Linux-3.14.12內存管理筆記【夥伴管理算法（1）】

前面分析了memblock算法、內核頁表的創建、內存管理框架的構建，這些都是x86處理的setup_arch()函數裏面初始化的，因地制宜，具備明顯處理器的特徵。而start_kernel()接下來的初始化則是linux通用的內存管理算法框架了。

build_all_zonelists()用來初始化內存分配器使用的存儲節點中的管理區鏈表，是爲內存管理算法（夥伴管理算法）作準備工做的。具體實現：

【file：/mm/page_alloc.c】
/*
 * Called with zonelists_mutex held always
 * unless system_state == SYSTEM_BOOTING.
 */
void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
{
    set_zonelist_order();
 
    if (system_state == SYSTEM_BOOTING) {
        __build_all_zonelists(NULL);
        mminit_verify_zonelist();
        cpuset_init_current_mems_allowed();
    } else {
#ifdef CONFIG_MEMORY_HOTPLUG
        if (zone)
            setup_zone_pageset(zone);
#endif
        /* we have to stop all cpus to guarantee there is no user
           of zonelist */
        stop_machine(__build_all_zonelists, pgdat, NULL);
        /* cpuset refresh routine should be here */
    }
    vm_total_pages = nr_free_pagecache_pages();
    /*
     * Disable grouping by mobility if the number of pages in the
     * system is too low to allow the mechanism to work. It would be
     * more accurate, but expensive to check per-zone. This check is
     * made on memory-hotadd so a system can start with mobility
     * disabled and enable it later
     */
    if (vm_total_pages < (pageblock_nr_pages * MIGRATE_TYPES))
        page_group_by_mobility_disabled = 1;
    else
        page_group_by_mobility_disabled = 0;
 
    printk("Built %i zonelists in %s order, mobility grouping %s. "
        "Total pages: %ld\n",
            nr_online_nodes,
            zonelist_order_name[current_zonelist_order],
            page_group_by_mobility_disabled ? "off" : "on",
            vm_total_pages);
#ifdef CONFIG_NUMA
    printk("Policy zone: %s\n", zone_names[policy_zone]);
#endif
}

首先看到set_zonelist_order()：

【file：/mm/page_alloc.c】
static void set_zonelist_order(void)
{
    current_zonelist_order = ZONELIST_ORDER_ZONE;
}

此處用於設置zonelist的順序，ZONELIST_ORDER_ZONE用於表示順序(-zonetype, [node] distance)，另外還有ZONELIST_ORDER_NODE表示順序([node] distance, -zonetype)。但其僅限於對NUMA環境存在區別，非NUMA環境則毫無差別。

若是系統狀態system_state爲SYSTEM_BOOTING，系統狀態只有在start_kernel執行到最後一個函數rest_init後，纔會進入SYSTEM_RUNNING，因而初始化時將會接着是__build_all_zonelists()函數:

【file：/mm/page_alloc.c】
/* return values int ....just for stop_machine() */
static int __build_all_zonelists(void *data)
{
    int nid;
    int cpu;
    pg_data_t *self = data;
 
#ifdef CONFIG_NUMA
    memset(node_load, 0, sizeof(node_load));
#endif
 
    if (self && !node_online(self->node_id)) {
        build_zonelists(self);
        build_zonelist_cache(self);
    }
 
    for_each_online_node(nid) {
        pg_data_t *pgdat = NODE_DATA(nid);
 
        build_zonelists(pgdat);
        build_zonelist_cache(pgdat);
    }
 
    /*
     * Initialize the boot_pagesets that are going to be used
     * for bootstrapping processors. The real pagesets for
     * each zone will be allocated later when the per cpu
     * allocator is available.
     *
     * boot_pagesets are used also for bootstrapping offline
     * cpus if the system is already booted because the pagesets
     * are needed to initialize allocators on a specific cpu too.
     * F.e. the percpu allocator needs the page allocator which
     * needs the percpu allocator in order to allocate its pagesets
     * (a chicken-egg dilemma).
     */
    for_each_possible_cpu(cpu) {
        setup_pageset(&per_cpu(boot_pageset, cpu), 0);
 
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
        /*
         * We now know the "local memory node" for each node--
         * i.e., the node of the first zone in the generic zonelist.
         * Set up numa_mem percpu variable for on-line cpus. During
         * boot, only the boot cpu should be on-line; we'll init the
         * secondary cpus' numa_mem as they come on-line. During
         * node/memory hotplug, we'll fixup all on-line cpus.
         */
        if (cpu_online(cpu))
            set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
#endif
    }
 
    return 0;
}

其中build_zonelists_node()函數實現：

【file：/mm/page_alloc.c】
/*
 * Builds allocation fallback zone lists.
 *
 * Add all populated zones of a node to the zonelist.
 */
static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
                int nr_zones)
{
    struct zone *zone;
    enum zone_type zone_type = MAX_NR_ZONES;
 
    do {
        zone_type--;
        zone = pgdat->node_zones + zone_type;
        if (populated_zone(zone)) {
            zoneref_set_zone(zone,
                &zonelist->_zonerefs[nr_zones++]);
            check_highest_zone(zone_type);
        }
    } while (zone_type);
 
    return nr_zones;
}

populated_zone()用於判斷管理區zone的present_pages成員是否爲0，若是不爲0的話，表示該管理區存在頁面，那麼則經過zoneref_set_zone()將其設置到zonelist的_zonerefs裏面，而check_highest_zone()在沒有開啓NUMA的狀況下是個空函數。由此能夠看出build_zonelists_node()實則上是按照ZONE_HIGHMEM—>ZONE_NORMAL—>ZONE_DMA的順序去迭代排布到_zonerefs裏面的，表示一個申請內存的代價由低廉到昂貴的順序，這是一個分配內存時的備用次序。

回到build_zonelists()函數中，而它代碼顯示將本地的內存管理區進行分配備用次序排序，接着再是分配內存代價低於本地的，最後纔是分配內存代價高於本地的。

分析完build_zonelists()，再回到__build_all_zonelists()看一下build_zonelist_cache()：

【file：/mm/page_alloc.c】
/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
static void build_zonelist_cache(pg_data_t *pgdat)
{
    pgdat->node_zonelists[0].zlcache_ptr = NULL;
}

該函數與CONFIG_NUMA相關，用來設置zlcache相關的成員。因爲沒有開啓該配置，故直接設置爲NULL。

基於build_all_zonelists()調用__build_all_zonelists()入參爲NULL，由此可知__build_all_zonelists()運行的代碼是：

for_each_online_node(nid) {

    pg_data_t *pgdat = NODE_DATA(nid);

    build_zonelists(pgdat);

    build_zonelist_cache(pgdat);

}

主要是設置各個內存管理節點node裏面各自的內存管理分區zone的內存分配次序。

__build_all_zonelists()接着的是：

for_each_possible_cpu(cpu) {

    setup_pageset(&per_cpu(boot_pageset, cpu), 0);

#ifdef CONFIG_HAVE_MEMORYLESS_NODES
    if (cpu_online(cpu))
        set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
#endif

}

其中CONFIG_HAVE_MEMORYLESS_NODES未配置，主要分析一下setup_pageset()：

【file：/mm/page_alloc.c】
static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
    pageset_init(p);
    pageset_set_batch(p, batch);
}

setup_pageset()裏面調用的兩個函數較爲簡單，就直接過一下。先是：

【file：/mm/page_alloc.c】
static void pageset_init(struct per_cpu_pageset *p)
{
    struct per_cpu_pages *pcp;
    int migratetype;
 
    memset(p, 0, sizeof(*p));
 
    pcp = &p->pcp;
    pcp->count = 0;
    for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
        INIT_LIST_HEAD(&pcp->lists[migratetype]);
}

pageset_init()主要是將struct per_cpu_pages結構體進行初始化，而pageset_set_batch()則是對其進行設置。pageset_set_batch()實現：

【file：/mm/page_alloc.c】
/*
 * pcp->high and pcp->batch values are related and dependent on one another:
 * ->batch must never be higher then ->high.
 * The following function updates them in a safe manner without read side
 * locking.
 *
 * Any new users of pcp->batch and pcp->high should ensure they can cope with
 * those fields changing asynchronously (acording the the above rule).
 *
 * mutex_is_locked(&pcp_batch_high_lock) required when calling this function
 * outside of boot time (or some other assurance that no concurrent updaters
 * exist).
 */
static void pageset_update(struct per_cpu_pages *pcp, unsigned long high,
        unsigned long batch)
{
       /* start with a fail safe value for batch */
    pcp->batch = 1;
    smp_wmb();
 
       /* Update high, then batch, in order */
    pcp->high = high;
    smp_wmb();
 
    pcp->batch = batch;
}
 
/* a companion to pageset_set_high() */
static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch)
{
    pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch));
}

setup_pageset()函數入參p是一個struct per_cpu_pageset結構體的指針，per_cpu_pageset結構是內核的各個zone用於每CPU的頁面高速緩存管理結構。該高速緩存包含一些預先分配的頁面，以用於知足本地CPU發出的單一內存請求。而struct per_cpu_pages定義的pcp是該管理結構的成員，用於具體頁面管理。本來是每一個管理結構有兩個pcp數組成員，裏面的兩條隊列分別用於冷頁面和熱頁面管理，而當前分析的3.14.12版本已經將二者合併起來，統一管理冷熱頁，熱頁面在隊列前面，而冷頁面則在隊列後面。暫且先記着這麼多，後續在Buddy算法的時候再詳細分析了。

至此，能夠知道__build_all_zonelists()是內存管理框架向後續的內存頁面管理算法作準備，排布了內存管理區zone的分配次序，同時初始化了冷熱頁管理。

最後回到build_all_zonelists()函數。因爲沒有開啓內存初始化調試功能CONFIG_DEBUG_MEMORY_INIT，mminit_verify_zonelist()是一個空函數。

基於CONFIG_CPUSETS配置項開啓的狀況下，而cpuset_init_current_mems_allowed()實現以下：

【file：/kernel/cpuset.c】
void cpuset_init_current_mems_allowed(void)
{
    nodes_setall(current->mems_allowed);
}

這裏面的current 是一個cpuset的數據結構，用來管理cgroup中的任務可以使用的cpu和內存節點。而成員mems_allowed，該成員是nodemask_t類型的結構體

【file：/include/linux/nodemask.h】
typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;

該結構其實就是定義了一個位域，每一個位對應一個內存結點，若是置1表示該節點內存可用。而nodes_setall則是將這個位域中每一個位都置1。

末了看一下build_all_zonelists()裏面nr_free_pagecache_pages()的實現：

【file：/mm/page_alloc.c】
/**
 * nr_free_pagecache_pages - count number of pages beyond high watermark
 *
 * nr_free_pagecache_pages() counts the number of pages which are beyond the
 * high watermark within all zones.
 */
unsigned long nr_free_pagecache_pages(void)
{
    return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
}

而裏面調用的nr_free_zone_pages()實現爲：

【file：/mm/page_alloc.c】
/**
 * nr_free_zone_pages - count number of pages beyond high watermark
 * @offset: The zone index of the highest zone
 *
 * nr_free_zone_pages() counts the number of counts pages which are beyond the
 * high watermark within all zones at or below a given zone index. For each
 * zone, the number of pages is calculated as:
 * managed_pages - high_pages
 */
static unsigned long nr_free_zone_pages(int offset)
{
    struct zoneref *z;
    struct zone *zone;
 
    /* Just pick one node, since fallback list is circular */
    unsigned long sum = 0;
 
    struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
 
    for_each_zone_zonelist(zone, z, zonelist, offset) {
        unsigned long size = zone->managed_pages;
        unsigned long high = high_wmark_pages(zone);
        if (size > high)
            sum += size - high;
    }
 
    return sum;
}

能夠看到nr_free_zone_pages()遍歷全部內存管理區並將各管理區的內存空間求和，其實質是用於統計全部的管理區能夠用於分配的內存頁面數。

接着在build_all_zonelists()後面則是判斷當前系統中的內存頁框數目，以決定是否啓用流動分組機制(Mobility Grouping)，該機制能夠在分配大內存塊時減小內存碎片。一般只有內存足夠大時纔會啓用該功能，不然將會提高消耗下降性能。其中pageblock_nr_pages表示夥伴系統中的最高階頁塊所能包含的頁面數。

至此，內存管理框架算法基本準備完畢。