page_alloc.c

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 {
		printk(KERN_WARNING
		       "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 zone *zone;

	(void)first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
				   gfp_zone(GFP_KERNEL),
				   NULL,
				   &zone);
	return 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);
}
#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);
}

/*
 * 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 vmem_altmap *altmap = to_vmem_altmap(__pfn_to_phys(start_pfn));
	unsigned long end_pfn = start_pfn + size;
	pg_data_t *pgdat = NODE_DATA(nid);
	unsigned long pfn;
	unsigned long nr_initialised = 0;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
	struct memblock_region *r = NULL, *tmp;
#endif

	if (highest_memmap_pfn < end_pfn - 1)
		highest_memmap_pfn = end_pfn - 1;

	/*
	 * Honor reservation requested by the driver for this ZONE_DEVICE
	 * memory
	 */
	if (altmap && start_pfn == altmap->base_pfn)
		start_pfn += altmap->reserve;

	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)
			goto not_early;

		if (!early_pfn_valid(pfn))
			continue;
		if (!early_pfn_in_nid(pfn, nid))
			continue;
		if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
			break;

#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
		/*
		 * If not mirrored_kernelcore and ZONE_MOVABLE exists, range
		 * from zone_movable_pfn[nid] to end of each node should be
		 * ZONE_MOVABLE not ZONE_NORMAL. skip it.
		 */
		if (!mirrored_kernelcore && zone_movable_pfn[nid])
			if (zone == ZONE_NORMAL && pfn >= zone_movable_pfn[nid])
				continue;

		/*
		 * Check given memblock attribute by firmware which can affect
		 * kernel memory layout.  If zone==ZONE_MOVABLE but memory is
		 * mirrored, it's an overlapped memmap init. skip it.
		 */
		if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
			if (!r || pfn >= memblock_region_memory_end_pfn(r)) {
				for_each_memblock(memory, tmp)
					if (pfn < memblock_region_memory_end_pfn(tmp))
						break;
				r = tmp;
			}
			if (pfn >= memblock_region_memory_base_pfn(r) &&
			    memblock_is_mirror(r)) {
				/* already initialized as NORMAL */
				pfn = memblock_region_memory_end_pfn(r);
				continue;
			}
		}
#endif

not_early:
		/*
		 * Mark the block movable so that blocks are reserved for
		 * movable at startup. This will force kernel allocations
		 * to reserve their blocks rather than leaking throughout
		 * the address space during boot when many long-lived
		 * kernel allocations are made.
		 *
		 * bitmap is created for zone's valid pfn range. but memmap
		 * can be created for invalid pages (for alignment)
		 * check here not to call set_pageblock_migratetype() against
		 * pfn out of zone.
		 */
		if (!(pfn & (pageblock_nr_pages - 1))) {
			struct page *page = pfn_to_page(pfn);

			__init_single_page(page, pfn, zone, nid);
			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
		} else {
			__init_single_pfn(pfn, zone, nid);
		}
	}
}

static void __meminit zone_init_free_lists(struct zone *zone)
{
	unsigned int order, t;
	for_each_migratetype_order(order, t) {
		INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
		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 zone_batchsize(struct zone *zone)
{
#ifdef CONFIG_MMU
	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->managed_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 = rounddown_pow_of_two(batch + batch/2) - 1;

	return batch;

#else
	/* The deferral and batching of frees should be suppressed under NOMMU
	 * conditions.
	 *
	 * The problem is that NOMMU needs to be able to allocate large chunks
	 * of contiguous memory as there's no hardware page translation to
	 * assemble apparent contiguous memory from discontiguous pages.
	 *
	 * Queueing large contiguous runs of pages for batching, however,
	 * causes the pages to actually be freed in smaller chunks.  As there
	 * can be a significant delay between the individual batches being
	 * recycled, this leads to the once large chunks of space being
	 * fragmented and becoming unavailable for high-order allocations.
	 */
	return 0;
#endif
}

/*
 * pcp->high and pcp->batch values are related and dependent on one another:
 * ->batch must never be higher then ->high.
 * The following function updates them in a safe manner without read side
 * locking.
 *
 * Any new users of pcp->batch and pcp->high should ensure they can cope with
 * those fields changing asynchronously (acording the the above rule).
 *
 * mutex_is_locked(&pcp_batch_high_lock) required when calling this function
 * outside of boot time (or some other assurance that no concurrent updaters
 * exist).
 */
static void pageset_update(struct per_cpu_pages *pcp, unsigned long high,
		unsigned long batch)
{
       /* start with a fail safe value for batch */
	pcp->batch = 1;
	smp_wmb();

       /* Update high, then batch, in order */
	pcp->high = high;
	smp_wmb();

	pcp->batch = batch;
}

/* a companion to pageset_set_high() */
static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch)
{
	pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch));
}

static void pageset_init(struct per_cpu_pageset *p)
{
	struct per_cpu_pages *pcp;
	int migratetype;

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

	pcp = &p->pcp;
	pcp->count = 0;
	for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
		INIT_LIST_HEAD(&pcp->lists[migratetype]);
}

static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
	pageset_init(p);
	pageset_set_batch(p, batch);
}

/*
 * pageset_set_high() sets the high water mark for hot per_cpu_pagelist
 * to the value high for the pageset p.
 */
static void pageset_set_high(struct per_cpu_pageset *p,
				unsigned long high)
{
	unsigned long batch = max(1UL, high / 4);
	if ((high / 4) > (PAGE_SHIFT * 8))
		batch = PAGE_SHIFT * 8;

	pageset_update(&p->pcp, high, batch);
}

static void pageset_set_high_and_batch(struct zone *zone,
				       struct per_cpu_pageset *pcp)
{
	if (percpu_pagelist_fraction)
		pageset_set_high(pcp,
			(zone->managed_pages /
				percpu_pagelist_fraction));
	else
		pageset_set_batch(pcp, zone_batchsize(zone));
}

static void __meminit zone_pageset_init(struct zone *zone, int cpu)
{
	struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);

	pageset_init(pcp);
	pageset_set_high_and_batch(zone, pcp);
}

static void __meminit setup_zone_pageset(struct zone *zone)
{
	int cpu;
	zone->pageset = alloc_percpu(struct per_cpu_pageset);
	for_each_possible_cpu(cpu)
		zone_pageset_init(zone, cpu);
}

/*
 * Allocate per cpu pagesets and initialize them.
 * Before this call only boot pagesets were available.
 */
void __init setup_per_cpu_pageset(void)
{
	struct zone *zone;

	for_each_populated_zone(zone)
		setup_zone_pageset(zone);
}

static noinline __init_refok
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
	int i;
	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 (!slab_is_available()) {
		zone->wait_table = (wait_queue_head_t *)
			memblock_virt_alloc_node_nopanic(
				alloc_size, zone->zone_pgdat->node_id);
	} 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 = 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)
{
	/*
	 * per cpu subsystem is not up at this point. The following code
	 * relies on the ability of the linker to provide the
	 * offset of a (static) per cpu variable into the per cpu area.
	 */
	zone->pageset = &boot_pageset;

	if (populated_zone(zone))
		printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%u\n",
			zone->name, zone->present_pages,
					 zone_batchsize(zone));
}

int __meminit init_currently_empty_zone(struct zone *zone,
					unsigned long zone_start_pfn,
					unsigned long size)
{
	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;

	mminit_dprintk(MMINIT_TRACE, "memmap_init",
			"Initialising map node %d zone %lu pfns %lu -> %lu\n",
			pgdat->node_id,
			(unsigned long)zone_idx(zone),
			zone_start_pfn, (zone_start_pfn + size));

	zone_init_free_lists(zone);

	return 0;
}

#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID

/*
 * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
 */
int __meminit __early_pfn_to_nid(unsigned long pfn,
					struct mminit_pfnnid_cache *state)
{
	unsigned long start_pfn, end_pfn;
	int nid;

	if (state->last_start <= pfn && pfn < state->last_end)
		return state->last_nid;

	nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
	if (nid != -1) {
		state->last_start = start_pfn;
		state->last_end = end_pfn;
		state->last_nid = nid;
	}

	return nid;
}
#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */

/**
 * free_bootmem_with_active_regions - Call memblock_free_early_nid 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 memblock_free_early_nid
 *
 * If an architecture guarantees that all ranges registered contain no holes
 * and may be freed, this this function may be used instead of calling
 * memblock_free_early_nid() manually.
 */
void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)