内存快速分配和慢速分配

内存快速分配和慢速分配

内存页面的分配最终都交由伙伴系统的页面分配器。页面分配的函数在内核有各种各样的实现，但最终都会调用一个共同的接口：：__alloc_pages_nodemask()

常见的页面分配的API

__alloc_pages_node  /*返回struct page的指针*/
    __alloc_pages
    	__alloc_pages_nodemask

alloc_pages         /*返回struct page的指针*/
    alloc_pages_current
    	__alloc_pages_nodemask
        
__get_free_pages    /*返回页面的虚拟地址*/
    __get_free_pages
    	alloc_pages
            alloc_pages_current
            	__alloc_pages_nodemask

他们最终都调用了__alloc_pages_nodemask。

伙伴系统的心脏

__alloc_pages_nodemask()是伙伴系统的心脏

struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
							nodemask_t *nodemask)
{
   
	struct page *page;
	unsigned int alloc_flags = ALLOC_WMARK_LOW;
	gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */
	struct alloc_context ac = {
    };

	/*
	 * There are several places where we assume that the order value is sane
	 * so bail out early if the request is out of bound.
	 */
	if (unlikely(order >= MAX_ORDER)) {
   //请求页的阶数超过了最大阶数就失败了
		WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
		return NULL;
	}

	gfp_mask &= gfp_allowed_mask;
	alloc_mask = gfp_mask;
	if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags))
		return NULL;

	finalise_ac(gfp_mask, &ac);

	/*
	 * Forbid the first pass from falling back to types that fragment
	 * memory until all local zones are considered.
	 */
	alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp_mask);	

	/* First allocation attempt */
	page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
	if (likely(page))
		goto out;

	/*
	 * Apply scoped allocation constraints. This is mainly about GFP_NOFS
	 * resp. GFP_NOIO which has to be inherited for all allocation requests
	 * from a particular context which has been marked by
	 * memalloc_no{fs,io}_{save,restore}.
	 */
	alloc_mask = current_gfp_context(gfp_mask);
	ac.spread_dirty_pages = false;

	/*
	 * Restore the original nodemask if it was potentially replaced with
	 * &cpuset_current_mems_allowed to optimize the fast-path attempt.
	 */
	if (unlikely(ac.nodemask != nodemask))
		ac.nodemask = nodemask;

	page = __alloc_pages_slowpath(alloc_mask, order, &ac);

out:
	if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
	    unlikely(__memcg_kmem_charge(page, gfp_mask, order) != 0)) {
   
		__free_pages(page, order);
		page = NULL;
	}

	trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype);

	return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);

通过上述源码其实可以总结出__alloc_pages_nodemask它的核心其实是做了3件事：

prepare_alloc_context   //1.准备参数
alloc_flags_nofragment  //2.根据区域和gfp掩码请求添加分配标志
get_page_from_freelist  //3.快路径尝试分配内存 
__alloc_pages_slowpath  //4.慢路径尝试分配内存

prepare_alloc_context

static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
		int preferred_nid, nodemask_t *nodemask,
		struct alloc_context *ac, gfp_t *alloc_mask,
		unsigned int *alloc_flags)
{
	ac->high_zoneidx = gfp_zone(gfp_mask);
	ac->zonelist = node_zonelist(preferred_nid, gfp_mask);
	ac->nodemask = nodemask;
	ac->migratetype = gfpflags_to_migratetype(gfp_mask);

	if (cpusets_enabled()) {
		*alloc_mask |= __GFP_HARDWALL;
		if (!ac->nodemask)
			ac->nodemask = &cpuset_current_mems_allowed;
		else
			*alloc_flags |= ALLOC_CPUSET;
	}

	fs_reclaim_acquire(gfp_mask);
	fs_reclaim_release(gfp_mask);

	might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);

	if (should_fail_alloc_page(gfp_mask, order))
		return false;

	if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
		*alloc_flags |= ALLOC_CMA;

	return true;

prepare_alloc_context它主要是做了如下的事情：

1.填充alloc_context结构体

2.对gfp掩码做处理存放在alloc_mask中

3.填充alloc_flags字段

他做完预备工作之后，执行finalise_ac获得可分配的内存域zone。

alloc_flags_nofragment

static inline unsigned int
alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
{
   
	unsigned int alloc_flags = 0;

	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
		alloc_flags |= ALLOC_KSWAPD;

#ifdef CONFIG_ZONE_DMA32
	if (!zone)
		return alloc_flags;

	if (zone_idx(zone) != ZONE_NORMAL)
		return alloc_flags;

	/*
	 * If ZONE_DMA32 exi