page_alloc.c

	unsigned int order = get_order(size);
	struct page *p = alloc_pages_node(nid, gfp_mask, order);
	if (!p)
		return NULL;
	return make_alloc_exact((unsigned long)page_address(p), order, size);
}

/**
 * free_pages_exact - release memory allocated via alloc_pages_exact()
 * @virt: the value returned by alloc_pages_exact.
 * @size: size of allocation, same value as passed to alloc_pages_exact().
 *
 * Release the memory allocated by a previous call to alloc_pages_exact.
 */
void free_pages_exact(void *virt, size_t size)
{
	unsigned long addr = (unsigned long)virt;
	unsigned long end = addr + PAGE_ALIGN(size);

	while (addr < end) {
		free_page(addr);
		addr += PAGE_SIZE;
	}
}
EXPORT_SYMBOL(free_pages_exact);

/**
 * nr_free_zone_pages - count number of pages beyond high watermark
 * @offset: The zone index of the highest zone
 *
 * nr_free_zone_pages() counts the number of counts pages which are beyond the
 * high watermark within all zones at or below a given zone index.  For each
 * zone, the number of pages is calculated as:
 *     managed_pages - high_pages
 */
static unsigned long nr_free_zone_pages(int offset)
{
	struct zoneref *z;
	struct zone *zone;

	/* Just pick one node, since fallback list is circular */
	unsigned long sum = 0;

	struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);

	for_each_zone_zonelist(zone, z, zonelist, offset) {
		unsigned long size = zone->managed_pages;
		unsigned long high = high_wmark_pages(zone);
		if (size > high)
			sum += size - high;
	}

	return sum;
}

/**
 * nr_free_buffer_pages - count number of pages beyond high watermark
 *
 * nr_free_buffer_pages() counts the number of pages which are beyond the high
 * watermark within ZONE_DMA and ZONE_NORMAL.
 */
unsigned long nr_free_buffer_pages(void)
{
	return nr_free_zone_pages(gfp_zone(GFP_USER));
}
EXPORT_SYMBOL_GPL(nr_free_buffer_pages);

/**
 * nr_free_pagecache_pages - count number of pages beyond high watermark
 *
 * nr_free_pagecache_pages() counts the number of pages which are beyond the
 * high watermark within all zones.
 */
unsigned long nr_free_pagecache_pages(void)
{
	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
}

static inline void show_node(struct zone *zone)
{
	if (IS_ENABLED(CONFIG_NUMA))
		printk("Node %d ", zone_to_nid(zone));
}

long si_mem_available(void)
{
	long available;
	unsigned long pagecache;
	unsigned long wmark_low = 0;
	unsigned long pages[NR_LRU_LISTS];
	struct zone *zone;
	int lru;

	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
		pages[lru] = global_page_state(NR_LRU_BASE + lru);

	for_each_zone(zone)
		wmark_low += zone->watermark[WMARK_LOW];

	/*
	 * Estimate the amount of memory available for userspace allocations,
	 * without causing swapping.
	 */
	available = global_page_state(NR_FREE_PAGES) - totalreserve_pages;

	/*
	 * Not all the page cache can be freed, otherwise the system will
	 * start swapping. Assume at least half of the page cache, or the
	 * low watermark worth of cache, needs to stay.
	 */
	pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
	pagecache -= min(pagecache / 2, wmark_low);
	available += pagecache;

	/*
	 * Part of the reclaimable slab consists of items that are in use,
	 * and cannot be freed. Cap this estimate at the low watermark.
	 */
	available += global_page_state(NR_SLAB_RECLAIMABLE) -
		     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);

	if (available < 0)
		available = 0;
	return available;
}
EXPORT_SYMBOL_GPL(si_mem_available);

void si_meminfo(struct sysinfo *val)
{
	val->totalram = totalram_pages;
	val->sharedram = global_node_page_state(NR_SHMEM);
	val->freeram = global_page_state(NR_FREE_PAGES);
	val->bufferram = nr_blockdev_pages();
	val->totalhigh = totalhigh_pages;
	val->freehigh = nr_free_highpages();
	val->mem_unit = PAGE_SIZE;
}

EXPORT_SYMBOL(si_meminfo);

#ifdef CONFIG_NUMA
void si_meminfo_node(struct sysinfo *val, int nid)
{
	int zone_type;		/* needs to be signed */
	unsigned long managed_pages = 0;
	unsigned long managed_highpages = 0;
	unsigned long free_highpages = 0;
	pg_data_t *pgdat = NODE_DATA(nid);

	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
		managed_pages += pgdat->node_zones[zone_type].managed_pages;
	val->totalram = managed_pages;
	val->sharedram = node_page_state(pgdat, NR_SHMEM);
	val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES);
#ifdef CONFIG_HIGHMEM
	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
		struct zone *zone = &pgdat->node_zones[zone_type];

		if (is_highmem(zone)) {
			managed_highpages += zone->managed_pages;
			free_highpages += zone_page_state(zone, NR_FREE_PAGES);
		}
	}
	val->totalhigh = managed_highpages;
	val->freehigh = free_highpages;
#else
	val->totalhigh = managed_highpages;
	val->freehigh = free_highpages;
#endif
	val->mem_unit = PAGE_SIZE;
}
#endif

/*
 * Determine whether the node should be displayed or not, depending on whether
 * SHOW_MEM_FILTER_NODES was passed to show_free_areas().
 */
bool skip_free_areas_node(unsigned int flags, int nid)
{
	bool ret = false;
	unsigned int cpuset_mems_cookie;

	if (!(flags & SHOW_MEM_FILTER_NODES))
		goto out;

	do {
		cpuset_mems_cookie = read_mems_allowed_begin();
		ret = !node_isset(nid, cpuset_current_mems_allowed);
	} while (read_mems_allowed_retry(cpuset_mems_cookie));
out:
	return ret;
}

#define K(x) ((x) << (PAGE_SHIFT-10))

static void show_migration_types(unsigned char type)
{
	static const char types[MIGRATE_TYPES] = {
		[MIGRATE_UNMOVABLE]	= 'U',
		[MIGRATE_MOVABLE]	= 'M',
		[MIGRATE_RECLAIMABLE]	= 'E',
		[MIGRATE_HIGHATOMIC]	= 'H',
#ifdef CONFIG_CMA
		[MIGRATE_CMA]		= 'C',
#endif
#ifdef CONFIG_MEMORY_ISOLATION
		[MIGRATE_ISOLATE]	= 'I',
#endif
	};
	char tmp[MIGRATE_TYPES + 1];
	char *p = tmp;
	int i;

	for (i = 0; i < MIGRATE_TYPES; i++) {
		if (type & (1 << i))
			*p++ = types[i];
	}

	*p = '\0';
	printk("(%s) ", tmp);
}

/*
 * Show free area list (used inside shift_scroll-lock stuff)
 * We also calculate the percentage fragmentation. We do this by counting the
 * memory on each free list with the exception of the first item on the list.
 *
 * Bits in @filter:
 * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's
 *   cpuset.
 */
void show_free_areas(unsigned int filter)
{
	unsigned long free_pcp = 0;
	int cpu;
	struct zone *zone;
	pg_data_t *pgdat;

	for_each_populated_zone(zone) {
		if (skip_free_areas_node(filter, zone_to_nid(zone)))
			continue;

		for_each_online_cpu(cpu)
			free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count;
	}

	printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
		" active_file:%lu inactive_file:%lu isolated_file:%lu\n"
		" unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n"
		" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
		" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
		" free:%lu free_pcp:%lu free_cma:%lu\n",
		global_node_page_state(NR_ACTIVE_ANON),
		global_node_page_state(NR_INACTIVE_ANON),
		global_node_page_state(NR_ISOLATED_ANON),
		global_node_page_state(NR_ACTIVE_FILE),
		global_node_page_state(NR_INACTIVE_FILE),
		global_node_page_state(NR_ISOLATED_FILE),
		global_node_page_state(NR_UNEVICTABLE),
		global_node_page_state(NR_FILE_DIRTY),
		global_node_page_state(NR_WRITEBACK),
		global_node_page_state(NR_UNSTABLE_NFS),
		global_page_state(NR_SLAB_RECLAIMABLE),
		global_page_state(NR_SLAB_UNRECLAIMABLE),
		global_node_page_state(NR_FILE_MAPPED),
		global_node_page_state(NR_SHMEM),
		global_page_state(NR_PAGETABLE),
		global_page_state(NR_BOUNCE),
		global_page_state(NR_FREE_PAGES),
		free_pcp,
		global_page_state(NR_FREE_CMA_PAGES));

	for_each_online_pgdat(pgdat) {
		printk("Node %d"
			" active_anon:%lukB"
			" inactive_anon:%lukB"
			" active_file:%lukB"
			" inactive_file:%lukB"
			" unevictable:%lukB"
			" isolated(anon):%lukB"
			" isolated(file):%lukB"
			" mapped:%lukB"
			" dirty:%lukB"
			" writeback:%lukB"
			" shmem:%lukB"
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
			" shmem_thp: %lukB"
			" shmem_pmdmapped: %lukB"
			" anon_thp: %lukB"
#endif
			" writeback_tmp:%lukB"
			" unstable:%lukB"
			" pages_scanned:%lu"
			" all_unreclaimable? %s"
			"\n",
			pgdat->node_id,
			K(node_page_state(pgdat, NR_ACTIVE_ANON)),
			K(node_page_state(pgdat, NR_INACTIVE_ANON)),
			K(node_page_state(pgdat, NR_ACTIVE_FILE)),
			K(node_page_state(pgdat, NR_INACTIVE_FILE)),
			K(node_page_state(pgdat, NR_UNEVICTABLE)),
			K(node_page_state(pgdat, NR_ISOLATED_ANON)),
			K(node_page_state(pgdat, NR_ISOLATED_FILE)),
			K(node_page_state(pgdat, NR_FILE_MAPPED)),
			K(node_page_state(pgdat, NR_FILE_DIRTY)),
			K(node_page_state(pgdat, NR_WRITEBACK)),
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
			K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
			K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
					* HPAGE_PMD_NR),
			K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
#endif
			K(node_page_state(pgdat, NR_SHMEM)),
			K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
			K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
			node_page_state(pgdat, NR_PAGES_SCANNED),
			!pgdat_reclaimable(pgdat) ? "yes" : "no");
	}

	for_each_populated_zone(zone) {
		int i;

		if (skip_free_areas_node(filter, zone_to_nid(zone)))
			continue;

		free_pcp = 0;
		for_each_online_cpu(cpu)
			free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count;

		show_node(zone);
		printk("%s"
			" free:%lukB"
			" min:%lukB"
			" low:%lukB"
			" high:%lukB"
			" active_anon:%lukB"
			" inactive_anon:%lukB"
			" active_file:%lukB"
			" inactive_file:%lukB"
			" unevictable:%lukB"
			" writepending:%lukB"
			" present:%lukB"
			" managed:%lukB"
			" mlocked:%lukB"
			" slab_reclaimable:%lukB"
			" slab_unreclaimable:%lukB"
			" kernel_stack:%lukB"
			" pagetables:%lukB"
			" bounce:%lukB"
			" free_pcp:%lukB"
			" local_pcp:%ukB"
			" free_cma:%lukB"
			"\n",
			zone->name,
			K(zone_page_state(zone, NR_FREE_PAGES)),
			K(min_wmark_pages(zone)),
			K(low_wmark_pages(zone)),
			K(high_wmark_pages(zone)),
			K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)),
			K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)),
			K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)),
			K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)),
			K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)),
			K(zone_page_state(zone, NR_ZONE_WRITE_PENDING)),
			K(zone->present_pages),
			K(zone->managed_pages),
			K(zone_page_state(zone, NR_MLOCK)),
			K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
			K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
			zone_page_state(zone, NR_KERNEL_STACK_KB),
			K(zone_page_state(zone, NR_PAGETABLE)),
			K(zone_page_state(zone, NR_BOUNCE)),
			K(free_pcp),
			K(this_cpu_read(zone->pageset->pcp.count)),
			K(zone_page_state(zone, NR_FREE_CMA_PAGES)));
		printk("lowmem_reserve[]:");
		for (i = 0; i < MAX_NR_ZONES; i++)
			printk(" %ld", zone->lowmem_reserve[i]);
		printk("\n");
	}

	for_each_populated_zone(zone) {
		unsigned int order;
		unsigned long nr[MAX_ORDER], flags, total = 0;
		unsigned char types[MAX_ORDER];

		if (skip_free_areas_node(filter, zone_to_nid(zone)))
			continue;
		show_node(zone);
		printk("%s: ", zone->name);

		spin_lock_irqsave(&zone->lock, flags);
		for (order = 0; order < MAX_ORDER; order++) {
			struct free_area *area = &zone->free_area[order];
			int type;

			nr[order] = area->nr_free;
			total += nr[order] << order;

			types[order] = 0;
			for (type = 0; type < MIGRATE_TYPES; type++) {
				if (!list_empty(&area->free_list[type]))
					types[order] |= 1 << type;
			}
		}
		spin_unlock_irqrestore(&zone->lock, flags);
		for (order = 0; order < MAX_ORDER; order++) {
			printk("%lu*%lukB ", nr[order], K(1UL) << order);
			if (nr[order])
				show_migration_types(types[order]);
		}
		printk("= %lukB\n", K(total));
	}

	hugetlb_show_meminfo();

	printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES));

	show_swap_cache_info();
}

static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
{
	zoneref->zone = zone;
	zoneref->zone_idx = zone_idx(zone);
}

/*
 * Builds allocation fallback zone lists.
 *
 * Add all populated zones of a node to the zonelist.
 */
static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
				int nr_zones)
{
	struct zone *zone;
	enum zone_type zone_type = MAX_NR_ZONES;

	do {
		zone_type--;
		zone = pgdat->node_zones + zone_type;
		if (populated_zone(zone)) {
			zoneref_set_zone(zone,
				&zonelist->_zonerefs[nr_zones++]);
			check_highest_zone(zone_type);
		}
	} while (zone_type);

	return nr_zones;
}


/*
 *  zonelist_order:
 *  0 = automatic detection of better ordering.
 *  1 = order by ([node] distance, -zonetype)
 *  2 = order by (-zonetype, [node] distance)
 *
 *  If not NUMA, ZONELIST_ORDER_ZONE and ZONELIST_ORDER_NODE will create
 *  the same zonelist. So only NUMA can configure this param.
 */
#define ZONELIST_ORDER_DEFAULT  0
#define ZONELIST_ORDER_NODE     1
#define ZONELIST_ORDER_ZONE     2

/* zonelist order in the kernel.
 * set_zonelist_order() will set this to NODE or ZONE.
 */
static int current_zonelist_order = ZONELIST_ORDER_DEFAULT;
static char zonelist_order_name[3][8] = {"Default", "Node", "Zone"};


#ifdef CONFIG_NUMA
/* The value user specified ....changed by config */
static int user_zonelist_order = ZONELIST_ORDER_DEFAULT;
/* string for sysctl */
#define NUMA_ZONELIST_ORDER_LEN	16
char numa_zonelist_order[16] = "default";

/*
 * interface for configure zonelist ordering.
 * command line option "numa_zonelist_order"
 *	= "[dD]efault	- default, automatic configuration.
 *	= "[nN]ode 	- order by node locality, then by zone within node
 *	= "[zZ]one      - order by zone, then by locality within zone
 */

static int __parse_numa_zonelist_order(char *s)
{
	if (*s == 'd' || *s == 'D') {
		user_zonelist_order = ZONELIST_ORDER_DEFAULT;
	} else if (*s == 'n' || *s == 'N') {
		user_zonelist_order = ZONELIST_ORDER_NODE;
	} else if (*s == 'z' || *s == 'Z') {
		user_zonelist_order = ZONELIST_ORDER_ZONE;
	} else {
		pr_warn("Ignoring invalid numa_zonelist_order value:  %s\n", s);
		return -EINVAL;
	}
	return 0;
}

static __init int setup_numa_zonelist_order(char *s)
{
	int ret;

	if (!s)
		return 0;

	ret = __parse_numa_zonelist_order(s);
	if (ret == 0)
		strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN);

	return ret;
}
early_param("numa_zonelist_order", setup_numa_zonelist_order);

/*
 * sysctl handler for numa_zonelist_order
 */
int numa_zonelist_order_handler(struct ctl_table *table, int write,
		void __user *buffer, size_t *length,
		loff_t *ppos)
{
	char saved_string[NUMA_ZONELIST_ORDER_LEN];
	int ret;
	static DEFINE_MUTEX(zl_order_mutex);

	mutex_lock(&zl_order_mutex);
	if (write) {
		if (strlen((char *)table->data) >= NUMA_ZONELIST_ORDER_LEN) {
			ret = -EINVAL;
			goto out;
		}
		strcpy(saved_string, (char *)table->data);
	}
	ret = proc_dostring(table, write, buffer, length, ppos);
	if (ret)
		goto out;
	if (write) {
		int oldval = user_zonelist_order;

		ret = __parse_numa_zonelist_order((char *)table->data);
		if (ret) {
			/*
			 * bogus value.  restore saved string
			 */
			strncpy((char *)table->data, saved_string,
				NUMA_ZONELIST_ORDER_LEN);
			user_zonelist_order = oldval;
		} else if (oldval != user_zonelist_order) {
			mutex_lock(&zonelists_mutex);
			build_all_zonelists(NULL, NULL);
			mutex_unlock(&zonelists_mutex);
		}
	}
out:
	mutex_unlock(&zl_order_mutex);
	return ret;
}


#define MAX_NODE_LOAD (nr_online_nodes)
static int node_load[MAX_NUMNODES];

/**
 * find_next_best_node - find the next node that should appear in a given node's fallback list
 * @node: node whose fallback list we're appending
 * @used_node_mask: nodemask_t of already used nodes
 *
 * We use a number of factors to determine which is the next node that should
 * appear on a given node's fallback list.  The node should not have appeared
 * already in @node's fallback list, and it should be the next closest node
 * according to the distance array (which contains arbitrary distance values
 * from each node to each node in the system), and should also prefer nodes
 * with no CPUs, since presumably they'll have very little allocation pressure
 * on them otherwise.
 * It returns -1 if no node is found.
 */
static int find_next_best_node(int node, nodemask_t *used_node_mask)
{
	int n, val;
	int min_val = INT_MAX;
	int best_node = NUMA_NO_NODE;
	const struct cpumask *tmp = cpumask_of_node(0);

	/* Use the local node if we haven't already */
	if (!node_isset(node, *used_node_mask)) {
		node_set(node, *used_node_mask);
		return node;
	}

	for_each_node_state(n, N_MEMORY) {

		/* Don't want a node to appear more than once */
		if (node_isset(n, *used_node_mask))
			continue;

		/* Use the distance array to find the distance */
		val = node_distance(node, n);

		/* Penalize nodes under us ("prefer the next node") */
		val += (n < node);

		/* Give preference to headless and unused nodes */
		tmp = cpumask_of_node(n);
		if (!cpumask_empty(tmp))
			val += PENALTY_FOR_NODE_WITH_CPUS;

		/* Slight preference for less loaded node */
		val *= (MAX_NODE_LOAD*MAX_NUMNODES);
		val += node_load[n];

		if (val < min_val) {
			min_val = val;
			best_node = n;
		}
	}

	if (best_node >= 0)
		node_set(best_node, *used_node_mask);

	return best_node;
}


/*
 * Build zonelists ordered by node and zones within node.
 * This results in maximum locality--normal zone overflows into local
 * DMA zone, if any--but risks exhausting DMA zone.
 */
static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
{
	int j;
	struct zonelist *zonelist;

	zonelist = &pgdat->node_zonelists[0];
	for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
		;
	j = build_zonelists_node(NODE_DATA(node), zonelist, j);
	zonelist->_zonerefs[j].zone = NULL;
	zonelist->_zonerefs[j].zone_idx = 0;
}

/*
 * Build gfp_thisnode zonelists
 */
static void build_thisnode_zonelists(pg_data_t *pgdat)
{
	int j;
	struct zonelist *zonelist;

	zonelist = &pgdat->node_zonelists[1];
	j = build_zonelists_node(pgdat, zonelist, 0);
	zonelist->_zonerefs[j].zone = NULL;
	zonelist->_zonerefs[j].zone_idx = 0;
}

/*
 * Build zonelists ordered by zone and nodes within zones.
 * This results in conserving DMA zone[s] until all Normal memory is
 * exhausted, but results in overflowing to remote node while memory
 * may still exist in local DMA zone.
 */
static int node_order[MAX_NUMNODES];

static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
{
	int pos, j, node;
	int zone_type;		/* needs to be signed */
	struct zone *z;
	struct zonelist *zonelist;

	zonelist = &pgdat->node_zonelists[0];
	pos = 0;
	for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) {
		for (j = 0; j < nr_nodes; j++) {
			node = node_order[j];
			z = &NODE_DATA(node)->node_zones[zone_type];
			if (populated_zone(z)) {
				zoneref_set_zone(z,
					&zonelist->_zonerefs[pos++]);
				check_highest_zone(zone_type);
			}
		}
	}
	zonelist->_zonerefs[pos].zone = NULL;
	zonelist->_zonerefs[pos].zone_idx = 0;
}

#if defined(CONFIG_64BIT)
/*
 * Devices that require DMA32/DMA are relatively rare and do not justify a
 * penalty to every machine in case the specialised case applies. Default
 * to Node-ordering on 64-bit NUMA machines
 */
static int default_zonelist_order(void)
{
	return ZONELIST_ORDER_NODE;
}
#else
/*
 * On 32-bit, the Normal zone needs to be preserved for allocations accessible
 * by the kernel. If processes running on node 0 deplete the low memory zone
 * then reclaim will occur more frequency increasing stalls and potentially
 * be easier to OOM if a large percentage of the zone is under writeback or
 * dirty. The problem is significantly worse if CONFIG_HIGHPTE is not set.
 * Hence, default to zone ordering on 32-bit.
 */
static int default_zonelist_order(void)
{
	return ZONELIST_ORDER_ZONE;
}
#endif /* CONFIG_64BIT */

static void set_zonelist_order(void)
{
	if (user_zonelist_order == ZONELIST_ORDER_DEFAULT)
		current_zonelist_order = default_zonelist_order();
	else
		current_zonelist_order = user_zonelist_order;
}

static void build_zonelists(pg_data_t *pgdat)
{
	int i, node, load;
	nodemask_t used_mask;
	int local_node, prev_node;
	struct zonelist *zonelist;
	unsigned int order = current_zonelist_order;

	/* initialize zonelists */
	for (i = 0; i < MAX_ZONELISTS; i++) {
		zonelist = pgdat->node_zonelists + i;
		zonelist->_zonerefs[0].zone = NULL;
		zonelist->_zonerefs[0].zone_idx = 0;
	}

	/* NUMA-aware ordering of nodes */
	local_node = pgdat->node_id;
	load = nr_online_nodes;
	prev_node = local_node;
	nodes_clear(used_mask);

	memset(node_order, 0, sizeof(node_order));
	i = 0;

	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
		/*
		 * We don't want to pressure a particular node.
		 * So adding penalty to the first node in same
		 * distance group to make it round-robin.
		 */
		if (node_distance(local_node, node) !=
		    node_distance(local_node, prev_node))
			node_load[node] = load;

		prev_node = node;
		load--;
		if (order == ZONELIST_ORDER_NODE)
			build_zonelists_in_node_order(pgdat, node);
		else
			node_order[i++] = node;	/* remember order */
	}

	if (order == ZONELIST_ORDER_ZONE) {
		/* calculate node order -- i.e., DMA last! */
		build_zonelists_in_zone_order(pgdat, i);
	}

	build_thisnode_zonelists(pgdat);
}

#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
 * Return node id of node used for "local" allocations.
 * I.e., first node id of first zone in arg node's generic zonelist.
 * Used for initializing percpu 'numa_mem', which is used primarily
 * for kernel allocations, so use GFP_KERNEL flags to locate zonelist.
 */
int local_memory_node(int node)
{
	struct zoneref *z;

	z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
				   gfp_zone(GFP_KERNEL),
				   NULL);
	return z->zone->node;
}
#endif

#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 j;
	struct zonelist *zonelist;

	local_node = pgdat->node_id;

	zonelist = &pgdat->node_zonelists[0];
	j = build_zonelists_node(pgdat, zonelist, 0);

	/*
	 * 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);
	}
	for (node = 0; node < local_node; node++) {
		if (!node_online(node))
			continue;
		j = build_zonelists_node(NODE_DATA(node), zonelist, j);
	}

	zonelist->_zonerefs[j].zone = NULL;
	zonelist->_zonerefs[j].zone_idx = 0;
}

#endif	/* 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.
 *
 * 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 void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
static void setup_zone_pageset(struct zone *zone);

/*
 * Global mutex to protect against size modification of zonelists
 * as well as to serialize pageset setup for the new populated zone.
 */
DEFINE_MUTEX(zonelists_mutex);

/* return values int ....just for stop_machine() */
static int __build_all_zonelists(void *data)
{
	int nid;
	int cpu;
	pg_data_t *self = data;

#ifdef CONFIG_NUMA
	memset(node_load, 0, sizeof(node_load));
#endif

	if (self && !node_online(self->node_id)) {
		build_zonelists(self);
	}

	for_each_online_node(nid) {
		pg_data_t *pgdat = NODE_DATA(nid);

		build_zonelists(pgdat);
	}

	/*
	 * 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;
}

static noinline void __init
build_all_zonelists_init(void)
{
	__build_all_zonelists(NULL);
	mminit_verify_zonelist();
	cpuset_init_current_mems_allowed();
}

/*
 * Called with zonelists_mutex held always
 * unless system_state == SYSTEM_BOOTING.
 *
 * __ref due to (1) call of __meminit annotated setup_zone_pageset
 * [we're only called with non-NULL zone through __meminit paths] and
 * (2) call of __init annotated helper build_all_zonelists_init
 * [protected by SYSTEM_BOOTING].
 */
void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
{
	set_zonelist_order();

	if (system_state == SYSTEM_BOOTING) {
		build_all_zonelists_init();
	} else {
#ifdef CONFIG_MEMORY_HOTPLUG
		if (zone)
			setup_zone_pageset(zone);
#endif
		/* we have to stop all cpus to guarantee there is no user
		   of zonelist */
		stop_machine(__build_all_zonelists, pgdat, 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;

	pr_info("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
	pr_info("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);