Linux伙伴系统初始化

上一篇文章记述了node和zone初始化的基本流程。本篇记录一下伙伴系统初始化。

跟伙伴系统相关的数据结构

struct zone {
...
    /* free areas of different sizes */
	struct free_area	free_area[MAX_ORDER];
...
}

struct free_area {
	struct list_head	free_list[MIGRATE_TYPES];
	unsigned long		nr_free;
};

enum migratetype {
	MIGRATE_UNMOVABLE,
	MIGRATE_MOVABLE,
	MIGRATE_RECLAIMABLE,
	MIGRATE_PCPTYPES,	/* the number of types on the pcp lists */
	MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES,
#ifdef CONFIG_CMA
	/*
	 * MIGRATE_CMA migration type is designed to mimic the way
	 * ZONE_MOVABLE works.  Only movable pages can be allocated
	 * from MIGRATE_CMA pageblocks and page allocator never
	 * implicitly change migration type of MIGRATE_CMA pageblock.
	 *
	 * The way to use it is to change migratetype of a range of
	 * pageblocks to MIGRATE_CMA which can be done by
	 * __free_pageblock_cma() function.  What is important though
	 * is that a range of pageblocks must be aligned to
	 * MAX_ORDER_NR_PAGES should biggest page be bigger then
	 * a single pageblock.
	 */
	MIGRATE_CMA,
#endif
#ifdef CONFIG_MEMORY_ISOLATION
	MIGRATE_ISOLATE,	/* can't allocate from here */
#endif
	MIGRATE_TYPES
};

 这个migrate_type是为了内存反碎片化而引入的。以前最重要的是MIGRATE_MOVABLE,MIGRATE_RECLAIMABLE，cma是近两年引入的。

linux内存初始化：

asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
{
	...
    //跟架构相关，zone，node初始化
	setup_arch(&command_line);
	...

    //zonelists 初始化
	build_all_zonelists(NULL);
	page_alloc_init();

	...
    // 伙伴系统初始化
	mm_init();

	...
}

在mm_init()之前free_area已经初始化了，只不过nr_page都初始化为0了。

 

/*
 * mem_init() marks the free areas in the mem_map and tells us how much memory
 * is free.  This is done after various parts of the system have claimed their
 * memory after the kernel image.
 */
void __init mem_init(void)
{
	...
    /* this will put all unused low memory onto the freelists */
	memblock_free_all();

	...
}

/**
 * memblock_free_all - release free pages to the buddy allocator
 *
 * Return: the number of pages actually released.
 */
unsigned long __init memblock_free_all(void)
{
	unsigned long pages;

	free_unused_memmap();
	reset_all_zones_managed_pages();

	pages = free_low_memory_core_early();
	totalram_pages_add(pages);

	return pages;
}

static unsigned long __init free_low_memory_core_early(void)
{
	unsigned long count = 0;
	phys_addr_t start, end;
	u64 i;

	memblock_clear_hotplug(0, -1);

	for_each_reserved_mem_range(i, &start, &end)
		reserve_bootmem_region(start, end);

	/*
	 * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id
	 *  because in some case like Node0 doesn't have RAM installed
	 *  low ram will be on Node1
	 */
	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
				NULL)
		count += __free_memory_core(start, end);

	return count;
}

通过for_each_free_mem_range遍历memblock中的memory bank，然后通过__free_memory_core释放给buddy system。该函数会调用__free_pages_memory。

static void __init __free_pages_memory(unsigned long start, unsigned long end)
{
	int order;

	while (start < end) {
		order = min(MAX_ORDER - 1UL, __ffs(start));

		while (start + (1UL << order) > end)
			order--;

		memblock_free_pages(pfn_to_page(start), start, order);

		start += (1UL << order);
	}
}

可以看出，页是按照order进行释放的，并非一页一页。最终会引导页在free_lists中按照order组织。

memblock_free_pages->__free_pages_core->free_pages_ok

static void __free_pages_ok(struct page *page, unsigned int order,
			    fpi_t fpi_flags)
{
	unsigned long flags;
	int migratetype;
	unsigned long pfn = page_to_pfn(page);

	if (!free_pages_prepare(page, order, true))
		return;

    //从page中获取迁移类型
	migratetype = get_pfnblock_migratetype(page, pfn);
	local_irq_save(flags);
	__count_vm_events(PGFREE, 1 << order);

    // 按照order和迁移类型组织page
	free_one_page(page_zone(page), page, pfn, order, migratetype,
		      fpi_flags);
	local_irq_restore(flags);
}

除了order，page还需要按照迁移类型进行组织。最终将页释放给buddy system的是__free_one_page。free_one_page会调用__free_one_page。__free_one_page就是buddy system的释放页的函数。也就是在初始化buddy system时就是用的伙伴系统的释放页所用的函数，因为两者都是将页还给伙伴系统。具体组织页的细节比较复杂，最终形成的结构大约是这样。

-----图片转自《奔跑吧，linux kernel》