page_alloc.c

		zone->zone_pgdat = pgdat;
		zone_pcp_init(zone);

		/* For bootup, initialized properly in watermark setup */
		mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);

		lruvec_init(&zone->lruvec);
		if (!size)
			continue;

		set_pageblock_order();
		setup_usemap(pgdat, zone, zone_start_pfn, size);
		ret = init_currently_empty_zone(zone, zone_start_pfn, size);
		BUG_ON(ret);
		memmap_init(size, nid, j, zone_start_pfn);
	}
}

static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
{
	unsigned long __maybe_unused start = 0;
	unsigned long __maybe_unused offset = 0;

	/* Skip empty nodes */
	if (!pgdat->node_spanned_pages)
		return;

#ifdef CONFIG_FLAT_NODE_MEM_MAP
	start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
	offset = pgdat->node_start_pfn - start;
	/* ia64 gets its own node_mem_map, before this, without bootmem */
	if (!pgdat->node_mem_map) {
		unsigned long size, end;
		struct page *map;

		/*
		 * The zone's endpoints aren't required to be MAX_ORDER
		 * aligned but the node_mem_map endpoints must be in order
		 * for the buddy allocator to function correctly.
		 */
		end = pgdat_end_pfn(pgdat);
		end = ALIGN(end, MAX_ORDER_NR_PAGES);
		size =  (end - start) * sizeof(struct page);
		map = alloc_remap(pgdat->node_id, size);
		if (!map)
			map = memblock_virt_alloc_node_nopanic(size,
							       pgdat->node_id);
		pgdat->node_mem_map = map + offset;
	}
#ifndef CONFIG_NEED_MULTIPLE_NODES
	/*
	 * With no DISCONTIG, the global mem_map is just set as node 0's
	 */
	if (pgdat == NODE_DATA(0)) {
		mem_map = NODE_DATA(0)->node_mem_map;
#if defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) || defined(CONFIG_FLATMEM)
		if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
			mem_map -= offset;
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
	}
#endif
#endif /* CONFIG_FLAT_NODE_MEM_MAP */
}

void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
		unsigned long node_start_pfn, unsigned long *zholes_size)
{
	pg_data_t *pgdat = NODE_DATA(nid);
	unsigned long start_pfn = 0;
	unsigned long end_pfn = 0;

	/* pg_data_t should be reset to zero when it's allocated */
	WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);

	reset_deferred_meminit(pgdat);
	pgdat->node_id = nid;
	pgdat->node_start_pfn = node_start_pfn;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
	pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
		(u64)start_pfn << PAGE_SHIFT,
		end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0);
#else
	start_pfn = node_start_pfn;
#endif
	calculate_node_totalpages(pgdat, start_pfn, end_pfn,
				  zones_size, zholes_size);

	alloc_node_mem_map(pgdat);
#ifdef CONFIG_FLAT_NODE_MEM_MAP
	printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n",
		nid, (unsigned long)pgdat,
		(unsigned long)pgdat->node_mem_map);
#endif

	free_area_init_core(pgdat);
}

#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP

#if MAX_NUMNODES > 1
/*
 * Figure out the number of possible node ids.
 */
void __init setup_nr_node_ids(void)
{
	unsigned int highest;

	highest = find_last_bit(node_possible_map.bits, MAX_NUMNODES);
	nr_node_ids = highest + 1;
}
#endif

/**
 * node_map_pfn_alignment - determine the maximum internode alignment
 *
 * This function should be called after node map is populated and sorted.
 * It calculates the maximum power of two alignment which can distinguish
 * all the nodes.
 *
 * For example, if all nodes are 1GiB and aligned to 1GiB, the return value
 * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)).  If the
 * nodes are shifted by 256MiB, 256MiB.  Note that if only the last node is
 * shifted, 1GiB is enough and this function will indicate so.
 *
 * This is used to test whether pfn -> nid mapping of the chosen memory
 * model has fine enough granularity to avoid incorrect mapping for the
 * populated node map.
 *
 * Returns the determined alignment in pfn's.  0 if there is no alignment
 * requirement (single node).
 */
unsigned long __init node_map_pfn_alignment(void)
{
	unsigned long accl_mask = 0, last_end = 0;
	unsigned long start, end, mask;
	int last_nid = -1;
	int i, nid;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
		if (!start || last_nid < 0 || last_nid == nid) {
			last_nid = nid;
			last_end = end;
			continue;
		}

		/*
		 * Start with a mask granular enough to pin-point to the
		 * start pfn and tick off bits one-by-one until it becomes
		 * too coarse to separate the current node from the last.
		 */
		mask = ~((1 << __ffs(start)) - 1);
		while (mask && last_end <= (start & (mask << 1)))
			mask <<= 1;

		/* accumulate all internode masks */
		accl_mask |= mask;
	}

	/* convert mask to number of pages */
	return ~accl_mask + 1;
}

/* Find the lowest pfn for a node */
static unsigned long __init find_min_pfn_for_node(int nid)
{
	unsigned long min_pfn = ULONG_MAX;
	unsigned long start_pfn;
	int i;

	for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL)
		min_pfn = min(min_pfn, start_pfn);

	if (min_pfn == ULONG_MAX) {
		pr_warn("Could not find start_pfn for node %d\n", nid);
		return 0;
	}

	return min_pfn;
}

/**
 * find_min_pfn_with_active_regions - Find the minimum PFN registered
 *
 * It returns the minimum PFN based on information provided via
 * memblock_set_node().
 */
unsigned long __init find_min_pfn_with_active_regions(void)
{
	return find_min_pfn_for_node(MAX_NUMNODES);
}

/*
 * early_calculate_totalpages()
 * Sum pages in active regions for movable zone.
 * Populate N_MEMORY for calculating usable_nodes.
 */
static unsigned long __init early_calculate_totalpages(void)
{
	unsigned long totalpages = 0;
	unsigned long start_pfn, end_pfn;
	int i, nid;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
		unsigned long pages = end_pfn - start_pfn;

		totalpages += pages;
		if (pages)
			node_set_state(nid, N_MEMORY);
	}
	return totalpages;
}

/*
 * Find the PFN the Movable zone begins in each node. Kernel memory
 * is spread evenly between nodes as long as the nodes have enough
 * memory. When they don't, some nodes will have more kernelcore than
 * others
 */
static void __init find_zone_movable_pfns_for_nodes(void)
{
	int i, nid;
	unsigned long usable_startpfn;
	unsigned long kernelcore_node, kernelcore_remaining;
	/* save the state before borrow the nodemask */
	nodemask_t saved_node_state = node_states[N_MEMORY];
	unsigned long totalpages = early_calculate_totalpages();
	int usable_nodes = nodes_weight(node_states[N_MEMORY]);
	struct memblock_region *r;

	/* Need to find movable_zone earlier when movable_node is specified. */
	find_usable_zone_for_movable();

	/*
	 * If movable_node is specified, ignore kernelcore and movablecore
	 * options.
	 */
	if (movable_node_is_enabled()) {
		for_each_memblock(memory, r) {
			if (!memblock_is_hotpluggable(r))
				continue;

			nid = r->nid;

			usable_startpfn = PFN_DOWN(r->base);
			zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
				min(usable_startpfn, zone_movable_pfn[nid]) :
				usable_startpfn;
		}

		goto out2;
	}

	/*
	 * If kernelcore=mirror is specified, ignore movablecore option
	 */
	if (mirrored_kernelcore) {
		bool mem_below_4gb_not_mirrored = false;

		for_each_memblock(memory, r) {
			if (memblock_is_mirror(r))
				continue;

			nid = r->nid;

			usable_startpfn = memblock_region_memory_base_pfn(r);

			if (usable_startpfn < 0x100000) {
				mem_below_4gb_not_mirrored = true;
				continue;
			}

			zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
				min(usable_startpfn, zone_movable_pfn[nid]) :
				usable_startpfn;
		}

		if (mem_below_4gb_not_mirrored)
			pr_warn("This configuration results in unmirrored kernel memory.");

		goto out2;
	}

	/*
	 * If movablecore=nn[KMG] was specified, calculate what size of
	 * kernelcore that corresponds so that memory usable for
	 * any allocation type is evenly spread. If both kernelcore
	 * and movablecore are specified, then the value of kernelcore
	 * will be used for required_kernelcore if it's greater than
	 * what movablecore would have allowed.
	 */
	if (required_movablecore) {
		unsigned long corepages;

		/*
		 * Round-up so that ZONE_MOVABLE is at least as large as what
		 * was requested by the user
		 */
		required_movablecore =
			roundup(required_movablecore, MAX_ORDER_NR_PAGES);
		required_movablecore = min(totalpages, required_movablecore);
		corepages = totalpages - required_movablecore;

		required_kernelcore = max(required_kernelcore, corepages);
	}

	/*
	 * If kernelcore was not specified or kernelcore size is larger
	 * than totalpages, there is no ZONE_MOVABLE.
	 */
	if (!required_kernelcore || required_kernelcore >= totalpages)
		goto out;

	/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
	usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];

restart:
	/* Spread kernelcore memory as evenly as possible throughout nodes */
	kernelcore_node = required_kernelcore / usable_nodes;
	for_each_node_state(nid, N_MEMORY) {
		unsigned long start_pfn, end_pfn;

		/*
		 * Recalculate kernelcore_node if the division per node
		 * now exceeds what is necessary to satisfy the requested
		 * amount of memory for the kernel
		 */
		if (required_kernelcore < kernelcore_node)
			kernelcore_node = required_kernelcore / usable_nodes;

		/*
		 * As the map is walked, we track how much memory is usable
		 * by the kernel using kernelcore_remaining. When it is
		 * 0, the rest of the node is usable by ZONE_MOVABLE
		 */
		kernelcore_remaining = kernelcore_node;

		/* Go through each range of PFNs within this node */
		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
			unsigned long size_pages;

			start_pfn = max(start_pfn, zone_movable_pfn[nid]);
			if (start_pfn >= end_pfn)
				continue;

			/* Account for what is only usable for kernelcore */
			if (start_pfn < usable_startpfn) {
				unsigned long kernel_pages;
				kernel_pages = min(end_pfn, usable_startpfn)
								- start_pfn;

				kernelcore_remaining -= min(kernel_pages,
							kernelcore_remaining);
				required_kernelcore -= min(kernel_pages,
							required_kernelcore);

				/* Continue if range is now fully accounted */
				if (end_pfn <= usable_startpfn) {

					/*
					 * Push zone_movable_pfn to the end so
					 * that if we have to rebalance
					 * kernelcore across nodes, we will
					 * not double account here
					 */
					zone_movable_pfn[nid] = end_pfn;
					continue;
				}
				start_pfn = usable_startpfn;
			}

			/*
			 * The usable PFN range for ZONE_MOVABLE is from
			 * start_pfn->end_pfn. Calculate size_pages as the
			 * number of pages used as kernelcore
			 */
			size_pages = end_pfn - start_pfn;
			if (size_pages > kernelcore_remaining)
				size_pages = kernelcore_remaining;
			zone_movable_pfn[nid] = start_pfn + size_pages;

			/*
			 * Some kernelcore has been met, update counts and
			 * break if the kernelcore for this node has been
			 * satisfied
			 */
			required_kernelcore -= min(required_kernelcore,
								size_pages);
			kernelcore_remaining -= size_pages;
			if (!kernelcore_remaining)
				break;
		}
	}

	/*
	 * If there is still required_kernelcore, we do another pass with one
	 * less node in the count. This will push zone_movable_pfn[nid] further
	 * along on the nodes that still have memory until kernelcore is
	 * satisfied
	 */
	usable_nodes--;
	if (usable_nodes && required_kernelcore > usable_nodes)
		goto restart;

out2:
	/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
	for (nid = 0; nid < MAX_NUMNODES; nid++)
		zone_movable_pfn[nid] =
			roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);

out:
	/* restore the node_state */
	node_states[N_MEMORY] = saved_node_state;
}

/* Any regular or high memory on that node ? */
static void check_for_memory(pg_data_t *pgdat, int nid)
{
	enum zone_type zone_type;

	if (N_MEMORY == N_NORMAL_MEMORY)
		return;

	for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
		struct zone *zone = &pgdat->node_zones[zone_type];
		if (populated_zone(zone)) {
			node_set_state(nid, N_HIGH_MEMORY);
			if (N_NORMAL_MEMORY != N_HIGH_MEMORY &&
			    zone_type <= ZONE_NORMAL)
				node_set_state(nid, N_NORMAL_MEMORY);
			break;
		}
	}
}

/**
 * free_area_init_nodes - Initialise all pg_data_t and zone data
 * @max_zone_pfn: an array of max PFNs for each zone
 *
 * This will call free_area_init_node() for each active node in the system.
 * Using the page ranges provided by memblock_set_node(), the size of each
 * zone in each node and their holes is calculated. If the maximum PFN
 * between two adjacent zones match, it is assumed that the zone is empty.
 * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed
 * that arch_max_dma32_pfn has no pages. It is also assumed that a zone
 * starts where the previous one ended. For example, ZONE_DMA32 starts
 * at arch_max_dma_pfn.
 */
void __init free_area_init_nodes(unsigned long *max_zone_pfn)
{
	unsigned long start_pfn, end_pfn;
	int i, nid;

	/* Record where the zone boundaries are */
	memset(arch_zone_lowest_possible_pfn, 0,
				sizeof(arch_zone_lowest_possible_pfn));
	memset(arch_zone_highest_possible_pfn, 0,
				sizeof(arch_zone_highest_possible_pfn));
	arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions();
	arch_zone_highest_possible_pfn[0] = max_zone_pfn[0];
	for (i = 1; i < MAX_NR_ZONES; i++) {
		if (i == ZONE_MOVABLE)
			continue;
		arch_zone_lowest_possible_pfn[i] =
			arch_zone_highest_possible_pfn[i-1];
		arch_zone_highest_possible_pfn[i] =
			max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]);
	}
	arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0;
	arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0;

	/* Find the PFNs that ZONE_MOVABLE begins at in each node */
	memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
	find_zone_movable_pfns_for_nodes();

	/* Print out the zone ranges */
	pr_info("Zone ranges:\n");
	for (i = 0; i < MAX_NR_ZONES; i++) {
		if (i == ZONE_MOVABLE)
			continue;
		pr_info("  %-8s ", zone_names[i]);
		if (arch_zone_lowest_possible_pfn[i] ==
				arch_zone_highest_possible_pfn[i])
			pr_cont("empty\n");
		else
			pr_cont("[mem %#018Lx-%#018Lx]\n",
				(u64)arch_zone_lowest_possible_pfn[i]
					<< PAGE_SHIFT,
				((u64)arch_zone_highest_possible_pfn[i]
					<< PAGE_SHIFT) - 1);
	}

	/* Print out the PFNs ZONE_MOVABLE begins at in each node */
	pr_info("Movable zone start for each node\n");
	for (i = 0; i < MAX_NUMNODES; i++) {
		if (zone_movable_pfn[i])
			pr_info("  Node %d: %#018Lx\n", i,
			       (u64)zone_movable_pfn[i] << PAGE_SHIFT);
	}

	/* Print out the early node map */
	pr_info("Early memory node ranges\n");
	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
		pr_info("  node %3d: [mem %#018Lx-%#018Lx]\n", nid,
			(u64)start_pfn << PAGE_SHIFT,
			((u64)end_pfn << PAGE_SHIFT) - 1);

	/* Initialise every node */
	mminit_verify_pageflags_layout();
	setup_nr_node_ids();
	for_each_online_node(nid) {
		pg_data_t *pgdat = NODE_DATA(nid);
		free_area_init_node(nid, NULL,
				find_min_pfn_for_node(nid), NULL);

		/* Any memory on that node */
		if (pgdat->node_present_pages)
			node_set_state(nid, N_MEMORY);
		check_for_memory(pgdat, nid);
	}
}

static int __init cmdline_parse_core(char *p, unsigned long *core)
{
	unsigned long long coremem;
	if (!p)
		return -EINVAL;

	coremem = memparse(p, &p);
	*core = coremem >> PAGE_SHIFT;

	/* Paranoid check that UL is enough for the coremem value */
	WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);

	return 0;
}

/*
 * kernelcore=size sets the amount of memory for use for allocations that
 * cannot be reclaimed or migrated.
 */
static int __init cmdline_parse_kernelcore(char *p)
{
	/* parse kernelcore=mirror */
	if (parse_option_str(p, "mirror")) {
		mirrored_kernelcore = true;
		return 0;
	}

	return cmdline_parse_core(p, &required_kernelcore);
}

/*
 * movablecore=size sets the amount of memory for use for allocations that
 * can be reclaimed or migrated.
 */
static int __init cmdline_parse_movablecore(char *p)
{
	return cmdline_parse_core(p, &required_movablecore);
}

early_param("kernelcore", cmdline_parse_kernelcore);
early_param("movablecore", cmdline_parse_movablecore);

#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */

void adjust_managed_page_count(struct page *page, long count)
{
	spin_lock(&managed_page_count_lock);
	page_zone(page)->managed_pages += count;
	totalram_pages += count;
#ifdef CONFIG_HIGHMEM
	if (PageHighMem(page))
		totalhigh_pages += count;
#endif
	spin_unlock(&managed_page_count_lock);
}
EXPORT_SYMBOL(adjust_managed_page_count);

unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
{
	void *pos;
	unsigned long pages = 0;

	start = (void *)PAGE_ALIGN((unsigned long)start);
	end = (void *)((unsigned long)end & PAGE_MASK);
	for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
		if ((unsigned int)poison <= 0xFF)
			memset(pos, poison, PAGE_SIZE);
		free_reserved_page(virt_to_page(pos));
	}

	if (pages && s)
		pr_info("Freeing %s memory: %ldK (%p - %p)\n",
			s, pages << (PAGE_SHIFT - 10), start, end);

	return pages;
}
EXPORT_SYMBOL(free_reserved_area);

#ifdef	CONFIG_HIGHMEM
void free_highmem_page(struct page *page)
{
	__free_reserved_page(page);
	totalram_pages++;
	page_zone(page)->managed_pages++;
	totalhigh_pages++;
}
#endif


void __init mem_init_print_info(const char *str)
{
	unsigned long physpages, codesize, datasize, rosize, bss_size;
	unsigned long init_code_size, init_data_size;

	physpages = get_num_physpages();
	codesize = _etext - _stext;
	datasize = _edata - _sdata;
	rosize = __end_rodata - __start_rodata;
	bss_size = __bss_stop - __bss_start;
	init_data_size = __init_end - __init_begin;
	init_code_size = _einittext - _sinittext;

	/*
	 * Detect special cases and adjust section sizes accordingly:
	 * 1) .init.* may be embedded into .data sections
	 * 2) .init.text.* may be out of [__init_begin, __init_end],
	 *    please refer to arch/tile/kernel/vmlinux.lds.S.
	 * 3) .rodata.* may be embedded into .text or .data sections.
	 */
#define adj_init_size(start, end, size, pos, adj) \
	do { \
		if (start <= pos && pos < end && size > adj) \
			size -= adj; \
	} while (0)

	adj_init_size(__init_begin, __init_end, init_data_size,
		     _sinittext, init_code_size);
	adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size);
	adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size);
	adj_init_size(_stext, _etext, codesize, __start_rodata, rosize);
	adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize);

#undef	adj_init_size

	pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved"
#ifdef	CONFIG_HIGHMEM
		", %luK highmem"
#endif
		"%s%s)\n",
		nr_free_pages() << (PAGE_SHIFT - 10),
		physpages << (PAGE_SHIFT - 10),
		codesize >> 10, datasize >> 10, rosize >> 10,
		(init_data_size + init_code_size) >> 10, bss_size >> 10,
		(physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT - 10),
		totalcma_pages << (PAGE_SHIFT - 10),
#ifdef	CONFIG_HIGHMEM
		totalhigh_pages << (PAGE_SHIFT - 10),
#endif
		str ? ", " : "", str ? str : "");
}

/**
 * set_dma_reserve - set the specified number of pages reserved in the first zone
 * @new_dma_reserve: The number of pages to mark reserved
 *
 * The per-cpu batchsize and zone watermarks are determined by managed_pages.
 * In the DMA zone, a significant percentage may be consumed by kernel image
 * and other unfreeable allocations which can skew the watermarks badly. This
 * function may optionally be used to account for unfreeable pages in the
 * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and
 * smaller per-cpu batchsize.
 */
void __init set_dma_reserve(unsigned long new_dma_reserve)
{
	dma_reserve = new_dma_reserve;
}

void __init free_area_init(unsigned long *zones_size)
{
	free_area_init_node(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) {
		lru_add_drain_cpu(cpu);
		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.
		 */
		cpu_vm_stats_fold(cpu);
	}
	return NOTIFY_OK;
}

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

/*
 * calculate_totalreserve_pages - called when sysctl_lowmem_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;
			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 the high watermark as reserved pages. */
			max += high_wmark_pages(zone);

			if (max > zone->managed_pages)
				max = zone->managed_pages;

			zone->totalreserve_pages = max;

			reserve_pages += max;
		}
	}
	totalreserve_pages = reserve_pages;
}

/*
 * setup_per_zone_lowmem_reserve - called whenever
 *	sysctl_lowmem_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 managed_pages = zone->managed_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] = managed_pages /
					sysctl_lowmem_reserve_ratio[idx];
				managed_pages += lower_zone->managed_pages;
			}
		}
	}

	/* update totalreserve_pages */
	calculate_totalreserve_pages();
}

static void __setup_per_zone_wmarks(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->managed_pages;
	}

	for_each_zone(zone) {
		u64 tmp;

		spin_lock_irqsave(&zone->lock, flags);
		tmp = (u64)pages_min * zone->managed_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 WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
			 * deltas control asynch page reclaim, and so should
			 * not be capped for highmem.
			 */
			unsigned long min_pages;

			min_pages = zone->managed_pages / 1024;
			min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL);
			zone->watermark[WMARK_MIN] = min_pages;
		} else {
			/*
			 * If it's a lowmem zone, reserve a number of pages
			 * proportionate to the zone's size.
			 */
			zone->watermark[WMARK_MIN] = tmp;
		}

		/*
		 * Set the kswapd watermarks distance according to the
		 * scale factor in proportion to available memory, but
		 * ensure a minimum size on small systems.
		 */
		tmp = max_t(u64, tmp >> 2,
			    mult_frac(zone->managed_pages,
				      watermark_scale_factor, 10000));

		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + tmp;
		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;

		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
			high_wmark_pages(zone) - low_wmark_pages(zone) -
			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));

		spin_unlock_irqrestore(&zone->lock, flags);
	}

	/* update totalreserve_pages */
	calculate_totalreserve_pages();
}

/**
 * setup_per_zone_wmarks - called when min_free_kbytes changes
 * or when memory is hot-{added|removed}
 *
 * Ensures that the watermark[min,low,high] values for each zone are set
 * correctly with respect to min_free_kbytes.
 */
void setup_per_zone_wmarks(void)
{
	mutex_lock(&zonelists_mutex);
	__setup_per_zone_wmarks();
	mutex_unlock(&zonelists_mutex);
}

/*
 * 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
 */
int __meminit init_per_zone_wmark_min(void)
{
	unsigned long lowmem_kbytes;
	int new_min_free_kbytes;

	lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
	new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16);

	if (new_min_free_kbytes > user_min_free_kbytes) {
		min_free_kbytes = new_min_free_kbytes;
		if (min_free_kbytes < 128)
			min_free_kbytes = 128;
		if (min_free_kbytes > 65536)
			min_free_kbytes = 65536;
	} else {
		pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n",
				new_min_free_kbytes, user_min_free_kbytes);
	}
	setup_per_zone_wmarks();
	refresh_zone_stat_thresholds();
	setup_per_zone_lowmem_reserve();
	return 0;
}
core_initcall(init_per_zone_wmark_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(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	if (write) {
		user_min_free_kbytes = min_free_kbytes;
		setup_per_zone_wmarks();
	}
	return 0;
}

int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	if (write)
		setup_per_zone_wmarks();

	return 0;
}

#ifdef CONFIG_NUMA
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	struct zone *zone;
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	for_each_zone(zone)
		zone->min_unmapped_pages = (zone->managed_pages *
				sysctl_min_unmapped_ratio) / 100;
	return 0;
}

int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	struct zone *zone;
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	for_each_zone(zone)
		zone->min_slab_pages = (zone->managed_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
 * minimum watermarks. The lowmem reserve ratio can only make sense
 * if in function of the boot time zone sizes.
 */