Kernel 3.0.8 内存管理函数

1. 内存分配函数

相关代码如下：

#define alloc_pages(gfp_mask, order)   alloc_pages_node(numa_node_id(), gfp_mask, order)
#define alloc_page_vma(gfp_mask, vma, addr) alloc_pages(gfp_mask, 0)
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)

#define __get_free_page(gfp_mask)   __get_free_pages((gfp_mask),0)
#define __get_dma_pages(gfp_mask, order)   __get_free_pages((gfp_mask) | GFP_DMA,(order))

 #define pfn_to_page(pfn) (mem_map + ((pfn) - PHYS_PFN_OFFSET))
#define page_to_pfn(page) ((unsigned long)((page) - mem_map) + PHYS_PFN_OFFSET)
#define pfn_valid(pfn) ((pfn) >= PHYS_PFN_OFFSET && (pfn) < (PHYS_PFN_OFFSET + max_mapnr))

#define phys_to_page(phys) (pfn_to_page(phys >> PAGE_SHIFT))
#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT)

#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)

 

1）__get_free_pages实现代码如下，它返回页的虚拟地址：

unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
	struct page *page;

	/*
	 * __get_free_pages() returns a 32-bit address, which cannot represent
	 * a highmem page
	 */
	VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);

	page = alloc_pages(gfp_mask, order);
	if (!page)
		return 0;
	return (unsigned long) page_address(page);
}

 

/**
 * page_address - get the mapped virtual address of a page
 * @page: &struct page to get the virtual address of
 *
 * Returns the page's virtual address.
 */
void *page_address(struct page *page)
{
	unsigned long flags;
	void *ret;
	struct page_address_slot *pas;

	if (!PageHighMem(page))
		return lowmem_page_address(page);

	pas = page_slot(page);
	ret = NULL;
	spin_lock_irqsave(&pas->lock, flags);
	if (!list_empty(&pas->lh)) {
		struct page_address_map *pam;

		list_for_each_entry(pam, &pas->lh, list) {
			if (pam->page == page) {
				ret = pam->virtual;
				goto done;
			}
		}
	}
done:
	spin_unlock_irqrestore(&pas->lock, flags);
	return ret;
}

 

static __always_inline void *lowmem_page_address(struct page *page)
{
	return __va(PFN_PHYS(page_to_pfn(page)));
}

 

2）alloc_pages_node

static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
						unsigned int order)
{
	/* Unknown node is current node */
	if (nid < 0)
		nid = numa_node_id();

	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
}

参数nid是要分配内存的 NUMA节点 ID，
参数gfp_mask是 GFP_分配标志,
参数order是分配内存的大小(2^order个页面).
返回值是一个指向第一个(可能返回多个页)page结构的指针,失败时返回NULL。
 

static inline struct page *
__alloc_pages(gfp_t gfp_mask, unsigned int order,
		struct zonelist *zonelist)
{
	return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
}

 

/*
 * This is the 'heart' of the zoned buddy allocator.
 */
struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
			struct zonelist *zonelist, nodemask_t *nodemask)
{
	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
	struct zone *preferred_zone;
	struct page *page;
	int migratetype = allocflags_to_migratetype(gfp_mask);

	gfp_mask &= gfp_allowed_mask;

	lockdep_trace_alloc(gfp_mask);

	might_sleep_if(gfp_mask & __GFP_WAIT);

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

	/*
	 * Check the zones suitable for the gfp_mask contain at least one
	 * valid zone. It's possible to have an empty zonelist as a result
	 * of GFP_THISNODE and a memoryless node
	 */
	if (unlikely(!zonelist->_zonerefs->zone))
		return NULL;

	get_mems_allowed();
	/* The preferred zone is used for statistics later */
	first_zones_zonelist(zonelist, high_zoneidx,
				nodemask ? : &cpuset_current_mems_allowed,
				&preferred_zone);
	if (!preferred_zone) {
		put_mems_allowed();
		return NULL;
	}

	/* First allocation attempt */
	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
			zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET,
			preferred_zone, migratetype);
	if (unlikely(!page))
		page = __alloc_pages_slowpath(gfp_mask, order,
				zonelist, high_zoneidx, nodemask,
				preferred_zone, migratetype);
	put_mems_allowed();

	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
	return page;
}

其接下来的主要调用流程如下：

get_page_from_freelist->

buffered_rmqueue

3) buffered_rmqueue

     从区域zone中获取一块大小为2^order的物理内存块，返回该内存块的首个页框的描述符page。

 

static inline
struct page *buffered_rmqueue(struct zone *preferred_zone,
			struct zone *zone, int order, gfp_t gfp_flags,
			int migratetype)
{
	unsigned long flags;
	struct page *page;
	int cold = !!(gfp_flags & __GFP_COLD);

again:
	if (likely(order == 0)) { //获取一页物理内存(2^0),从当前cpu的高速缓存内存中申请
		struct per_cpu_pages *pcp;
		struct list_head *list;

		local_irq_save(flags);
		pcp = &this_cpu_ptr(zone->pageset)->pcp; //获取zone的当前处理器的高速缓存内存描述结构指针
		list = &pcp->lists[migratetype];
		if (list_empty(list)) { //高速缓存内存为空
			pcp->count += rmqueue_bulk(zone, 0,//调用此函数从伙伴系统中分配batch空闲内存到高速缓存内存中
					pcp->batch, list,
					migratetype, cold);
			if (unlikely(list_empty(list)))
				goto failed;
		}
                   //我们从pcp->list链表开始的第一个lru起，去寻找相应的struct page结构体
		if (cold)
			page = list_entry(list->prev, struct page, lru);
		else
			page = list_entry(list->next, struct page, lru);
                  //由于被分配出去了，所以高速缓存内存中不再包含这页内存，所以从链表里删除这一项。
		list_del(&page->lru);
		pcp->count--;  //相应的当前页数也要减少
	} else { //获取一块物理内存(2^order)
		if (unlikely(gfp_flags & __GFP_NOFAIL)) {
			/*
			 * __GFP_NOFAIL is not to be used in new code.
			 *
			 * All __GFP_NOFAIL callers should be fixed so that they
			 * properly detect and handle allocation failures.
			 *
			 * We most definitely don't want callers attempting to
			 * allocate greater than order-1 page units with
			 * __GFP_NOFAIL.
			 */
			WARN_ON_ONCE(order > 1);
		}
		spin_lock_irqsave(&zone->lock, flags);
		page = __rmqueue(zone, order, migratetype); //调用函数申请内存
		spin_unlock(&zone->lock);
		if (!page)
			goto failed;
		__mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
	}

	__count_zone_vm_events(PGALLOC, zone, 1 << order);
	zone_statistics(preferred_zone, zone, gfp_flags);
	local_irq_restore(flags);

	VM_BUG_ON(bad_range(zone, page));
	if (prep_new_page(page, order, gfp_flags))
		goto again;
	return page; //返回申请到的内存空间的首页内存页的struct page结构指针

failed:
	local_irq_restore(flags);
	return NULL;
}

4) rmqueue_bulk

 用于多次（count）内存申请.

/* 
 * Obtain a specified number of elements from the buddy allocator, all under
 * a single hold of the lock, for efficiency.  Add them to the supplied list.
 * Returns the number of new pages which were placed at *list.
 */
static int rmqueue_bulk(struct zone *zone, unsigned int order, 
			unsigned long count, struct list_head *list,
			int migratetype, int cold)
{
	int i;
	
	spin_lock(&zone->lock);
	for (i = 0; i < count; ++i) {
		struct page *page = __rmqueue(zone, order, migratetype);
		if (unlikely(page == NULL))
			break;

		/*
		 * Split buddy pages returned by expand() are received here
		 * in physical page order. The page is added to the callers and
		 * list and the list head then moves forward. From the callers
		 * perspective, the linked list is ordered by page number in
		 * some conditions. This is useful for IO devices that can
		 * merge IO requests if the physical pages are ordered
		 * properly.
		 */
		if (likely(cold == 0))
			list_add(&page->lru, list);
		else
			list_add_tail(&page->lru, list);
		set_page_private(page, migratetype);
		list = &page->lru;
	}
	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
	spin_unlock(&zone->lock);
	return i;
}

  

5) __rmqueue

 用于一次内存申请。

/*
 * Do the hard work of removing an element from the buddy allocator.
 * Call me with the zone->lock already held.
 */
static struct page *__rmqueue(struct zone *zone, unsigned int order,
						int migratetype)
{
	struct page *page;

retry_reserve:
	page = __rmqueue_smallest(zone, order, migratetype);

	if (unlikely(!page) && migratetype != MIGRATE_RESERVE) {
		page = __rmqueue_fallback(zone, order, migratetype);

		/*
		 * Use MIGRATE_RESERVE rather than fail an allocation. goto
		 * is used because __rmqueue_smallest is an inline function
		 * and we want just one call site
		 */
		if (!page) {
			migratetype = MIGRATE_RESERVE;
			goto retry_reserve;
		}
	}

	trace_mm_page_alloc_zone_locked(page, order, migratetype);
	return page;
}

 

 

2. 内存释放函数

相关宏定义如下：

#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr),0)