page_alloc.c

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

		if (j < ZONE_HIGHMEM)
			nr_kernel_pages += realsize;
		nr_all_pages += realsize;

		zone->spanned_pages = size;
		zone->present_pages = realsize;
		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->free_pages = 0;

		zone->temp_priority = 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;
		zone->nr_active = 0;
		zone->nr_inactive = 0;
		atomic_set(&zone->reclaim_in_progress, 0);
		if (!size)
			continue;

		zonetable_add(zone, nid, j, zone_start_pfn, size);
		init_currently_empty_zone(zone, zone_start_pfn, size);
		zone_start_pfn += size;
	}
}

static void __init 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;
		struct page *map;

		size = (pgdat->node_spanned_pages + 1) * sizeof(struct page);
		map = alloc_remap(pgdat->node_id, size);
		if (!map)
			map = alloc_bootmem_node(pgdat, size);
		pgdat->node_mem_map = map;
	}
#ifdef CONFIG_FLATMEM
	/*
	 * With no DISCONTIG, the global mem_map is just set as node 0's
	 */
	if (pgdat == NODE_DATA(0))
		mem_map = NODE_DATA(0)->node_mem_map;
#endif
#endif /* CONFIG_FLAT_NODE_MEM_MAP */
}

void __init free_area_init_node(int nid, struct pglist_data *pgdat,
		unsigned long *zones_size, unsigned long node_start_pfn,
		unsigned long *zholes_size)
{
	pgdat->node_id = nid;
	pgdat->node_start_pfn = node_start_pfn;
	calculate_zone_totalpages(pgdat, zones_size, zholes_size);

	alloc_node_mem_map(pgdat);

	free_area_init_core(pgdat, zones_size, zholes_size);
}

#ifndef CONFIG_NEED_MULTIPLE_NODES
static bootmem_data_t contig_bootmem_data;
struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data };

EXPORT_SYMBOL(contig_page_data);
#endif

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

#ifdef CONFIG_PROC_FS

#include <linux/seq_file.h>

static void *frag_start(struct seq_file *m, loff_t *pos)
{
	pg_data_t *pgdat;
	loff_t node = *pos;

	for (pgdat = pgdat_list; pgdat && node; pgdat = pgdat->pgdat_next)
		--node;

	return pgdat;
}

static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	(*pos)++;
	return pgdat->pgdat_next;
}

static void frag_stop(struct seq_file *m, void *arg)
{
}

/* 
 * This walks the free areas for each zone.
 */
static int frag_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = (pg_data_t *)arg;
	struct zone *zone;
	struct zone *node_zones = pgdat->node_zones;
	unsigned long flags;
	int order;

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
		if (!populated_zone(zone))
			continue;

		spin_lock_irqsave(&zone->lock, flags);
		seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
		for (order = 0; order < MAX_ORDER; ++order)
			seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
		spin_unlock_irqrestore(&zone->lock, flags);
		seq_putc(m, '\n');
	}
	return 0;
}

struct seq_operations fragmentation_op = {
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

/*
 * Output information about zones in @pgdat.
 */
static int zoneinfo_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = arg;
	struct zone *zone;
	struct zone *node_zones = pgdat->node_zones;
	unsigned long flags;

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) {
		int i;

		if (!populated_zone(zone))
			continue;

		spin_lock_irqsave(&zone->lock, flags);
		seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
		seq_printf(m,
			   "\n  pages free     %lu"
			   "\n        min      %lu"
			   "\n        low      %lu"
			   "\n        high     %lu"
			   "\n        active   %lu"
			   "\n        inactive %lu"
			   "\n        scanned  %lu (a: %lu i: %lu)"
			   "\n        spanned  %lu"
			   "\n        present  %lu",
			   zone->free_pages,
			   zone->pages_min,
			   zone->pages_low,
			   zone->pages_high,
			   zone->nr_active,
			   zone->nr_inactive,
			   zone->pages_scanned,
			   zone->nr_scan_active, zone->nr_scan_inactive,
			   zone->spanned_pages,
			   zone->present_pages);
		seq_printf(m,
			   "\n        protection: (%lu",
			   zone->lowmem_reserve[0]);
		for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
			seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
		seq_printf(m,
			   ")"
			   "\n  pagesets");
		for (i = 0; i < ARRAY_SIZE(zone->pageset); i++) {
			struct per_cpu_pageset *pageset;
			int j;

			pageset = zone_pcp(zone, i);
			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
				if (pageset->pcp[j].count)
					break;
			}
			if (j == ARRAY_SIZE(pageset->pcp))
				continue;
			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
				seq_printf(m,
					   "\n    cpu: %i pcp: %i"
					   "\n              count: %i"
					   "\n              high:  %i"
					   "\n              batch: %i",
					   i, j,
					   pageset->pcp[j].count,
					   pageset->pcp[j].high,
					   pageset->pcp[j].batch);
			}
#ifdef CONFIG_NUMA
			seq_printf(m,
				   "\n            numa_hit:       %lu"
				   "\n            numa_miss:      %lu"
				   "\n            numa_foreign:   %lu"
				   "\n            interleave_hit: %lu"
				   "\n            local_node:     %lu"
				   "\n            other_node:     %lu",
				   pageset->numa_hit,
				   pageset->numa_miss,
				   pageset->numa_foreign,
				   pageset->interleave_hit,
				   pageset->local_node,
				   pageset->other_node);
#endif
		}
		seq_printf(m,
			   "\n  all_unreclaimable: %u"
			   "\n  prev_priority:     %i"
			   "\n  temp_priority:     %i"
			   "\n  start_pfn:         %lu",
			   zone->all_unreclaimable,
			   zone->prev_priority,
			   zone->temp_priority,
			   zone->zone_start_pfn);
		spin_unlock_irqrestore(&zone->lock, flags);
		seq_putc(m, '\n');
	}
	return 0;
}

struct seq_operations zoneinfo_op = {
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

static char *vmstat_text[] = {
	"nr_dirty",
	"nr_writeback",
	"nr_unstable",
	"nr_page_table_pages",
	"nr_mapped",
	"nr_slab",

	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

	"pgalloc_high",
	"pgalloc_normal",
	"pgalloc_dma32",
	"pgalloc_dma",

	"pgfree",
	"pgactivate",
	"pgdeactivate",

	"pgfault",
	"pgmajfault",

	"pgrefill_high",
	"pgrefill_normal",
	"pgrefill_dma32",
	"pgrefill_dma",

	"pgsteal_high",
	"pgsteal_normal",
	"pgsteal_dma32",
	"pgsteal_dma",

	"pgscan_kswapd_high",
	"pgscan_kswapd_normal",
	"pgscan_kswapd_dma32",
	"pgscan_kswapd_dma",

	"pgscan_direct_high",
	"pgscan_direct_normal",
	"pgscan_direct_dma32",
	"pgscan_direct_dma",

	"pginodesteal",
	"slabs_scanned",
	"kswapd_steal",
	"kswapd_inodesteal",
	"pageoutrun",
	"allocstall",

	"pgrotated",
	"nr_bounce",
};

static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
	struct page_state *ps;

	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;

	ps = kmalloc(sizeof(*ps), GFP_KERNEL);
	m->private = ps;
	if (!ps)
		return ERR_PTR(-ENOMEM);
	get_full_page_state(ps);
	ps->pgpgin /= 2;		/* sectors -> kbytes */
	ps->pgpgout /= 2;
	return (unsigned long *)ps + *pos;
}

static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
{
	(*pos)++;
	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
	return (unsigned long *)m->private + *pos;
}

static int vmstat_show(struct seq_file *m, void *arg)
{
	unsigned long *l = arg;
	unsigned long off = l - (unsigned long *)m->private;

	seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
	return 0;
}

static void vmstat_stop(struct seq_file *m, void *arg)
{
	kfree(m->private);
	m->private = NULL;
}

struct seq_operations vmstat_op = {
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};

#endif /* CONFIG_PROC_FS */

#ifdef CONFIG_HOTPLUG_CPU
static int page_alloc_cpu_notify(struct notifier_block *self,
				 unsigned long action, void *hcpu)
{
	int cpu = (unsigned long)hcpu;
	long *count;
	unsigned long *src, *dest;

	if (action == CPU_DEAD) {
		int i;

		/* Drain local pagecache count. */
		count = &per_cpu(nr_pagecache_local, cpu);
		atomic_add(*count, &nr_pagecache);
		*count = 0;
		local_irq_disable();
		__drain_pages(cpu);

		/* Add dead cpu's page_states to our own. */
		dest = (unsigned long *)&__get_cpu_var(page_states);
		src = (unsigned long *)&per_cpu(page_states, cpu);

		for (i = 0; i < sizeof(struct page_state)/sizeof(unsigned long);
				i++) {
			dest[i] += src[i];
			src[i] = 0;
		}

		local_irq_enable();
	}
	return NOTIFY_OK;
}
#endif /* CONFIG_HOTPLUG_CPU */

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

/*
 * 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;
	int j, idx;

	for_each_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;

			for (idx = j-1; idx >= 0; idx--) {
				struct zone *lower_zone;

				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;
			}
		}
	}
}

/*
 * setup_per_zone_pages_min - called when min_free_kbytes changes.  Ensures 
 *	that the pages_{min,low,high} values for each zone are set correctly 
 *	with respect to min_free_kbytes.
 */
void setup_per_zone_pages_min(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) {
		unsigned long tmp;
		spin_lock_irqsave(&zone->lru_lock, flags);
		tmp = (pages_min * zone->present_pages) / 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 (pages_high-pages_low) and (pages_low-pages_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->pages_min = min_pages;
		} else {
			/*
			 * If it's a lowmem zone, reserve a number of pages
			 * proportionate to the zone's size.
			 */
			zone->pages_min = tmp;
		}

		zone->pages_low   = zone->pages_min + tmp / 4;
		zone->pages_high  = zone->pages_min + tmp / 2;
		spin_unlock_irqrestore(&zone->lru_lock, flags);
	}
}

/*
 * 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_pages_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_pages_min();
	setup_per_zone_lowmem_reserve();
	return 0;
}
module_init(init_per_zone_pages_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);
	setup_per_zone_pages_min();
	return 0;
}

/*
 * 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
 * pages_min 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;
}

__initdata 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 = (flags & HASH_HIGHMEM) ? nr_all_pages : 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);
	}
	/* rounded up to nearest power of 2 in size */
	numentries = 1UL << (long_log2(numentries) + 1);

	/* 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 = long_log2(numentries);

	do {
		size = bucketsize << log2qty;
		if (flags & HASH_EARLY)
			table = alloc_bootmem(size);
		else if (hashdist)
			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
		else {
			unsigned long order;
			for (order = 0; ((1UL << order) << PAGE_SHIFT) < size; order++)
				;
			table = (void*) __get_free_pages(GFP_ATOMIC, order);
		}
	} while (!table && size > PAGE_SIZE && --log2qty);

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

	printk("%s hash table entries: %d (order: %d, %lu bytes)\n",
	       tablename,
	       (1U << log2qty),
	       long_log2(size) - PAGE_SHIFT,
	       size);

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

	return table;
}