buddy allocator是怎样开始工作的？

时间：2010-12-18 来源：letmego163

For x86_64 Architecture:

1.
Linux启动阶段用的分配器是 boot allocator, 在start_kernel()中调用mm_init(), 然后把boot allocator管理的物理内存交给buddy allocator, 以__free_pages()的方式把pages放到buddy的数据结构free_areas中。

mm_init() > mem_init() > free_all_bootmem() > free_all_bootmem_core() > __free_pages()

2.
boot allocator, kernel首先调用initmem_init()把管理的所有页都标记为已经分配，然后再选择空闲的页标记为0，表示可以分配。然后，调用

void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
                int acpi, int k8)
{
#ifndef CONFIG_NO_BOOTMEM
    unsigned long bootmap_size, bootmap;

    bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
    bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
                 PAGE_SIZE);
    if (bootmap == -1L)
        panic("Cannot find bootmem map of size %ld\n", bootmap_size);
    reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
    /* don't touch min_low_pfn */
    bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
                     0, end_pfn);
    e820_register_active_regions(0, start_pfn, end_pfn);
    free_bootmem_with_active_regions(0, end_pfn);
#else
    e820_register_active_regions(0, start_pfn, end_pfn);
#endif
}
#endif

void __init paging_init(void)
{
    unsigned long max_zone_pfns[MAX_NR_ZONES];

    memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
    max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
    max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
    max_zone_pfns[ZONE_NORMAL] = max_pfn;

    sparse_memory_present_with_active_regions(MAX_NUMNODES);
    sparse_init();

    /*
     * clear the default setting with node 0
     * note: don't use nodes_clear here, that is really clearing when
     *     numa support is not compiled in, and later node_set_state
     *     will not set it back.
     */
    node_clear_state(0, N_NORMAL_MEMORY);

    free_area_init_nodes(max_zone_pfns);
}

然后，调用early_res_to_bootmem(), dma32_reserve_bootmem() 保留一部分页，不能交给boot allocator分配。为什么要这样做呢？前面free的页包括内核代码和数据占用的页，如果这些页也拿给boot
allocator的话，系统可能会崩溃，所以，要把这些页标记为保留。 x86_64_start_reservations()中调用reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"), 通过这种方式把要保留的地址段记录在early_res[]数组中，而early_res_to_bootmem()则根据early_res[]数组中记录的要保留的地址信息进行保留页操作。

void __init early_res_to_bootmem(u64 start, u64 end)
{
    int i, count;
    u64 final_start, final_end;
    int idx = 0;

    count = 0;
    for (i = 0; i < max_early_res && early_res[i].end; i++)
        count++;

    /* need to skip first one ?*/
    if (early_res != early_res_x)
        idx = 1;

    printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
             count - idx, max_early_res, start, end);
    for (i = idx; i < count; i++) {
        struct early_res *r = &early_res[i];
        printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i,
            r->start, r->end, r->name);
        final_start = max(start, r->start);
        final_end = min(end, r->end);
        if (final_start >= final_end) {
            printk(KERN_CONT "\n");
            continue;
        }
        printk(KERN_CONT " ==> [%010llx - %010llx]\n",
            final_start, final_end);
        reserve_bootmem_generic(final_start, final_end - final_start%2