memory_hotplug.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/mm/memory_hotplug.c
 *
 *  Copyright (C)
 */

#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/memory.h>
#include <linux/memremap.h>
#include <linux/memory_hotplug.h>
#include <linux/highmem.h>
#include <linux/vmalloc.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/mm_inline.h>
#include <linux/firmware-map.h>
#include <linux/stop_machine.h>
#include <linux/hugetlb.h>
#include <linux/memblock.h>
#include <linux/compaction.h>
#include <linux/rmap.h>

#include <asm/tlbflush.h>

#include "internal.h"
#include "shuffle.h"

/*
 * online_page_callback contains pointer to current page onlining function.
 * Initially it is generic_online_page(). If it is required it could be
 * changed by calling set_online_page_callback() for callback registration
 * and restore_online_page_callback() for generic callback restore.
 */

static online_page_callback_t online_page_callback = generic_online_page;
static DEFINE_MUTEX(online_page_callback_lock);

DEFINE_STATIC_PERCPU_RWSEM(mem_hotplug_lock);

void get_online_mems(void)
{
	percpu_down_read(&mem_hotplug_lock);
}

void put_online_mems(void)
{
	percpu_up_read(&mem_hotplug_lock);
}

bool movable_node_enabled = false;

#ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE
bool memhp_auto_online;
#else
bool memhp_auto_online = true;
#endif
EXPORT_SYMBOL_GPL(memhp_auto_online);

static int __init setup_memhp_default_state(char *str)
{
	if (!strcmp(str, "online"))
		memhp_auto_online = true;
	else if (!strcmp(str, "offline"))
		memhp_auto_online = false;

	return 1;
}
__setup("memhp_default_state=", setup_memhp_default_state);

void mem_hotplug_begin(void)
{
	cpus_read_lock();
	percpu_down_write(&mem_hotplug_lock);
}

void mem_hotplug_done(void)
{
	percpu_up_write(&mem_hotplug_lock);
	cpus_read_unlock();
}

u64 max_mem_size = U64_MAX;

/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
	struct resource *res;
	unsigned long flags =  IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
	char *resource_name = "System RAM";

	if (start + size > max_mem_size)
		return ERR_PTR(-E2BIG);

	/*
	 * Request ownership of the new memory range.  This might be
	 * a child of an existing resource that was present but
	 * not marked as busy.
	 */
	res = __request_region(&iomem_resource, start, size,
			       resource_name, flags);

	if (!res) {
		pr_debug("Unable to reserve System RAM region: %016llx->%016llx\n",
				start, start + size);
		return ERR_PTR(-EEXIST);
	}
	return res;
}

static void release_memory_resource(struct resource *res)
{
	if (!res)
		return;
	release_resource(res);
	kfree(res);
}

#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
void get_page_bootmem(unsigned long info,  struct page *page,
		      unsigned long type)
{
	page->freelist = (void *)type;
	SetPagePrivate(page);
	set_page_private(page, info);
	page_ref_inc(page);
}

void put_page_bootmem(struct page *page)
{
	unsigned long type;

	type = (unsigned long) page->freelist;
	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);

	if (page_ref_dec_return(page) == 1) {
		page->freelist = NULL;
		ClearPagePrivate(page);
		set_page_private(page, 0);
		INIT_LIST_HEAD(&page->lru);
		free_reserved_page(page);
	}
}

#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
#ifndef CONFIG_SPARSEMEM_VMEMMAP
static void register_page_bootmem_info_section(unsigned long start_pfn)
{
	unsigned long mapsize, section_nr, i;
	struct mem_section *ms;
	struct page *page, *memmap;
	struct mem_section_usage *usage;

	section_nr = pfn_to_section_nr(start_pfn);
	ms = __nr_to_section(section_nr);

	/* Get section's memmap address */
	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);

	/*
	 * Get page for the memmap's phys address
	 * XXX: need more consideration for sparse_vmemmap...
	 */
	page = virt_to_page(memmap);
	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;

	/* remember memmap's page */
	for (i = 0; i < mapsize; i++, page++)
		get_page_bootmem(section_nr, page, SECTION_INFO);

	usage = ms->usage;
	page = virt_to_page(usage);

	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;

	for (i = 0; i < mapsize; i++, page++)
		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);

}
#else /* CONFIG_SPARSEMEM_VMEMMAP */
static void register_page_bootmem_info_section(unsigned long start_pfn)
{
	unsigned long mapsize, section_nr, i;
	struct mem_section *ms;
	struct page *page, *memmap;
	struct mem_section_usage *usage;

	section_nr = pfn_to_section_nr(start_pfn);
	ms = __nr_to_section(section_nr);

	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);

	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);

	usage = ms->usage;
	page = virt_to_page(usage);

	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;

	for (i = 0; i < mapsize; i++, page++)
		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */

void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
{
	unsigned long i, pfn, end_pfn, nr_pages;
	int node = pgdat->node_id;
	struct page *page;

	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
	page = virt_to_page(pgdat);

	for (i = 0; i < nr_pages; i++, page++)
		get_page_bootmem(node, page, NODE_INFO);

	pfn = pgdat->node_start_pfn;
	end_pfn = pgdat_end_pfn(pgdat);

	/* register section info */
	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
		/*
		 * Some platforms can assign the same pfn to multiple nodes - on
		 * node0 as well as nodeN.  To avoid registering a pfn against
		 * multiple nodes we check that this pfn does not already
		 * reside in some other nodes.
		 */
		if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node))
			register_page_bootmem_info_section(pfn);
	}
}
#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */

static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
		const char *reason)
{
	/*
	 * Disallow all operations smaller than a sub-section and only
	 * allow operations smaller than a section for
	 * SPARSEMEM_VMEMMAP. Note that check_hotplug_memory_range()
	 * enforces a larger memory_block_size_bytes() granularity for
	 * memory that will be marked online, so this check should only
	 * fire for direct arch_{add,remove}_memory() users outside of
	 * add_memory_resource().
	 */
	unsigned long min_align;

	if (IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP))
		min_align = PAGES_PER_SUBSECTION;
	else
		min_align = PAGES_PER_SECTION;
	if (!IS_ALIGNED(pfn, min_align)
			|| !IS_ALIGNED(nr_pages, min_align)) {
		WARN(1, "Misaligned __%s_pages start: %#lx end: #%lx\n",
				reason, pfn, pfn + nr_pages - 1);
		return -EINVAL;
	}
	return 0;
}

static int check_hotplug_memory_addressable(unsigned long pfn,
					    unsigned long nr_pages)
{
	const u64 max_addr = PFN_PHYS(pfn + nr_pages) - 1;

	if (max_addr >> MAX_PHYSMEM_BITS) {
		const u64 max_allowed = (1ull << (MAX_PHYSMEM_BITS + 1)) - 1;
		WARN(1,
		     "Hotplugged memory exceeds maximum addressable address, range=%#llx-%#llx, maximum=%#llx\n",
		     (u64)PFN_PHYS(pfn), max_addr, max_allowed);
		return -E2BIG;
	}

	return 0;
}

/*
 * Reasonably generic function for adding memory.  It is
 * expected that archs that support memory hotplug will
 * call this function after deciding the zone to which to
 * add the new pages.
 */
int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
		struct mhp_restrictions *restrictions)
{
	int err;
	unsigned long nr, start_sec, end_sec;
	struct vmem_altmap *altmap = restrictions->altmap;

	err = check_hotplug_memory_addressable(pfn, nr_pages);
	if (err)
		return err;

	if (altmap) {
		/*
		 * Validate altmap is within bounds of the total request
		 */
		if (altmap->base_pfn != pfn
				|| vmem_altmap_offset(altmap) > nr_pages) {
			pr_warn_once("memory add fail, invalid altmap\n");
			return -EINVAL;
		}
		altmap->alloc = 0;
	}

	err = check_pfn_span(pfn, nr_pages, "add");
	if (err)
		return err;

	start_sec = pfn_to_section_nr(pfn);
	end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
	for (nr = start_sec; nr <= end_sec; nr++) {
		unsigned long pfns;

		pfns = min(nr_pages, PAGES_PER_SECTION
				- (pfn & ~PAGE_SECTION_MASK));
		err = sparse_add_section(nid, pfn, pfns, altmap);
		if (err)
			break;
		pfn += pfns;
		nr_pages -= pfns;
		cond_resched();
	}
	vmemmap_populate_print_last();
	return err;
}

/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
				     unsigned long start_pfn,
				     unsigned long end_pfn)
{
	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) {
		if (unlikely(!pfn_to_online_page(start_pfn)))
			continue;

		if (unlikely(pfn_to_nid(start_pfn) != nid))
			continue;

		if (zone != page_zone(pfn_to_page(start_pfn)))
			continue;

		return start_pfn;
	}

	return 0;
}

/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
				    unsigned long start_pfn,
				    unsigned long end_pfn)
{
	unsigned long pfn;

	/* pfn is the end pfn of a memory section. */
	pfn = end_pfn - 1;
	for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) {
		if (unlikely(!pfn_to_online_page(pfn)))
			continue;

		if (unlikely(pfn_to_nid(pfn) != nid))
			continue;

		if (zone != page_zone(pfn_to_page(pfn)))
			continue;

		return pfn;
	}

	return 0;
}

static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
			     unsigned long end_pfn)
{
	unsigned long pfn;
	int nid = zone_to_nid(zone);

	zone_span_writelock(zone);
	if (zone->zone_start_pfn == start_pfn) {
		/*
		 * If the section is smallest section in the zone, it need
		 * shrink zone->zone_start_pfn and zone->zone_spanned_pages.
		 * In this case, we find second smallest valid mem_section
		 * for shrinking zone.
		 */
		pfn = find_smallest_section_pfn(nid, zone, end_pfn,
						zone_end_pfn(zone));
		if (pfn) {
			zone->spanned_pages = zone_end_pfn(zone) - pfn;
			zone->zone_start_pfn = pfn;
		} else {
			zone->zone_start_pfn = 0;
			zone->spanned_pages = 0;
		}
	} else if (zone_end_pfn(zone) == end_pfn) {
		/*
		 * If the section is biggest section in the zone, it need
		 * shrink zone->spanned_pages.
		 * In this case, we find second biggest valid mem_section for
		 * shrinking zone.
		 */
		pfn = find_biggest_section_pfn(nid, zone, zone->zone_start_pfn,
					       start_pfn);
		if (pfn)
			zone->spanned_pages = pfn - zone->zone_start_pfn + 1;
		else {
			zone->zone_start_pfn = 0;
			zone->spanned_pages = 0;
		}
	}
	zone_span_writeunlock(zone);
}

static void update_pgdat_span(struct pglist_data *pgdat)
{
	unsigned long node_start_pfn = 0, node_end_pfn = 0;
	struct zone *zone;

	for (zone = pgdat->node_zones;
	     zone < pgdat->node_zones + MAX_NR_ZONES; zone++) {
		unsigned long zone_end_pfn = zone->zone_start_pfn +
					     zone->spanned_pages;

		/* No need to lock the zones, they can't change. */
		if (!zone->spanned_pages)
			continue;
		if (!node_end_pfn) {
			node_start_pfn = zone->zone_start_pfn;
			node_end_pfn = zone_end_pfn;
			continue;
		}

		if (zone_end_pfn > node_end_pfn)
			node_end_pfn = zone_end_pfn;
		if (zone->zone_start_pfn < node_start_pfn)
			node_start_pfn = zone->zone_start_pfn;
	}

	pgdat->node_start_pfn = node_start_pfn;
	pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
}

void __ref remove_pfn_range_from_zone(struct zone *zone,
				      unsigned long start_pfn,
				      unsigned long nr_pages)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	unsigned long flags;

	/* Poison struct pages because they are now uninitialized again. */
	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);

#ifdef CONFIG_ZONE_DEVICE
	/*
	 * Zone shrinking code cannot properly deal with ZONE_DEVICE. So
	 * we will not try to shrink the zones - which is okay as
	 * set_zone_contiguous() cannot deal with ZONE_DEVICE either way.
	 */
	if (zone_idx(zone) == ZONE_DEVICE)
		return;
#endif

	clear_zone_contiguous(zone);

	pgdat_resize_lock(zone->zone_pgdat, &flags);
	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
	update_pgdat_span(pgdat);
	pgdat_resize_unlock(zone->zone_pgdat, &flags);

	set_zone_contiguous(zone);
}

static void __remove_section(unsigned long pfn, unsigned long nr_pages,
			     unsigned long map_offset,
			     struct vmem_altmap *altmap)
{
	struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));

	if (WARN_ON_ONCE(!valid_section(ms)))
		return;

	sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap);
}

/**
 * __remove_pages() - remove sections of pages
 * @pfn: starting pageframe (must be aligned to start of a section)
 * @nr_pages: number of pages to remove (must be multiple of section size)
 * @altmap: alternative device page map or %NULL if default memmap is used
 *
 * Generic helper function to remove section mappings and sysfs entries
 * for the section of the memory we are removing. Caller needs to make
 * sure that pages are marked reserved and zones are adjust properly by
 * calling offline_pages().
 */
void __remove_pages(unsigned long pfn, unsigned long nr_pages,
		    struct vmem_altmap *altmap)
{
	unsigned long map_offset = 0;
	unsigned long nr, start_sec, end_sec;

	map_offset = vmem_altmap_offset(altmap);

	if (check_pfn_span(pfn, nr_pages, "remove"))
		return;

	start_sec = pfn_to_section_nr(pfn);
	end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
	for (nr = start_sec; nr <= end_sec; nr++) {
		unsigned long pfns;

		cond_resched();
		pfns = min(nr_pages, PAGES_PER_SECTION
				- (pfn & ~PAGE_SECTION_MASK));
		__remove_section(pfn, pfns, map_offset, altmap);
		pfn += pfns;
		nr_pages -= pfns;
		map_offset = 0;
	}
}

int set_online_page_callback(online_page_callback_t callback)
{
	int rc = -EINVAL;

	get_online_mems();
	mutex_lock(&online_page_callback_lock);

	if (online_page_callback == generic_online_page) {
		online_page_callback = callback;
		rc = 0;
	}

	mutex_unlock(&online_page_callback_lock);
	put_online_mems();

	return rc;
}
EXPORT_SYMBOL_GPL(set_online_page_callback);

int restore_online_page_callback(online_page_callback_t callback)
{
	int rc = -EINVAL;

	get_online_mems();
	mutex_lock(&online_page_callback_lock);

	if (online_page_callback == callback) {
		online_page_callback = generic_online_page;
		rc = 0;
	}

	mutex_unlock(&online_page_callback_lock);
	put_online_mems();

	return rc;
}
EXPORT_SYMBOL_GPL(restore_online_page_callback);

void generic_online_page(struct page *page, unsigned int order)
{
	kernel_map_pages(page, 1 << order, 1);
	__free_pages_core(page, order);
	totalram_pages_add(1UL << order);
#ifdef CONFIG_HIGHMEM
	if (PageHighMem(page))
		totalhigh_pages_add(1UL << order);
#endif
}
EXPORT_SYMBOL_GPL(generic_online_page);

static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
			void *arg)
{
	const unsigned long end_pfn = start_pfn + nr_pages;
	unsigned long pfn;
	int order;

	/*
	 * Online the pages. The callback might decide to keep some pages
	 * PG_reserved (to add them to the buddy later), but we still account
	 * them as being online/belonging to this zone ("present").
	 */
	for (pfn = start_pfn; pfn < end_pfn; pfn += 1ul << order) {
		order = min(MAX_ORDER - 1, get_order(PFN_PHYS(end_pfn - pfn)));
		/* __free_pages_core() wants pfns to be aligned to the order */
		if (WARN_ON_ONCE(!IS_ALIGNED(pfn, 1ul << order)))
			order = 0;
		(*online_page_callback)(pfn_to_page(pfn), order);
	}

	/* mark all involved sections as online */
	online_mem_sections(start_pfn, end_pfn);

	*(unsigned long *)arg += nr_pages;
	return 0;
}

/* check which state of node_states will be changed when online memory */
static void node_states_check_changes_online(unsigned long nr_pages,
	struct zone *zone, struct memory_notify *arg)
{
	int nid = zone_to_nid(zone);

	arg->status_change_nid = NUMA_NO_NODE;
	arg->status_change_nid_normal = NUMA_NO_NODE;
	arg->status_change_nid_high = NUMA_NO_NODE;

	if (!node_state(nid, N_MEMORY))
		arg->status_change_nid = nid;
	if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY))
		arg->status_change_nid_normal = nid;
#ifdef CONFIG_HIGHMEM
	if (zone_idx(zone) <= ZONE_HIGHMEM && !node_state(nid, N_HIGH_MEMORY))
		arg->status_change_nid_high = nid;
#endif
}

static void node_states_set_node(int node, struct memory_notify *arg)
{
	if (arg->status_change_nid_normal >= 0)
		node_set_state(node, N_NORMAL_MEMORY);

	if (arg->status_change_nid_high >= 0)
		node_set_state(node, N_HIGH_MEMORY);

	if (arg->status_change_nid >= 0)
		node_set_state(node, N_MEMORY);
}

static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn,
		unsigned long nr_pages)
{
	unsigned long old_end_pfn = zone_end_pfn(zone);

	if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn)
		zone->zone_start_pfn = start_pfn;

	zone->spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - zone->zone_start_pfn;
}

static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned long start_pfn,
                                     unsigned long nr_pages)
{
	unsigned long old_end_pfn = pgdat_end_pfn(pgdat);

	if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
		pgdat->node_start_pfn = start_pfn;

	pgdat->node_spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - pgdat->node_start_pfn;

}
/*
 * Associate the pfn range with the given zone, initializing the memmaps
 * and resizing the pgdat/zone data to span the added pages. After this
 * call, all affected pages are PG_reserved.
 */
void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
		unsigned long nr_pages, struct vmem_altmap *altmap)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int nid = pgdat->node_id;
	unsigned long flags;

	clear_zone_contiguous(zone);

	/* TODO Huh pgdat is irqsave while zone is not. It used to be like that before */
	pgdat_resize_lock(pgdat, &flags);
	zone_span_writelock(zone);
	if (zone_is_empty(zone))
		init_currently_empty_zone(zone, start_pfn, nr_pages);
	resize_zone_range(zone, start_pfn, nr_pages);
	zone_span_writeunlock(zone);
	resize_pgdat_range(pgdat, start_pfn, nr_pages);
	pgdat_resize_unlock(pgdat, &flags);

	/*
	 * TODO now we have a visible range of pages which are not associated
	 * with their zone properly. Not nice but set_pfnblock_flags_mask
	 * expects the zone spans the pfn range. All the pages in the range
	 * are reserved so nobody should be touching them so we should be safe
	 */
	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
			MEMMAP_HOTPLUG, altmap);

	set_zone_contiguous(zone);
}

/*
 * Returns a default kernel memory zone for the given pfn range.
 * If no kernel zone covers this pfn range it will automatically go
 * to the ZONE_NORMAL.
 */
static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn,
		unsigned long nr_pages)
{
	struct pglist_data *pgdat = NODE_DATA(nid);
	int zid;

	for (zid = 0; zid <= ZONE_NORMAL; zid++) {
		struct zone *zone = &pgdat->node_zones[zid];

		if (zone_intersects(zone, start_pfn, nr_pages))
			return zone;
	}

	return &pgdat->node_zones[ZONE_NORMAL];
}

static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
		unsigned long nr_pages)
{
	struct zone *kernel_zone = default_kernel_zone_for_pfn(nid, start_pfn,
			nr_pages);
	struct zone *movable_zone = &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];
	bool in_kernel = zone_intersects(kernel_zone, start_pfn, nr_pages);
	bool in_movable = zone_intersects(movable_zone, start_pfn, nr_pages);

	/*
	 * We inherit the existing zone in a simple case where zones do not
	 * overlap in the given range
	 */
	if (in_kernel ^ in_movable)
		return (in_kernel) ? kernel_zone : movable_zone;

	/*
	 * If the range doesn't belong to any zone or two zones overlap in the
	 * given range then we use movable zone only if movable_node is
	 * enabled because we always online to a kernel zone by default.
	 */
	return movable_node_enabled ? movable_zone : kernel_zone;
}

struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
		unsigned long nr_pages)
{
	if (online_type == MMOP_ONLINE_KERNEL)
		return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages);

	if (online_type == MMOP_ONLINE_MOVABLE)
		return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];

	return default_zone_for_pfn(nid, start_pfn, nr_pages);
}

int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
		       int online_type, int nid)
{
	unsigned long flags;
	unsigned long onlined_pages = 0;
	struct zone *zone;
	int need_zonelists_rebuild = 0;
	int ret;
	struct memory_notify arg;

	mem_hotplug_begin();

	/* associate pfn range with the zone */
	zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL);

	arg.start_pfn = pfn;
	arg.nr_pages = nr_pages;
	node_states_check_changes_online(nr_pages, zone, &arg);

	ret = memory_notify(MEM_GOING_ONLINE, &arg);
	ret = notifier_to_errno(ret);
	if (ret)
		goto failed_addition;

	/*
	 * If this zone is not populated, then it is not in zonelist.
	 * This means the page allocator ignores this zone.
	 * So, zonelist must be updated after online.
	 */
	if (!populated_zone(zone)) {
		need_zonelists_rebuild = 1;
		setup_zone_pageset(zone);
	}

	ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
		online_pages_range);
	if (ret) {
		/* not a single memory resource was applicable */
		if (need_zonelists_rebuild)
			zone_pcp_reset(zone);
		goto failed_addition;
	}

	zone->present_pages += onlined_pages;

	pgdat_resize_lock(zone->zone_pgdat, &flags);
	zone->zone_pgdat->node_present_pages += onlined_pages;
	pgdat_resize_unlock(zone->zone_pgdat, &flags);

	shuffle_zone(zone);

	node_states_set_node(nid, &arg);
	if (need_zonelists_rebuild)
		build_all_zonelists(NULL);
	else
		zone_pcp_update(zone);

	init_per_zone_wmark_min();

	kswapd_run(nid);
	kcompactd_run(nid);

	vm_total_pages = nr_free_pagecache_pages();

	writeback_set_ratelimit();

	memory_notify(MEM_ONLINE, &arg);
	mem_hotplug_done();
	return 0;

failed_addition:
	pr_debug("online_pages [mem %#010llx-%#010llx] failed\n",
		 (unsigned long long) pfn << PAGE_SHIFT,
		 (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
	memory_notify(MEM_CANCEL_ONLINE, &arg);
	remove_pfn_range_from_zone(zone, pfn, nr_pages);
	mem_hotplug_done();
	return ret;
}
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */

static void reset_node_present_pages(pg_data_t *pgdat)
{
	struct zone *z;

	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
		z->present_pages = 0;

	pgdat->node_present_pages = 0;
}

/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
{
	struct pglist_data *pgdat;
	unsigned long start_pfn = PFN_DOWN(start);

	pgdat = NODE_DATA(nid);
	if (!pgdat) {
		pgdat = arch_alloc_nodedata(nid);
		if (!pgdat)
			return NULL;

		pgdat->per_cpu_nodestats =
			alloc_percpu(struct per_cpu_nodestat);
		arch_refresh_nodedata(nid, pgdat);
	} else {
		int cpu;
		/*
		 * Reset the nr_zones, order and classzone_idx before reuse.
		 * Note that kswapd will init kswapd_classzone_idx properly
		 * when it starts in the near future.
		 */
		pgdat->nr_zones = 0;
		pgdat->kswapd_order = 0;
		pgdat->kswapd_classzone_idx = 0;
		for_each_online_cpu(cpu) {
			struct per_cpu_nodestat *p;

			p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu);
			memset(p, 0, sizeof(*p));
		}
	}

	/* we can use NODE_DATA(nid) from here */

	pgdat->node_id = nid;
	pgdat->node_start_pfn = start_pfn;

	/* init node's zones as empty zones, we don't have any present pages.*/
	free_area_init_core_hotplug(nid);

	/*
	 * The node we allocated has no zone fallback lists. For avoiding
	 * to access not-initialized zonelist, build here.
	 */
	build_all_zonelists(pgdat);

	/*
	 * When memory is hot-added, all the memory is in offline state. So
	 * clear all zones' present_pages because they will be updated in
	 * online_pages() and offline_pages().
	 */
	reset_node_managed_pages(pgdat);
	reset_node_present_pages(pgdat);

	return pgdat;
}

static void rollback_node_hotadd(int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);

	arch_refresh_nodedata(nid, NULL);
	free_percpu(pgdat->per_cpu_nodestats);
	arch_free_nodedata(pgdat);
}


/**
 * try_online_node - online a node if offlined
 * @nid: the node ID
 * @start: start addr of the node
 * @set_node_online: Whether we want to online the node
 * called by cpu_up() to online a node without onlined memory.
 *
 * Returns:
 * 1 -> a new node has been allocated
 * 0 -> the node is already online
 * -ENOMEM -> the node could not be allocated
 */
static int __try_online_node(int nid, u64 start, bool set_node_online)
{
	pg_data_t *pgdat;
	int ret = 1;

	if (node_online(nid))
		return 0;

	pgdat = hotadd_new_pgdat(nid, start);
	if (!pgdat) {
		pr_err("Cannot online node %d due to NULL pgdat\n", nid);
		ret = -ENOMEM;
		goto out;
	}

	if (set_node_online) {
		node_set_online(nid);
		ret = register_one_node(nid);
		BUG_ON(ret);
	}
out:
	return ret;
}

/*
 * Users of this function always want to online/register the node
 */
int try_online_node(int nid)
{
	int ret;

	mem_hotplug_begin();
	ret =  __try_online_node(nid, 0, true);
	mem_hotplug_done();
	return ret;
}

static int check_hotplug_memory_range(u64 start, u64 size)
{
	/* memory range must be block size aligned */
	if (!size || !IS_ALIGNED(start, memory_block_size_bytes()) ||
	    !IS_ALIGNED(size, memory_block_size_bytes())) {
		pr_err("Block size [%#lx] unaligned hotplug range: start %#llx, size %#llx",
		       memory_block_size_bytes(), start, size);
		return -EINVAL;
	}

	return 0;
}

static int online_memory_block(struct memory_block *mem, void *arg)
{
	return device_online(&mem->dev);
}

/*
 * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
 * and online/offline operations (triggered e.g. by sysfs).
 *
 * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG
 */
int __ref add_memory_resource(int nid, struct resource *res)
{