaim_nodes;

——用于记录可回收的内存管理节点node信息；

• wait_queue_head_t kswapd_wait;

——kswapd是页面交换守护线程，该线程会阻塞在这个等待队列，当满足条件后，调用wake_up_interruptible()唤醒该队列进行相关操作；

• wait_queue_head_t pfmemalloc_wait;

——用于减缓内存直接回收；

• struct task_struct *kswapd;

——指向kswapd守护线程的任务指针；

• int kswapd_max_order;

——用于表示kswapd守护线程每次回收的页面个数；

• enum zone_type classzone_idx;

——该成员与kswapd有关；

【file：/include/linux/mmzone.h】
struct zone {
    /* Fields commonly accessed by the page allocator */
 
    /* zone watermarks, access with *_wmark_pages(zone) macros */
    unsigned long watermark[NR_WMARK];
 
    /*
     * 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;
 
    /*
     * 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];
 
    /*
     * This is a per-zone reserve of pages that should not be
     * considered dirtyable memory.
     */
    unsigned long dirty_balance_reserve;
 
#ifdef CONFIG_NUMA
    int node;
    /*
     * zone reclaim becomes active if more unmapped pages exist.
     */
    unsigned long min_unmapped_pages;
    unsigned long min_slab_pages;
#endif
    struct per_cpu_pageset __percpu *pageset;
    /*
     * free areas of different sizes
     */
    spinlock_t lock;
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
    /* Set to true when the PG_migrate_skip bits should be cleared */
    bool compact_blockskip_flush;
 
    /* pfns where compaction scanners should start */
    unsigned long compact_cached_free_pfn;
    unsigned long compact_cached_migrate_pfn;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
    /* see spanned/present_pages for more description */
    seqlock_t span_seqlock;
#endif
    struct free_area free_area[MAX_ORDER];
 
#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_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
 
    ZONE_PADDING(_pad1_)
 
    /* Fields commonly accessed by the page reclaim scanner */
    spinlock_t lru_lock;
    struct lruvec lruvec;
 
    unsigned long pages_scanned; /* since last reclaim */
    unsigned long flags; /* zone flags, see below */
 
    /* Zone statistics */
    atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
 
    /*
     * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
     * this zone's LRU. Maintained by the pageout code.
     */
    unsigned int inactive_ratio;
 
 
    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;
 
    /*
     * 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
     * lock_memory_hotplug()/unlock_memory_hotplug(). Any reader who can't
     * tolerant drift of present_pages should hold memory hotplug lock 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 spanned_pages;
    unsigned long present_pages;
    unsigned long managed_pages;
 
    /*
     * Number of MIGRATE_RESEVE page block. To maintain for just
     * optimization. Protected by zone->lock.
     */
    int nr_migrate_reserve_block;
 
    /*
     * rarely used fields:
     */
    const char *name;
} ____cacheline_internodealigned_in_smp;

• unsigned long watermark[NR_WMARK];

——该数组有三个值WMARK_MIN、WMARK_LOW、WMARK_HIGH，如命名所标识，min最小，low居中，high最大。内存分配过程中，当空闲页面达到low时，内存分配器会唤醒kswapd守护进程来回收物理页面；当空闲页面达到min时，内存分配器就会唤醒kswapd以同步方式回收；如果kswapd被唤醒后，空闲页面达到high时，则会使kswapd再次休眠；

• unsigned long percpu_drift_mark;

——当空闲页面低于该值，将会引发附加操作的执行，用于避免前面的watermark被冲破；

• unsigned long lowmem_reserve[MAX_NR_ZONES];

——记录每个管理区中必须保留的物理页面数，以用于紧急状况下的内存分配；

• unsigned long dirty_balance_reserve;

——用于表示不会被内存分配器分配出去的空闲页面部分的近似值；

• struct per_cpu_pageset __percpu *pageset;

——该数组里面的成员pcp用于实现冷热页面的管理；

• spinlock_t lock;

——spinlock锁，用于解决该管理区的并发问题；

• struct free_area free_area[MAX_ORDER];

——主要用于Buddy内存管理算法（伙伴算法）；

• unsigned long *pageblock_flags;

——与伙伴算法的碎片迁移算法有关；

• spinlock_t lru_lock;

——用于保护lruvec结构数据；

• struct lruvec lruvec;

——lruvec该数组里面有一个lists是用于lru管理的链表，另外有一个reclaim_stat用于页面回收的状态标示；

• unsigned long pages_scanned;

——用于记录上次物理页面回收时，扫描过的页描述符总数；

• unsigned long flags;

——用于表示当前内存管理区的状态；

• atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];

——用于统计该内存管理区中各项状态的数值；

• unsigned int inactive_ratio;

——不活跃的页面比例；

• wait_queue_head_t *wait_table;

• unsigned long wait_table_hash_nr_entries;

• unsigned long wait_table_bits;

• struct pglist_data *zone_pgdat;

——指向该内存管理区的pg_data_list；

• unsigned long zone_start_pfn;

——记录当前内存管理区中最小的物理页面号；

• unsigned long spanned_pages;

——记录内存管理区的总页面数，包括内存空洞的页面数，实则上是管理区末尾页面号和起始页面号的差值；

• unsigned long present_pages;

——除去内存空洞后的内存管理区实际有效的总页面数；

• unsigned long managed_pages;

——用于记录被内存管理算法管理的物理页面数，这是除去了在初始化阶段被申请的页面；

• int nr_migrate_reserve_block;

——用于优化的，记录内存迁移保留的页面数；

• const char *name;

——用于记录该管理区的名字；

【file：/include/linux/mmzone.h】
/*
 * Each physical page in the system has a struct page associated with
 * it to keep track of whatever it is we are using the page for at the
 * moment. Note that we have no way to track which tasks are using
 * a page, though if it is a pagecache page, rmap structures can tell us
 * who is mapping it.
 *
 * The objects in struct page are organized in double word blocks in
 * order to allows us to use atomic double word operations on portions
 * of struct page. That is currently only used by slub but the arrangement
 * allows the use of atomic double word operations on the flags/mapping
 * and lru list pointers also.
 */
struct page {
    /* First double word block */
    unsigned long flags; /* Atomic flags, some possibly
                     * updated asynchronously */
    union {
        struct address_space *mapping; /* If low bit clear, points to
                         * inode address_space, or NULL.
                         * If page mapped as anonymous
                         * memory, low bit is set, and
                         * it points to anon_vma object:
                         * see PAGE_MAPPING_ANON below.
                         */
        void *s_mem; /* slab first object */
    };
 
    /* Second double word */
    struct {
        union {
            pgoff_t index; /* Our offset within mapping. */
            void *freelist; /* sl[aou]b first free object */
            bool pfmemalloc; /* If set by the page allocator,
                         * ALLOC_NO_WATERMARKS was set
                         * and the low watermark was not
                         * met implying that the system
                         * is under some pressure. The
                         * caller should try ensure
                         * this page is only used to
                         * free other pages.
                         */
        };
 
        union {
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && 
    defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
            /* Used for cmpxchg_double in slub */
            unsigned long counters;
#else
            /*
             * Keep _count separate from slub cmpxchg_double data.
             * As the rest of the double word is protected by
             * slab_lock but _count is not.
             */
            unsigned counters;
#endif
 
            struct {
 
                union {
                    /*
                     * Count of ptes mapped in
                     * mms, to show when page is
                     * mapped & limit reverse map
                     * searches.
                     *
                     * Used also for tail pages
                     * refcounting instead of
                     * _count. Tail pages cannot
                     * be mapped and keeping the
                     * tail page _count zero at
                     * all times guarantees
                     * get_page_unless_zero() will
                     * never succeed on tail
                     * pages.
                     */
                    atomic_t _mapcount;
 
                    struct { /* SLUB */
                        unsigned inuse:16;
                        unsigned objects:15;
                        unsigned frozen:1;
                    };
                    int units; /* SLOB */
                };
                atomic_t _count; /* Usage count, see below. */
            };
            unsigned int active; /* SLAB */
        };
    };
 
    /* Third double word block */
    union {
        struct list_head lru; /* Pageout list, eg. active_list
                     * protected by zone->lru_lock !
                     */
        struct { /* slub per cpu partial pages */
            struct page *next; /* Next partial slab */
#ifdef CONFIG_64BIT
            int pages; /* Nr of partial slabs left */
            int pobjects; /* Approximate # of objects */
#else
            short int pages;
            short int pobjects;
#endif
        };
 
        struct list_head list; /* slobs list of pages */
        struct slab *slab_page; /* slab fields */
        struct rcu_head rcu_head; /* Used by SLAB
                         * when destroying via RCU
                         */
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
        pgtable_t pmd_huge_pte; /* protected by page->ptl */
#endif
    };
 
    /* Remainder is not double word aligned */
    union {
        unsigned long private; /* Mapping-private opaque data:
                         * usually used for buffer_heads
                         * if PagePrivate set; used for
                         * swp_entry_t if PageSwapCache;
                         * indicates order in the buddy
                         * system if PG_buddy is set.
                         */
#if USE_SPLIT_PTE_PTLOCKS
#if ALLOC_SPLIT_PTLOCKS
        spinlock_t *ptl;
#else
        spinlock_t ptl;
#endif
#endif
        struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */
        struct page *first_page; /* Compound tail pages */
    };
 
    /*
     * On machines where all RAM is mapped into kernel address space,
     * we can simply calculate the virtual address. On machines with
     * highmem some memory is mapped into kernel virtual memory
     * dynamically, so we need a place to store that address.
     * Note that this field could be 16 bits on x86 ... ;)
     *
     * Architectures with slow multiplication can define
     * WANT_PAGE_VIRTUAL in asm/page.h
     */
#if defined(WANT_PAGE_VIRTUAL)
    void *virtual; /* Kernel virtual address (NULL if
                       not kmapped, ie. highmem) */
#endif /* WANT_PAGE_VIRTUAL */
#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
    unsigned long debug_flags; /* Use atomic bitops on this */
#endif
 
#ifdef CONFIG_KMEMCHECK
    /*
     * kmemcheck wants to track the status of each byte in a page; this
     * is a pointer to such a status block. NULL if not tracked.
     */
    void *shadow;
#endif
 
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
    int _last_cpupid;
#endif
}

（该结构很多union结构，主要是用于各种算法不同数据的空间复用，暂时记录部分常见的数据成员）

• unsigned long flags;

——用于记录页框的类型；

• struct address_space *mapping;

——用于区分该页是映射页框还是匿名页框；

• atomic_t _mapcount;

——记录了系统中页表有多少项指向该页；

• atomic_t _count;

——当前系统对该页面的引用次数；

• struct list_head lru;

——当页框处于分配状态时，该成员用于zone的lruvec里面的list，当页框未被分配时则用于伙伴算法；

• unsigned long private;

——指向“私有”数据的指针。根据页的用途，可以用不同的方式使用该指针，通常用于与数据缓冲区关联起来；

• void *virtual;

——用于高端内存区域的页，即用于无法直接映射的页，该成员用于存储该页的虚拟地址；