page_alloc.c

}

/* Construct the zonelist performance cache - see further mmzone.h */
static void build_zonelist_cache(pg_data_t *pgdat)
{
	int i;

	for (i = 0; i < MAX_NR_ZONES; i++) {
		struct zonelist *zonelist;
		struct zonelist_cache *zlc;
		struct zone **z;

		zonelist = pgdat->node_zonelists + i;
		zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
		for (z = zonelist->zones; *z; z++)
			zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*z);
	}
}


#else	/* CONFIG_NUMA */

static void set_zonelist_order(void)
{
	current_zonelist_order = ZONELIST_ORDER_ZONE;
}

static void build_zonelists(pg_data_t *pgdat)
{
	int node, local_node;
	enum zone_type i,j;

	local_node = pgdat->node_id;
	for (i = 0; i < MAX_NR_ZONES; i++) {
		struct zonelist *zonelist;

		zonelist = pgdat->node_zonelists + i;

 		j = build_zonelists_node(pgdat, zonelist, 0, i);
 		/*
 		 * Now we build the zonelist so that it contains the zones
 		 * of all the other nodes.
 		 * We don't want to pressure a particular node, so when
 		 * building the zones for node N, we make sure that the
 		 * zones coming right after the local ones are those from
 		 * node N+1 (modulo N)
 		 */
		for (node = local_node + 1; node < MAX_NUMNODES; node++) {
			if (!node_online(node))
				continue;
			j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
		}
		for (node = 0; node < local_node; node++) {
			if (!node_online(node))
				continue;
			j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
		}

		zonelist->zones[j] = NULL;
	}
}

/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
static void build_zonelist_cache(pg_data_t *pgdat)
{
	int i;

	for (i = 0; i < MAX_NR_ZONES; i++)
		pgdat->node_zonelists[i].zlcache_ptr = NULL;
}

#endif	/* CONFIG_NUMA */

/* return values int ....just for stop_machine_run() */
static int __build_all_zonelists(void *dummy)
{
	int nid;

	for_each_online_node(nid) {
		build_zonelists(NODE_DATA(nid));
		build_zonelist_cache(NODE_DATA(nid));
	}
	return 0;
}

void build_all_zonelists(void)
{
	set_zonelist_order();

	if (system_state == SYSTEM_BOOTING) {
		__build_all_zonelists(NULL);
		cpuset_init_current_mems_allowed();
	} else {
		/* we have to stop all cpus to guaranntee there is no user
		   of zonelist */
		stop_machine_run(__build_all_zonelists, NULL, NR_CPUS);
		/* cpuset refresh routine should be here */
	}
	vm_total_pages = nr_free_pagecache_pages();
	printk("Built %i zonelists in %s order.  Total pages: %ld\n",
			num_online_nodes(),
			zonelist_order_name[current_zonelist_order],
			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))

/*
 * 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;

	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);
		init_page_count(page);
		reset_page_mapcount(page);
		SetPageReserved(page);
		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 pglist_data *pgdat,
				struct zone *zone, unsigned long size)
{
	int order;
	for (order = 0; order < MAX_ORDER ; order++) {
		INIT_LIST_HEAD(&zone->free_area[order].free_list);
		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 __devinit zone_batchsize(struct zone *zone)
{
	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 = (1 << (fls(batch + batch/2)-1)) - 1;

	return batch;
}

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

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

	pcp = &p->pcp[0];		/* hot */
	pcp->count = 0;
	pcp->high = 6 * batch;
	pcp->batch = max(1UL, 1 * batch);
	INIT_LIST_HEAD(&pcp->list);

	pcp = &p->pcp[1];		/* cold*/
	pcp->count = 0;
	pcp->high = 2 * batch;
	pcp->batch = max(1UL, batch/2);
	INIT_LIST_HEAD(&pcp->list);
}

/*
 * 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[0]; /* hot list */
	pcp->high = high;
	pcp->batch = max(1UL, high/4);
	if ((high/4) > (PAGE_SHIFT * 8))
		pcp->batch = PAGE_SHIFT * 8;
}


#ifdef CONFIG_NUMA
/*
 * Boot pageset table. One per cpu which is going to be used for all
 * zones and all nodes. The parameters will be set in such a way
 * that an item put on a list will immediately be handed over to
 * the buddy list. This is safe since pageset manipulation is done
 * with interrupts disabled.
 *
 * Some NUMA counter updates may also be caught by the boot pagesets.
 *
 * The boot_pagesets must be kept even after bootup is complete for
 * unused processors and/or zones. They do play a role for bootstrapping
 * hotplugged processors.
 *
 * zoneinfo_show() and maybe other functions do
 * not check if the processor is online before following the pageset pointer.
 * Other parts of the kernel may not check if the zone is available.
 */
static struct per_cpu_pageset boot_pageset[NR_CPUS];

/*
 * Dynamically allocate memory for the
 * per cpu pageset array in struct zone.
 */
static int __cpuinit process_zones(int cpu)
{
	struct zone *zone, *dzone;

	for_each_zone(zone) {

		if (!populated_zone(zone))
			continue;

		zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
					 GFP_KERNEL, cpu_to_node(cpu));
		if (!zone_pcp(zone, cpu))
			goto bad;

		setup_pageset(zone_pcp(zone, cpu), zone_batchsize(zone));

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

	return 0;
bad:
	for_each_zone(dzone) {
		if (dzone == zone)
			break;
		kfree(zone_pcp(dzone, cpu));
		zone_pcp(dzone, cpu) = NULL;
	}
	return -ENOMEM;
}

static inline void free_zone_pagesets(int cpu)
{
	struct zone *zone;

	for_each_zone(zone) {
		struct per_cpu_pageset *pset = zone_pcp(zone, cpu);

		/* Free per_cpu_pageset if it is slab allocated */
		if (pset != &boot_pageset[cpu])
			kfree(pset);
		zone_pcp(zone, cpu) = NULL;
	}
}

static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
		unsigned long action,
		void *hcpu)
{
	int cpu = (long)hcpu;
	int ret = NOTIFY_OK;

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		if (process_zones(cpu))
			ret = NOTIFY_BAD;
		break;
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		free_zone_pagesets(cpu);
		break;
	default:
		break;
	}
	return ret;
}

static struct notifier_block __cpuinitdata pageset_notifier =
	{ &pageset_cpuup_callback, NULL, 0 };

void __init setup_per_cpu_pageset(void)
{
	int err;

	/* Initialize per_cpu_pageset for cpu 0.
	 * A cpuup callback will do this for every cpu
	 * as it comes online
	 */
	err = process_zones(smp_processor_id());
	BUG_ON(err);
	register_cpu_notifier(&pageset_notifier);
}

#endif

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 (system_state == SYSTEM_BOOTING) {
		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 = (wait_queue_head_t *)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 __meminit void zone_pcp_init(struct zone *zone)
{
	int cpu;
	unsigned long batch = zone_batchsize(zone);

	for (cpu = 0; cpu < NR_CPUS; cpu++) {
#ifdef CONFIG_NUMA
		/* Early boot. Slab allocator not functional yet */
		zone_pcp(zone, cpu) = &boot_pageset[cpu];
		setup_pageset(&boot_pageset[cpu],0);
#else
		setup_pageset(zone_pcp(zone,cpu), batch);
#endif
	}
	if (zone->present_pages)
		printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%lu\n",
			zone->name, zone->present_pages, batch);
}

__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;

	memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);

	zone_init_free_lists(pgdat, zone, zone->spanned_pages);

	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 regardles 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;
	}

	return 0;
}
#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */

/* 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);
	}
}

/**
 * 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);
}

/**
 * push_node_boundaries - Push node boundaries to at least the requested boundary
 * @nid: The nid of the node to push the boundary for
 * @start_pfn: The start pfn of the node
 * @end_pfn: The end pfn of the node
 *
 * In reserve-based hot-add, mem_map is allocated that is unused until hotadd
 * time. Specifically, on x86_64, SRAT will report ranges that can potentially
 * be hotplugged even though no physical memory exists. This function allows
 * an arch to push out the node boundaries so mem_map is allocated that can
 * be used later.
 */
#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
void __init push_node_boundaries(unsigned int nid,
		unsigned long start_pfn, unsigned long end_pfn)
{
	printk(KERN_DEBUG "Entering push_node_boundaries(%u, %lu, %lu)\n",
			nid, start_pfn, end_pfn);

	/* Initialise the boundary for this node if necessary */
	if (node_boundary_end_pfn[nid] == 0)
		node_boundary_start_pfn[nid] = -1UL;

	/* Update the boundaries */
	if (node_boundary_start_pfn[nid] > start_pfn)
		node_boundary_start_pfn[nid] = start_pfn;
	if (node_boundary_end_pfn[nid] < end_pfn)
		node_boundary_end_pfn[nid] = end_pfn;
}

/* If necessary, push the node boundary out for reserve hotadd */
static void __meminit account_node_boundary(unsigned int nid,
		unsigned long *start_pfn, unsigned long *end_pfn)
{
	printk(KERN_DEBUG "Entering account_node_boundary(%u, %lu, %lu)\n",
			nid, *start_pfn, *end_pfn);

	/* Return if boundary information has not been provided */
	if (node_boundary_end_pfn[nid] == 0)
		return;

	/* Check the boundaries and update if necessary */
	if (node_boundary_start_pfn[nid] < *start_pfn)
		*start_pfn = node_boundary_start_pfn[nid];
	if (node_boundary_end_pfn[nid] > *end_pfn)
		*end_pfn = node_boundary_end_pfn[nid];
}
#else
void __init push_node_boundaries(unsigned int nid,
		unsigned long start_pfn, unsigned long end_pfn) {}

static void __meminit account_node_boundary(unsigned int nid,
		unsigned long *start_pfn, unsigned long *end_pfn) {}
#endif


/**
 * 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) {
		printk(KERN_WARNING "Node %u active with no memory\n", nid);
		*start_pfn = 0;
	}

	/* Push the node boundaries out if requested */
	account_node_boundary(nid, start_pfn, end_pfn);
}

/*
 * 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
 */
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
 */
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);
}

/*
 * Set up the zone data structures:
 *   - mark all pages reserved
 *   - mark all memory queues empty
 *   - clear the memory bitmaps
 */
static void __meminit free_area_init_core(struct pglist_data *pgdat,
		unsigned long *zones_size, unsigned long *zholes_size)
{
	enum zone_type j;
	int nid = pgdat->node_id;
	unsigned long zone_start_pfn = pgdat->node_start_pfn;
	int ret;

	pgdat_resize_init(pgdat);
	pgdat->nr_zones = 0;
	init_waitqueue_head(&pgdat->kswapd_wait);
	pgdat->kswapd_max_order = 0;
	
	for (j = 0; j < MAX_NR_ZONES; j++) {
		struct zone *zone = pgdat->node_zones + j;
		unsigned long size, realsize, memmap_pages;

		size = zone_spanned_pages_in_node(nid, j, zones_size);
		realsize = size - zone_absent_pages_in_node(nid, j,
								zholes_size);

		/*
		 * Adjust realsize so that it accounts for how much memory
		 * is used by this zone for memmap. This affects the watermark
		 * and per-cpu initialisations
		 */
		memmap_pages = (size * sizeof(struct page)) >> PAGE_SHIFT;
		if (realsize >= memmap_pages) {
			realsize -= memmap_pages;
			printk(KERN_DEBUG
				"  %s zone: %lu pages used for memmap\n",
				zone_names[j], memmap_pages);
		} else
			printk(KERN_WARNING
				"  %s zone: %lu pages exceeds realsize %lu\n",
				zone_names[j], memmap_pages, realsize);

		/* Account for reserved pages */
		if (j == 0 && realsize > dma_reserve) {
			realsize -= dma_reserve;
			printk(KERN_DEBUG "  %s zone: %lu pages reserved\n",
					zone_names[0], dma_reserve);
		}

		if (!is_highmem_idx(j))
			nr_kernel_pages += realsize;
		nr_all_pages += realsize;

		zone->spanned_pages = size;
		zone->present_pages = realsize;
#ifdef CONFIG_NUMA
		zone->node = nid;
		zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio)
						/ 100;
		zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100;
#endif
		zone->name = zone_names[j];
		spin_lock_init(&zone->lock);
		spin_lock_init(&zone->lru_lock);
		zone_seqlock_init(zone);
		zone->zone_pgdat = pgdat;

		zone->prev_priority = DEF_PRIORITY;

		zone_pcp_init(zone);
		INIT_LIST_HEAD(&zone->active_list);
		INIT_LIST_HEAD(&zone->inactive_list);
		zone->nr_scan_active = 0;
		zone->nr_scan_inactive = 0;
		zap_zone_vm_stats(zone);
		atomic_set(&zone->reclaim_in_progress, 0);
		if (!size)
			continue;

		ret = init_currently_empty_zone(zone, zone_start_pfn,
						size, MEMMAP_EARLY);
		BUG_ON(ret);
		zone_start_pfn += size;
	}
}

static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
{
	/* Skip empty nodes */
	if (!pgdat->node_spanned_pages)
		return;

#ifdef CONFIG_FLAT_NODE_MEM_MAP
	/* ia64 gets its own node_mem_map, before this, without bootmem */
	if (!pgdat->node_mem_map) {
		unsigned long size, start, end;
		struct page *map;