page_alloc.c

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);
}

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 pages_high as reserved pages. */
			max += zone->pages_high;

			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_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) {
		u64 tmp;

		spin_lock_irqsave(&zone->lru_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 (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 >> 2);
		zone->pages_high  = zone->pages_min + (tmp >> 1);
		setup_zone_migrate_reserve(zone);
		spin_unlock_irqrestore(&zone->lru_lock, flags);
	}

	/* update totalreserve_pages */
	calculate_totalreserve_pages();
}

/*
 * 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);
	if (write)
		setup_per_zone_pages_min();
	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
 * 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;
}

/*
 * 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(size);
		else if (hashdist)
			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
		else {
			unsigned long order = get_order(size);
			table = (void*) __get_free_pages(GFP_ATOMIC, order);
			/*
			 * If bucketsize is not a power-of-two, we may free
			 * some pages at the end of hash table.
			 */
			if (table) {
				unsigned long alloc_end = (unsigned long)table +
						(PAGE_SIZE << order);
				unsigned long used = (unsigned long)table +
						PAGE_ALIGN(size);
				split_page(virt_to_page(table), order);
				while (used < alloc_end) {
					free_page(used);
					used += PAGE_SIZE;
				}
			}
		}
	} 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;

	return table;
}

#ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE
struct page *pfn_to_page(unsigned long pfn)
{
	return __pfn_to_page(pfn);
}
unsigned long page_to_pfn(struct page *page)
{
	return __page_to_pfn(page);
}
EXPORT_SYMBOL(pfn_to_page);
EXPORT_SYMBOL(page_to_pfn);
#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */

/* 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