memory_hotplug.c

	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.
		 */
		pgdat->nr_zones = 0;
		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);
	arch_free_nodedata(pgdat);
	return;
}


/**
 * 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)
{
	pg_data_t	*pgdat;
	int	ret;

	if (node_online(nid))
		return 0;

	mem_hotplug_begin();
	pgdat = hotadd_new_pgdat(nid, 0);
	if (!pgdat) {
		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);
	}

out:
	mem_hotplug_done();
	return ret;
}

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;
}

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

/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
int __ref add_memory_resource(int nid, struct resource *res, bool online)
{
	u64 start, size;
	pg_data_t *pgdat = NULL;
	bool new_pgdat;
	bool new_node;
	int ret;

	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);
		ret = -ENOMEM;
		if (!pgdat)
			goto error;
	}

	/* call arch's memory hotadd */
	ret = arch_add_memory(nid, start, size, true);

	if (ret < 0)
		goto error;

	/* we online node here. we can't roll back from here. */
	node_set_online(nid);

	if (new_node) {
		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);

	goto out;

error:
	/* rollback pgdat allocation and others */
	if (new_pgdat && pgdat)
		rollback_node_hotadd(nid, pgdat);
	memblock_remove(start, size);

out:
	mem_hotplug_done();
	return ret;
}
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))
			return false;
		cond_resched();
	}

	/* All pageblocks in the memory block are likely to be hot-removable */
	return true;
}

/*
 * 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)
{
	unsigned long pfn, sec_end_pfn;
	unsigned long start, 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;
			if (!zone)
				start = pfn + i;
			zone = page_zone(page);
			end = pfn + MAX_ORDER_NR_PAGES;
		}
	}

	if (zone) {
		*valid_start = start;
		*valid_end = min(end, end_pfn);
		return 1;
	} else {
		return 0;
	}
}

/*
 * 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 (PageHuge(page)) {
				if (page_huge_active(page))
					return pfn;
				else
					pfn = round_up(pfn + 1,
						1 << compound_order(page)) - 1;
			}
		}
	}
	return 0;
}

static struct page *new_node_page(struct page *page, unsigned long private,
		int **result)
{
	int nid = page_to_nid(page);
	nodemask_t nmask = node_states[N_MEMORY];

	/*
	 * try to allocate from a different node but reuse this node if there
	 * are no other online nodes to be used (e.g. we are offlining a part
	 * of the only existing node)
	 */
	node_clear(nid, nmask);
	if (nodes_empty(nmask))
		node_set(nid, nmask);

	return new_page_nodemask(page, nid, &nmask);
}

#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))
			continue;
		/*
		 * 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 */
			put_page(page);
			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");
#endif
			put_page(page);
			/* Because we don't have big zone->lock. we should
			   check this again here. */
			if (page_count(page)) {
				not_managed++;
				ret = -EBUSY;
				break;
			}
		}
	}
	if (!list_empty(&source)) {
		if (not_managed) {
			putback_movable_pages(&source);
			goto out;
		}

		/* Allocate a new page from the nearest neighbor node */
		ret = migrate_pages(&source, new_node_page, NULL, 0,
					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
		if (ret)
			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)
{
	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;

	ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, &offlined,
			check_pages_isolated_cb);
	if (ret < 0)
		offlined = (long)ret;
	return offlined;
}

static int __init cmdline_parse_movable_node(char *p)
{
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
	movable_node_enabled = true;
#else
	pr_warn("movable_node parameter depends on CONFIG_HAVE_MEMBLOCK_NODE_MAP to work properly\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 flags;
	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;

	/* set above range as isolated */
	ret = start_isolate_page_range(start_pfn, end_pfn,
				       MIGRATE_MOVABLE, true);
	if (ret)
		return 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_cpuslocked();
		cond_resched();
		drain_all_pages(zone);
	}

	pfn = scan_movable_pages(start_pfn, end_pfn);
	if (pfn) { /* We have movable pages */
		ret = do_migrate_range(pfn, end_pfn);
		if (!ret) {
			drain = 1;
			goto repeat;
		} else {
			if (ret < 0)
				if (--retry_max == 0)
					goto failed_removal;
			yield();
			drain = 1;
			goto repeat;
		}
	}
	/* drain all zone's lru pagevec, this is asynchronous... */
	lru_add_drain_all_cpuslocked();
	yield();
	/* drain pcp pages, this is synchronous. */
	drain_all_pages(zone);
	/*
	 * dissolve free hugepages in the memory block before doing offlining
	 * actually in order to make hugetlbfs's object counting consistent.
	 */
	ret = dissolve_free_huge_pages(start_pfn, end_pfn);
	if (ret)
		goto failed_removal;
	/* check again */
	offlined_pages = check_pages_isolated(start_pfn, end_pfn);
	if (offlined_pages < 0) {
		ret = -EBUSY;
		goto failed_removal;
	}
	pr_info("Offlined Pages %ld\n", offlined_pages);
	/* Ok, all of our target is isolated.
	   We cannot do rollback at this point. */
	offline_isolated_pages(start_pfn, end_pfn);
	/* reset pagetype flags and makes migrate type to be MOVABLE */
	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
	/* removal success */
	adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages);
	zone->present_pages -= offlined_pages;

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

	init_per_zone_wmark_min();

	if (!populated_zone(zone)) {
		zone_pcp_reset(zone);
		mutex_lock(&zonelists_mutex);
		build_all_zonelists(NULL, NULL);
		mutex_unlock(&zonelists_mutex);
	} else
		zone_pcp_update(zone);

	node_states_clear_node(node, &arg);
	if (arg.status_change_nid >= 0) {
		kswapd_stop(node);
		kcompactd_stop(node);
	}

	vm_total_pages = nr_free_pagecache_pages();
	writeback_set_ratelimit();

	memory_notify(MEM_OFFLINE, &arg);
	return 0;

failed_removal:
	pr_debug("memory offlining [mem %#010llx-%#010llx] failed\n",
		 (unsigned long long) start_pfn << PAGE_SHIFT,
		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1);
	memory_notify(MEM_CANCEL_OFFLINE, &arg);
	/* pushback to free area */
	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
	return ret;
}

/* Must be protected by mem_hotplug_begin() */
int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
{
	return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ);
}
#endif /* CONFIG_MEMORY_HOTREMOVE */

/**
 * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn)
 * @start_pfn: start pfn of the memory range
 * @end_pfn: end pfn of the memory range
 * @arg: argument passed to func
 * @func: callback for each memory section walked
 *
 * This function walks through all present mem sections in range
 * [start_pfn, end_pfn) and call func on each mem section.
 *
 * Returns the return value of func.
 */
int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
		void *arg, int (*func)(struct memory_block *, void *))
{
	struct memory_block *mem = NULL;
	struct mem_section *section;
	unsigned long pfn, section_nr;
	int ret;

	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
		section_nr = pfn_to_section_nr(pfn);
		if (!present_section_nr(section_nr))
			continue;

		section = __nr_to_section(section_nr);
		/* same memblock? */
		if (mem)
			if ((section_nr >= mem->start_section_nr) &&
			    (section_nr <= mem->end_section_nr))
				continue;

		mem = find_memory_block_hinted(section, mem);
		if (!mem)
			continue;

		ret = func(mem, arg);
		if (ret) {
			kobject_put(&mem->dev.kobj);
			return ret;
		}
	}

	if (mem)
		kobject_put(&mem->dev.kobj);

	return 0;
}

#ifdef CONFIG_MEMORY_HOTREMOVE
static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
{
	int ret = !is_memblock_offlined(mem);

	if (unlikely(ret)) {
		phys_addr_t beginpa, endpa;

		beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr));
		endpa = PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1;
		pr_warn("removing memory fails, because memory [%pa-%pa] is onlined\n",
			&beginpa, &endpa);
	}

	return ret;
}

static int check_cpu_on_node(pg_data_t *pgdat)
{
	int cpu;

	for_each_present_cpu(cpu) {
		if (cpu_to_node(cpu) == pgdat->node_id)
			/*
			 * the cpu on this node isn't removed, and we can't
			 * offline this node.
			 */
			return -EBUSY;
	}

	return 0;
}

static void unmap_cpu_on_node(pg_data_t *pgdat)
{
#ifdef CONFIG_ACPI_NUMA
	int cpu;

	for_each_possible_cpu(cpu)
		if (cpu_to_node(cpu) == pgdat->node_id)
			numa_clear_node(cpu);
#endif
}

static int check_and_unmap_cpu_on_node(pg_data_t *pgdat)
{
	int ret;

	ret = check_cpu_on_node(pgdat);
	if (ret)
		return ret;

	/*
	 * the node will be offlined when we come here, so we can clear
	 * the cpu_to_node() now.
	 */

	unmap_cpu_on_node(pgdat);
	return 0;
}

/**
 * try_offline_node
 *
 * Offline a node if all memory sections and cpus of the node are removed.
 *
 * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
 * and online/offline operations before this call.
 */
void try_offline_node(int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);
	unsigned long start_pfn = pgdat->node_start_pfn;
	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
	unsigned long pfn;

	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
		unsigned long section_nr = pfn_to_section_nr(pfn);

		if (!present_section_nr(section_nr))
			continue;

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

		/*
		 * some memory sections of this node are not removed, and we
		 * can't offline node now.
		 */
		return;
	}

	if (check_and_unmap_cpu_on_node(pgdat))
		return;

	/*
	 * all memory/cpu of this node are removed, we can offline this
	 * node now.
	 */
	node_set_offline(nid);
	unregister_one_node(nid);
}
EXPORT_SYMBOL(try_offline_node);

/**
 * remove_memory
 *
 * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
 * and online/offline operations before this call, as required by
 * try_offline_node().
 */
void __ref remove_memory(int nid, u64 start, u64 size)
{
	int ret;

	BUG_ON(check_hotplug_memory_range(start, size));

	mem_hotplug_begin();

	/*
	 * All memory blocks must be offlined before removing memory.  Check
	 * whether all memory blocks in question are offline and trigger a BUG()
	 * if this is not the case.
	 */
	ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL,
				check_memblock_offlined_cb);
	if (ret)
		BUG();

	/* remove memmap entry */
	firmware_map_remove(start, start + size, "System RAM");
	memblock_free(start, size);
	memblock_remove(start, size);

	arch_remove_memory(start, size);

	try_offline_node(nid);

	mem_hotplug_done();
}
EXPORT_SYMBOL_GPL(remove_memory);
#endif /* CONFIG_MEMORY_HOTREMOVE */