page_alloc.c

		", %luK highmem"
#endif
		"%s%s)\n",
		nr_free_pages() << (PAGE_SHIFT - 10),
		physpages << (PAGE_SHIFT - 10),
		codesize >> 10, datasize >> 10, rosize >> 10,
		(init_data_size + init_code_size) >> 10, bss_size >> 10,
		(physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT - 10),
		totalcma_pages << (PAGE_SHIFT - 10),
#ifdef	CONFIG_HIGHMEM
		totalhigh_pages << (PAGE_SHIFT - 10),
#endif
		str ? ", " : "", str ? str : "");
}

/**
 * set_dma_reserve - set the specified number of pages reserved in the first zone
 * @new_dma_reserve: The number of pages to mark reserved
 *
 * The per-cpu batchsize and zone watermarks are determined by managed_pages.
 * In the DMA zone, a significant percentage may be consumed by kernel image
 * and other unfreeable allocations which can skew the watermarks badly. This
 * function may optionally be used to account for unfreeable pages in the
 * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and
 * smaller per-cpu batchsize.
 */
void __init set_dma_reserve(unsigned long new_dma_reserve)
{
	dma_reserve = new_dma_reserve;
}

void __init free_area_init(unsigned long *zones_size)
{
	free_area_init_node(0, zones_size,
			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
	zero_resv_unavail();
}

static int page_alloc_cpu_dead(unsigned int cpu)
{

	lru_add_drain_cpu(cpu);
	drain_pages(cpu);

	/*
	 * Spill the event counters of the dead processor
	 * into the current processors event counters.
	 * This artificially elevates the count of the current
	 * processor.
	 */
	vm_events_fold_cpu(cpu);

	/*
	 * Zero the differential counters of the dead processor
	 * so that the vm statistics are consistent.
	 *
	 * This is only okay since the processor is dead and cannot
	 * race with what we are doing.
	 */
	cpu_vm_stats_fold(cpu);
	return 0;
}

void __init page_alloc_init(void)
{
	int ret;

	ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC_DEAD,
					"mm/page_alloc:dead", NULL,
					page_alloc_cpu_dead);
	WARN_ON(ret < 0);
}

/*
 * calculate_totalreserve_pages - called when sysctl_lowmem_reserve_ratio
 *	or min_free_kbytes changes.
 */
static void calculate_totalreserve_pages(void)
{
	struct pglist_data *pgdat;
	unsigned long reserve_pages = 0;
	enum zone_type i, j;

	for_each_online_pgdat(pgdat) {

		pgdat->totalreserve_pages = 0;

		for (i = 0; i < MAX_NR_ZONES; i++) {
			struct zone *zone = pgdat->node_zones + i;
			long max = 0;

			/* Find valid and maximum lowmem_reserve in the zone */
			for (j = i; j < MAX_NR_ZONES; j++) {
				if (zone->lowmem_reserve[j] > max)
					max = zone->lowmem_reserve[j];
			}

			/* we treat the high watermark as reserved pages. */
			max += high_wmark_pages(zone);

			if (max > zone->managed_pages)
				max = zone->managed_pages;

			pgdat->totalreserve_pages += max;

			reserve_pages += max;
		}
	}
	totalreserve_pages = reserve_pages;
}

/*
 * setup_per_zone_lowmem_reserve - called whenever
 *	sysctl_lowmem_reserve_ratio changes.  Ensures that each zone
 *	has a correct pages reserved value, so an adequate number of
 *	pages are left in the zone after a successful __alloc_pages().
 */
static void setup_per_zone_lowmem_reserve(void)
{
	struct pglist_data *pgdat;
	enum zone_type j, idx;

	for_each_online_pgdat(pgdat) {
		for (j = 0; j < MAX_NR_ZONES; j++) {
			struct zone *zone = pgdat->node_zones + j;
			unsigned long managed_pages = zone->managed_pages;

			zone->lowmem_reserve[j] = 0;

			idx = j;
			while (idx) {
				struct zone *lower_zone;

				idx--;

				if (sysctl_lowmem_reserve_ratio[idx] < 1)
					sysctl_lowmem_reserve_ratio[idx] = 1;

				lower_zone = pgdat->node_zones + idx;
				lower_zone->lowmem_reserve[j] = managed_pages /
					sysctl_lowmem_reserve_ratio[idx];
				managed_pages += lower_zone->managed_pages;
			}
		}
	}

	/* update totalreserve_pages */
	calculate_totalreserve_pages();
}

static void __setup_per_zone_wmarks(void)
{
	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
	unsigned long lowmem_pages = 0;
	struct zone *zone;
	unsigned long flags;

	/* Calculate total number of !ZONE_HIGHMEM pages */
	for_each_zone(zone) {
		if (!is_highmem(zone))
			lowmem_pages += zone->managed_pages;
	}

	for_each_zone(zone) {
		u64 tmp;

		spin_lock_irqsave(&zone->lock, flags);
		tmp = (u64)pages_min * zone->managed_pages;
		do_div(tmp, lowmem_pages);
		if (is_highmem(zone)) {
			/*
			 * __GFP_HIGH and PF_MEMALLOC allocations usually don't
			 * need highmem pages, so cap pages_min to a small
			 * value here.
			 *
			 * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
			 * deltas control asynch page reclaim, and so should
			 * not be capped for highmem.
			 */
			unsigned long min_pages;

			min_pages = zone->managed_pages / 1024;
			min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL);
			zone->watermark[WMARK_MIN] = min_pages;
		} else {
			/*
			 * If it's a lowmem zone, reserve a number of pages
			 * proportionate to the zone's size.
			 */
			zone->watermark[WMARK_MIN] = tmp;
		}

		/*
		 * Set the kswapd watermarks distance according to the
		 * scale factor in proportion to available memory, but
		 * ensure a minimum size on small systems.
		 */
		tmp = max_t(u64, tmp >> 2,
			    mult_frac(zone->managed_pages,
				      watermark_scale_factor, 10000));

		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + tmp;
		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;

		spin_unlock_irqrestore(&zone->lock, flags);
	}

	/* update totalreserve_pages */
	calculate_totalreserve_pages();
}

/**
 * setup_per_zone_wmarks - called when min_free_kbytes changes
 * or when memory is hot-{added|removed}
 *
 * Ensures that the watermark[min,low,high] values for each zone are set
 * correctly with respect to min_free_kbytes.
 */
void setup_per_zone_wmarks(void)
{
	static DEFINE_SPINLOCK(lock);

	spin_lock(&lock);
	__setup_per_zone_wmarks();
	spin_unlock(&lock);
}

/*
 * Initialise min_free_kbytes.
 *
 * For small machines we want it small (128k min).  For large machines
 * we want it large (64MB max).  But it is not linear, because network
 * bandwidth does not increase linearly with machine size.  We use
 *
 *	min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
 *	min_free_kbytes = sqrt(lowmem_kbytes * 16)
 *
 * which yields
 *
 * 16MB:	512k
 * 32MB:	724k
 * 64MB:	1024k
 * 128MB:	1448k
 * 256MB:	2048k
 * 512MB:	2896k
 * 1024MB:	4096k
 * 2048MB:	5792k
 * 4096MB:	8192k
 * 8192MB:	11584k
 * 16384MB:	16384k
 */
int __meminit init_per_zone_wmark_min(void)
{
	unsigned long lowmem_kbytes;
	int new_min_free_kbytes;

	lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
	new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16);

	if (new_min_free_kbytes > user_min_free_kbytes) {
		min_free_kbytes = new_min_free_kbytes;
		if (min_free_kbytes < 128)
			min_free_kbytes = 128;
		if (min_free_kbytes > 65536)
			min_free_kbytes = 65536;
	} else {
		pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n",
				new_min_free_kbytes, user_min_free_kbytes);
	}
	setup_per_zone_wmarks();
	refresh_zone_stat_thresholds();
	setup_per_zone_lowmem_reserve();

#ifdef CONFIG_NUMA
	setup_min_unmapped_ratio();
	setup_min_slab_ratio();
#endif

	return 0;
}
core_initcall(init_per_zone_wmark_min)

/*
 * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
 *	that we can call two helper functions whenever min_free_kbytes
 *	changes.
 */
int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	if (write) {
		user_min_free_kbytes = min_free_kbytes;
		setup_per_zone_wmarks();
	}
	return 0;
}

int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	if (write)
		setup_per_zone_wmarks();

	return 0;
}

#ifdef CONFIG_NUMA
static void setup_min_unmapped_ratio(void)
{
	pg_data_t *pgdat;
	struct zone *zone;

	for_each_online_pgdat(pgdat)
		pgdat->min_unmapped_pages = 0;

	for_each_zone(zone)
		zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
				sysctl_min_unmapped_ratio) / 100;
}


int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	setup_min_unmapped_ratio();

	return 0;
}

static void setup_min_slab_ratio(void)
{
	pg_data_t *pgdat;
	struct zone *zone;

	for_each_online_pgdat(pgdat)
		pgdat->min_slab_pages = 0;

	for_each_zone(zone)
		zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
				sysctl_min_slab_ratio) / 100;
}

int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	int rc;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	setup_min_slab_ratio();

	return 0;
}
#endif

/*
 * lowmem_reserve_ratio_sysctl_handler - just a wrapper around
 *	proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
 *	whenever sysctl_lowmem_reserve_ratio changes.
 *
 * The reserve ratio obviously has absolutely no relation with the
 * minimum watermarks. The lowmem reserve ratio can only make sense
 * if in function of the boot time zone sizes.
 */
int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec_minmax(table, write, buffer, length, ppos);
	setup_per_zone_lowmem_reserve();
	return 0;
}

/*
 * percpu_pagelist_fraction - changes the pcp->high for each zone on each
 * cpu.  It is the fraction of total pages in each zone that a hot per cpu
 * pagelist can have before it gets flushed back to buddy allocator.
 */
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	struct zone *zone;
	int old_percpu_pagelist_fraction;
	int ret;

	mutex_lock(&pcp_batch_high_lock);
	old_percpu_pagelist_fraction = percpu_pagelist_fraction;

	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (!write || ret < 0)
		goto out;

	/* Sanity checking to avoid pcp imbalance */
	if (percpu_pagelist_fraction &&
	    percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) {
		percpu_pagelist_fraction = old_percpu_pagelist_fraction;
		ret = -EINVAL;
		goto out;
	}

	/* No change? */
	if (percpu_pagelist_fraction == old_percpu_pagelist_fraction)
		goto out;

	for_each_populated_zone(zone) {
		unsigned int cpu;

		for_each_possible_cpu(cpu)
			pageset_set_high_and_batch(zone,
					per_cpu_ptr(zone->pageset, cpu));
	}
out:
	mutex_unlock(&pcp_batch_high_lock);
	return ret;
}

#ifdef CONFIG_NUMA
int hashdist = HASHDIST_DEFAULT;

static int __init set_hashdist(char *str)
{
	if (!str)
		return 0;
	hashdist = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("hashdist=", set_hashdist);
#endif

#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES
/*
 * Returns the number of pages that arch has reserved but
 * is not known to alloc_large_system_hash().
 */
static unsigned long __init arch_reserved_kernel_pages(void)
{
	return 0;
}
#endif

/*
 * Adaptive scale is meant to reduce sizes of hash tables on large memory
 * machines. As memory size is increased the scale is also increased but at
 * slower pace.  Starting from ADAPT_SCALE_BASE (64G), every time memory
 * quadruples the scale is increased by one, which means the size of hash table
 * only doubles, instead of quadrupling as well.
 * Because 32-bit systems cannot have large physical memory, where this scaling
 * makes sense, it is disabled on such platforms.
 */
#if __BITS_PER_LONG > 32
#define ADAPT_SCALE_BASE	(64ul << 30)
#define ADAPT_SCALE_SHIFT	2
#define ADAPT_SCALE_NPAGES	(ADAPT_SCALE_BASE >> PAGE_SHIFT)
#endif

/*
 * allocate a large system hash table from bootmem
 * - it is assumed that the hash table must contain an exact power-of-2
 *   quantity of entries
 * - limit is the number of hash buckets, not the total allocation size
 */
void *__init alloc_large_system_hash(const char *tablename,
				     unsigned long bucketsize,
				     unsigned long numentries,
				     int scale,
				     int flags,
				     unsigned int *_hash_shift,
				     unsigned int *_hash_mask,
				     unsigned long low_limit,
				     unsigned long high_limit)
{
	unsigned long long max = high_limit;
	unsigned long log2qty, size;
	void *table = NULL;
	gfp_t gfp_flags;

	/* allow the kernel cmdline to have a say */
	if (!numentries) {
		/* round applicable memory size up to nearest megabyte */
		numentries = nr_kernel_pages;
		numentries -= arch_reserved_kernel_pages();

		/* It isn't necessary when PAGE_SIZE >= 1MB */
		if (PAGE_SHIFT < 20)
			numentries = round_up(numentries, (1<<20)/PAGE_SIZE);

#if __BITS_PER_LONG > 32
		if (!high_limit) {
			unsigned long adapt;

			for (adapt = ADAPT_SCALE_NPAGES; adapt < numentries;
			     adapt <<= ADAPT_SCALE_SHIFT)
				scale++;
		}
#endif

		/* limit to 1 bucket per 2^scale bytes of low memory */
		if (scale > PAGE_SHIFT)
			numentries >>= (scale - PAGE_SHIFT);
		else
			numentries <<= (PAGE_SHIFT - scale);

		/* Make sure we've got at least a 0-order allocation.. */
		if (unlikely(flags & HASH_SMALL)) {
			/* Makes no sense without HASH_EARLY */
			WARN_ON(!(flags & HASH_EARLY));
			if (!(numentries >> *_hash_shift)) {
				numentries = 1UL << *_hash_shift;
				BUG_ON(!numentries);
			}
		} else if (unlikely((numentries * bucketsize) < PAGE_SIZE))
			numentries = PAGE_SIZE / bucketsize;
	}
	numentries = roundup_pow_of_two(numentries);

	/* limit allocation size to 1/16 total memory by default */
	if (max == 0) {
		max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
		do_div(max, bucketsize);
	}
	max = min(max, 0x80000000ULL);

	if (numentries < low_limit)
		numentries = low_limit;
	if (numentries > max)
		numentries = max;

	log2qty = ilog2(numentries);

	gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC;
	do {
		size = bucketsize << log2qty;
		if (flags & HASH_EARLY) {
			if (flags & HASH_ZERO)
				table = memblock_virt_alloc_nopanic(size, 0);
			else
				table = memblock_virt_alloc_raw(size, 0);
		} else if (hashdist) {
			table = __vmalloc(size, gfp_flags, PAGE_KERNEL);
		} else {
			/*
			 * If bucketsize is not a power-of-two, we may free
			 * some pages at the end of hash table which
			 * alloc_pages_exact() automatically does
			 */
			if (get_order(size) < MAX_ORDER) {
				table = alloc_pages_exact(size, gfp_flags);
				kmemleak_alloc(table, size, 1, gfp_flags);
			}
		}
	} while (!table && size > PAGE_SIZE && --log2qty);

	if (!table)
		panic("Failed to allocate %s hash table\n", tablename);

	pr_info("%s hash table entries: %ld (order: %d, %lu bytes)\n",
		tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size);

	if (_hash_shift)
		*_hash_shift = log2qty;
	if (_hash_mask)
		*_hash_mask = (1 << log2qty) - 1;

	return table;
}

/*
 * This function checks whether pageblock includes unmovable pages or not.
 * If @count is not zero, it is okay to include less @count unmovable pages
 *
 * PageLRU check without isolation or lru_lock could race so that
 * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
 * check without lock_page also may miss some movable non-lru pages at
 * race condition. So you can't expect this function should be exact.
 */
bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
			 int migratetype,
			 bool skip_hwpoisoned_pages)
{
	unsigned long pfn, iter, found;

	/*
	 * For avoiding noise data, lru_add_drain_all() should be called
	 * If ZONE_MOVABLE, the zone never contains unmovable pages
	 */
	if (zone_idx(zone) == ZONE_MOVABLE)
		return false;

	/*
	 * CMA allocations (alloc_contig_range) really need to mark isolate
	 * CMA pageblocks even when they are not movable in fact so consider
	 * them movable here.
	 */
	if (is_migrate_cma(migratetype) &&
			is_migrate_cma(get_pageblock_migratetype(page)))
		return false;

	pfn = page_to_pfn(page);
	for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
		unsigned long check = pfn + iter;

		if (!pfn_valid_within(check))
			continue;

		page = pfn_to_page(check);

		if (PageReserved(page))
			return true;

		/*
		 * Hugepages are not in LRU lists, but they're movable.
		 * We need not scan over tail pages bacause we don't
		 * handle each tail page individually in migration.
		 */
		if (PageHuge(page)) {
			iter = round_up(iter + 1, 1<<compound_order(page)) - 1;
			continue;
		}

		/*
		 * We can't use page_count without pin a page
		 * because another CPU can free compound page.
		 * This check already skips compound tails of THP
		 * because their page->_refcount is zero at all time.
		 */
		if (!page_ref_count(page)) {
			if (PageBuddy(page))
				iter += (1 << page_order(page)) - 1;
			continue;
		}

		/*
		 * The HWPoisoned page may be not in buddy system, and
		 * page_count() is not 0.
		 */
		if (skip_hwpoisoned_pages && PageHWPoison(page))
			continue;

		if (__PageMovable(page))
			continue;

		if (!PageLRU(page))
			found++;
		/*
		 * If there are RECLAIMABLE pages, we need to check
		 * it.  But now, memory offline itself doesn't call
		 * shrink_node_slabs() and it still to be fixed.
		 */
		/*
		 * If the page is not RAM, page_count()should be 0.
		 * we don't need more check. This is an _used_ not-movable page.
		 *
		 * The problematic thing here is PG_reserved pages. PG_reserved
		 * is set to both of a memory hole page and a _used_ kernel
		 * page at boot.
		 */
		if (found > count)
			return true;
	}
	return false;
}

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

	/*
	 * 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, true);
}

#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)

static unsigned long pfn_max_align_down(unsigned long pfn)
{
	return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
			     pageblock_nr_pages) - 1);
}

static unsigned long pfn_max_align_up(unsigned long pfn)
{
	return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
				pageblock_nr_pages));
}

/* [start, end) must belong to a single zone. */
static int __alloc_contig_migrate_range(struct compact_control *cc,
					unsigned long start, unsigned long end)
{
	/* This function is based on compact_zone() from compaction.c. */
	unsigned long nr_reclaimed;
	unsigned long pfn = start;
	unsigned int tries = 0;
	int ret = 0;

	migrate_prep();

	while (pfn < end || !list_empty(&cc->migratepages)) {
		if (fatal_signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		if (list_empty(&cc->migratepages)) {
			cc->nr_migratepages = 0;
			pfn = isolate_migratepages_range(cc, pfn, end);
			if (!pfn) {
				ret = -EINTR;
				break;
			}
			tries = 0;
		} else if (++tries == 5) {
			ret = ret < 0 ? ret : -EBUSY;
			break;
		}

		nr_reclaimed = reclaim_clean_pages_from_list(cc->zone,
							&cc->migratepages);
		cc->nr_migratepages -= nr_reclaimed;

		ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
				    NULL, 0, cc->mode, MR_CONTIG_RANGE);
	}
	if (ret < 0) {
		putback_movable_pages(&cc->migratepages);
		return ret;
	}
	return 0;
}

/**
 * alloc_contig_range() -- tries to allocate given range of pages
 * @start:	start PFN to allocate
 * @end:	one-past-the-last PFN to allocate
 * @migratetype:	migratetype of the underlaying pageblocks (either
 *			#MIGRATE_MOVABLE or #MIGRATE_CMA).  All pageblocks
 *			in range must have the same migratetype and it must
 *			be either of the two.
 * @gfp_mask:	GFP mask to use during compaction
 *
 * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
 * aligned.  The PFN range must belong to a single zone.
 *
 * The first thing this routine does is attempt to MIGRATE_ISOLATE all
 * pageblocks in the range.  Once isolated, the pageblocks should not
 * be modified by others.
 *
 * Returns zero on success or negative error code.  On success all
 * pages which PFN is in [start, end) are allocated for the caller and
 * need to be freed with free_contig_range().
 */
int alloc_contig_range(unsigned long start, unsigned long end,
		       unsigned migratetype, gfp_t gfp_mask)
{
	unsigned long outer_start, outer_end;
	unsigned int order;
	int ret = 0;

	struct compact_control cc = {
		.nr_migratepages = 0,
		.order = -1,
		.zone = page_zone(pfn_to_page(start)),
		.mode = MIGRATE_SYNC,
		.ignore_skip_hint = true,
		.no_set_skip_hint = true,
		.gfp_mask = current_gfp_context(gfp_mask),
	};
	INIT_LIST_HEAD(&cc.migratepages);

	/*
	 * What we do here is we mark all pageblocks in range as
	 * MIGRATE_ISOLATE.  Because pageblock and max order pages may
	 * have different sizes, and due to the way page allocator
	 * work, we align the range to biggest of the two pages so
	 * that page allocator won't try to merge buddies from
	 * different pageblocks and change MIGRATE_ISOLATE to some
	 * other migration type.
	 *
	 * Once the pageblocks are marked as MIGRATE_ISOLATE, we
	 * migrate the pages from an unaligned range (ie. pages that
	 * we are interested in).  This will put all the pages in
	 * range back to page allocator as MIGRATE_ISOLATE.
	 *
	 * When this is done, we take the pages in range from page
	 * allocator removing them from the buddy system.  This way
	 * page allocator will never consider using them.
	 *
	 * This lets us mark the pageblocks back as
	 * MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the
	 * aligned range but not in the unaligned, original range are
	 * put back to page allocator so that buddy can use them.
	 */

	ret = start_isolate_page_range(pfn_max_align_down(start),
				       pfn_max_align_up(end), migratetype,
				       false);
	if (ret)
		return ret;

	/*
	 * In case of -EBUSY, we'd like to know which page causes problem.
	 * So, just fall through. test_pages_isolated() has a tracepoint
	 * which will report the busy page.
	 *
	 * It is possible that busy pages could become available before
	 * the call to test_pages_isolated, and the range will actually be
	 * allocated.  So, if we fall through be sure to clear ret so that
	 * -EBUSY is not accidentally used or returned to caller.
	 */
	ret = __alloc_contig_migrate_range(&cc, start, end);
	if (ret && ret != -EBUSY)
		goto done;
	ret =0;

	/*
	 * Pages from [start, end) are within a MAX_ORDER_NR_PAGES
	 * aligned blocks that are marked as MIGRATE_ISOLATE.  What's
	 * more, all pages in [start, end) are free in page allocator.
	 * What we are going to do is to allocate all pages from
	 * [start, end) (that is remove them from page allocator).
	 *
	 * The only problem is that pages at the beginning and at the
	 * end of interesting range may be not aligned with pages that
	 * page allocator holds, ie. they can be part of higher order
	 * pages.  Because of this, we reserve the bigger range and
	 * once this is done free the pages we are not interested in.
	 *
	 * We don't have to hold zone->lock here because the pages are
	 * isolated thus they won't get removed from buddy.
	 */

	lru_add_drain_all();
	drain_all_pages(cc.zone);

	order = 0;
	outer_start = start;
	while (!PageBuddy(pfn_to_page(outer_start))) {
		if (++order >= MAX_ORDER) {
			outer_start = start;
			break;
		}
		outer_start &= ~0UL << order;
	}

	if (outer_start != start) {
		order = page_order(pfn_to_page(outer_start));

		/*
		 * outer_start page could be small order buddy page and
		 * it doesn't include start page. Adjust outer_start
		 * in this case to report failed page properly
		 * on tracepoint in test_pages_isolated()
		 */
		if (outer_start + (1UL << order) <= start)
			outer_start = start;
	}

	/* Make sure the range is really isolated. */
	if (test_pages_isolated(outer_start, end, false)) {
		pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
			__func__, outer_start, end);
		ret = -EBUSY;
		goto done;
	}

	/* Grab isolated pages from freelists. */
	outer_end = isolate_freepages_range(&cc, outer_start, end);
	if (!outer_end) {
		ret = -EBUSY;
		goto done;
	}

	/* Free head and tail (if any) */
	if (start != outer_start)
		free_contig_range(outer_start, start - outer_start);
	if (end != outer_end)
		free_contig_range(end, outer_end - end);

done:
	undo_isolate_page_range(pfn_max_align_down(start),
				pfn_max_align_up(end), migratetype);
	return ret;
}

void free_contig_range(unsigned long pfn, unsigned nr_pages)
{
	unsigned int count = 0;

	for (; nr_pages--; pfn++) {
		struct page *page = pfn_to_page(pfn);

		count += page_count(page) != 1;
		__free_page(page);
	}
	WARN(count != 0, "%d pages are still in use!\n", count);
}
#endif

#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * The zone indicated has a new number of managed_pages; batch sizes and percpu
 * page high values need to be recalulated.
 */
void __meminit zone_pcp_update(struct zone *zone)
{
	unsigned cpu;
	mutex_lock(&pcp_batch_high_lock);
	for_each_possible_cpu(cpu)
		pageset_set_high_and_batch(zone,
				per_cpu_ptr(zone->pageset, cpu));
	mutex_unlock(&pcp_batch_high_lock);
}
#endif

void zone_pcp_reset(struct zone *zone)
{
	unsigned long flags;
	int cpu;
	struct per_cpu_pageset *pset;

	/* avoid races with drain_pages()  */
	local_irq_save(flags);
	if (zone->pageset != &boot_pageset) {
		for_each_online_cpu(cpu) {
			pset = per_cpu_ptr(zone->pageset, cpu);
			drain_zonestat(zone, pset);
		}
		free_percpu(zone->pageset);
		zone->pageset = &boot_pageset;
	}
	local_irq_restore(flags);
}

#ifdef CONFIG_MEMORY_HOTREMOVE
/*
 * All pages in the range must be in a single zone and isolated
 * before calling this.
 */
void
__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
	struct page *page;
	struct zone *zone;
	unsigned int order, i;
	unsigned long pfn;
	unsigned long flags;
	/* find the first valid pfn */
	for (pfn = start_pfn; pfn < end_pfn; pfn++)
		if (pfn_valid(pfn))
			break;
	if (pfn == end_pfn)
		return;
	offline_mem_sections(pfn, end_pfn);
	zone = page_zone(pfn_to_page(pfn));
	spin_lock_irqsave(&zone->lock, flags);
	pfn = start_pfn;
	while (pfn < end_pfn) {
		if (!pfn_valid(pfn)) {
			pfn++;
			continue;
		}
		page = pfn_to_page(pfn);
		/*
		 * The HWPoisoned page may be not in buddy system, and
		 * page_count() is not 0.
		 */
		if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {