page_alloc.c

	int i, nid;
	unsigned long usable_startpfn;
	unsigned long kernelcore_node, kernelcore_remaining;
	unsigned long totalpages = early_calculate_totalpages();
	int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);

	/*
	 * If movablecore was specified, calculate what size of
	 * kernelcore that corresponds so that memory usable for
	 * any allocation type is evenly spread. If both kernelcore
	 * and movablecore are specified, then the value of kernelcore
	 * will be used for required_kernelcore if it's greater than
	 * what movablecore would have allowed.
	 */
	if (required_movablecore) {
		unsigned long corepages;

		/*
		 * Round-up so that ZONE_MOVABLE is at least as large as what
		 * was requested by the user
		 */
		required_movablecore =
			roundup(required_movablecore, MAX_ORDER_NR_PAGES);
		corepages = totalpages - required_movablecore;

		required_kernelcore = max(required_kernelcore, corepages);
	}

	/* If kernelcore was not specified, there is no ZONE_MOVABLE */
	if (!required_kernelcore)
		return;

	/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
	find_usable_zone_for_movable();
	usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];

restart:
	/* Spread kernelcore memory as evenly as possible throughout nodes */
	kernelcore_node = required_kernelcore / usable_nodes;
	for_each_node_state(nid, N_HIGH_MEMORY) {
		/*
		 * Recalculate kernelcore_node if the division per node
		 * now exceeds what is necessary to satisfy the requested
		 * amount of memory for the kernel
		 */
		if (required_kernelcore < kernelcore_node)
			kernelcore_node = required_kernelcore / usable_nodes;

		/*
		 * As the map is walked, we track how much memory is usable
		 * by the kernel using kernelcore_remaining. When it is
		 * 0, the rest of the node is usable by ZONE_MOVABLE
		 */
		kernelcore_remaining = kernelcore_node;

		/* Go through each range of PFNs within this node */
		for_each_active_range_index_in_nid(i, nid) {
			unsigned long start_pfn, end_pfn;
			unsigned long size_pages;

			start_pfn = max(early_node_map[i].start_pfn,
						zone_movable_pfn[nid]);
			end_pfn = early_node_map[i].end_pfn;
			if (start_pfn >= end_pfn)
				continue;

			/* Account for what is only usable for kernelcore */
			if (start_pfn < usable_startpfn) {
				unsigned long kernel_pages;
				kernel_pages = min(end_pfn, usable_startpfn)
								- start_pfn;

				kernelcore_remaining -= min(kernel_pages,
							kernelcore_remaining);
				required_kernelcore -= min(kernel_pages,
							required_kernelcore);

				/* Continue if range is now fully accounted */
				if (end_pfn <= usable_startpfn) {

					/*
					 * Push zone_movable_pfn to the end so
					 * that if we have to rebalance
					 * kernelcore across nodes, we will
					 * not double account here
					 */
					zone_movable_pfn[nid] = end_pfn;
					continue;
				}
				start_pfn = usable_startpfn;
			}

			/*
			 * The usable PFN range for ZONE_MOVABLE is from
			 * start_pfn->end_pfn. Calculate size_pages as the
			 * number of pages used as kernelcore
			 */
			size_pages = end_pfn - start_pfn;
			if (size_pages > kernelcore_remaining)
				size_pages = kernelcore_remaining;
			zone_movable_pfn[nid] = start_pfn + size_pages;

			/*
			 * Some kernelcore has been met, update counts and
			 * break if the kernelcore for this node has been
			 * satisified
			 */
			required_kernelcore -= min(required_kernelcore,
								size_pages);
			kernelcore_remaining -= size_pages;
			if (!kernelcore_remaining)
				break;
		}
	}

	/*
	 * If there is still required_kernelcore, we do another pass with one
	 * less node in the count. This will push zone_movable_pfn[nid] further
	 * along on the nodes that still have memory until kernelcore is
	 * satisified
	 */
	usable_nodes--;
	if (usable_nodes && required_kernelcore > usable_nodes)
		goto restart;

	/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
	for (nid = 0; nid < MAX_NUMNODES; nid++)
		zone_movable_pfn[nid] =
			roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
}

/* Any regular memory on that node ? */
static void check_for_regular_memory(pg_data_t *pgdat)
{
#ifdef CONFIG_HIGHMEM
	enum zone_type zone_type;

	for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
		struct zone *zone = &pgdat->node_zones[zone_type];
		if (zone->present_pages)
			node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
	}
#endif
}

/**
 * free_area_init_nodes - Initialise all pg_data_t and zone data
 * @max_zone_pfn: an array of max PFNs for each zone
 *
 * This will call free_area_init_node() for each active node in the system.
 * Using the page ranges provided by add_active_range(), the size of each
 * zone in each node and their holes is calculated. If the maximum PFN
 * between two adjacent zones match, it is assumed that the zone is empty.
 * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed
 * that arch_max_dma32_pfn has no pages. It is also assumed that a zone
 * starts where the previous one ended. For example, ZONE_DMA32 starts
 * at arch_max_dma_pfn.
 */
void __init free_area_init_nodes(unsigned long *max_zone_pfn)
{
	unsigned long nid;
	int i;

	/* Sort early_node_map as initialisation assumes it is sorted */
	sort_node_map();

	/* Record where the zone boundaries are */
	memset(arch_zone_lowest_possible_pfn, 0,
				sizeof(arch_zone_lowest_possible_pfn));
	memset(arch_zone_highest_possible_pfn, 0,
				sizeof(arch_zone_highest_possible_pfn));
	arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions();
	arch_zone_highest_possible_pfn[0] = max_zone_pfn[0];
	for (i = 1; i < MAX_NR_ZONES; i++) {
		if (i == ZONE_MOVABLE)
			continue;
		arch_zone_lowest_possible_pfn[i] =
			arch_zone_highest_possible_pfn[i-1];
		arch_zone_highest_possible_pfn[i] =
			max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]);
	}
	arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0;
	arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0;

	/* Find the PFNs that ZONE_MOVABLE begins at in each node */
	memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
	find_zone_movable_pfns_for_nodes(zone_movable_pfn);

	/* Print out the zone ranges */
	printk("Zone PFN ranges:\n");
	for (i = 0; i < MAX_NR_ZONES; i++) {
		if (i == ZONE_MOVABLE)
			continue;
		printk("  %-8s %0#10lx -> %0#10lx\n",
				zone_names[i],
				arch_zone_lowest_possible_pfn[i],
				arch_zone_highest_possible_pfn[i]);
	}

	/* Print out the PFNs ZONE_MOVABLE begins at in each node */
	printk("Movable zone start PFN for each node\n");
	for (i = 0; i < MAX_NUMNODES; i++) {
		if (zone_movable_pfn[i])
			printk("  Node %d: %lu\n", i, zone_movable_pfn[i]);
	}

	/* Print out the early_node_map[] */
	printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
	for (i = 0; i < nr_nodemap_entries; i++)
		printk("  %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid,
						early_node_map[i].start_pfn,
						early_node_map[i].end_pfn);

	/* Initialise every node */
	mminit_verify_pageflags_layout();
	setup_nr_node_ids();
	for_each_online_node(nid) {
		pg_data_t *pgdat = NODE_DATA(nid);
		free_area_init_node(nid, NULL,
				find_min_pfn_for_node(nid), NULL);

		/* Any memory on that node */
		if (pgdat->node_present_pages)
			node_set_state(nid, N_HIGH_MEMORY);
		check_for_regular_memory(pgdat);
	}
}

static int __init cmdline_parse_core(char *p, unsigned long *core)
{
	unsigned long long coremem;
	if (!p)
		return -EINVAL;

	coremem = memparse(p, &p);
	*core = coremem >> PAGE_SHIFT;

	/* Paranoid check that UL is enough for the coremem value */
	WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);

	return 0;
}

/*
 * kernelcore=size sets the amount of memory for use for allocations that
 * cannot be reclaimed or migrated.
 */
static int __init cmdline_parse_kernelcore(char *p)
{
	return cmdline_parse_core(p, &required_kernelcore);
}

/*
 * movablecore=size sets the amount of memory for use for allocations that
 * can be reclaimed or migrated.
 */
static int __init cmdline_parse_movablecore(char *p)
{
	return cmdline_parse_core(p, &required_movablecore);
}

early_param("kernelcore", cmdline_parse_kernelcore);
early_param("movablecore", cmdline_parse_movablecore);

#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */

/**
 * set_dma_reserve - set the specified number of pages reserved in the first zone
 * @new_dma_reserve: The number of pages to mark reserved
 *
 * The per-cpu batchsize and zone watermarks are determined by present_pages.
 * In the DMA zone, a significant percentage may be consumed by kernel image
 * and other unfreeable allocations which can skew the watermarks badly. This
 * function may optionally be used to account for unfreeable pages in the
 * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and
 * smaller per-cpu batchsize.
 */
void __init set_dma_reserve(unsigned long new_dma_reserve)
{
	dma_reserve = new_dma_reserve;
}

#ifndef CONFIG_NEED_MULTIPLE_NODES
struct pglist_data __refdata contig_page_data = { .bdata = &bootmem_node_data[0] };
EXPORT_SYMBOL(contig_page_data);
#endif

void __init free_area_init(unsigned long *zones_size)
{
	free_area_init_node(0, zones_size,
			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
}

static int page_alloc_cpu_notify(struct notifier_block *self,
				 unsigned long action, void *hcpu)
{
	int cpu = (unsigned long)hcpu;

	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
		drain_pages(cpu);

		/*
		 * Spill the event counters of the dead processor
		 * into the current processors event counters.
		 * This artificially elevates the count of the current
		 * processor.
		 */
		vm_events_fold_cpu(cpu);

		/*
		 * Zero the differential counters of the dead processor
		 * so that the vm statistics are consistent.
		 *
		 * This is only okay since the processor is dead and cannot
		 * race with what we are doing.
		 */
		refresh_cpu_vm_stats(cpu);
	}
	return NOTIFY_OK;
}

void __init page_alloc_init(void)
{
	hotcpu_notifier(page_alloc_cpu_notify, 0);
}

/*
 * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio
 *	or min_free_kbytes changes.
 */
static void calculate_totalreserve_pages(void)
{
	struct pglist_data *pgdat;
	unsigned long reserve_pages = 0;
	enum zone_type i, j;

	for_each_online_pgdat(pgdat) {
		for (i = 0; i < MAX_NR_ZONES; i++) {
			struct zone *zone = pgdat->node_zones + i;
			unsigned long max = 0;

			/* Find valid and maximum lowmem_reserve in the zone */
			for (j = i; j < MAX_NR_ZONES; j++) {
				if (zone->lowmem_reserve[j] > max)
					max = zone->lowmem_reserve[j];
			}

			/* we treat the high watermark as reserved pages. */
			max += high_wmark_pages(zone);

			if (max > zone->present_pages)
				max = zone->present_pages;
			reserve_pages += max;
		}
	}
	totalreserve_pages = reserve_pages;
}

/*
 * setup_per_zone_lowmem_reserve - called whenever
 *	sysctl_lower_zone_reserve_ratio changes.  Ensures that each zone
 *	has a correct pages reserved value, so an adequate number of
 *	pages are left in the zone after a successful __alloc_pages().
 */
static void setup_per_zone_lowmem_reserve(void)
{
	struct pglist_data *pgdat;
	enum zone_type j, idx;

	for_each_online_pgdat(pgdat) {
		for (j = 0; j < MAX_NR_ZONES; j++) {
			struct zone *zone = pgdat->node_zones + j;
			unsigned long present_pages = zone->present_pages;

			zone->lowmem_reserve[j] = 0;

			idx = j;
			while (idx) {
				struct zone *lower_zone;

				idx--;

				if (sysctl_lowmem_reserve_ratio[idx] < 1)
					sysctl_lowmem_reserve_ratio[idx] = 1;

				lower_zone = pgdat->node_zones + idx;
				lower_zone->lowmem_reserve[j] = present_pages /
					sysctl_lowmem_reserve_ratio[idx];
				present_pages += lower_zone->present_pages;
			}
		}
	}

	/* update totalreserve_pages */
	calculate_totalreserve_pages();
}

/**
 * setup_per_zone_wmarks - called when min_free_kbytes changes
 * or when memory is hot-added
 *
 * Ensures that the watermark[min,low,high] values for each zone are set
 * correctly with respect to min_free_kbytes.
 */
void setup_per_zone_wmarks(void)
{
	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
	unsigned long lowmem_pages = 0;
	struct zone *zone;
	unsigned long flags;

	/* Calculate total number of !ZONE_HIGHMEM pages */
	for_each_zone(zone) {
		if (!is_highmem(zone))
			lowmem_pages += zone->present_pages;
	}

	for_each_zone(zone) {
		u64 tmp;

		spin_lock_irqsave(&zone->lock, flags);
		tmp = (u64)pages_min * zone->present_pages;
		do_div(tmp, lowmem_pages);
		if (is_highmem(zone)) {
			/*
			 * __GFP_HIGH and PF_MEMALLOC allocations usually don't
			 * need highmem pages, so cap pages_min to a small
			 * value here.
			 *
			 * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
			 * deltas controls asynch page reclaim, and so should
			 * not be capped for highmem.
			 */
			int min_pages;

			min_pages = zone->present_pages / 1024;
			if (min_pages < SWAP_CLUSTER_MAX)
				min_pages = SWAP_CLUSTER_MAX;
			if (min_pages > 128)
				min_pages = 128;
			zone->watermark[WMARK_MIN] = min_pages;
		} else {
			/*
			 * If it's a lowmem zone, reserve a number of pages
			 * proportionate to the zone's size.
			 */
			zone->watermark[WMARK_MIN] = tmp;
		}

		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
		setup_zone_migrate_reserve(zone);
		spin_unlock_irqrestore(&zone->lock, flags);
	}

	/* update totalreserve_pages */
	calculate_totalreserve_pages();
}

/**
 * The inactive anon list should be small enough that the VM never has to
 * do too much work, but large enough that each inactive page has a chance
 * to be referenced again before it is swapped out.
 *
 * The inactive_anon ratio is the target ratio of ACTIVE_ANON to
 * INACTIVE_ANON pages on this zone's LRU, maintained by the
 * pageout code. A zone->inactive_ratio of 3 means 3:1 or 25% of
 * the anonymous pages are kept on the inactive list.
 *
 * total     target    max
 * memory    ratio     inactive anon
 * -------------------------------------
 *   10MB       1         5MB
 *  100MB       1        50MB
 *    1GB       3       250MB
 *   10GB      10       0.9GB
 *  100GB      31         3GB
 *    1TB     101        10GB
 *   10TB     320        32GB
 */
void calculate_zone_inactive_ratio(struct zone *zone)
{
	unsigned int gb, ratio;

	/* Zone size in gigabytes */
	gb = zone->present_pages >> (30 - PAGE_SHIFT);
	if (gb)
		ratio = int_sqrt(10 * gb);
	else
		ratio = 1;

	zone->inactive_ratio = ratio;
}

static void __init setup_per_zone_inactive_ratio(void)
{
	struct zone *zone;

	for_each_zone(zone)
		calculate_zone_inactive_ratio(zone);
}

/*
 * Initialise min_free_kbytes.
 *
 * For small machines we want it small (128k min).  For large machines
 * we want it large (64MB max).  But it is not linear, because network
 * bandwidth does not increase linearly with machine size.  We use
 *
 * 	min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
 *	min_free_kbytes = sqrt(lowmem_kbytes * 16)
 *
 * which yields
 *
 * 16MB:	512k
 * 32MB:	724k
 * 64MB:	1024k
 * 128MB:	1448k
 * 256MB:	2048k
 * 512MB:	2896k
 * 1024MB:	4096k
 * 2048MB:	5792k
 * 4096MB:	8192k
 * 8192MB:	11584k
 * 16384MB:	16384k
 */
static int __init init_per_zone_wmark_min(void)
{
	unsigned long lowmem_kbytes;

	lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);

	min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
	if (min_free_kbytes < 128)
		min_free_kbytes = 128;
	if (min_free_kbytes > 65536)
		min_free_kbytes = 65536;
	setup_per_zone_wmarks();
	setup_per_zone_lowmem_reserve();
	setup_per_zone_inactive_ratio();
	return 0;
}
module_init(init_per_zone_wmark_min)

/*
 * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so 
 *	that we can call two helper functions whenever min_free_kbytes
 *	changes.
 */
int min_free_kbytes_sysctl_handler(ctl_table *table, int write, 
	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec(table, write, file, buffer, length, ppos);
	if (write)
		setup_per_zone_wmarks();
	return 0;
}

#ifdef CONFIG_NUMA
int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
	struct zone *zone;
	int rc;

	rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
	if (rc)
		return rc;

	for_each_zone(zone)
		zone->min_unmapped_pages = (zone->present_pages *
				sysctl_min_unmapped_ratio) / 100;
	return 0;
}

int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
	struct zone *zone;
	int rc;

	rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
	if (rc)
		return rc;

	for_each_zone(zone)
		zone->min_slab_pages = (zone->present_pages *
				sysctl_min_slab_ratio) / 100;
	return 0;
}
#endif

/*
 * lowmem_reserve_ratio_sysctl_handler - just a wrapper around
 *	proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
 *	whenever sysctl_lowmem_reserve_ratio changes.
 *
 * The reserve ratio obviously has absolutely no relation with the
 * minimum watermarks. The lowmem reserve ratio can only make sense
 * if in function of the boot time zone sizes.
 */
int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec_minmax(table, write, file, buffer, length, ppos);
	setup_per_zone_lowmem_reserve();
	return 0;
}

/*
 * percpu_pagelist_fraction - changes the pcp->high for each zone on each
 * cpu.  It is the fraction of total pages in each zone that a hot per cpu pagelist
 * can have before it gets flushed back to buddy allocator.
 */

int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
	struct zone *zone;
	unsigned int cpu;
	int ret;

	ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
	if (!write || (ret == -EINVAL))
		return ret;
	for_each_zone(zone) {
		for_each_online_cpu(cpu) {
			unsigned long  high;
			high = zone->present_pages / percpu_pagelist_fraction;
			setup_pagelist_highmark(zone_pcp(zone, cpu), high);
		}
	}
	return 0;
}

int hashdist = HASHDIST_DEFAULT;

#ifdef CONFIG_NUMA
static int __init set_hashdist(char *str)
{
	if (!str)
		return 0;
	hashdist = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("hashdist=", set_hashdist);
#endif

/*
 * allocate a large system hash table from bootmem
 * - it is assumed that the hash table must contain an exact power-of-2
 *   quantity of entries
 * - limit is the number of hash buckets, not the total allocation size
 */
void *__init alloc_large_system_hash(const char *tablename,
				     unsigned long bucketsize,
				     unsigned long numentries,
				     int scale,
				     int flags,
				     unsigned int *_hash_shift,
				     unsigned int *_hash_mask,
				     unsigned long limit)
{
	unsigned long long max = limit;
	unsigned long log2qty, size;
	void *table = NULL;

	/* allow the kernel cmdline to have a say */
	if (!numentries) {
		/* round applicable memory size up to nearest megabyte */
		numentries = nr_kernel_pages;
		numentries += (1UL << (20 - PAGE_SHIFT)) - 1;
		numentries >>= 20 - PAGE_SHIFT;
		numentries <<= 20 - PAGE_SHIFT;

		/* limit to 1 bucket per 2^scale bytes of low memory */
		if (scale > PAGE_SHIFT)
			numentries >>= (scale - PAGE_SHIFT);
		else
			numentries <<= (PAGE_SHIFT - scale);

		/* Make sure we've got at least a 0-order allocation.. */
		if (unlikely((numentries * bucketsize) < PAGE_SIZE))
			numentries = PAGE_SIZE / bucketsize;
	}
	numentries = roundup_pow_of_two(numentries);

	/* limit allocation size to 1/16 total memory by default */
	if (max == 0) {
		max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
		do_div(max, bucketsize);
	}

	if (numentries > max)
		numentries = max;

	log2qty = ilog2(numentries);

	do {
		size = bucketsize << log2qty;
		if (flags & HASH_EARLY)
			table = alloc_bootmem_nopanic(size);
		else if (hashdist)
			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
		else {
			/*
			 * If bucketsize is not a power-of-two, we may free
			 * some pages at the end of hash table which
			 * alloc_pages_exact() automatically does
			 */
			if (get_order(size) < MAX_ORDER)
				table = alloc_pages_exact(size, GFP_ATOMIC);
		}
	} while (!table && size > PAGE_SIZE && --log2qty);

	if (!table)
		panic("Failed to allocate %s hash table\n", tablename);

	printk(KERN_INFO "%s hash table entries: %d (order: %d, %lu bytes)\n",
	       tablename,
	       (1U << log2qty),
	       ilog2(size) - PAGE_SHIFT,
	       size);

	if (_hash_shift)
		*_hash_shift = log2qty;
	if (_hash_mask)
		*_hash_mask = (1 << log2qty) - 1;

	/*
	 * If hashdist is set, the table allocation is done with __vmalloc()
	 * which invokes the kmemleak_alloc() callback. This function may also
	 * be called before the slab and kmemleak are initialised when
	 * kmemleak simply buffers the request to be executed later
	 * (GFP_ATOMIC flag ignored in this case).
	 */
	if (!hashdist)
		kmemleak_alloc(table, size, 1, GFP_ATOMIC);

	return table;
}

/* Return a pointer to the bitmap storing bits affecting a block of pages */
static inline unsigned long *get_pageblock_bitmap(struct zone *zone,
							unsigned long pfn)
{
#ifdef CONFIG_SPARSEMEM
	return __pfn_to_section(pfn)->pageblock_flags;
#else
	return zone->pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
}

static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
{
#ifdef CONFIG_SPARSEMEM
	pfn &= (PAGES_PER_SECTION-1);
	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#else
	pfn = pfn - zone->zone_start_pfn;
	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#endif /* CONFIG_SPARSEMEM */
}

/**
 * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages
 * @page: The page within the block of interest
 * @start_bitidx: The first bit of interest to retrieve
 * @end_bitidx: The last bit of interest
 * returns pageblock_bits flags
 */
unsigned long get_pageblock_flags_group(struct page *page,
					int start_bitidx, int end_bitidx)
{
	struct zone *zone;
	unsigned long *bitmap;
	unsigned long pfn, bitidx;
	unsigned long flags = 0;
	unsigned long value = 1;

	zone = page_zone(page);
	pfn = page_to_pfn(page);
	bitmap = get_pageblock_bitmap(zone, pfn);
	bitidx = pfn_to_bitidx(zone, pfn);

	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
		if (test_bit(bitidx + start_bitidx, bitmap))
			flags |= value;

	return flags;
}

/**
 * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages
 * @page: The page within the block of interest
 * @start_bitidx: The first bit of interest
 * @end_bitidx: The last bit of interest
 * @flags: The flags to set
 */
void set_pageblock_flags_group(struct page *page, unsigned long flags,
					int start_bitidx, int end_bitidx)
{
	struct zone *zone;
	unsigned long *bitmap;
	unsigned long pfn, bitidx;
	unsigned long value = 1;

	zone = page_zone(page);
	pfn = page_to_pfn(page);
	bitmap = get_pageblock_bitmap(zone, pfn);
	bitidx = pfn_to_bitidx(zone, pfn);
	VM_BUG_ON(pfn < zone->zone_start_pfn);
	VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages);

	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
		if (flags & value)
			__set_bit(bitidx + start_bitidx, bitmap);
		else
			__clear_bit(bitidx + start_bitidx, bitmap);
}

/*
 * This is designed as sub function...plz see page_isolation.c also.
 * set/clear page block's type to be ISOLATE.
 * page allocater never alloc memory from ISOLATE block.
 */

int set_migratetype_isolate(struct page *page)
{
	struct zone *zone;
	unsigned long flags;
	int ret = -EBUSY;

	zone = page_zone(page);
	spin_lock_irqsave(&zone->lock, flags);
	/*
	 * In future, more migrate types will be able to be isolation target.
	 */
	if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
		goto out;
	set_pageblock_migratetype(page, MIGRATE_ISOLATE);
	move_freepages_block(zone, page, MIGRATE_ISOLATE);
	ret = 0;
out:
	spin_unlock_irqrestore(&zone->lock, flags);
	if (!ret)
		drain_all_pages();
	return ret;
}

void unset_migratetype_isolate(struct page *page)
{
	struct zone *zone;
	unsigned long flags;
	zone = page_zone(page);
	spin_lock_irqsave(&zone->lock, flags);
	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
		goto out;
	set_pageblock_migratetype(page, MIGRATE_MOVABLE);
	move_freepages_block(zone, page, MIGRATE_MOVABLE);
out:
	spin_unlock_irqrestore(&zone->lock, flags);
}

#ifdef CONFIG_MEMORY_HOTREMOVE
/*
 * All pages in the range must be isolated before calling this.
 */
void
__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
	struct page *page;
	struct zone *zone;
	int order, i;
	unsigned long pfn;
	unsigned long flags;
	/* find the first valid pfn */
	for (pfn = start_pfn; pfn < end_pfn; pfn++)
		if (pfn_valid(pfn))
			break;
	if (pfn == end_pfn)
		return;
	zone = page_zone(pfn_to_page(pfn));
	spin_lock_irqsave(&zone->lock, flags);
	pfn = start_pfn;
	while (pfn < end_pfn) {
		if (!pfn_valid(pfn)) {
			pfn++;
			continue;
		}
		page = pfn_to_page(pfn);
		BUG_ON(page_count(page));
		BUG_ON(!PageBuddy(page));
		order = page_order(page);
#ifdef CONFIG_DEBUG_VM
		printk(KERN_INFO "remove from free list %lx %d %lx\n",
		       pfn, 1 << order, end_pfn);
#endif
		list_del(&page->lru);
		rmv_page_order(page);
		zone->free_area[order].nr_free--;
		__mod_zone_page_state(zone, NR_FREE_PAGES,
				      - (1UL << order));
		for (i = 0; i < (1 << order); i++)
			SetPageReserved((page+i));
		pfn += (1 << order);
	}
	spin_unlock_irqrestore(&zone->lock, flags);
}
#endif