Skip to content
Snippets Groups Projects
memory_hotplug.c 58.5 KiB
Newer Older
#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
	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);
bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, int online_type)
	struct pglist_data *pgdat = NODE_DATA(nid);
	struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
	struct zone *default_zone = default_zone_for_pfn(nid, pfn, nr_pages);
	/*
	 * TODO there shouldn't be any inherent reason to have ZONE_NORMAL
	 * physically before ZONE_MOVABLE. All we need is they do not
	 * overlap. Historically we didn't allow ZONE_NORMAL after ZONE_MOVABLE
	 * though so let's stick with it for simplicity for now.
	 * TODO make sure we do not overlap with ZONE_DEVICE
	 */
	if (online_type == MMOP_ONLINE_KERNEL) {
		if (zone_is_empty(movable_zone))
			return true;
		return movable_zone->zone_start_pfn >= pfn + nr_pages;
	} else if (online_type == MMOP_ONLINE_MOVABLE) {
		return zone_end_pfn(default_zone) <= pfn;
	/* MMOP_ONLINE_KEEP will always succeed and inherits the current zone */
	return online_type == MMOP_ONLINE_KEEP;
}
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 move_pfn_range_to_zone(struct zone *zone,
		unsigned long start_pfn, unsigned long nr_pages)
{
	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);

	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.
 */
struct zone *default_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];
}

/*
 * 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 pglist_data *pgdat = NODE_DATA(nid);
	struct zone *zone = default_zone_for_pfn(nid, start_pfn, nr_pages);

	if (online_type == MMOP_ONLINE_KEEP) {
		struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
		/*
		 * MMOP_ONLINE_KEEP defaults to MMOP_ONLINE_KERNEL but use
		 * movable zone if that is not possible (e.g. we are within
		 * or past the existing movable zone)
		if (!allow_online_pfn_range(nid, start_pfn, nr_pages,
					MMOP_ONLINE_KERNEL))
			zone = movable_zone;
	} else if (online_type == MMOP_ONLINE_MOVABLE) {
		zone = &pgdat->node_zones[ZONE_MOVABLE];
	move_pfn_range_to_zone(zone, start_pfn, nr_pages);
	return zone;
/* Must be protected by mem_hotplug_begin() */
int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
	unsigned long onlined_pages = 0;
	struct zone *zone;
	int nid;
	int ret;
	struct memory_notify arg;

	nid = pfn_to_nid(pfn);
	if (!allow_online_pfn_range(nid, pfn, nr_pages, online_type))
	if (online_type == MMOP_ONLINE_MOVABLE && !can_online_high_movable(nid))
		return -EINVAL;
	/* 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 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)) {
		build_all_zonelists(NULL, zone);
	}
KAMEZAWA Hiroyuki's avatar
KAMEZAWA Hiroyuki committed
	ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
		online_pages_range);
		if (need_zonelists_rebuild)
			zone_pcp_reset(zone);
	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);

		node_states_set_node(nid, &arg);
			build_all_zonelists(NULL, NULL);
	if (onlined_pages) {
		kcompactd_run(nid);
	}
	vm_total_pages = nr_free_pagecache_pages();

	if (onlined_pages)
		memory_notify(MEM_ONLINE, &arg);

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);
		/*
		 * 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->kswapd_order = 0;
		pgdat->kswapd_classzone_idx = 0;

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

	/* init node's zones as empty zones, we don't have any present pages.*/
	free_area_init_node(nid, zones_size, start_pfn, zholes_size);
	pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat);
	/*
	 * The node we allocated has no zone fallback lists. For avoiding
	 * to access not-initialized zonelist, build here.
	 */
	mutex_lock(&zonelists_mutex);
	build_all_zonelists(pgdat, NULL);
	mutex_unlock(&zonelists_mutex);
	/*
	 * zone->managed_pages is set to an approximate value in
	 * free_area_init_core(), which will cause
	 * /sys/device/system/node/nodeX/meminfo has wrong data.
	 * So reset it to 0 before any memory is onlined.
	 */
	reset_node_managed_pages(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_present_pages(pgdat);

	return pgdat;
}

static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
{
	arch_refresh_nodedata(nid, NULL);
	free_percpu(pgdat->per_cpu_nodestats);
/**
 * try_online_node - online a node if offlined
 *
 * called by cpu_up() to online a node without onlined memory.
 */
int try_online_node(int nid)
	if (node_online(nid))
		return 0;

	mem_hotplug_begin();
	pgdat = hotadd_new_pgdat(nid, 0);
		pr_err("Cannot online node %d due to NULL pgdat\n", nid);
		ret = -ENOMEM;
		goto out;
	}
	node_set_online(nid);
	ret = register_one_node(nid);
	BUG_ON(ret);

	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
		mutex_lock(&zonelists_mutex);
		build_all_zonelists(NULL, NULL);
		mutex_unlock(&zonelists_mutex);
	}

	mem_hotplug_done();
static int check_hotplug_memory_range(u64 start, u64 size)
{
	u64 start_pfn = PFN_DOWN(start);
	u64 nr_pages = size >> PAGE_SHIFT;

	/* Memory range must be aligned with section */
	if ((start_pfn & ~PAGE_SECTION_MASK) ||
	    (nr_pages % PAGES_PER_SECTION) || (!nr_pages)) {
		pr_err("Section-unaligned hotplug range: start 0x%llx, size 0x%llx\n",
				(unsigned long long)start,
				(unsigned long long)size);
		return -EINVAL;
	}

	return 0;
}

/*
 * If movable zone has already been setup, newly added memory should be check.
 * If its address is higher than movable zone, it should be added as movable.
 * Without this check, movable zone may overlap with other zone.
 */
static int should_add_memory_movable(int nid, u64 start, u64 size)
{
	unsigned long start_pfn = start >> PAGE_SHIFT;
	pg_data_t *pgdat = NODE_DATA(nid);
	struct zone *movable_zone = pgdat->node_zones + ZONE_MOVABLE;

	if (zone_is_empty(movable_zone))
		return 0;

	if (movable_zone->zone_start_pfn <= start_pfn)
		return 1;

	return 0;
}

int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
		bool for_device)
#ifdef CONFIG_ZONE_DEVICE
	if (for_device)
		return ZONE_DEVICE;
#endif
	if (should_add_memory_movable(nid, start, size))
		return ZONE_MOVABLE;

	return zone_default;
}

static int online_memory_block(struct memory_block *mem, void *arg)
{
	return device_online(&mem->dev);
Al Viro's avatar
Al Viro committed
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
int __ref add_memory_resource(int nid, struct resource *res, bool online)
	start = res->start;
	size = resource_size(res);

	ret = check_hotplug_memory_range(start, size);
	if (ret)
		return ret;

	{	/* Stupid hack to suppress address-never-null warning */
		void *p = NODE_DATA(nid);
		new_pgdat = !p;
	}
	mem_hotplug_begin();
	/*
	 * Add new range to memblock so that when hotadd_new_pgdat() is called
	 * to allocate new pgdat, get_pfn_range_for_nid() will be able to find
	 * this new range and calculate total pages correctly.  The range will
	 * be removed at hot-remove time.
	 */
	memblock_add_node(start, size, nid);

	new_node = !node_online(nid);
	if (new_node) {
		pgdat = hotadd_new_pgdat(nid, start);
	/* call arch's memory hotadd */
	ret = arch_add_memory(nid, start, size, false);
	/* we online node here. we can't roll back from here. */
		unsigned long start_pfn = start >> PAGE_SHIFT;
		unsigned long nr_pages = size >> PAGE_SHIFT;

		ret = __register_one_node(nid);
		if (ret)
			goto register_fail;

		/*
		 * link memory sections under this node. This is already
		 * done when creatig memory section in register_new_memory
		 * but that depends to have the node registered so offline
		 * nodes have to go through register_node.
		 * TODO clean up this mess.
		 */
		ret = link_mem_sections(nid, start_pfn, nr_pages);
register_fail:
		/*
		 * If sysfs file of new node can't create, cpu on the node
		 * can't be hot-added. There is no rollback way now.
		 * So, check by BUG_ON() to catch it reluctantly..
		 */
		BUG_ON(ret);
	}

	/* create new memmap entry */
	firmware_map_add_hotplug(start, start + size, "System RAM");

	/* online pages if requested */
	if (online)
		walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1),
				  NULL, online_memory_block);

error:
	/* rollback pgdat allocation and others */
	if (new_pgdat)
		rollback_node_hotadd(nid, pgdat);
	mem_hotplug_done();
EXPORT_SYMBOL_GPL(add_memory_resource);

int __ref add_memory(int nid, u64 start, u64 size)
{
	struct resource *res;
	int ret;

	res = register_memory_resource(start, size);
	if (IS_ERR(res))
		return PTR_ERR(res);
	ret = add_memory_resource(nid, res, memhp_auto_online);
	if (ret < 0)
		release_memory_resource(res);
	return ret;
}
EXPORT_SYMBOL_GPL(add_memory);

#ifdef CONFIG_MEMORY_HOTREMOVE
/*
 * A free page on the buddy free lists (not the per-cpu lists) has PageBuddy
 * set and the size of the free page is given by page_order(). Using this,
 * the function determines if the pageblock contains only free pages.
 * Due to buddy contraints, a free page at least the size of a pageblock will
 * be located at the start of the pageblock
 */
static inline int pageblock_free(struct page *page)
{
	return PageBuddy(page) && page_order(page) >= pageblock_order;
}

/* Return the start of the next active pageblock after a given page */
static struct page *next_active_pageblock(struct page *page)
{
	/* Ensure the starting page is pageblock-aligned */
	BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));

	/* If the entire pageblock is free, move to the end of free page */
	if (pageblock_free(page)) {
		int order;
		/* be careful. we don't have locks, page_order can be changed.*/
		order = page_order(page);
		if ((order < MAX_ORDER) && (order >= pageblock_order))
			return page + (1 << order);
	}
	return page + pageblock_nr_pages;
}

/* Checks if this range of memory is likely to be hot-removable. */
bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
{
	struct page *page = pfn_to_page(start_pfn);
	struct page *end_page = page + nr_pages;

	/* Check the starting page of each pageblock within the range */
	for (; page < end_page; page = next_active_pageblock(page)) {
		if (!is_pageblock_removable_nolock(page))
	}

	/* All pageblocks in the memory block are likely to be hot-removable */
 * Confirm all pages in a range [start, end) belong to the same zone.
 * When true, return its valid [start, end).
int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
			 unsigned long *valid_start, unsigned long *valid_end)
	struct zone *zone = NULL;
	struct page *page;
	int i;
	for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1);
	     pfn < end_pfn;
	     pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) {
		/* Make sure the memory section is present first */
		if (!present_section_nr(pfn_to_section_nr(pfn)))
			continue;
		for (; pfn < sec_end_pfn && pfn < end_pfn;
		     pfn += MAX_ORDER_NR_PAGES) {
			i = 0;
			/* This is just a CONFIG_HOLES_IN_ZONE check.*/
			while ((i < MAX_ORDER_NR_PAGES) &&
				!pfn_valid_within(pfn + i))
				i++;
			if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn)
				continue;
			page = pfn_to_page(pfn + i);
			if (zone && page_zone(page) != zone)
				return 0;
			end = pfn + MAX_ORDER_NR_PAGES;
	if (zone) {
		*valid_start = start;
		*valid_end = min(end, end_pfn);
 * Scan pfn range [start,end) to find movable/migratable pages (LRU pages,
 * non-lru movable pages and hugepages). We scan pfn because it's much
 * easier than scanning over linked list. This function returns the pfn
 * of the first found movable page if it's found, otherwise 0.
static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
{
	unsigned long pfn;
	struct page *page;
	for (pfn = start; pfn < end; pfn++) {
		if (pfn_valid(pfn)) {
			page = pfn_to_page(pfn);
			if (PageLRU(page))
				return pfn;
			if (__PageMovable(page))
				return pfn;
				if (page_huge_active(page))
					return pfn;
				else
					pfn = round_up(pfn + 1,
						1 << compound_order(page)) - 1;
			}
static struct page *new_node_page(struct page *page, unsigned long private,
		int **result)
{
	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
	int nid = page_to_nid(page);
	nodemask_t nmask = node_states[N_MEMORY];
	struct page *new_page = NULL;

	/*
	 * TODO: allocate a destination hugepage from a nearest neighbor node,
	 * accordance with memory policy of the user process if possible. For
	 * now as a simple work-around, we use the next node for destination.
	 */
	if (PageHuge(page))
		return alloc_huge_page_node(page_hstate(compound_head(page)),
					next_node_in(nid, nmask));

	if (PageHighMem(page)
	    || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
		gfp_mask |= __GFP_HIGHMEM;

	if (!nodes_empty(nmask))
		new_page = __alloc_pages_nodemask(gfp_mask, 0,
					node_zonelist(nid, gfp_mask), &nmask);
	if (!new_page)
		new_page = __alloc_pages(gfp_mask, 0,
					node_zonelist(nid, gfp_mask));

	return new_page;
}

#define NR_OFFLINE_AT_ONCE_PAGES	(256)
static int
do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long pfn;
	struct page *page;
	int move_pages = NR_OFFLINE_AT_ONCE_PAGES;
	int not_managed = 0;
	int ret = 0;
	LIST_HEAD(source);

	for (pfn = start_pfn; pfn < end_pfn && move_pages > 0; pfn++) {
		if (!pfn_valid(pfn))
			continue;
		page = pfn_to_page(pfn);

		if (PageHuge(page)) {
			struct page *head = compound_head(page);
			pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1;
			if (compound_order(head) > PFN_SECTION_SHIFT) {
				ret = -EBUSY;
				break;
			}
			if (isolate_huge_page(page, &source))
				move_pages -= 1 << compound_order(head);
			continue;
		}

		if (!get_page_unless_zero(page))
		 * We can skip free pages. And we can deal with pages on
		 * LRU and non-lru movable pages.
		if (PageLRU(page))
			ret = isolate_lru_page(page);
		else
			ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE);
		if (!ret) { /* Success */
			list_add_tail(&page->lru, &source);
			move_pages--;
			if (!__PageMovable(page))
				inc_node_page_state(page, NR_ISOLATED_ANON +
						    page_is_file_cache(page));
		} else {
#ifdef CONFIG_DEBUG_VM
			pr_alert("failed to isolate pfn %lx\n", pfn);
			dump_page(page, "isolation failed");
Lucas De Marchi's avatar
Lucas De Marchi committed
			/* Because we don't have big zone->lock. we should
			   check this again here. */
			if (page_count(page)) {
				not_managed++;
	if (!list_empty(&source)) {
		if (not_managed) {
			putback_movable_pages(&source);
		/* Allocate a new page from the nearest neighbor node */
		ret = migrate_pages(&source, new_node_page, NULL, 0,
					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
			putback_movable_pages(&source);
	}
out:
	return ret;
}

/*
 * remove from free_area[] and mark all as Reserved.
 */
static int
offline_isolated_pages_cb(unsigned long start, unsigned long nr_pages,
			void *data)
{
	__offline_isolated_pages(start, start + nr_pages);
	return 0;
}

static void
offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
KAMEZAWA Hiroyuki's avatar
KAMEZAWA Hiroyuki committed
	walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL,
				offline_isolated_pages_cb);
}

/*
 * Check all pages in range, recoreded as memory resource, are isolated.
 */
static int
check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages,
			void *data)
{
	int ret;
	long offlined = *(long *)data;
	ret = test_pages_isolated(start_pfn, start_pfn + nr_pages, true);
	offlined = nr_pages;
	if (!ret)
		*(long *)data += offlined;
	return ret;
}

static long
check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
{
	long offlined = 0;
	int ret;

KAMEZAWA Hiroyuki's avatar
KAMEZAWA Hiroyuki committed
	ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, &offlined,
			check_pages_isolated_cb);
	if (ret < 0)
		offlined = (long)ret;
	return offlined;
}

/*
 * When CONFIG_MOVABLE_NODE, we permit offlining of a node which doesn't have
 * normal memory.
 */
static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
{
	return true;
}
#else /* CONFIG_MOVABLE_NODE */
/* ensure the node has NORMAL memory if it is still online */
static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	unsigned long present_pages = 0;
	enum zone_type zt;

	for (zt = 0; zt <= ZONE_NORMAL; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;

	if (present_pages > nr_pages)
		return true;

	present_pages = 0;
	for (; zt <= ZONE_MOVABLE; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;

	/*
	 * we can't offline the last normal memory until all
	 * higher memory is offlined.
	 */
	return present_pages == 0;
}
#endif /* CONFIG_MOVABLE_NODE */
static int __init cmdline_parse_movable_node(char *p)
{
#ifdef CONFIG_MOVABLE_NODE
#else
	pr_warn("movable_node option not supported\n");
#endif
	return 0;
}
early_param("movable_node", cmdline_parse_movable_node);

/* check which state of node_states will be changed when offline memory */
static void node_states_check_changes_offline(unsigned long nr_pages,
		struct zone *zone, struct memory_notify *arg)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	unsigned long present_pages = 0;
	enum zone_type zt, 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;

	/*
	 * check whether node_states[N_NORMAL_MEMORY] will be changed.
	 * If the memory to be offline is in a zone of 0...zone_last,
	 * and it is the last present memory, 0...zone_last will
	 * become empty after offline , thus we can determind we will
	 * need to clear the node from node_states[N_NORMAL_MEMORY].
	 */
	for (zt = 0; zt <= zone_last; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;
	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
		arg->status_change_nid_normal = zone_to_nid(zone);
	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;

	for (; zt <= zone_last; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;
	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
		arg->status_change_nid_high = zone_to_nid(zone);
	else
		arg->status_change_nid_high = -1;
#else
	arg->status_change_nid_high = arg->status_change_nid_normal;
#endif

	/*
	 * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE
	 */
	zone_last = ZONE_MOVABLE;

	/*
	 * check whether node_states[N_HIGH_MEMORY] will be changed
	 * If we try to offline the last present @nr_pages from the node,
	 * we can determind we will need to clear the node from
	 * node_states[N_HIGH_MEMORY].
	 */
	for (; zt <= zone_last; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;
	if (nr_pages >= present_pages)
		arg->status_change_nid = zone_to_nid(zone);
	else
		arg->status_change_nid = -1;
}

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

	if ((N_MEMORY != N_NORMAL_MEMORY) &&
	    (arg->status_change_nid_high >= 0))
		node_clear_state(node, N_HIGH_MEMORY);

	if ((N_MEMORY != N_HIGH_MEMORY) &&
	    (arg->status_change_nid >= 0))
		node_clear_state(node, N_MEMORY);
static int __ref __offline_pages(unsigned long start_pfn,
		  unsigned long end_pfn, unsigned long timeout)
{
	unsigned long pfn, nr_pages, expire;
	long offlined_pages;
	int ret, drain, retry_max, node;
	unsigned long valid_start, valid_end;
	struct zone *zone;
	struct memory_notify arg;

	/* at least, alignment against pageblock is necessary */
	if (!IS_ALIGNED(start_pfn, pageblock_nr_pages))
		return -EINVAL;
	if (!IS_ALIGNED(end_pfn, pageblock_nr_pages))
		return -EINVAL;
	/* This makes hotplug much easier...and readable.
	   we assume this for now. .*/
	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
		return -EINVAL;
	zone = page_zone(pfn_to_page(valid_start));
	node = zone_to_nid(zone);
	nr_pages = end_pfn - start_pfn;

	if (zone_idx(zone) <= ZONE_NORMAL && !can_offline_normal(zone, nr_pages))
	/* set above range as isolated */
	ret = start_isolate_page_range(start_pfn, end_pfn,
				       MIGRATE_MOVABLE, true);
	if (ret)

	arg.start_pfn = start_pfn;
	arg.nr_pages = nr_pages;
	node_states_check_changes_offline(nr_pages, zone, &arg);

	ret = memory_notify(MEM_GOING_OFFLINE, &arg);
	ret = notifier_to_errno(ret);
	if (ret)
		goto failed_removal;

	pfn = start_pfn;
	expire = jiffies + timeout;
	drain = 0;
	retry_max = 5;
repeat:
	/* start memory hot removal */
	ret = -EAGAIN;
	if (time_after(jiffies, expire))
		goto failed_removal;
	ret = -EINTR;
	if (signal_pending(current))
		goto failed_removal;
	ret = 0;
	if (drain) {
		lru_add_drain_all();
		cond_resched();