linux-next/mm/memory_hotplug.c

/*
 *  linux/mm/memory_hotplug.c
 *
 *  Copyright (C)
 */

#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/module.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/memory_hotplug.h>
#include <linux/highmem.h>
#include <linux/vmalloc.h>
#include <linux/ioport.h>
#include <linux/cpuset.h>
#include <linux/delay.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>

#include <asm/tlbflush.h>

/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
	struct resource *res;
	res = kzalloc(sizeof(struct resource), GFP_KERNEL);
	BUG_ON(!res);

	res->name = "System RAM";
	res->start = start;
	res->end = start + size - 1;
	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
	if (request_resource(&iomem_resource, res) < 0) {
		printk("System RAM resource %llx - %llx cannot be added\n",
		(unsigned long long)res->start, (unsigned long long)res->end);
		kfree(res);
		res = NULL;
	}
	return res;
}

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


#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int nr_pages = PAGES_PER_SECTION;
	int nid = pgdat->node_id;
	int zone_type;

	zone_type = zone - pgdat->node_zones;
	if (!zone->wait_table) {
		int ret = 0;
		ret = init_currently_empty_zone(zone, phys_start_pfn,
						nr_pages, MEMMAP_HOTPLUG);
		if (ret < 0)
			return ret;
	}
	memmap_init_zone(nr_pages, nid, zone_type,
			 phys_start_pfn, MEMMAP_HOTPLUG);
	return 0;
}

static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
{
	int nr_pages = PAGES_PER_SECTION;
	int ret;

	if (pfn_valid(phys_start_pfn))
		return -EEXIST;

	ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);

	if (ret < 0)
		return ret;

	ret = __add_zone(zone, phys_start_pfn);

	if (ret < 0)
		return ret;

	return register_new_memory(__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 __add_pages(struct zone *zone, unsigned long phys_start_pfn,
		 unsigned long nr_pages)
{
	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);

	for (i = start_sec; i <= end_sec; i++) {
		err = __add_section(zone, i << PFN_SECTION_SHIFT);

		/*
		 * 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;
	}

	return err;
}
EXPORT_SYMBOL_GPL(__add_pages);

static void grow_zone_span(struct zone *zone,
		unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long old_zone_end_pfn;

	zone_span_writelock(zone);

	old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
	if (start_pfn < zone->zone_start_pfn)
		zone->zone_start_pfn = start_pfn;

	zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
				zone->zone_start_pfn;

	zone_span_writeunlock(zone);
}

static void grow_pgdat_span(struct pglist_data *pgdat,
		unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long old_pgdat_end_pfn =
		pgdat->node_start_pfn + pgdat->node_spanned_pages;

	if (start_pfn < pgdat->node_start_pfn)
		pgdat->node_start_pfn = start_pfn;

	pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
					pgdat->node_start_pfn;
}

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


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

	arg.start_pfn = pfn;
	arg.nr_pages = nr_pages;
	arg.status_change_nid = -1;

	nid = page_to_nid(pfn_to_page(pfn));
	if (node_present_pages(nid) == 0)
		arg.status_change_nid = nid;

	ret = memory_notify(MEM_GOING_ONLINE, &arg);
	ret = notifier_to_errno(ret);
	if (ret) {
		memory_notify(MEM_CANCEL_ONLINE, &arg);
		return ret;
	}
	/*
	 * This doesn't need a lock to do pfn_to_page().
	 * The section can't be removed here because of the
	 * memory_block->state_mutex.
	 */
	zone = page_zone(pfn_to_page(pfn));
	pgdat_resize_lock(zone->zone_pgdat, &flags);
	grow_zone_span(zone, pfn, pfn + nr_pages);
	grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages);
	pgdat_resize_unlock(zone->zone_pgdat, &flags);

	/*
	 * 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;

	walk_memory_resource(pfn, nr_pages, &onlined_pages,
		online_pages_range);
	zone->present_pages += onlined_pages;
	zone->zone_pgdat->node_present_pages += onlined_pages;

	setup_per_zone_pages_min();
	if (onlined_pages) {
		kswapd_run(zone_to_nid(zone));
		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
	}

	if (need_zonelists_rebuild)
		build_all_zonelists();
	vm_total_pages = nr_free_pagecache_pages();
	writeback_set_ratelimit();

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

	return 0;
}
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */

static pg_data_t *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 = start >> PAGE_SHIFT;

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

	arch_refresh_nodedata(nid, pgdat);

	/* 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, pgdat, zones_size, start_pfn, zholes_size);

	return pgdat;
}

static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
{
	arch_refresh_nodedata(nid, NULL);
	arch_free_nodedata(pgdat);
	return;
}


int add_memory(int nid, u64 start, u64 size)
{
	pg_data_t *pgdat = NULL;
	int new_pgdat = 0;
	struct resource *res;
	int ret;

	res = register_memory_resource(start, size);
	if (!res)
		return -EEXIST;

	if (!node_online(nid)) {
		pgdat = hotadd_new_pgdat(nid, start);
		if (!pgdat)
			return -ENOMEM;
		new_pgdat = 1;
	}

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

	if (ret < 0)
		goto error;

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

	cpuset_track_online_nodes();

	if (new_pgdat) {
		ret = register_one_node(nid);
		/*
		 * 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);
	}

	return ret;
error:
	/* rollback pgdat allocation and others */
	if (new_pgdat)
		rollback_node_hotadd(nid, pgdat);
	if (res)
		release_memory_resource(res);

	return ret;
}
EXPORT_SYMBOL_GPL(add_memory);

#ifdef CONFIG_MEMORY_HOTREMOVE
/*
 * Confirm all pages in a range [start, end) is belongs to the same zone.
 */
static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long pfn;
	struct zone *zone = NULL;
	struct page *page;
	int i;
	for (pfn = start_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)
			continue;
		page = pfn_to_page(pfn + i);
		if (zone && page_zone(page) != zone)
			return 0;
		zone = page_zone(page);
	}
	return 1;
}

/*
 * Scanning pfn is much easier than scanning lru list.
 * Scan pfn from start to end and Find LRU page.
 */
int scan_lru_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;
		}
	}
	return 0;
}

static struct page *
hotremove_migrate_alloc(struct page *page,
			unsigned long private,
			int **x)
{
	/* This should be improoooooved!! */
	return alloc_page(GFP_HIGHUSER_PAGECACHE);
}


#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 (!page_count(page))
			continue;
		/*
		 * We can skip free pages. And we can only deal with pages on
		 * LRU.
		 */
		ret = isolate_lru_page(page, &source);
		if (!ret) { /* Success */
			move_pages--;
		} else {
			/* Becasue we don't have big zone->lock. we should
			   check this again here. */
			if (page_count(page))
				not_managed++;
#ifdef CONFIG_DEBUG_VM
			printk(KERN_INFO "removing from LRU failed"
					 " %lx/%d/%lx\n",
				pfn, page_count(page), page->flags);
#endif
		}
	}
	ret = -EBUSY;
	if (not_managed) {
		if (!list_empty(&source))
			putback_lru_pages(&source);
		goto out;
	}
	ret = 0;
	if (list_empty(&source))
		goto out;
	/* this function returns # of failed pages */
	ret = migrate_pages(&source, hotremove_migrate_alloc, 0);

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

int 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;
	struct zone *zone;
	struct memory_notify arg;

	BUG_ON(start_pfn >= end_pfn);
	/* 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))
		return -EINVAL;

	zone = page_zone(pfn_to_page(start_pfn));
	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);
	if (ret)
		return ret;

	arg.start_pfn = start_pfn;
	arg.nr_pages = nr_pages;
	arg.status_change_nid = -1;
	if (nr_pages >= node_present_pages(node))
		arg.status_change_nid = node;

	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();
		flush_scheduled_work();
		cond_resched();
		drain_all_pages();
	}

	pfn = scan_lru_pages(start_pfn, end_pfn);
	if (pfn) { /* We have page on LRU */
		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 asyncronous... */
	lru_add_drain_all();
	flush_scheduled_work();
	yield();
	/* drain pcp pages , this is synchrouns. */
	drain_all_pages();
	/* check again */
	offlined_pages = check_pages_isolated(start_pfn, end_pfn);
	if (offlined_pages < 0) {
		ret = -EBUSY;
		goto failed_removal;
	}
	printk(KERN_INFO "Offlined Pages %ld\n", offlined_pages);
	/* Ok, all of our target is islaoted.
	   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);
	/* removal success */
	zone->present_pages -= offlined_pages;
	zone->zone_pgdat->node_present_pages -= offlined_pages;
	totalram_pages -= offlined_pages;
	num_physpages -= offlined_pages;

	vm_total_pages = nr_free_pagecache_pages();
	writeback_set_ratelimit();

	memory_notify(MEM_OFFLINE, &arg);
	return 0;

failed_removal:
	printk(KERN_INFO "memory offlining %lx to %lx failed\n",
		start_pfn, end_pfn);
	memory_notify(MEM_CANCEL_OFFLINE, &arg);
	/* pushback to free area */
	undo_isolate_page_range(start_pfn, end_pfn);

	return ret;
}
#else
int remove_memory(u64 start, u64 size)
{
	return -EINVAL;
}
EXPORT_SYMBOL_GPL(remove_memory);
#endif /* CONFIG_MEMORY_HOTREMOVE */