memory_hotplug.c

		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)
{
	struct mhp_restrictions restrictions = {};
	u64 start, size;
	bool new_node = false;
	int ret;

	start = res->start;
	size = resource_size(res);

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

	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);

	ret = __try_online_node(nid, start, false);
	if (ret < 0)
		goto error;
	new_node = ret;

	/* call arch's memory hotadd */
	ret = arch_add_memory(nid, start, size, &restrictions);
	if (ret < 0)
		goto error;

	/* create memory block devices after memory was added */
	ret = create_memory_block_devices(start, size);
	if (ret) {
		arch_remove_memory(nid, start, size, NULL);
		goto error;
	}

	if (new_node) {
		/* If sysfs file of new node can't be created, cpu on the node
		 * can't be hot-added. There is no rollback way now.
		 * So, check by BUG_ON() to catch it reluctantly..
		 * We online node here. We can't roll back from here.
		 */
		node_set_online(nid);
		ret = __register_one_node(nid);
		BUG_ON(ret);
	}

	/* link memory sections under this node.*/
	ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1));
	BUG_ON(ret);

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

	/* device_online() will take the lock when calling online_pages() */
	mem_hotplug_done();

	/* online pages if requested */
	if (memhp_auto_online)
		walk_memory_blocks(start, size, NULL, online_memory_block);

	return ret;
error:
	/* rollback pgdat allocation and others */
	if (new_node)
		rollback_node_hotadd(nid);
	memblock_remove(start, size);
	mem_hotplug_done();
	return ret;
}

/* requires device_hotplug_lock, see 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);
	if (ret < 0)
		release_memory_resource(res);
	return ret;
}

int add_memory(int nid, u64 start, u64 size)
{
	int rc;

	lock_device_hotplug();
	rc = __add_memory(nid, start, size);
	unlock_device_hotplug();

	return rc;
}
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 pfn of the start of the next active pageblock after a given pfn */
static unsigned long next_active_pageblock(unsigned long pfn)
{
	struct page *page = pfn_to_page(pfn);

	/* Ensure the starting page is pageblock-aligned */
	BUG_ON(pfn & (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 pfn + (1 << order);
	}

	return pfn + pageblock_nr_pages;
}

static bool is_pageblock_removable_nolock(unsigned long pfn)
{
	struct page *page = pfn_to_page(pfn);
	struct zone *zone;

	/*
	 * We have to be careful here because we are iterating over memory
	 * sections which are not zone aware so we might end up outside of
	 * the zone but still within the section.
	 * We have to take care about the node as well. If the node is offline
	 * its NODE_DATA will be NULL - see page_zone.
	 */
	if (!node_online(page_to_nid(page)))
		return false;

	zone = page_zone(page);
	pfn = page_to_pfn(page);
	if (!zone_spans_pfn(zone, pfn))
		return false;

	return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, SKIP_HWPOISON);
}

/* 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)
{
	unsigned long end_pfn, pfn;

	end_pfn = min(start_pfn + nr_pages,
			zone_end_pfn(page_zone(pfn_to_page(start_pfn))));

	/* Check the starting page of each pageblock within the range */
	for (pfn = start_pfn; pfn < end_pfn; pfn = next_active_pageblock(pfn)) {
		if (!is_pageblock_removable_nolock(pfn))
			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;
			/* Check if we got outside of the zone */
			if (zone && !zone_spans_pfn(zone, pfn + i))
				return 0;
			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;

	for (pfn = start; pfn < end; pfn++) {
		struct page *page, *head;
		unsigned long skip;

		if (!pfn_valid(pfn))
			continue;
		page = pfn_to_page(pfn);
		if (PageLRU(page))
			return pfn;
		if (__PageMovable(page))
			return pfn;

		if (!PageHuge(page))
			continue;
		head = compound_head(page);
		if (page_huge_active(head))
			return pfn;
		skip = compound_nr(head) - (page - head);
		pfn += skip - 1;
	}
	return 0;
}

static struct page *new_node_page(struct page *page, unsigned long private)
{
	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);
}

static int
do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long pfn;
	struct page *page;
	int ret = 0;
	LIST_HEAD(source);

	for (pfn = start_pfn; pfn < end_pfn; 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) + compound_nr(head) - 1;
			isolate_huge_page(head, &source);
			continue;
		} else if (PageTransHuge(page))
			pfn = page_to_pfn(compound_head(page))
				+ hpage_nr_pages(page) - 1;

		/*
		 * HWPoison pages have elevated reference counts so the migration would
		 * fail on them. It also doesn't make any sense to migrate them in the
		 * first place. Still try to unmap such a page in case it is still mapped
		 * (e.g. current hwpoison implementation doesn't unmap KSM pages but keep
		 * the unmap as the catch all safety net).
		 */
		if (PageHWPoison(page)) {
			if (WARN_ON(PageLRU(page)))
				isolate_lru_page(page);
			if (page_mapped(page))
				try_to_unmap(page, TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS);
			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 */
			list_add_tail(&page->lru, &source);
			if (!__PageMovable(page))
				inc_node_page_state(page, NR_ISOLATED_ANON +
						    page_is_file_cache(page));

		} else {
			pr_warn("failed to isolate pfn %lx\n", pfn);
			dump_page(page, "isolation failed");
		}
		put_page(page);
	}
	if (!list_empty(&source)) {
		/* 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) {
			list_for_each_entry(page, &source, lru) {
				pr_warn("migrating pfn %lx failed ret:%d ",
				       page_to_pfn(page), ret);
				dump_page(page, "migration failure");
			}
			putback_movable_pages(&source);
		}
	}

	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)
{
	unsigned long *offlined_pages = (unsigned long *)data;

	*offlined_pages += __offline_isolated_pages(start, start + nr_pages);
	return 0;
}

/*
 * 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)
{
	return test_pages_isolated(start_pfn, start_pfn + nr_pages, true);
}

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;

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

	/*
	 * Check whether node_states[N_NORMAL_MEMORY] will be changed.
	 * If the memory to be offline is within the range
	 * [0..ZONE_NORMAL], and it is the last present memory there,
	 * the zones in that range will become empty after the offlining,
	 * thus we can determine that we need to clear the node from
	 * node_states[N_NORMAL_MEMORY].
	 */
	for (zt = 0; zt <= ZONE_NORMAL; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;
	if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages)
		arg->status_change_nid_normal = zone_to_nid(zone);

#ifdef CONFIG_HIGHMEM
	/*
	 * node_states[N_HIGH_MEMORY] contains nodes which
	 * have normal memory or high memory.
	 * Here we add the present_pages belonging to ZONE_HIGHMEM.
	 * If the zone is within the range of [0..ZONE_HIGHMEM), and
	 * we determine that the zones in that range become empty,
	 * we need to clear the node for N_HIGH_MEMORY.
	 */
	present_pages += pgdat->node_zones[ZONE_HIGHMEM].present_pages;
	if (zone_idx(zone) <= ZONE_HIGHMEM && nr_pages >= present_pages)
		arg->status_change_nid_high = zone_to_nid(zone);
#endif

	/*
	 * We have accounted the pages from [0..ZONE_NORMAL), and
	 * in case of CONFIG_HIGHMEM the pages from ZONE_HIGHMEM
	 * as well.
	 * Here we count the possible pages from ZONE_MOVABLE.
	 * If after having accounted all the pages, we see that the nr_pages
	 * to be offlined is over or equal to the accounted pages,
	 * we know that the node will become empty, and so, we can clear
	 * it for N_MEMORY as well.
	 */
	present_pages += pgdat->node_zones[ZONE_MOVABLE].present_pages;

	if (nr_pages >= present_pages)
		arg->status_change_nid = zone_to_nid(zone);
}

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

	if (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 pfn, nr_pages;
	unsigned long offlined_pages = 0;
	int ret, node, nr_isolate_pageblock;
	unsigned long flags;
	unsigned long valid_start, valid_end;
	struct zone *zone;
	struct memory_notify arg;
	char *reason;

	mem_hotplug_begin();

	/* 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)) {
		ret = -EINVAL;
		reason = "multizone range";
		goto failed_removal;
	}

	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,
				       SKIP_HWPOISON | REPORT_FAILURE);
	if (ret < 0) {
		reason = "failure to isolate range";
		goto failed_removal;
	}
	nr_isolate_pageblock = 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) {
		reason = "notifier failure";
		goto failed_removal_isolated;
	}

	do {
		for (pfn = start_pfn; pfn;) {
			if (signal_pending(current)) {
				ret = -EINTR;
				reason = "signal backoff";
				goto failed_removal_isolated;
			}

			cond_resched();
			lru_add_drain_all();

			pfn = scan_movable_pages(pfn, end_pfn);
			if (pfn) {
				/*
				 * TODO: fatal migration failures should bail
				 * out
				 */
				do_migrate_range(pfn, end_pfn);
			}
		}

		/*
		 * 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) {
			reason = "failure to dissolve huge pages";
			goto failed_removal_isolated;
		}
		/* check again */
		ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
					    NULL, check_pages_isolated_cb);
	} while (ret);

	/* Ok, all of our target is isolated.
	   We cannot do rollback at this point. */
	walk_system_ram_range(start_pfn, end_pfn - start_pfn,
			      &offlined_pages, offline_isolated_pages_cb);
	pr_info("Offlined Pages %ld\n", offlined_pages);
	/*
	 * Onlining will reset pagetype flags and makes migrate type
	 * MOVABLE, so just need to decrease the number of isolated
	 * pageblocks zone counter here.
	 */
	spin_lock_irqsave(&zone->lock, flags);
	zone->nr_isolate_pageblock -= nr_isolate_pageblock;
	spin_unlock_irqrestore(&zone->lock, flags);

	/* 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);
		build_all_zonelists(NULL);
	} 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);
	mem_hotplug_done();
	return 0;

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

int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
{
	return __offline_pages(start_pfn, start_pfn + nr_pages);
}

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 = beginpa + memory_block_size_bytes() - 1;
		pr_warn("removing memory fails, because memory [%pa-%pa] is onlined\n",
			&beginpa, &endpa);

		return -EBUSY;
	}
	return 0;
}

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;
}

/**
 * try_offline_node
 * @nid: the node ID
 *
 * 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_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);

static void __release_memory_resource(resource_size_t start,
				      resource_size_t size)
{
	int ret;

	/*
	 * When removing memory in the same granularity as it was added,
	 * this function never fails. It might only fail if resources
	 * have to be adjusted or split. We'll ignore the error, as
	 * removing of memory cannot fail.
	 */
	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);
	}
}

static int __ref try_remove_memory(int nid, u64 start, u64 size)
{
	int rc = 0;

	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 return error
	 * if this is not the case.
	 */
	rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb);
	if (rc)
		goto done;

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

	/* remove memory block devices before removing memory */
	remove_memory_block_devices(start, size);

	arch_remove_memory(nid, start, size, NULL);
	__release_memory_resource(start, size);

	try_offline_node(nid);

done:
	mem_hotplug_done();
	return rc;
}

/**
 * remove_memory
 * @nid: the node ID
 * @start: physical address of the region to remove
 * @size: size of the region to remove
 *
 * 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 __remove_memory(int nid, u64 start, u64 size)
{

	/*
	 * trigger BUG() is some memory is not offlined prior to calling this
	 * function
	 */
	if (try_remove_memory(nid, start, size))
		BUG();
}

/*
 * Remove memory if every memory block is offline, otherwise return -EBUSY is
 * some memory is not offline
 */
int remove_memory(int nid, u64 start, u64 size)
{
	int rc;

	lock_device_hotplug();
	rc  = try_remove_memory(nid, start, size);
	unlock_device_hotplug();

	return rc;
}
EXPORT_SYMBOL_GPL(remove_memory);
#endif /* CONFIG_MEMORY_HOTREMOVE */