【linux kernel】linux内存管理 | 释放内存页面

一、简介

​ linux内核中释放页面的核心函数是free_page()。该函数最后会调用__free_pages()函数。本文将分析该该函数。

二、__free_pages函数

​ __free_pages函数定义如下（/mm/page_alloc.c）：

void __free_pages(struct page *page, unsigned int order)
{
	if (put_page_testzero(page)) {
		if (order == 0)
			free_hot_cold_page(page, false);
		else
			__free_pages_ok(page, order);
	}
}

由以上代码可知，根据order是否等于0分为两个执行流：

（1）free_hot_cold_page(page, false)执行流

（2）__free_pages_ok(page, order)执行流

（2-1）free_hot_cold_page()执行流

​ （【注】该执行流属于特殊情况）

free_hot_cold_page()函数定义如下（/mm/page_alloc.c）:

void free_hot_cold_page(struct page *page, bool cold)
{
	struct zone *zone = page_zone(page);
	struct per_cpu_pages *pcp;
	unsigned long flags;
    //从page中计算出pfn
	unsigned long pfn = page_to_pfn(page);
	int migratetype;

	if (!free_pages_prepare(page, 0))
		return;
	//获取pfnblock的页面类型
	migratetype = get_pfnblock_migratetype(page, pfn);
    //设置freepage的页面类型
	set_freepage_migratetype(page, migratetype);
	local_irq_save(flags);
	__count_vm_event(PGFREE);

	/*
	 * We only track unmovable, reclaimable and movable on pcp lists.
	 * Free ISOLATE pages back to the allocator because they are being
	 * offlined but treat RESERVE as movable pages so we can get those
	 * areas back if necessary. Otherwise, we may have to free
	 * excessively into the page allocator
	 */
	if (migratetype >= MIGRATE_PCPTYPES) {
		if (unlikely(is_migrate_isolate(migratetype))) {
		    //释放内存页面
			free_one_page(zone, page, pfn, 0, migratetype);
			goto out;
		}
		migratetype = MIGRATE_MOVABLE;
	}

	pcp = &this_cpu_ptr(zone->pageset)->pcp;
	if (!cold)
		list_add(&page->lru, &pcp->lists[migratetype]);
	else
		list_add_tail(&page->lru, &pcp->lists[migratetype]);
	pcp->count++;
	if (pcp->count >= pcp->high) {
		unsigned long batch = READ_ONCE(pcp->batch);
        //从PCP链表中释放一定数量的页面
		free_pcppages_bulk(zone, batch, pcp);
		pcp->count -= batch;
	}

out:
	local_irq_restore(flags);
}

以上代码片段中，出现了struct per_cpu_pages结构体，该结构体定义如下：

struct per_cpu_pages {
	int count;		/* number of pages in the list */
	int high;		/* high watermark, emptying needed */
	int batch;		/* chunk size for buddy add/remove */

	/* Lists of pages, one per migrate type stored on the pcp-lists */
	struct list_head lists[MIGRATE_PCPTYPES];
};

• count：表示list中page数量。
• hign：高水位值。用于指示当缓存中的页面高于该水位值时，将回收页面到伙伴系统。
• batch：表示一次回收到伙伴系统的页面数量。（batch值是通过zone_batchsize()函数计算得出的）

zone_batchsize()函数定义如下（/mm/page_alloc.c）：

static int zone_batchsize(struct zone *zone)
{
#ifdef CONFIG_MMU
	int batch;
	batch = zone->managed_pages / 1024;
	if (batch * PAGE_SIZE > 512 * 1024)
		batch = (512 * 1024) / PAGE_SIZE;
	batch /= 4;		/* We effectively *= 4 below */
	if (batch < 1)
		batch = 1;
	batch = rounddown_pow_of_two(batch + batch/2) - 1;
	return batch;
#else
	return 0;
#endif
}

---

以下代码中，如果cold为false，页面将以堆栈方式释放到per_cpu_page->list对应链表中；如果cold为true，页面以队列方式释放到per_cpu_page->list对应链表中。

if (!cold)
	list_add(&page->lru, &pcp->lists[migratetype]);
else
	list_add_tail(&page->lru, &pcp->lists[migratetype]);

（2-2）__free_pages_ok()执行流

​ （【注】该执行流属于正常情况）

__free_pages_ok()函数定义如下（/mm/page_alloc.c）：

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

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

	migratetype = get_pfnblock_migratetype(page, pfn);
	local_irq_save(flags);
	__count_vm_events(PGFREE, 1 << order);
	set_freepage_migratetype(page, migratetype);
	free_one_page(page_zone(page), page, pfn, order, migratetype);
	local_irq_restore(flags);
}

以上代码中，调用free_one_page()函数来释放页面。该函数将调用__free_one_page()来执行核心操作。这个函数功能比较强大，不仅释放内存页面到伙伴系统，而且还将处理空闲页面的合并工作。具体定义如下（/mm/page_alloc.c）：

static inline void __free_one_page(struct page *page,
		unsigned long pfn,
		struct zone *zone, unsigned int order,
		int migratetype)
{
	unsigned long page_idx;
	unsigned long combined_idx;
	unsigned long uninitialized_var(buddy_idx);
	struct page *buddy;
	int max_order = MAX_ORDER;

	VM_BUG_ON(!zone_is_initialized(zone));
	VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);

	VM_BUG_ON(migratetype == -1);
	if (is_migrate_isolate(migratetype)) {
		/*
		 * We restrict max order of merging to prevent merge
		 * between freepages on isolate pageblock and normal
		 * pageblock. Without this, pageblock isolation
		 * could cause incorrect freepage accounting.
		 */
		max_order = min(MAX_ORDER, pageblock_order + 1);
	} else {
		__mod_zone_freepage_state(zone, 1 << order, migratetype);
	}

	page_idx = pfn & ((1 << max_order) - 1);

	VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
	VM_BUG_ON_PAGE(bad_range(zone, page), page);

	while (order < max_order - 1) {
		buddy_idx = __find_buddy_index(page_idx, order);
		buddy = page + (buddy_idx - page_idx);
		if (!page_is_buddy(page, buddy, order))
			break;
		/*
		 * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
		 * merge with it and move up one order.
		 */
		if (page_is_guard(buddy)) {
			clear_page_guard(zone, buddy, order, migratetype);
		} else {
			list_del(&buddy->lru);
			zone->free_area[order].nr_free--;
			rmv_page_order(buddy);
		}
		combined_idx = buddy_idx & page_idx;
		page = page + (combined_idx - page_idx);
		page_idx = combined_idx;
		order++;
	}
	set_page_order(page, order);

	/*
	 * If this is not the largest possible page, check if the buddy
	 * of the next-highest order is free. If it is, it's possible
	 * that pages are being freed that will coalesce soon. In case,
	 * that is happening, add the free page to the tail of the list
	 * so it's less likely to be used soon and more likely to be merged
	 * as a higher order page
	 */
	if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) {
		struct page *higher_page, *higher_buddy;
		combined_idx = buddy_idx & page_idx;
		higher_page = page + (combined_idx - page_idx);
		buddy_idx = __find_buddy_index(combined_idx, order + 1);
		higher_buddy = higher_page + (buddy_idx - combined_idx);
		if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
			list_add_tail(&page->lru,
				&zone->free_area[order].free_list[migratetype]);
			goto out;
		}
	}

	list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
out:
	zone->free_area[order].nr_free++;
}

以上代码功能主要有两个：1、释放页面到伙伴系统。2、合并空闲内存块。

（1）【释放页面到伙伴系统】：将页面添加到伙伴系统中适当的free_area链表中。

（2）【合并空闲内存块】：当在释放内存块的时候，会查询相邻内存块是否空闲，如果存在空闲的内存块，那么将合并这两个内存块成为一个更大的内存块，并将其放置到高阶free_area空闲链表中。该过程是一个循环过程，直到所有可能合并的内存块合并完成后才结束循环。