page_alloc.c

#ifdef CONFIG_NUMA
	memset(node_load, 0, sizeof(node_load));
#endif
	for_each_online_node(nid) {
		pg_data_t *pgdat = NODE_DATA(nid);

		build_zonelists(pgdat);
		build_zonelist_cache(pgdat);
	}

#ifdef CONFIG_MEMORY_HOTPLUG
	/* Setup real pagesets for the new zone */
	if (data) {
		struct zone *zone = data;
		setup_zone_pageset(zone);
	}
#endif

	/*
	 * Initialize the boot_pagesets that are going to be used
	 * for bootstrapping processors. The real pagesets for
	 * each zone will be allocated later when the per cpu
	 * allocator is available.
	 *
	 * boot_pagesets are used also for bootstrapping offline
	 * cpus if the system is already booted because the pagesets
	 * are needed to initialize allocators on a specific cpu too.
	 * F.e. the percpu allocator needs the page allocator which
	 * needs the percpu allocator in order to allocate its pagesets
	 * (a chicken-egg dilemma).
	 */
	for_each_possible_cpu(cpu) {
		setup_pageset(&per_cpu(boot_pageset, cpu), 0);

#ifdef CONFIG_HAVE_MEMORYLESS_NODES
		/*
		 * We now know the "local memory node" for each node--
		 * i.e., the node of the first zone in the generic zonelist.
		 * Set up numa_mem percpu variable for on-line cpus.  During
		 * boot, only the boot cpu should be on-line;  we'll init the
		 * secondary cpus' numa_mem as they come on-line.  During
		 * node/memory hotplug, we'll fixup all on-line cpus.
		 */
		if (cpu_online(cpu))
			set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
#endif
	}

	return 0;
}

/*
 * Called with zonelists_mutex held always
 * unless system_state == SYSTEM_BOOTING.
 */
void build_all_zonelists(void *data)
{
	set_zonelist_order();

	if (system_state == SYSTEM_BOOTING) {
		__build_all_zonelists(NULL);
		mminit_verify_zonelist();
		cpuset_init_current_mems_allowed();
	} else {
		/* we have to stop all cpus to guarantee there is no user
		   of zonelist */
		stop_machine(__build_all_zonelists, data, NULL);
		/* cpuset refresh routine should be here */
	}
	vm_total_pages = nr_free_pagecache_pages();
	/*
	 * Disable grouping by mobility if the number of pages in the
	 * system is too low to allow the mechanism to work. It would be
	 * more accurate, but expensive to check per-zone. This check is
	 * made on memory-hotadd so a system can start with mobility
	 * disabled and enable it later
	 */
	if (vm_total_pages < (pageblock_nr_pages * MIGRATE_TYPES))
		page_group_by_mobility_disabled = 1;
	else
		page_group_by_mobility_disabled = 0;

	printk("Built %i zonelists in %s order, mobility grouping %s.  "
		"Total pages: %ld\n",
			nr_online_nodes,
			zonelist_order_name[current_zonelist_order],
			page_group_by_mobility_disabled ? "off" : "on",
			vm_total_pages);
#ifdef CONFIG_NUMA
	printk("Policy zone: %s\n", zone_names[policy_zone]);
#endif
}

/*
 * Helper functions to size the waitqueue hash table.
 * Essentially these want to choose hash table sizes sufficiently
 * large so that collisions trying to wait on pages are rare.
 * But in fact, the number of active page waitqueues on typical
 * systems is ridiculously low, less than 200. So this is even
 * conservative, even though it seems large.
 *
 * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
 * waitqueues, i.e. the size of the waitq table given the number of pages.
 */
#define PAGES_PER_WAITQUEUE	256

#ifndef CONFIG_MEMORY_HOTPLUG
static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
{
	unsigned long size = 1;

	pages /= PAGES_PER_WAITQUEUE;

	while (size < pages)
		size <<= 1;

	/*
	 * Once we have dozens or even hundreds of threads sleeping
	 * on IO we've got bigger problems than wait queue collision.
	 * Limit the size of the wait table to a reasonable size.
	 */
	size = min(size, 4096UL);

	return max(size, 4UL);
}
#else
/*
 * A zone's size might be changed by hot-add, so it is not possible to determine
 * a suitable size for its wait_table.  So we use the maximum size now.
 *
 * The max wait table size = 4096 x sizeof(wait_queue_head_t).   ie:
 *
 *    i386 (preemption config)    : 4096 x 16 = 64Kbyte.
 *    ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte.
 *    ia64, x86-64 (preemption)   : 4096 x 24 = 96Kbyte.
 *
 * The maximum entries are prepared when a zone's memory is (512K + 256) pages
 * or more by the traditional way. (See above).  It equals:
 *
 *    i386, x86-64, powerpc(4K page size) : =  ( 2G + 1M)byte.
 *    ia64(16K page size)                 : =  ( 8G + 4M)byte.
 *    powerpc (64K page size)             : =  (32G +16M)byte.
 */
static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
{
	return 4096UL;
}
#endif

/*
 * This is an integer logarithm so that shifts can be used later
 * to extract the more random high bits from the multiplicative
 * hash function before the remainder is taken.
 */
static inline unsigned long wait_table_bits(unsigned long size)
{
	return ffz(~size);
}

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

/*
 * Mark a number of pageblocks as MIGRATE_RESERVE. The number
 * of blocks reserved is based on min_wmark_pages(zone). The memory within
 * the reserve will tend to store contiguous free pages. Setting min_free_kbytes
 * higher will lead to a bigger reserve which will get freed as contiguous
 * blocks as reclaim kicks in
 */
static void setup_zone_migrate_reserve(struct zone *zone)
{
	unsigned long start_pfn, pfn, end_pfn;
	struct page *page;
	unsigned long block_migratetype;
	int reserve;

	/* Get the start pfn, end pfn and the number of blocks to reserve */
	start_pfn = zone->zone_start_pfn;
	end_pfn = start_pfn + zone->spanned_pages;
	reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
							pageblock_order;

	/*
	 * Reserve blocks are generally in place to help high-order atomic
	 * allocations that are short-lived. A min_free_kbytes value that
	 * would result in more than 2 reserve blocks for atomic allocations
	 * is assumed to be in place to help anti-fragmentation for the
	 * future allocation of hugepages at runtime.
	 */
	reserve = min(2, reserve);

	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
		if (!pfn_valid(pfn))
			continue;
		page = pfn_to_page(pfn);

		/* Watch out for overlapping nodes */
		if (page_to_nid(page) != zone_to_nid(zone))
			continue;

		/* Blocks with reserved pages will never free, skip them. */
		if (PageReserved(page))
			continue;

		block_migratetype = get_pageblock_migratetype(page);

		/* If this block is reserved, account for it */
		if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
			reserve--;
			continue;
		}

		/* Suitable for reserving if this block is movable */
		if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
			set_pageblock_migratetype(page, MIGRATE_RESERVE);
			move_freepages_block(zone, page, MIGRATE_RESERVE);
			reserve--;
			continue;
		}

		/*
		 * If the reserve is met and this is a previous reserved block,
		 * take it back
		 */
		if (block_migratetype == MIGRATE_RESERVE) {
			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
			move_freepages_block(zone, page, MIGRATE_MOVABLE);
		}
	}
}

/*
 * Initially all pages are reserved - free ones are freed
 * up by free_all_bootmem() once the early boot process is
 * done. Non-atomic initialization, single-pass.
 */
void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
		unsigned long start_pfn, enum memmap_context context)
{
	struct page *page;
	unsigned long end_pfn = start_pfn + size;
	unsigned long pfn;
	struct zone *z;

	if (highest_memmap_pfn < end_pfn - 1)
		highest_memmap_pfn = end_pfn - 1;

	z = &NODE_DATA(nid)->node_zones[zone];
	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
		/*
		 * There can be holes in boot-time mem_map[]s
		 * handed to this function.  They do not
		 * exist on hotplugged memory.
		 */
		if (context == MEMMAP_EARLY) {
			if (!early_pfn_valid(pfn))
				continue;
			if (!early_pfn_in_nid(pfn, nid))
				continue;
		}
		page = pfn_to_page(pfn);
		set_page_links(page, zone, nid, pfn);
		mminit_verify_page_links(page, zone, nid, pfn);
		init_page_count(page);
		reset_page_mapcount(page);
		SetPageReserved(page);
		/*
		 * Mark the block movable so that blocks are reserved for
		 * movable at startup. This will force kernel allocations
		 * to reserve their blocks rather than leaking throughout
		 * the address space during boot when many long-lived
		 * kernel allocations are made. Later some blocks near
		 * the start are marked MIGRATE_RESERVE by
		 * setup_zone_migrate_reserve()
		 *
		 * bitmap is created for zone's valid pfn range. but memmap
		 * can be created for invalid pages (for alignment)
		 * check here not to call set_pageblock_migratetype() against
		 * pfn out of zone.
		 */
		if ((z->zone_start_pfn <= pfn)
		    && (pfn < z->zone_start_pfn + z->spanned_pages)
		    && !(pfn & (pageblock_nr_pages - 1)))
			set_pageblock_migratetype(page, MIGRATE_MOVABLE);

		INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
		/* The shift won't overflow because ZONE_NORMAL is below 4G. */
		if (!is_highmem_idx(zone))
			set_page_address(page, __va(pfn << PAGE_SHIFT));
#endif
	}
}

static void __meminit zone_init_free_lists(struct zone *zone)
{
	int order, t;
	for_each_migratetype_order(order, t) {
		INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
		zone->free_area[order].nr_free = 0;
	}
}

#ifndef __HAVE_ARCH_MEMMAP_INIT
#define memmap_init(size, nid, zone, start_pfn) \
	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
#endif

static int zone_batchsize(struct zone *zone)
{
#ifdef CONFIG_MMU
	int batch;

	/*
	 * The per-cpu-pages pools are set to around 1000th of the
	 * size of the zone.  But no more than 1/2 of a meg.
	 *
	 * OK, so we don't know how big the cache is.  So guess.
	 */
	batch = zone->present_pages / 1024;
	if (batch * PAGE_SIZE > 512 * 1024)
		batch = (512 * 1024) / PAGE_SIZE;
	batch /= 4;		/* We effectively *= 4 below */
	if (batch < 1)
		batch = 1;

	/*
	 * Clamp the batch to a 2^n - 1 value. Having a power
	 * of 2 value was found to be more likely to have
	 * suboptimal cache aliasing properties in some cases.
	 *
	 * For example if 2 tasks are alternately allocating
	 * batches of pages, one task can end up with a lot
	 * of pages of one half of the possible page colors
	 * and the other with pages of the other colors.
	 */
	batch = rounddown_pow_of_two(batch + batch/2) - 1;

	return batch;

#else
	/* The deferral and batching of frees should be suppressed under NOMMU
	 * conditions.
	 *
	 * The problem is that NOMMU needs to be able to allocate large chunks
	 * of contiguous memory as there's no hardware page translation to
	 * assemble apparent contiguous memory from discontiguous pages.
	 *
	 * Queueing large contiguous runs of pages for batching, however,
	 * causes the pages to actually be freed in smaller chunks.  As there
	 * can be a significant delay between the individual batches being
	 * recycled, this leads to the once large chunks of space being
	 * fragmented and becoming unavailable for high-order allocations.
	 */
	return 0;
#endif
}

static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
	struct per_cpu_pages *pcp;
	int migratetype;

	memset(p, 0, sizeof(*p));

	pcp = &p->pcp;
	pcp->count = 0;
	pcp->high = 6 * batch;
	pcp->batch = max(1UL, 1 * batch);
	for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
		INIT_LIST_HEAD(&pcp->lists[migratetype]);
}

/*
 * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist
 * to the value high for the pageset p.
 */

static void setup_pagelist_highmark(struct per_cpu_pageset *p,
				unsigned long high)
{
	struct per_cpu_pages *pcp;

	pcp = &p->pcp;
	pcp->high = high;
	pcp->batch = max(1UL, high/4);
	if ((high/4) > (PAGE_SHIFT * 8))
		pcp->batch = PAGE_SHIFT * 8;
}

static __meminit void setup_zone_pageset(struct zone *zone)
{
	int cpu;

	zone->pageset = alloc_percpu(struct per_cpu_pageset);

	for_each_possible_cpu(cpu) {
		struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);

		setup_pageset(pcp, zone_batchsize(zone));

		if (percpu_pagelist_fraction)
			setup_pagelist_highmark(pcp,
				(zone->present_pages /
					percpu_pagelist_fraction));
	}
}

/*
 * Allocate per cpu pagesets and initialize them.
 * Before this call only boot pagesets were available.
 */
void __init setup_per_cpu_pageset(void)
{
	struct zone *zone;

	for_each_populated_zone(zone)
		setup_zone_pageset(zone);
}

static noinline __init_refok
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
	int i;
	struct pglist_data *pgdat = zone->zone_pgdat;
	size_t alloc_size;

	/*
	 * The per-page waitqueue mechanism uses hashed waitqueues
	 * per zone.
	 */
	zone->wait_table_hash_nr_entries =
		 wait_table_hash_nr_entries(zone_size_pages);
	zone->wait_table_bits =
		wait_table_bits(zone->wait_table_hash_nr_entries);
	alloc_size = zone->wait_table_hash_nr_entries
					* sizeof(wait_queue_head_t);

	if (!slab_is_available()) {
		zone->wait_table = (wait_queue_head_t *)
			alloc_bootmem_node(pgdat, alloc_size);
	} else {
		/*
		 * This case means that a zone whose size was 0 gets new memory
		 * via memory hot-add.
		 * But it may be the case that a new node was hot-added.  In
		 * this case vmalloc() will not be able to use this new node's
		 * memory - this wait_table must be initialized to use this new
		 * node itself as well.
		 * To use this new node's memory, further consideration will be
		 * necessary.
		 */
		zone->wait_table = vmalloc(alloc_size);
	}
	if (!zone->wait_table)
		return -ENOMEM;

	for(i = 0; i < zone->wait_table_hash_nr_entries; ++i)
		init_waitqueue_head(zone->wait_table + i);

	return 0;
}

static int __zone_pcp_update(void *data)
{
	struct zone *zone = data;
	int cpu;
	unsigned long batch = zone_batchsize(zone), flags;

	for_each_possible_cpu(cpu) {
		struct per_cpu_pageset *pset;
		struct per_cpu_pages *pcp;

		pset = per_cpu_ptr(zone->pageset, cpu);
		pcp = &pset->pcp;

		local_irq_save(flags);
		free_pcppages_bulk(zone, pcp->count, pcp);
		setup_pageset(pset, batch);
		local_irq_restore(flags);
	}
	return 0;
}

void zone_pcp_update(struct zone *zone)
{
	stop_machine(__zone_pcp_update, zone, NULL);
}

static __meminit void zone_pcp_init(struct zone *zone)
{
	/*
	 * per cpu subsystem is not up at this point. The following code
	 * relies on the ability of the linker to provide the
	 * offset of a (static) per cpu variable into the per cpu area.
	 */
	zone->pageset = &boot_pageset;

	if (zone->present_pages)
		printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%u\n",
			zone->name, zone->present_pages,
					 zone_batchsize(zone));
}

__meminit int init_currently_empty_zone(struct zone *zone,
					unsigned long zone_start_pfn,
					unsigned long size,
					enum memmap_context context)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int ret;
	ret = zone_wait_table_init(zone, size);
	if (ret)
		return ret;
	pgdat->nr_zones = zone_idx(zone) + 1;

	zone->zone_start_pfn = zone_start_pfn;

	mminit_dprintk(MMINIT_TRACE, "memmap_init",
			"Initialising map node %d zone %lu pfns %lu -> %lu\n",
			pgdat->node_id,
			(unsigned long)zone_idx(zone),
			zone_start_pfn, (zone_start_pfn + size));

	zone_init_free_lists(zone);

	return 0;
}

#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
 * Basic iterator support. Return the first range of PFNs for a node
 * Note: nid == MAX_NUMNODES returns first region regardless of node
 */
static int __meminit first_active_region_index_in_nid(int nid)
{
	int i;

	for (i = 0; i < nr_nodemap_entries; i++)
		if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
			return i;

	return -1;
}

/*
 * Basic iterator support. Return the next active range of PFNs for a node
 * Note: nid == MAX_NUMNODES returns next region regardless of node
 */
static int __meminit next_active_region_index_in_nid(int index, int nid)
{
	for (index = index + 1; index < nr_nodemap_entries; index++)
		if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
			return index;

	return -1;
}

#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
/*
 * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
 * Architectures may implement their own version but if add_active_range()
 * was used and there are no special requirements, this is a convenient
 * alternative
 */
int __meminit __early_pfn_to_nid(unsigned long pfn)
{
	int i;

	for (i = 0; i < nr_nodemap_entries; i++) {
		unsigned long start_pfn = early_node_map[i].start_pfn;
		unsigned long end_pfn = early_node_map[i].end_pfn;

		if (start_pfn <= pfn && pfn < end_pfn)
			return early_node_map[i].nid;
	}
	/* This is a memory hole */
	return -1;
}
#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */

int __meminit early_pfn_to_nid(unsigned long pfn)
{
	int nid;

	nid = __early_pfn_to_nid(pfn);
	if (nid >= 0)
		return nid;
	/* just returns 0 */
	return 0;
}

#ifdef CONFIG_NODES_SPAN_OTHER_NODES
bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
	int nid;

	nid = __early_pfn_to_nid(pfn);
	if (nid >= 0 && nid != node)
		return false;
	return true;
}
#endif

/* Basic iterator support to walk early_node_map[] */
#define for_each_active_range_index_in_nid(i, nid) \
	for (i = first_active_region_index_in_nid(nid); i != -1; \
				i = next_active_region_index_in_nid(i, nid))

/**
 * free_bootmem_with_active_regions - Call free_bootmem_node for each active range
 * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
 * @max_low_pfn: The highest PFN that will be passed to free_bootmem_node
 *
 * If an architecture guarantees that all ranges registered with
 * add_active_ranges() contain no holes and may be freed, this
 * this function may be used instead of calling free_bootmem() manually.
 */
void __init free_bootmem_with_active_regions(int nid,
						unsigned long max_low_pfn)
{
	int i;

	for_each_active_range_index_in_nid(i, nid) {
		unsigned long size_pages = 0;
		unsigned long end_pfn = early_node_map[i].end_pfn;

		if (early_node_map[i].start_pfn >= max_low_pfn)
			continue;

		if (end_pfn > max_low_pfn)
			end_pfn = max_low_pfn;

		size_pages = end_pfn - early_node_map[i].start_pfn;
		free_bootmem_node(NODE_DATA(early_node_map[i].nid),
				PFN_PHYS(early_node_map[i].start_pfn),
				size_pages << PAGE_SHIFT);
	}
}

#ifdef CONFIG_HAVE_MEMBLOCK
u64 __init find_memory_core_early(int nid, u64 size, u64 align,
					u64 goal, u64 limit)
{
	int i;

	/* Need to go over early_node_map to find out good range for node */
	for_each_active_range_index_in_nid(i, nid) {
		u64 addr;
		u64 ei_start, ei_last;
		u64 final_start, final_end;

		ei_last = early_node_map[i].end_pfn;
		ei_last <<= PAGE_SHIFT;
		ei_start = early_node_map[i].start_pfn;
		ei_start <<= PAGE_SHIFT;

		final_start = max(ei_start, goal);
		final_end = min(ei_last, limit);

		if (final_start >= final_end)
			continue;

		addr = memblock_find_in_range(final_start, final_end, size, align);

		if (addr == MEMBLOCK_ERROR)
			continue;

		return addr;
	}

	return MEMBLOCK_ERROR;
}
#endif

int __init add_from_early_node_map(struct range *range, int az,
				   int nr_range, int nid)
{
	int i;
	u64 start, end;

	/* need to go over early_node_map to find out good range for node */
	for_each_active_range_index_in_nid(i, nid) {
		start = early_node_map[i].start_pfn;
		end = early_node_map[i].end_pfn;
		nr_range = add_range(range, az, nr_range, start, end);
	}
	return nr_range;
}

#ifdef CONFIG_NO_BOOTMEM
void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
					u64 goal, u64 limit)
{
	void *ptr;
	u64 addr;

	if (limit > memblock.current_limit)
		limit = memblock.current_limit;

	addr = find_memory_core_early(nid, size, align, goal, limit);

	if (addr == MEMBLOCK_ERROR)
		return NULL;

	ptr = phys_to_virt(addr);
	memset(ptr, 0, size);
	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
	/*
	 * The min_count is set to 0 so that bootmem allocated blocks
	 * are never reported as leaks.
	 */
	kmemleak_alloc(ptr, size, 0, 0);
	return ptr;
}
#endif


void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
{
	int i;
	int ret;

	for_each_active_range_index_in_nid(i, nid) {
		ret = work_fn(early_node_map[i].start_pfn,
			      early_node_map[i].end_pfn, data);
		if (ret)
			break;
	}
}
/**
 * sparse_memory_present_with_active_regions - Call memory_present for each active range
 * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
 *
 * If an architecture guarantees that all ranges registered with
 * add_active_ranges() contain no holes and may be freed, this
 * function may be used instead of calling memory_present() manually.
 */
void __init sparse_memory_present_with_active_regions(int nid)
{
	int i;

	for_each_active_range_index_in_nid(i, nid)
		memory_present(early_node_map[i].nid,
				early_node_map[i].start_pfn,
				early_node_map[i].end_pfn);
}

/**
 * get_pfn_range_for_nid - Return the start and end page frames for a node
 * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
 * @start_pfn: Passed by reference. On return, it will have the node start_pfn.
 * @end_pfn: Passed by reference. On return, it will have the node end_pfn.
 *
 * It returns the start and end page frame of a node based on information
 * provided by an arch calling add_active_range(). If called for a node
 * with no available memory, a warning is printed and the start and end
 * PFNs will be 0.
 */
void __meminit get_pfn_range_for_nid(unsigned int nid,
			unsigned long *start_pfn, unsigned long *end_pfn)
{
	int i;
	*start_pfn = -1UL;
	*end_pfn = 0;

	for_each_active_range_index_in_nid(i, nid) {
		*start_pfn = min(*start_pfn, early_node_map[i].start_pfn);
		*end_pfn = max(*end_pfn, early_node_map[i].end_pfn);
	}

	if (*start_pfn == -1UL)
		*start_pfn = 0;
}

/*
 * This finds a zone that can be used for ZONE_MOVABLE pages. The
 * assumption is made that zones within a node are ordered in monotonic
 * increasing memory addresses so that the "highest" populated zone is used
 */
static void __init find_usable_zone_for_movable(void)
{
	int zone_index;
	for (zone_index = MAX_NR_ZONES - 1; zone_index >= 0; zone_index--) {
		if (zone_index == ZONE_MOVABLE)
			continue;

		if (arch_zone_highest_possible_pfn[zone_index] >
				arch_zone_lowest_possible_pfn[zone_index])
			break;
	}

	VM_BUG_ON(zone_index == -1);
	movable_zone = zone_index;
}

/*
 * The zone ranges provided by the architecture do not include ZONE_MOVABLE
 * because it is sized independant of architecture. Unlike the other zones,
 * the starting point for ZONE_MOVABLE is not fixed. It may be different
 * in each node depending on the size of each node and how evenly kernelcore
 * is distributed. This helper function adjusts the zone ranges
 * provided by the architecture for a given node by using the end of the
 * highest usable zone for ZONE_MOVABLE. This preserves the assumption that
 * zones within a node are in order of monotonic increases memory addresses
 */
static void __meminit adjust_zone_range_for_zone_movable(int nid,
					unsigned long zone_type,
					unsigned long node_start_pfn,
					unsigned long node_end_pfn,
					unsigned long *zone_start_pfn,
					unsigned long *zone_end_pfn)
{
	/* Only adjust if ZONE_MOVABLE is on this node */
	if (zone_movable_pfn[nid]) {
		/* Size ZONE_MOVABLE */
		if (zone_type == ZONE_MOVABLE) {
			*zone_start_pfn = zone_movable_pfn[nid];
			*zone_end_pfn = min(node_end_pfn,
				arch_zone_highest_possible_pfn[movable_zone]);

		/* Adjust for ZONE_MOVABLE starting within this range */
		} else if (*zone_start_pfn < zone_movable_pfn[nid] &&
				*zone_end_pfn > zone_movable_pfn[nid]) {
			*zone_end_pfn = zone_movable_pfn[nid];

		/* Check if this whole range is within ZONE_MOVABLE */
		} else if (*zone_start_pfn >= zone_movable_pfn[nid])
			*zone_start_pfn = *zone_end_pfn;
	}
}

/*
 * Return the number of pages a zone spans in a node, including holes
 * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node()
 */
static unsigned long __meminit zone_spanned_pages_in_node(int nid,
					unsigned long zone_type,
					unsigned long *ignored)
{
	unsigned long node_start_pfn, node_end_pfn;
	unsigned long zone_start_pfn, zone_end_pfn;

	/* Get the start and end of the node and zone */
	get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
	zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
	zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
	adjust_zone_range_for_zone_movable(nid, zone_type,
				node_start_pfn, node_end_pfn,
				&zone_start_pfn, &zone_end_pfn);

	/* Check that this node has pages within the zone's required range */
	if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn)
		return 0;

	/* Move the zone boundaries inside the node if necessary */
	zone_end_pfn = min(zone_end_pfn, node_end_pfn);
	zone_start_pfn = max(zone_start_pfn, node_start_pfn);

	/* Return the spanned pages */
	return zone_end_pfn - zone_start_pfn;
}

/*
 * Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
 * then all holes in the requested range will be accounted for.
 */
unsigned long __meminit __absent_pages_in_range(int nid,
				unsigned long range_start_pfn,
				unsigned long range_end_pfn)
{
	int i = 0;
	unsigned long prev_end_pfn = 0, hole_pages = 0;
	unsigned long start_pfn;

	/* Find the end_pfn of the first active range of pfns in the node */
	i = first_active_region_index_in_nid(nid);
	if (i == -1)
		return 0;

	prev_end_pfn = min(early_node_map[i].start_pfn, range_end_pfn);

	/* Account for ranges before physical memory on this node */
	if (early_node_map[i].start_pfn > range_start_pfn)
		hole_pages = prev_end_pfn - range_start_pfn;

	/* Find all holes for the zone within the node */
	for (; i != -1; i = next_active_region_index_in_nid(i, nid)) {

		/* No need to continue if prev_end_pfn is outside the zone */
		if (prev_end_pfn >= range_end_pfn)
			break;

		/* Make sure the end of the zone is not within the hole */
		start_pfn = min(early_node_map[i].start_pfn, range_end_pfn);
		prev_end_pfn = max(prev_end_pfn, range_start_pfn);

		/* Update the hole size cound and move on */
		if (start_pfn > range_start_pfn) {
			BUG_ON(prev_end_pfn > start_pfn);
			hole_pages += start_pfn - prev_end_pfn;
		}
		prev_end_pfn = early_node_map[i].end_pfn;
	}

	/* Account for ranges past physical memory on this node */
	if (range_end_pfn > prev_end_pfn)
		hole_pages += range_end_pfn -
				max(range_start_pfn, prev_end_pfn);

	return hole_pages;
}

/**
 * absent_pages_in_range - Return number of page frames in holes within a range
 * @start_pfn: The start PFN to start searching for holes
 * @end_pfn: The end PFN to stop searching for holes
 *
 * It returns the number of pages frames in memory holes within a range.
 */
unsigned long __init absent_pages_in_range(unsigned long start_pfn,
							unsigned long end_pfn)
{
	return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn);
}

/* Return the number of page frames in holes in a zone on a node */
static unsigned long __meminit zone_absent_pages_in_node(int nid,
					unsigned long zone_type,
					unsigned long *ignored)
{
	unsigned long node_start_pfn, node_end_pfn;
	unsigned long zone_start_pfn, zone_end_pfn;

	get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
	zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type],
							node_start_pfn);
	zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type],
							node_end_pfn);

	adjust_zone_range_for_zone_movable(nid, zone_type,
			node_start_pfn, node_end_pfn,
			&zone_start_pfn, &zone_end_pfn);
	return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
}

#else
static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
					unsigned long zone_type,
					unsigned long *zones_size)
{
	return zones_size[zone_type];
}

static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
						unsigned long zone_type,
						unsigned long *zholes_size)
{
	if (!zholes_size)
		return 0;

	return zholes_size[zone_type];
}

#endif

static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
		unsigned long *zones_size, unsigned long *zholes_size)
{
	unsigned long realtotalpages, totalpages = 0;
	enum zone_type i;

	for (i = 0; i < MAX_NR_ZONES; i++)
		totalpages += zone_spanned_pages_in_node(pgdat->node_id, i,
								zones_size);
	pgdat->node_spanned_pages = totalpages;

	realtotalpages = totalpages;
	for (i = 0; i < MAX_NR_ZONES; i++)
		realtotalpages -=
			zone_absent_pages_in_node(pgdat->node_id, i,
								zholes_size);
	pgdat->node_present_pages = realtotalpages;
	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id,
							realtotalpages);
}

#ifndef CONFIG_SPARSEMEM
/*
 * Calculate the size of the zone->blockflags rounded to an unsigned long
 * Start by making sure zonesize is a multiple of pageblock_order by rounding
 * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally
 * round what is now in bits to nearest long in bits, then return it in
 * bytes.
 */
static unsigned long __init usemap_size(unsigned long zonesize)
{
	unsigned long usemapsize;

	usemapsize = roundup(zonesize, pageblock_nr_pages);
	usemapsize = usemapsize >> pageblock_order;