memory_hotplug.c

/*
 *  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/bootmem.h>
#include <linux/compaction.h>

#include <asm/tlbflush.h>

#include "internal.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 void generic_online_page(struct page *page);

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();
}

/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
	struct resource *res, *conflict;
	res = kzalloc(sizeof(struct resource), GFP_KERNEL);
	if (!res)
		return ERR_PTR(-ENOMEM);

	res->name = "System RAM";
	res->start = start;
	res->end = start + size - 1;
	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
	conflict =  request_resource_conflict(&iomem_resource, res);
	if (conflict) {
		if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) {
			pr_debug("Device unaddressable memory block "
				 "memory hotplug at %#010llx !\n",
				 (unsigned long long)start);
		}
		pr_debug("System RAM resource %pR cannot be added\n", res);
		kfree(res);
		return ERR_PTR(-EEXIST);
	}
	return res;
}

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

#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 *usemap, mapsize, section_nr, i;
	struct mem_section *ms;
	struct page *page, *memmap;

	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);

	usemap = ms->pageblock_flags;
	page = virt_to_page(usemap);

	mapsize = PAGE_ALIGN(usemap_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 *usemap, mapsize, section_nr, i;
	struct mem_section *ms;
	struct page *page, *memmap;

	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);

	usemap = ms->pageblock_flags;
	page = virt_to_page(usemap);

	mapsize = PAGE_ALIGN(usemap_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 __meminit __add_section(int nid, unsigned long phys_start_pfn,
		struct vmem_altmap *altmap, bool want_memblock)
{
	int ret;

	if (pfn_valid(phys_start_pfn))
		return -EEXIST;

	ret = sparse_add_one_section(NODE_DATA(nid), phys_start_pfn, altmap);
	if (ret < 0)
		return ret;

	if (!want_memblock)
		return 0;

	return hotplug_memory_register(nid, __pfn_to_section(phys_start_pfn));
}

/*
 * 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 phys_start_pfn,
		unsigned long nr_pages, struct vmem_altmap *altmap,
		bool want_memblock)
{
	unsigned long i;
	int err = 0;
	int start_sec, end_sec;

	/* during initialize mem_map, align hot-added range to section */
	start_sec = pfn_to_section_nr(phys_start_pfn);
	end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);

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

	for (i = start_sec; i <= end_sec; i++) {
		err = __add_section(nid, section_nr_to_pfn(i), altmap,
				want_memblock);

		/*
		 * EEXIST is finally dealt with by ioresource collision
		 * check. see add_memory() => register_memory_resource()
		 * Warning will be printed if there is collision.
		 */
		if (err && (err != -EEXIST))
			break;
		err = 0;
		cond_resched();
	}
	vmemmap_populate_print_last();
out:
	return err;
}

#ifdef CONFIG_MEMORY_HOTREMOVE
/* 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)
{
	struct mem_section *ms;

	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) {
		ms = __pfn_to_section(start_pfn);

		if (unlikely(!valid_section(ms)))
			continue;

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

		if (zone && 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)
{
	struct mem_section *ms;
	unsigned long pfn;

	/* pfn is the end pfn of a memory section. */
	pfn = end_pfn - 1;
	for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) {
		ms = __pfn_to_section(pfn);

		if (unlikely(!valid_section(ms)))
			continue;

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

		if (zone && 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 zone_start_pfn = zone->zone_start_pfn;
	unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
	unsigned long zone_end_pfn = z;
	unsigned long pfn;
	struct mem_section *ms;
	int nid = zone_to_nid(zone);

	zone_span_writelock(zone);
	if (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);
		if (pfn) {
			zone->zone_start_pfn = pfn;
			zone->spanned_pages = zone_end_pfn - pfn;
		}
	} else if (zone_end_pfn == 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_start_pfn,
					       start_pfn);
		if (pfn)
			zone->spanned_pages = pfn - zone_start_pfn + 1;
	}

	/*
	 * The section is not biggest or smallest mem_section in the zone, it
	 * only creates a hole in the zone. So in this case, we need not
	 * change the zone. But perhaps, the zone has only hole data. Thus
	 * it check the zone has only hole or not.
	 */
	pfn = zone_start_pfn;
	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) {
		ms = __pfn_to_section(pfn);

		if (unlikely(!valid_section(ms)))
			continue;

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

		 /* If the section is current section, it continues the loop */
		if (start_pfn == pfn)
			continue;

		/* If we find valid section, we have nothing to do */
		zone_span_writeunlock(zone);
		return;
	}

	/* The zone has no valid section */
	zone->zone_start_pfn = 0;
	zone->spanned_pages = 0;
	zone_span_writeunlock(zone);
}

static void shrink_pgdat_span(struct pglist_data *pgdat,
			      unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
	unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
	unsigned long pgdat_end_pfn = p;
	unsigned long pfn;
	struct mem_section *ms;
	int nid = pgdat->node_id;

	if (pgdat_start_pfn == start_pfn) {
		/*
		 * If the section is smallest section in the pgdat, it need
		 * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
		 * In this case, we find second smallest valid mem_section
		 * for shrinking zone.
		 */
		pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
						pgdat_end_pfn);
		if (pfn) {
			pgdat->node_start_pfn = pfn;
			pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
		}
	} else if (pgdat_end_pfn == end_pfn) {
		/*
		 * If the section is biggest section in the pgdat, it need
		 * shrink pgdat->node_spanned_pages.
		 * In this case, we find second biggest valid mem_section for
		 * shrinking zone.
		 */
		pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
					       start_pfn);
		if (pfn)
			pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
	}

	/*
	 * If the section is not biggest or smallest mem_section in the pgdat,
	 * it only creates a hole in the pgdat. So in this case, we need not
	 * change the pgdat.
	 * But perhaps, the pgdat has only hole data. Thus it check the pgdat
	 * has only hole or not.
	 */
	pfn = pgdat_start_pfn;
	for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) {
		ms = __pfn_to_section(pfn);

		if (unlikely(!valid_section(ms)))
			continue;

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

		 /* If the section is current section, it continues the loop */
		if (start_pfn == pfn)
			continue;

		/* If we find valid section, we have nothing to do */
		return;
	}

	/* The pgdat has no valid section */
	pgdat->node_start_pfn = 0;
	pgdat->node_spanned_pages = 0;
}

static void __remove_zone(struct zone *zone, unsigned long start_pfn)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int nr_pages = PAGES_PER_SECTION;
	unsigned long flags;

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

static int __remove_section(struct zone *zone, struct mem_section *ms,
		unsigned long map_offset, struct vmem_altmap *altmap)
{
	unsigned long start_pfn;
	int scn_nr;
	int ret = -EINVAL;

	if (!valid_section(ms))
		return ret;

	ret = unregister_memory_section(ms);
	if (ret)
		return ret;

	scn_nr = __section_nr(ms);
	start_pfn = section_nr_to_pfn((unsigned long)scn_nr);
	__remove_zone(zone, start_pfn);

	sparse_remove_one_section(zone, ms, map_offset, altmap);
	return 0;
}

/**
 * __remove_pages() - remove sections of pages from a zone
 * @zone: zone from which pages need to be removed
 * @phys_start_pfn: starting pageframe (must be aligned to start of a section)
 * @nr_pages: number of pages to remove (must be multiple of section size)
 *
 * 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().
 */
int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
		 unsigned long nr_pages, struct vmem_altmap *altmap)
{
	unsigned long i;
	unsigned long map_offset = 0;
	int sections_to_remove, ret = 0;

	/* In the ZONE_DEVICE case device driver owns the memory region */
	if (is_dev_zone(zone)) {
		if (altmap)
			map_offset = vmem_altmap_offset(altmap);
	} else {
		resource_size_t start, size;

		start = phys_start_pfn << PAGE_SHIFT;
		size = nr_pages * PAGE_SIZE;

		ret = release_mem_region_adjustable(&iomem_resource, start,
					size);
		if (ret) {
			resource_size_t endres = start + size - 1;

			pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
					&start, &endres, ret);
		}
	}

	clear_zone_contiguous(zone);

	/*
	 * We can only remove entire sections
	 */
	BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
	BUG_ON(nr_pages % PAGES_PER_SECTION);

	sections_to_remove = nr_pages / PAGES_PER_SECTION;
	for (i = 0; i < sections_to_remove; i++) {
		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;

		ret = __remove_section(zone, __pfn_to_section(pfn), map_offset,
				altmap);
		map_offset = 0;
		if (ret)
			break;
	}

	set_zone_contiguous(zone);

	return ret;
}
#endif /* CONFIG_MEMORY_HOTREMOVE */

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 __online_page_set_limits(struct page *page)
{
}
EXPORT_SYMBOL_GPL(__online_page_set_limits);

void __online_page_increment_counters(struct page *page)
{
	adjust_managed_page_count(page, 1);
}
EXPORT_SYMBOL_GPL(__online_page_increment_counters);

void __online_page_free(struct page *page)
{
	__free_reserved_page(page);
}
EXPORT_SYMBOL_GPL(__online_page_free);

static void generic_online_page(struct page *page)
{
	__online_page_set_limits(page);
	__online_page_increment_counters(page);
	__online_page_free(page);
}

static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
			void *arg)
{
	unsigned long i;
	unsigned long onlined_pages = *(unsigned long *)arg;
	struct page *page;

	if (PageReserved(pfn_to_page(start_pfn)))
		for (i = 0; i < nr_pages; i++) {
			page = pfn_to_page(start_pfn + i);
			(*online_page_callback)(page);
			onlined_pages++;
		}

	online_mem_sections(start_pfn, start_pfn + nr_pages);

	*(unsigned long *)arg = onlined_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);
	enum zone_type zone_last = ZONE_NORMAL;

	/*
	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
	 * contains nodes which have zones of 0...ZONE_NORMAL,
	 * set zone_last to ZONE_NORMAL.
	 *
	 * If we don't have HIGHMEM nor movable node,
	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
	 */
	if (N_MEMORY == N_NORMAL_MEMORY)
		zone_last = ZONE_MOVABLE;

	/*
	 * if the memory to be online is in a zone of 0...zone_last, and
	 * the zones of 0...zone_last don't have memory before online, we will
	 * need to set the node to node_states[N_NORMAL_MEMORY] after
	 * the memory is online.
	 */
	if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY))
		arg->status_change_nid_normal = nid;
	else
		arg->status_change_nid_normal = -1;

#ifdef CONFIG_HIGHMEM
	/*
	 * If we have movable node, node_states[N_HIGH_MEMORY]
	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
	 * set zone_last to ZONE_HIGHMEM.
	 *
	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
	 * contains nodes which have zones of 0...ZONE_MOVABLE,
	 * set zone_last to ZONE_MOVABLE.
	 */
	zone_last = ZONE_HIGHMEM;
	if (N_MEMORY == N_HIGH_MEMORY)
		zone_last = ZONE_MOVABLE;

	if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY))
		arg->status_change_nid_high = nid;
	else
		arg->status_change_nid_high = -1;
#else
	arg->status_change_nid_high = arg->status_change_nid_normal;
#endif

	/*
	 * if the node don't have memory befor online, we will need to
	 * set the node to node_states[N_MEMORY] after the memory
	 * is online.
	 */
	if (!node_state(nid, N_MEMORY))
		arg->status_change_nid = nid;
	else
		arg->status_change_nid = -1;
}

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);

	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;
}

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;

	if (zone_is_empty(zone))
		init_currently_empty_zone(zone, start_pfn, nr_pages);

	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);
	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);
}

/*
 * Associates the given pfn range with the given node and the zone appropriate
 * for the given online type.
 */
static struct zone * __meminit move_pfn_range(int online_type, int nid,
		unsigned long start_pfn, unsigned long nr_pages)
{
	struct zone *zone;

	zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages);
	move_pfn_range_to_zone(zone, start_pfn, nr_pages, NULL);
	return zone;
}

/* Must be protected by mem_hotplug_begin() or a device_lock */
int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
{
	unsigned long flags;
	unsigned long onlined_pages = 0;
	struct zone *zone;
	int need_zonelists_rebuild = 0;
	int nid;
	int ret;
	struct memory_notify arg;
	struct memory_block *mem;

	/*
	 * We can't use pfn_to_nid() because nid might be stored in struct page
	 * which is not yet initialized. Instead, we find nid from memory block.
	 */
	mem = find_memory_block(__pfn_to_section(pfn));
	nid = mem->nid;

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

	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) {
		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);

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

	init_per_zone_wmark_min();

	if (onlined_pages) {
		kswapd_run(nid);
		kcompactd_run(nid);
	}

	vm_total_pages = nr_free_pagecache_pages();

	writeback_set_ratelimit();

	if (onlined_pages)
		memory_notify(MEM_ONLINE, &arg);
	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);
	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 zones_size[MAX_NR_ZONES] = {0};
	unsigned long zholes_size[MAX_NR_ZONES] = {0};
	unsigned long start_pfn = PFN_DOWN(start);

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

		arch_refresh_nodedata(nid, pgdat);
	} else {
		/*
		 * 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.
		 */