page_alloc.c

		 * If there are RECLAIMABLE pages, we need to check it.
		 * But now, memory offline itself doesn't call shrink_slab()
		 * 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, true);
}

#ifdef 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->zone, cc,
							 pfn, end, true);
			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,
				    0, MIGRATE_SYNC, MR_CMA);
	}
	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.
 *
 * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
 * aligned, however it's the caller's responsibility to guarantee that
 * we are the only thread that changes migrate type of pageblocks the
 * pages fall in.
 *
 * The PFN range must belong to a single zone.
 *
 * 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)
{
	unsigned long outer_start, outer_end;
	int ret = 0, order;

	struct compact_control cc = {
		.nr_migratepages = 0,
		.order = -1,
		.zone = page_zone(pfn_to_page(start)),
		.sync = true,
		.ignore_skip_hint = true,
	};
	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;

	ret = __alloc_contig_migrate_range(&cc, start, end);
	if (ret)
		goto done;

	/*
	 * 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();

	order = 0;
	outer_start = start;
	while (!PageBuddy(pfn_to_page(outer_start))) {
		if (++order >= MAX_ORDER) {
			ret = -EBUSY;
			goto done;
		}
		outer_start &= ~0UL << order;
	}

	/* Make sure the range is really isolated. */
	if (test_pages_isolated(outer_start, end, false)) {
		pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n",
		       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
static int __meminit __zone_pcp_update(void *data)
{
	struct zone *zone = data;
	int cpu;
	unsigned long batch = zone_batchsize(zone), flags;

	for_each_possible_cpu(cpu) {
		struct per_cpu_pageset *pset;
		struct per_cpu_pages *pcp;

		pset = per_cpu_ptr(zone->pageset, cpu);
		pcp = &pset->pcp;

		local_irq_save(flags);
		if (pcp->count > 0)
			free_pcppages_bulk(zone, pcp->count, pcp);
		drain_zonestat(zone, pset);
		setup_pageset(pset, batch);
		local_irq_restore(flags);
	}
	return 0;
}

void __meminit zone_pcp_update(struct zone *zone)
{
	stop_machine(__zone_pcp_update, zone, NULL);
}
#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 isolated before calling this.
 */
void
__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
	struct page *page;
	struct zone *zone;
	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;
	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))) {
			pfn++;
			SetPageReserved(page);
			continue;
		}

		BUG_ON(page_count(page));
		BUG_ON(!PageBuddy(page));
		order = page_order(page);
#ifdef CONFIG_DEBUG_VM
		printk(KERN_INFO "remove from free list %lx %d %lx\n",
		       pfn, 1 << order, end_pfn);
#endif
		list_del(&page->lru);
		rmv_page_order(page);
		zone->free_area[order].nr_free--;
		for (i = 0; i < (1 << order); i++)
			SetPageReserved((page+i));
		pfn += (1 << order);
	}
	spin_unlock_irqrestore(&zone->lock, flags);
}
#endif

#ifdef CONFIG_MEMORY_FAILURE
bool is_free_buddy_page(struct page *page)
{
	struct zone *zone = page_zone(page);
	unsigned long pfn = page_to_pfn(page);
	unsigned long flags;
	int order;

	spin_lock_irqsave(&zone->lock, flags);
	for (order = 0; order < MAX_ORDER; order++) {
		struct page *page_head = page - (pfn & ((1 << order) - 1));

		if (PageBuddy(page_head) && page_order(page_head) >= order)
			break;
	}
	spin_unlock_irqrestore(&zone->lock, flags);

	return order < MAX_ORDER;
}
#endif

static const struct trace_print_flags pageflag_names[] = {
	{1UL << PG_locked,		"locked"	},
	{1UL << PG_error,		"error"		},
	{1UL << PG_referenced,		"referenced"	},
	{1UL << PG_uptodate,		"uptodate"	},
	{1UL << PG_dirty,		"dirty"		},
	{1UL << PG_lru,			"lru"		},
	{1UL << PG_active,		"active"	},
	{1UL << PG_slab,		"slab"		},
	{1UL << PG_owner_priv_1,	"owner_priv_1"	},
	{1UL << PG_arch_1,		"arch_1"	},
	{1UL << PG_reserved,		"reserved"	},
	{1UL << PG_private,		"private"	},
	{1UL << PG_private_2,		"private_2"	},
	{1UL << PG_writeback,		"writeback"	},
#ifdef CONFIG_PAGEFLAGS_EXTENDED
	{1UL << PG_head,		"head"		},
	{1UL << PG_tail,		"tail"		},
#else
	{1UL << PG_compound,		"compound"	},
#endif
	{1UL << PG_swapcache,		"swapcache"	},
	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
	{1UL << PG_reclaim,		"reclaim"	},
	{1UL << PG_swapbacked,		"swapbacked"	},
	{1UL << PG_unevictable,		"unevictable"	},
#ifdef CONFIG_MMU
	{1UL << PG_mlocked,		"mlocked"	},
#endif
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
	{1UL << PG_uncached,		"uncached"	},
#endif
#ifdef CONFIG_MEMORY_FAILURE
	{1UL << PG_hwpoison,		"hwpoison"	},
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	{1UL << PG_compound_lock,	"compound_lock"	},
#endif
};

static void dump_page_flags(unsigned long flags)
{
	const char *delim = "";
	unsigned long mask;
	int i;

	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);

	printk(KERN_ALERT "page flags: %#lx(", flags);

	/* remove zone id */
	flags &= (1UL << NR_PAGEFLAGS) - 1;

	for (i = 0; i < ARRAY_SIZE(pageflag_names) && flags; i++) {

		mask = pageflag_names[i].mask;
		if ((flags & mask) != mask)
			continue;

		flags &= ~mask;
		printk("%s%s", delim, pageflag_names[i].name);
		delim = "|";
	}

	/* check for left over flags */
	if (flags)
		printk("%s%#lx", delim, flags);

	printk(")\n");
}

void dump_page(struct page *page)
{
	printk(KERN_ALERT
	       "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
		page, atomic_read(&page->_count), page_mapcount(page),
		page->mapping, page->index);
	dump_page_flags(page->flags);
	mem_cgroup_print_bad_page(page);
}