page_alloc.c

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

		return NULL;

	/* Yield for kswapd, and try again */
	current->policy |= SCHED_YIELD;
	__set_current_state(TASK_RUNNING);
	schedule();
	goto rebalance;
}

/*
 * Common helper functions.
 */
unsigned long __get_free_pages(unsigned int gfp_mask, unsigned int order)
{
	struct page * page;

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

unsigned long get_zeroed_page(unsigned int gfp_mask)
{
	struct page * page;

	page = alloc_pages(gfp_mask, 0);
	if (page) {
		void *address = page_address(page);
		clear_page(address);
		return (unsigned long) address;
	}
	return 0;
}

void __free_pages(struct page *page, unsigned int order)
{
	if (!PageReserved(page) && put_page_testzero(page))
		__free_pages_ok(page, order);
}

void free_pages(unsigned long addr, unsigned int order)
{
	if (addr != 0)
		__free_pages(virt_to_page(addr), order);
}

/*
 * Total amount of free (allocatable) RAM:
 */
unsigned int nr_free_pages (void)
{
	unsigned int sum;
	zone_t *zone;
	pg_data_t *pgdat = pgdat_list;

	sum = 0;
	while (pgdat) {
		for (zone = pgdat->node_zones; zone < pgdat->node_zones + MAX_NR_ZONES; zone++)
			sum += zone->free_pages;
		pgdat = pgdat->node_next;
	}
	return sum;
}

/*
 * Amount of free RAM allocatable as buffer memory:
 */
unsigned int nr_free_buffer_pages (void)
{
	pg_data_t *pgdat = pgdat_list;
	unsigned int sum = 0;

	do {
		zonelist_t *zonelist = pgdat->node_zonelists + (GFP_USER & GFP_ZONEMASK);
		zone_t **zonep = zonelist->zones;
		zone_t *zone;

		for (zone = *zonep++; zone; zone = *zonep++) {
			unsigned long size = zone->size;
			unsigned long high = zone->pages_high;
			if (size > high)
				sum += size - high;
		}

		pgdat = pgdat->node_next;
	} while (pgdat);

	return sum;
}

#if CONFIG_HIGHMEM
unsigned int nr_free_highpages (void)
{
	pg_data_t *pgdat = pgdat_list;
	unsigned int pages = 0;

	while (pgdat) {
		pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;
		pgdat = pgdat->node_next;
	}
	return pages;
}
#endif

#define K(x) ((x) << (PAGE_SHIFT-10))

/*
 * Show free area list (used inside shift_scroll-lock stuff)
 * We also calculate the percentage fragmentation. We do this by counting the
 * memory on each free list with the exception of the first item on the list.
 */
void show_free_areas_core(pg_data_t *pgdat)
{
 	unsigned int order;
	unsigned type;
	pg_data_t *tmpdat = pgdat;

	printk("Free pages:      %6dkB (%6dkB HighMem)\n",
		K(nr_free_pages()),
		K(nr_free_highpages()));

	while (tmpdat) {
		zone_t *zone;
		for (zone = tmpdat->node_zones;
			       	zone < tmpdat->node_zones + MAX_NR_ZONES; zone++)
			printk("Zone:%s freepages:%6lukB min:%6lukB low:%6lukB " 
				       "high:%6lukB\n", 
					zone->name,
					K(zone->free_pages),
					K(zone->pages_min),
					K(zone->pages_low),
					K(zone->pages_high));
			
		tmpdat = tmpdat->node_next;
	}

	printk("( Active: %d, inactive: %d, free: %d )\n",
	       nr_active_pages,
	       nr_inactive_pages,
	       nr_free_pages());

	for (type = 0; type < MAX_NR_ZONES; type++) {
		struct list_head *head, *curr;
		zone_t *zone = pgdat->node_zones + type;
 		unsigned long nr, total, flags;

		total = 0;
		if (zone->size) {
			spin_lock_irqsave(&zone->lock, flags);
		 	for (order = 0; order < MAX_ORDER; order++) {
				head = &(zone->free_area + order)->free_list;
				curr = head;
				nr = 0;
				for (;;) {
					curr = memlist_next(curr);
					if (curr == head)
						break;
					nr++;
				}
				total += nr * (1 << order);
				printk("%lu*%lukB ", nr, K(1UL) << order);
			}
			spin_unlock_irqrestore(&zone->lock, flags);
		}
		printk("= %lukB)\n", K(total));
	}

#ifdef SWAP_CACHE_INFO
	show_swap_cache_info();
#endif	
}

void show_free_areas(void)
{
	show_free_areas_core(pgdat_list);
}

/*
 * Builds allocation fallback zone lists.
 */
static inline void build_zonelists(pg_data_t *pgdat)
{
	int i, j, k;

	for (i = 0; i <= GFP_ZONEMASK; i++) {
		zonelist_t *zonelist;
		zone_t *zone;

		zonelist = pgdat->node_zonelists + i;
		memset(zonelist, 0, sizeof(*zonelist));

		j = 0;
		k = ZONE_NORMAL;
		if (i & __GFP_HIGHMEM)
			k = ZONE_HIGHMEM;
		if (i & __GFP_DMA)
			k = ZONE_DMA;

		switch (k) {
			default:
				BUG();
			/*
			 * fallthrough:
			 */
			case ZONE_HIGHMEM:
				zone = pgdat->node_zones + ZONE_HIGHMEM;
				if (zone->size) {
#ifndef CONFIG_HIGHMEM
					BUG();
#endif
					zonelist->zones[j++] = zone;
				}
			case ZONE_NORMAL:
				zone = pgdat->node_zones + ZONE_NORMAL;
				if (zone->size)
					zonelist->zones[j++] = zone;
			case ZONE_DMA:
				zone = pgdat->node_zones + ZONE_DMA;
				if (zone->size)
					zonelist->zones[j++] = zone;
		}
		zonelist->zones[j++] = NULL;
	} 
}

#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))

/*
 * Set up the zone data structures:
 *   - mark all pages reserved
 *   - mark all memory queues empty
 *   - clear the memory bitmaps
 */
void __init free_area_init_core(int nid, pg_data_t *pgdat, struct page **gmap,
	unsigned long *zones_size, unsigned long zone_start_paddr, 
	unsigned long *zholes_size, struct page *lmem_map)
{
	struct page *p;
	unsigned long i, j;
	unsigned long map_size;
	unsigned long totalpages, offset, realtotalpages;
	const unsigned long zone_required_alignment = 1UL << (MAX_ORDER-1);

	if (zone_start_paddr & ~PAGE_MASK)
		BUG();

	totalpages = 0;
	for (i = 0; i < MAX_NR_ZONES; i++) {
		unsigned long size = zones_size[i];
		totalpages += size;
	}
	realtotalpages = totalpages;
	if (zholes_size)
		for (i = 0; i < MAX_NR_ZONES; i++)
			realtotalpages -= zholes_size[i];
			
	printk("On node %d totalpages: %lu\n", nid, realtotalpages);

	INIT_LIST_HEAD(&active_list);
	INIT_LIST_HEAD(&inactive_list);

	/*
	 * Some architectures (with lots of mem and discontinous memory
	 * maps) have to search for a good mem_map area:
	 * For discontigmem, the conceptual mem map array starts from 
	 * PAGE_OFFSET, we need to align the actual array onto a mem map 
	 * boundary, so that MAP_NR works.
	 */
	map_size = (totalpages + 1)*sizeof(struct page);
	if (lmem_map == (struct page *)0) {
		lmem_map = (struct page *) alloc_bootmem_node(pgdat, map_size);
		lmem_map = (struct page *)(PAGE_OFFSET + 
			MAP_ALIGN((unsigned long)lmem_map - PAGE_OFFSET));
	}
	*gmap = pgdat->node_mem_map = lmem_map;
	pgdat->node_size = totalpages;
	pgdat->node_start_paddr = zone_start_paddr;
	pgdat->node_start_mapnr = (lmem_map - mem_map);
	pgdat->nr_zones = 0;

	/*
	 * Initially all pages are reserved - free ones are freed
	 * up by free_all_bootmem() once the early boot process is
	 * done.
	 */
	for (p = lmem_map; p < lmem_map + totalpages; p++) {
		set_page_count(p, 0);
		SetPageReserved(p);
		init_waitqueue_head(&p->wait);
		memlist_init(&p->list);
	}

	offset = lmem_map - mem_map;	
	for (j = 0; j < MAX_NR_ZONES; j++) {
		zone_t *zone = pgdat->node_zones + j;
		unsigned long mask;
		unsigned long size, realsize;

		realsize = size = zones_size[j];
		if (zholes_size)
			realsize -= zholes_size[j];

		printk("zone(%lu): %lu pages.\n", j, size);
		zone->size = size;
		zone->name = zone_names[j];
		zone->lock = SPIN_LOCK_UNLOCKED;
		zone->zone_pgdat = pgdat;
		zone->free_pages = 0;
		zone->need_balance = 0;
		if (!size)
			continue;

		pgdat->nr_zones = j+1;

		mask = (realsize / zone_balance_ratio[j]);
		if (mask < zone_balance_min[j])
			mask = zone_balance_min[j];
		else if (mask > zone_balance_max[j])
			mask = zone_balance_max[j];
		zone->pages_min = mask;
		zone->pages_low = mask*2;
		zone->pages_high = mask*3;

		zone->zone_mem_map = mem_map + offset;
		zone->zone_start_mapnr = offset;
		zone->zone_start_paddr = zone_start_paddr;

		if ((zone_start_paddr >> PAGE_SHIFT) & (zone_required_alignment-1))
			printk("BUG: wrong zone alignment, it will crash\n");

		for (i = 0; i < size; i++) {
			struct page *page = mem_map + offset + i;
			page->zone = zone;
			if (j != ZONE_HIGHMEM)
				page->virtual = __va(zone_start_paddr);
			zone_start_paddr += PAGE_SIZE;
		}

		offset += size;
		for (i = 0; ; i++) {
			unsigned long bitmap_size;

			memlist_init(&zone->free_area[i].free_list);
			if (i == MAX_ORDER-1) {
				zone->free_area[i].map = NULL;
				break;
			}

			/*
			 * Page buddy system uses "index >> (i+1)",
			 * where "index" is at most "size-1".
			 *
			 * The extra "+3" is to round down to byte
			 * size (8 bits per byte assumption). Thus
			 * we get "(size-1) >> (i+4)" as the last byte
			 * we can access.
			 *
			 * The "+1" is because we want to round the
			 * byte allocation up rather than down. So
			 * we should have had a "+7" before we shifted
			 * down by three. Also, we have to add one as
			 * we actually _use_ the last bit (it's [0,n]
			 * inclusive, not [0,n[).
			 *
			 * So we actually had +7+1 before we shift
			 * down by 3. But (n+8) >> 3 == (n >> 3) + 1
			 * (modulo overflows, which we do not have).
			 *
			 * Finally, we LONG_ALIGN because all bitmap
			 * operations are on longs.
			 */
			bitmap_size = (size-1) >> (i+4);
			bitmap_size = LONG_ALIGN(bitmap_size+1);
			zone->free_area[i].map = 
			  (unsigned long *) alloc_bootmem_node(pgdat, bitmap_size);
		}
	}
	build_zonelists(pgdat);
}

void __init free_area_init(unsigned long *zones_size)
{
	free_area_init_core(0, &contig_page_data, &mem_map, zones_size, 0, 0, 0);
}

static int __init setup_mem_frac(char *str)
{
	int j = 0;

	while (get_option(&str, &zone_balance_ratio[j++]) == 2);
	printk("setup_mem_frac: ");
	for (j = 0; j < MAX_NR_ZONES; j++) printk("%d  ", zone_balance_ratio[j]);
	printk("\n");
	return 1;
}

__setup("memfrac=", setup_mem_frac);