page_alloc.c

	return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones);
}

/*
 * Given 'z' scanning a zonelist, set the corresponding bit in
 * zlc->fullzones, so that subsequent attempts to allocate a page
 * from that zone don't waste time re-examining it.
 */
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
{
	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
	int i;				/* index of *z in zonelist zones */

	zlc = zonelist->zlcache_ptr;
	if (!zlc)
		return;

	i = z - zonelist->zones;

	set_bit(i, zlc->fullzones);
}

#else	/* CONFIG_NUMA */

static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
	return NULL;
}

static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
				nodemask_t *allowednodes)
{
	return 1;
}

static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
{
}
#endif	/* CONFIG_NUMA */

/*
 * get_page_from_freelist goes through the zonelist trying to allocate
 * a page.
 */
static struct page *
get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
		struct zonelist *zonelist, int alloc_flags)
{
	struct zone **z;
	struct page *page = NULL;
	int classzone_idx = zone_idx(zonelist->zones[0]);
	struct zone *zone;
	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
	int zlc_active = 0;		/* set if using zonelist_cache */
	int did_zlc_setup = 0;		/* just call zlc_setup() one time */

zonelist_scan:
	/*
	 * Scan zonelist, looking for a zone with enough free.
	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
	 */
	z = zonelist->zones;

	do {
		if (NUMA_BUILD && zlc_active &&
			!zlc_zone_worth_trying(zonelist, z, allowednodes))
				continue;
		zone = *z;
		if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) &&
			zone->zone_pgdat != zonelist->zones[0]->zone_pgdat))
				break;
		if ((alloc_flags & ALLOC_CPUSET) &&
			!cpuset_zone_allowed(zone, gfp_mask))
				goto try_next_zone;

		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
			unsigned long mark;
			if (alloc_flags & ALLOC_WMARK_MIN)
				mark = zone->pages_min;
			else if (alloc_flags & ALLOC_WMARK_LOW)
				mark = zone->pages_low;
			else
				mark = zone->pages_high;
			if (!zone_watermark_ok(zone, order, mark,
				    classzone_idx, alloc_flags)) {
				if (!zone_reclaim_mode ||
				    !zone_reclaim(zone, gfp_mask, order))
					goto this_zone_full;
			}
		}

		page = buffered_rmqueue(zonelist, zone, order, gfp_mask);
		if (page)
			break;
this_zone_full:
		if (NUMA_BUILD)
			zlc_mark_zone_full(zonelist, z);
try_next_zone:
		if (NUMA_BUILD && !did_zlc_setup) {
			/* we do zlc_setup after the first zone is tried */
			allowednodes = zlc_setup(zonelist, alloc_flags);
			zlc_active = 1;
			did_zlc_setup = 1;
		}
	} while (*(++z) != NULL);

	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
		/* Disable zlc cache for second zonelist scan */
		zlc_active = 0;
		goto zonelist_scan;
	}
	return page;
}

/*
 * This is the 'heart' of the zoned buddy allocator.
 */
struct page * fastcall
__alloc_pages(gfp_t gfp_mask, unsigned int order,
		struct zonelist *zonelist)
{
	const gfp_t wait = gfp_mask & __GFP_WAIT;
	struct zone **z;
	struct page *page;
	struct reclaim_state reclaim_state;
	struct task_struct *p = current;
	int do_retry;
	int alloc_flags;
	int did_some_progress;

	might_sleep_if(wait);

restart:
	z = zonelist->zones;  /* the list of zones suitable for gfp_mask */

	if (unlikely(*z == NULL)) {
		/* Should this ever happen?? */
		return NULL;
	}

	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
				zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
	if (page)
		goto got_pg;

	for (z = zonelist->zones; *z; z++)
		wakeup_kswapd(*z, order);

	/*
	 * OK, we're below the kswapd watermark and have kicked background
	 * reclaim. Now things get more complex, so set up alloc_flags according
	 * to how we want to proceed.
	 *
	 * The caller may dip into page reserves a bit more if the caller
	 * cannot run direct reclaim, or if the caller has realtime scheduling
	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
	 */
	alloc_flags = ALLOC_WMARK_MIN;
	if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
		alloc_flags |= ALLOC_HARDER;
	if (gfp_mask & __GFP_HIGH)
		alloc_flags |= ALLOC_HIGH;
	if (wait)
		alloc_flags |= ALLOC_CPUSET;

	/*
	 * Go through the zonelist again. Let __GFP_HIGH and allocations
	 * coming from realtime tasks go deeper into reserves.
	 *
	 * This is the last chance, in general, before the goto nopage.
	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
	 */
	page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
	if (page)
		goto got_pg;

	/* This allocation should allow future memory freeing. */

	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
			&& !in_interrupt()) {
		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
nofail_alloc:
			/* go through the zonelist yet again, ignoring mins */
			page = get_page_from_freelist(gfp_mask, order,
				zonelist, ALLOC_NO_WATERMARKS);
			if (page)
				goto got_pg;
			if (gfp_mask & __GFP_NOFAIL) {
				congestion_wait(WRITE, HZ/50);
				goto nofail_alloc;
			}
		}
		goto nopage;
	}

	/* Atomic allocations - we can't balance anything */
	if (!wait)
		goto nopage;

rebalance:
	cond_resched();

	/* We now go into synchronous reclaim */
	cpuset_memory_pressure_bump();
	p->flags |= PF_MEMALLOC;
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

	did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask);

	p->reclaim_state = NULL;
	p->flags &= ~PF_MEMALLOC;

	cond_resched();

	if (likely(did_some_progress)) {
		page = get_page_from_freelist(gfp_mask, order,
						zonelist, alloc_flags);
		if (page)
			goto got_pg;
	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
		/*
		 * Go through the zonelist yet one more time, keep
		 * very high watermark here, this is only to catch
		 * a parallel oom killing, we must fail if we're still
		 * under heavy pressure.
		 */
		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
				zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
		if (page)
			goto got_pg;

		out_of_memory(zonelist, gfp_mask, order);
		goto restart;
	}

	/*
	 * Don't let big-order allocations loop unless the caller explicitly
	 * requests that.  Wait for some write requests to complete then retry.
	 *
	 * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
	 * <= 3, but that may not be true in other implementations.
	 */
	do_retry = 0;
	if (!(gfp_mask & __GFP_NORETRY)) {
		if ((order <= 3) || (gfp_mask & __GFP_REPEAT))
			do_retry = 1;
		if (gfp_mask & __GFP_NOFAIL)
			do_retry = 1;
	}
	if (do_retry) {
		congestion_wait(WRITE, HZ/50);
		goto rebalance;
	}

nopage:
	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
		printk(KERN_WARNING "%s: page allocation failure."
			" order:%d, mode:0x%x\n",
			p->comm, order, gfp_mask);
		dump_stack();
		show_mem();
	}
got_pg:
	return page;
}

EXPORT_SYMBOL(__alloc_pages);

/*
 * Common helper functions.
 */
fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
	struct page * page;
	page = alloc_pages(gfp_mask, order);
	if (!page)
		return 0;
	return (unsigned long) page_address(page);
}

EXPORT_SYMBOL(__get_free_pages);

fastcall unsigned long get_zeroed_page(gfp_t gfp_mask)
{
	struct page * page;

	/*
	 * get_zeroed_page() returns a 32-bit address, which cannot represent
	 * a highmem page
	 */
	VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);

	page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
	if (page)
		return (unsigned long) page_address(page);
	return 0;
}

EXPORT_SYMBOL(get_zeroed_page);

void __pagevec_free(struct pagevec *pvec)
{
	int i = pagevec_count(pvec);

	while (--i >= 0)
		free_hot_cold_page(pvec->pages[i], pvec->cold);
}

fastcall void __free_pages(struct page *page, unsigned int order)
{
	if (put_page_testzero(page)) {
		if (order == 0)
			free_hot_page(page);
		else
			__free_pages_ok(page, order);
	}
}

EXPORT_SYMBOL(__free_pages);

fastcall void free_pages(unsigned long addr, unsigned int order)
{
	if (addr != 0) {
		VM_BUG_ON(!virt_addr_valid((void *)addr));
		__free_pages(virt_to_page((void *)addr), order);
	}
}

EXPORT_SYMBOL(free_pages);

/*
 * Total amount of free (allocatable) RAM:
 */
unsigned int nr_free_pages(void)
{
	unsigned int sum = 0;
	struct zone *zone;

	for_each_zone(zone)
		sum += zone->free_pages;

	return sum;
}

EXPORT_SYMBOL(nr_free_pages);

#ifdef CONFIG_NUMA
unsigned int nr_free_pages_pgdat(pg_data_t *pgdat)
{
	unsigned int sum = 0;
	enum zone_type i;

	for (i = 0; i < MAX_NR_ZONES; i++)
		sum += pgdat->node_zones[i].free_pages;

	return sum;
}
#endif

static unsigned int nr_free_zone_pages(int offset)
{
	/* Just pick one node, since fallback list is circular */
	pg_data_t *pgdat = NODE_DATA(numa_node_id());
	unsigned int sum = 0;

	struct zonelist *zonelist = pgdat->node_zonelists + offset;
	struct zone **zonep = zonelist->zones;
	struct zone *zone;

	for (zone = *zonep++; zone; zone = *zonep++) {
		unsigned long size = zone->present_pages;
		unsigned long high = zone->pages_high;
		if (size > high)
			sum += size - high;
	}

	return sum;
}

/*
 * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL
 */
unsigned int nr_free_buffer_pages(void)
{
	return nr_free_zone_pages(gfp_zone(GFP_USER));
}

/*
 * Amount of free RAM allocatable within all zones
 */
unsigned int nr_free_pagecache_pages(void)
{
	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER));
}

static inline void show_node(struct zone *zone)
{
	if (NUMA_BUILD)
		printk("Node %ld ", zone_to_nid(zone));
}

void si_meminfo(struct sysinfo *val)
{
	val->totalram = totalram_pages;
	val->sharedram = 0;
	val->freeram = 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)
{
	pg_data_t *pgdat = NODE_DATA(nid);

	val->totalram = pgdat->node_present_pages;
	val->freeram = nr_free_pages_pgdat(pgdat);
#ifdef CONFIG_HIGHMEM
	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
	val->freehigh = pgdat->node_zones[ZONE_HIGHMEM].free_pages;
#else
	val->totalhigh = 0;
	val->freehigh = 0;
#endif
	val->mem_unit = PAGE_SIZE;
}
#endif

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

/*
 * 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.
 */
void show_free_areas(void)
{
	int cpu;
	unsigned long active;
	unsigned long inactive;
	unsigned long free;
	struct zone *zone;

	for_each_zone(zone) {
		if (!populated_zone(zone))
			continue;

		show_node(zone);
		printk("%s per-cpu:\n", zone->name);

		for_each_online_cpu(cpu) {
			struct per_cpu_pageset *pageset;

			pageset = zone_pcp(zone, cpu);

			printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d   "
			       "Cold: hi:%5d, btch:%4d usd:%4d\n",
			       cpu, pageset->pcp[0].high,
			       pageset->pcp[0].batch, pageset->pcp[0].count,
			       pageset->pcp[1].high, pageset->pcp[1].batch,
			       pageset->pcp[1].count);
		}
	}

	get_zone_counts(&active, &inactive, &free);

	printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu "
		"unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n",
		active,
		inactive,
		global_page_state(NR_FILE_DIRTY),
		global_page_state(NR_WRITEBACK),
		global_page_state(NR_UNSTABLE_NFS),
		nr_free_pages(),
		global_page_state(NR_SLAB_RECLAIMABLE) +
			global_page_state(NR_SLAB_UNRECLAIMABLE),
		global_page_state(NR_FILE_MAPPED),
		global_page_state(NR_PAGETABLE));

	for_each_zone(zone) {
		int i;

		if (!populated_zone(zone))
			continue;

		show_node(zone);
		printk("%s"
			" free:%lukB"
			" min:%lukB"
			" low:%lukB"
			" high:%lukB"
			" active:%lukB"
			" inactive:%lukB"
			" present:%lukB"
			" pages_scanned:%lu"
			" all_unreclaimable? %s"
			"\n",
			zone->name,
			K(zone->free_pages),
			K(zone->pages_min),
			K(zone->pages_low),
			K(zone->pages_high),
			K(zone->nr_active),
			K(zone->nr_inactive),
			K(zone->present_pages),
			zone->pages_scanned,
			(zone->all_unreclaimable ? "yes" : "no")
			);
		printk("lowmem_reserve[]:");
		for (i = 0; i < MAX_NR_ZONES; i++)
			printk(" %lu", zone->lowmem_reserve[i]);
		printk("\n");
	}

	for_each_zone(zone) {
 		unsigned long nr[MAX_ORDER], flags, order, total = 0;

		if (!populated_zone(zone))
			continue;

		show_node(zone);
		printk("%s: ", zone->name);

		spin_lock_irqsave(&zone->lock, flags);
		for (order = 0; order < MAX_ORDER; order++) {
			nr[order] = zone->free_area[order].nr_free;
			total += nr[order] << order;
		}
		spin_unlock_irqrestore(&zone->lock, flags);
		for (order = 0; order < MAX_ORDER; order++)
			printk("%lu*%lukB ", nr[order], K(1UL) << order);
		printk("= %lukB\n", K(total));
	}

	show_swap_cache_info();
}

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

	BUG_ON(zone_type >= MAX_NR_ZONES);
	zone_type++;

	do {
		zone_type--;
		zone = pgdat->node_zones + zone_type;
		if (populated_zone(zone)) {
			zonelist->zones[nr_zones++] = zone;
			check_highest_zone(zone_type);
		}

	} while (zone_type);
	return nr_zones;
}

#ifdef CONFIG_NUMA
#define MAX_NODE_LOAD (num_online_nodes())
static int __meminitdata 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 __meminit find_next_best_node(int node, nodemask_t *used_node_mask)
{
	int n, val;
	int min_val = INT_MAX;
	int best_node = -1;

	/* 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_online_node(n) {
		cpumask_t tmp;

		/* 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 = node_to_cpumask(n);
		if (!cpus_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;
}

static void __meminit build_zonelists(pg_data_t *pgdat)
{
	int j, node, local_node;
	enum zone_type i;
	int prev_node, load;
	struct zonelist *zonelist;
	nodemask_t used_mask;

	/* initialize zonelists */
	for (i = 0; i < MAX_NR_ZONES; i++) {
		zonelist = pgdat->node_zonelists + i;
		zonelist->zones[0] = NULL;
	}

	/* NUMA-aware ordering of nodes */
	local_node = pgdat->node_id;
	load = num_online_nodes();
	prev_node = local_node;
	nodes_clear(used_mask);
	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
		int distance = node_distance(local_node, node);

		/*
		 * If another node is sufficiently far away then it is better
		 * to reclaim pages in a zone before going off node.
		 */
		if (distance > RECLAIM_DISTANCE)
			zone_reclaim_mode = 1;

		/*
		 * 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 (distance != node_distance(local_node, prev_node))
			node_load[node] += load;
		prev_node = node;
		load--;
		for (i = 0; i < MAX_NR_ZONES; i++) {
			zonelist = pgdat->node_zonelists + i;
			for (j = 0; zonelist->zones[j] != NULL; j++);

	 		j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
			zonelist->zones[j] = NULL;
		}
	}
}

/* Construct the zonelist performance cache - see further mmzone.h */
static void __meminit build_zonelist_cache(pg_data_t *pgdat)
{
	int i;

	for (i = 0; i < MAX_NR_ZONES; i++) {
		struct zonelist *zonelist;
		struct zonelist_cache *zlc;
		struct zone **z;

		zonelist = pgdat->node_zonelists + i;
		zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
		for (z = zonelist->zones; *z; z++)
			zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*z);
	}
}

#else	/* CONFIG_NUMA */

static void __meminit build_zonelists(pg_data_t *pgdat)
{
	int node, local_node;
	enum zone_type i,j;

	local_node = pgdat->node_id;
	for (i = 0; i < MAX_NR_ZONES; i++) {
		struct zonelist *zonelist;

		zonelist = pgdat->node_zonelists + i;

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

		zonelist->zones[j] = NULL;
	}
}

/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
static void __meminit build_zonelist_cache(pg_data_t *pgdat)
{
	int i;

	for (i = 0; i < MAX_NR_ZONES; i++)
		pgdat->node_zonelists[i].zlcache_ptr = NULL;
}

#endif	/* CONFIG_NUMA */

/* return values int ....just for stop_machine_run() */
static int __meminit __build_all_zonelists(void *dummy)
{
	int nid;

	for_each_online_node(nid) {
		build_zonelists(NODE_DATA(nid));
		build_zonelist_cache(NODE_DATA(nid));
	}
	return 0;
}

void __meminit build_all_zonelists(void)
{
	if (system_state == SYSTEM_BOOTING) {
		__build_all_zonelists(NULL);
		cpuset_init_current_mems_allowed();
	} else {
		/* we have to stop all cpus to guaranntee there is no user
		   of zonelist */
		stop_machine_run(__build_all_zonelists, NULL, NR_CPUS);
		/* cpuset refresh routine should be here */
	}
	vm_total_pages = nr_free_pagecache_pages();
	printk("Built %i zonelists.  Total pages: %ld\n",
			num_online_nodes(), vm_total_pages);
}

/*
 * 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);
}

#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))

/*
 * 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)
{
	struct page *page;
	unsigned long end_pfn = start_pfn + size;
	unsigned long pfn;

	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
		if (!early_pfn_valid(pfn))
			continue;
		if (!early_pfn_in_nid(pfn, nid))
			continue;
		page = pfn_to_page(pfn);
		set_page_links(page, zone, nid, pfn);
		init_page_count(page);
		reset_page_mapcount(page);
		SetPageReserved(page);
		INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
		/* The shift won't overflow because ZONE_NORMAL is below 4G. */
		if (!is_highmem_idx(zone))
			set_page_address(page, __va(pfn << PAGE_SHIFT));
#endif
	}
}

void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone,
				unsigned long size)
{
	int order;
	for (order = 0; order < MAX_ORDER ; order++) {
		INIT_LIST_HEAD(&zone->free_area[order].free_list);
		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))
#endif

static int __cpuinit zone_batchsize(struct zone *zone)
{
	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->present_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 = (1 << (fls(batch + batch/2)-1)) - 1;

	return batch;
}

inline void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
	struct per_cpu_pages *pcp;

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

	pcp = &p->pcp[0];		/* hot */
	pcp->count = 0;
	pcp->high = 6 * batch;
	pcp->batch = max(1UL, 1 * batch);
	INIT_LIST_HEAD(&pcp->list);

	pcp = &p->pcp[1];		/* cold*/
	pcp->count = 0;
	pcp->high = 2 * batch;
	pcp->batch = max(1UL, batch/2);
	INIT_LIST_HEAD(&pcp->list);
}

/*
 * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist
 * to the value high for the pageset p.
 */

static void setup_pagelist_highmark(struct per_cpu_pageset *p,
				unsigned long high)
{
	struct per_cpu_pages *pcp;

	pcp = &p->pcp[0]; /* hot list */
	pcp->high = high;
	pcp->batch = max(1UL, high/4);
	if ((high/4) > (PAGE_SHIFT * 8))
		pcp->batch = PAGE_SHIFT * 8;
}


#ifdef 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.
 *
 * Some NUMA counter updates may also be caught by the boot pagesets.
 *
 * 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 struct per_cpu_pageset boot_pageset[NR_CPUS];

/*
 * Dynamically allocate memory for the
 * per cpu pageset array in struct zone.
 */
static int __cpuinit process_zones(int cpu)
{
	struct zone *zone, *dzone;

	for_each_zone(zone) {

		if (!populated_zone(zone))
			continue;

		zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
					 GFP_KERNEL, cpu_to_node(cpu));
		if (!zone_pcp(zone, cpu))
			goto bad;

		setup_pageset(zone_pcp(zone, cpu), zone_batchsize(zone));

		if (percpu_pagelist_fraction)
			setup_pagelist_highmark(zone_pcp(zone, cpu),