/*
   *  Copyright (C) 2009  Red Hat, Inc.
   *
   *  This work is licensed under the terms of the GNU GPL, version 2. See
   *  the COPYING file in the top-level directory.
   */
  
  #include <linux/mm.h>
  #include <linux/sched.h>
  #include <linux/highmem.h>
  #include <linux/hugetlb.h>
  #include <linux/mmu_notifier.h>
  #include <linux/rmap.h>
  #include <linux/swap.h>

  #include <linux/shrinker.h>

  #include <linux/mm_inline.h>
  #include <linux/kthread.h>
  #include <linux/khugepaged.h>

  #include <linux/freezer.h>

  #include <linux/mman.h>

  #include <linux/pagemap.h>

  #include <linux/migrate.h>

  #include <linux/hashtable.h>

  #include <asm/tlb.h>
  #include <asm/pgalloc.h>
  #include "internal.h"

  /*

   * By default transparent hugepage support is disabled in order that avoid
   * to risk increase the memory footprint of applications without a guaranteed
   * benefit. When transparent hugepage support is enabled, is for all mappings,
   * and khugepaged scans all mappings.
   * Defrag is invoked by khugepaged hugepage allocations and by page faults
   * for all hugepage allocations.

   */

  unsigned long transparent_hugepage_flags __read_mostly =

  #ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS

  	(1<<TRANSPARENT_HUGEPAGE_FLAG)|

  #endif
  #ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
  	(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
  #endif

  	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)|

  	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
  	(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);

  
  /* default scan 8*512 pte (or vmas) every 30 second */
  static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
  static unsigned int khugepaged_pages_collapsed;
  static unsigned int khugepaged_full_scans;
  static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
  /* during fragmentation poll the hugepage allocator once every minute */
  static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000;
  static struct task_struct *khugepaged_thread __read_mostly;
  static DEFINE_MUTEX(khugepaged_mutex);
  static DEFINE_SPINLOCK(khugepaged_mm_lock);
  static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
  /*
   * default collapse hugepages if there is at least one pte mapped like
   * it would have happened if the vma was large enough during page
   * fault.
   */
  static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
  
  static int khugepaged(void *none);

  static int khugepaged_slab_init(void);

  #define MM_SLOTS_HASH_BITS 10
  static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);

  static struct kmem_cache *mm_slot_cache __read_mostly;
  
  /**
   * struct mm_slot - hash lookup from mm to mm_slot
   * @hash: hash collision list
   * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head
   * @mm: the mm that this information is valid for
   */
  struct mm_slot {
  	struct hlist_node hash;
  	struct list_head mm_node;
  	struct mm_struct *mm;
  };
  
  /**
   * struct khugepaged_scan - cursor for scanning
   * @mm_head: the head of the mm list to scan
   * @mm_slot: the current mm_slot we are scanning
   * @address: the next address inside that to be scanned
   *
   * There is only the one khugepaged_scan instance of this cursor structure.
   */
  struct khugepaged_scan {
  	struct list_head mm_head;
  	struct mm_slot *mm_slot;
  	unsigned long address;

  };
  static struct khugepaged_scan khugepaged_scan = {

  	.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
  };

  
  static int set_recommended_min_free_kbytes(void)
  {
  	struct zone *zone;
  	int nr_zones = 0;
  	unsigned long recommended_min;

  	if (!khugepaged_enabled())

  		return 0;
  
  	for_each_populated_zone(zone)
  		nr_zones++;
  
  	/* Make sure at least 2 hugepages are free for MIGRATE_RESERVE */
  	recommended_min = pageblock_nr_pages * nr_zones * 2;
  
  	/*
  	 * Make sure that on average at least two pageblocks are almost free
  	 * of another type, one for a migratetype to fall back to and a
  	 * second to avoid subsequent fallbacks of other types There are 3
  	 * MIGRATE_TYPES we care about.
  	 */
  	recommended_min += pageblock_nr_pages * nr_zones *
  			   MIGRATE_PCPTYPES * MIGRATE_PCPTYPES;
  
  	/* don't ever allow to reserve more than 5% of the lowmem */
  	recommended_min = min(recommended_min,
  			      (unsigned long) nr_free_buffer_pages() / 20);
  	recommended_min <<= (PAGE_SHIFT-10);

  	if (recommended_min > min_free_kbytes) {
  		if (user_min_free_kbytes >= 0)
  			pr_info("raising min_free_kbytes from %d to %lu "
  				"to help transparent hugepage allocations
  ",
  				min_free_kbytes, recommended_min);

  		min_free_kbytes = recommended_min;

  	}

  	setup_per_zone_wmarks();
  	return 0;
  }
  late_initcall(set_recommended_min_free_kbytes);

  static int start_khugepaged(void)
  {
  	int err = 0;
  	if (khugepaged_enabled()) {

  		if (!khugepaged_thread)
  			khugepaged_thread = kthread_run(khugepaged, NULL,
  							"khugepaged");
  		if (unlikely(IS_ERR(khugepaged_thread))) {
  			printk(KERN_ERR
  			       "khugepaged: kthread_run(khugepaged) failed
  ");
  			err = PTR_ERR(khugepaged_thread);
  			khugepaged_thread = NULL;
  		}

  
  		if (!list_empty(&khugepaged_scan.mm_head))

  			wake_up_interruptible(&khugepaged_wait);

  
  		set_recommended_min_free_kbytes();

  	} else if (khugepaged_thread) {

  		kthread_stop(khugepaged_thread);
  		khugepaged_thread = NULL;
  	}

  	return err;
  }

  static atomic_t huge_zero_refcount;

  static struct page *huge_zero_page __read_mostly;

  static inline bool is_huge_zero_page(struct page *page)

  {

  	return ACCESS_ONCE(huge_zero_page) == page;

  }

  static inline bool is_huge_zero_pmd(pmd_t pmd)
  {

  	return is_huge_zero_page(pmd_page(pmd));

  }

  static struct page *get_huge_zero_page(void)

  {
  	struct page *zero_page;
  retry:
  	if (likely(atomic_inc_not_zero(&huge_zero_refcount)))

  		return ACCESS_ONCE(huge_zero_page);

  
  	zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,

  			HPAGE_PMD_ORDER);

  	if (!zero_page) {
  		count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);

  		return NULL;

  	}
  	count_vm_event(THP_ZERO_PAGE_ALLOC);

  	preempt_disable();

  	if (cmpxchg(&huge_zero_page, NULL, zero_page)) {

  		preempt_enable();
  		__free_page(zero_page);
  		goto retry;
  	}
  
  	/* We take additional reference here. It will be put back by shrinker */
  	atomic_set(&huge_zero_refcount, 2);
  	preempt_enable();

  	return ACCESS_ONCE(huge_zero_page);

  }

  static void put_huge_zero_page(void)

  {

  	/*
  	 * Counter should never go to zero here. Only shrinker can put
  	 * last reference.
  	 */
  	BUG_ON(atomic_dec_and_test(&huge_zero_refcount));

  }

  static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
  					struct shrink_control *sc)

  {

  	/* we can free zero page only if last reference remains */
  	return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
  }

  static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
  				       struct shrink_control *sc)
  {

  	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {

  		struct page *zero_page = xchg(&huge_zero_page, NULL);
  		BUG_ON(zero_page == NULL);
  		__free_page(zero_page);

  		return HPAGE_PMD_NR;

  	}
  
  	return 0;

  }

  static struct shrinker huge_zero_page_shrinker = {

  	.count_objects = shrink_huge_zero_page_count,
  	.scan_objects = shrink_huge_zero_page_scan,

  	.seeks = DEFAULT_SEEKS,
  };

  #ifdef CONFIG_SYSFS

  static ssize_t double_flag_show(struct kobject *kobj,
  				struct kobj_attribute *attr, char *buf,
  				enum transparent_hugepage_flag enabled,
  				enum transparent_hugepage_flag req_madv)
  {
  	if (test_bit(enabled, &transparent_hugepage_flags)) {
  		VM_BUG_ON(test_bit(req_madv, &transparent_hugepage_flags));
  		return sprintf(buf, "[always] madvise never
  ");
  	} else if (test_bit(req_madv, &transparent_hugepage_flags))
  		return sprintf(buf, "always [madvise] never
  ");
  	else
  		return sprintf(buf, "always madvise [never]
  ");
  }
  static ssize_t double_flag_store(struct kobject *kobj,
  				 struct kobj_attribute *attr,
  				 const char *buf, size_t count,
  				 enum transparent_hugepage_flag enabled,
  				 enum transparent_hugepage_flag req_madv)
  {
  	if (!memcmp("always", buf,
  		    min(sizeof("always")-1, count))) {
  		set_bit(enabled, &transparent_hugepage_flags);
  		clear_bit(req_madv, &transparent_hugepage_flags);
  	} else if (!memcmp("madvise", buf,
  			   min(sizeof("madvise")-1, count))) {
  		clear_bit(enabled, &transparent_hugepage_flags);
  		set_bit(req_madv, &transparent_hugepage_flags);
  	} else if (!memcmp("never", buf,
  			   min(sizeof("never")-1, count))) {
  		clear_bit(enabled, &transparent_hugepage_flags);
  		clear_bit(req_madv, &transparent_hugepage_flags);
  	} else
  		return -EINVAL;
  
  	return count;
  }
  
  static ssize_t enabled_show(struct kobject *kobj,
  			    struct kobj_attribute *attr, char *buf)
  {
  	return double_flag_show(kobj, attr, buf,
  				TRANSPARENT_HUGEPAGE_FLAG,
  				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
  }
  static ssize_t enabled_store(struct kobject *kobj,
  			     struct kobj_attribute *attr,
  			     const char *buf, size_t count)
  {

  	ssize_t ret;
  
  	ret = double_flag_store(kobj, attr, buf, count,
  				TRANSPARENT_HUGEPAGE_FLAG,
  				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
  
  	if (ret > 0) {

  		int err;
  
  		mutex_lock(&khugepaged_mutex);
  		err = start_khugepaged();
  		mutex_unlock(&khugepaged_mutex);

  		if (err)
  			ret = err;
  	}
  
  	return ret;

  }
  static struct kobj_attribute enabled_attr =
  	__ATTR(enabled, 0644, enabled_show, enabled_store);
  
  static ssize_t single_flag_show(struct kobject *kobj,
  				struct kobj_attribute *attr, char *buf,
  				enum transparent_hugepage_flag flag)
  {

  	return sprintf(buf, "%d
  ",
  		       !!test_bit(flag, &transparent_hugepage_flags));

  }

  static ssize_t single_flag_store(struct kobject *kobj,
  				 struct kobj_attribute *attr,
  				 const char *buf, size_t count,
  				 enum transparent_hugepage_flag flag)
  {

  	unsigned long value;
  	int ret;
  
  	ret = kstrtoul(buf, 10, &value);
  	if (ret < 0)
  		return ret;
  	if (value > 1)
  		return -EINVAL;
  
  	if (value)

  		set_bit(flag, &transparent_hugepage_flags);

  	else

  		clear_bit(flag, &transparent_hugepage_flags);

  
  	return count;
  }
  
  /*
   * Currently defrag only disables __GFP_NOWAIT for allocation. A blind
   * __GFP_REPEAT is too aggressive, it's never worth swapping tons of
   * memory just to allocate one more hugepage.
   */
  static ssize_t defrag_show(struct kobject *kobj,
  			   struct kobj_attribute *attr, char *buf)
  {
  	return double_flag_show(kobj, attr, buf,
  				TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
  				TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
  }
  static ssize_t defrag_store(struct kobject *kobj,
  			    struct kobj_attribute *attr,
  			    const char *buf, size_t count)
  {
  	return double_flag_store(kobj, attr, buf, count,
  				 TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
  				 TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
  }
  static struct kobj_attribute defrag_attr =
  	__ATTR(defrag, 0644, defrag_show, defrag_store);

  static ssize_t use_zero_page_show(struct kobject *kobj,
  		struct kobj_attribute *attr, char *buf)
  {
  	return single_flag_show(kobj, attr, buf,
  				TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
  }
  static ssize_t use_zero_page_store(struct kobject *kobj,
  		struct kobj_attribute *attr, const char *buf, size_t count)
  {
  	return single_flag_store(kobj, attr, buf, count,
  				 TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
  }
  static struct kobj_attribute use_zero_page_attr =
  	__ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_store);

  #ifdef CONFIG_DEBUG_VM
  static ssize_t debug_cow_show(struct kobject *kobj,
  				struct kobj_attribute *attr, char *buf)
  {
  	return single_flag_show(kobj, attr, buf,
  				TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
  }
  static ssize_t debug_cow_store(struct kobject *kobj,
  			       struct kobj_attribute *attr,
  			       const char *buf, size_t count)
  {
  	return single_flag_store(kobj, attr, buf, count,
  				 TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
  }
  static struct kobj_attribute debug_cow_attr =
  	__ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store);
  #endif /* CONFIG_DEBUG_VM */
  
  static struct attribute *hugepage_attr[] = {
  	&enabled_attr.attr,
  	&defrag_attr.attr,

  	&use_zero_page_attr.attr,

  #ifdef CONFIG_DEBUG_VM
  	&debug_cow_attr.attr,
  #endif
  	NULL,
  };
  
  static struct attribute_group hugepage_attr_group = {
  	.attrs = hugepage_attr,

  };
  
  static ssize_t scan_sleep_millisecs_show(struct kobject *kobj,
  					 struct kobj_attribute *attr,
  					 char *buf)
  {
  	return sprintf(buf, "%u
  ", khugepaged_scan_sleep_millisecs);
  }
  
  static ssize_t scan_sleep_millisecs_store(struct kobject *kobj,
  					  struct kobj_attribute *attr,
  					  const char *buf, size_t count)
  {
  	unsigned long msecs;
  	int err;

  	err = kstrtoul(buf, 10, &msecs);

  	if (err || msecs > UINT_MAX)
  		return -EINVAL;
  
  	khugepaged_scan_sleep_millisecs = msecs;
  	wake_up_interruptible(&khugepaged_wait);
  
  	return count;
  }
  static struct kobj_attribute scan_sleep_millisecs_attr =
  	__ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show,
  	       scan_sleep_millisecs_store);
  
  static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj,
  					  struct kobj_attribute *attr,
  					  char *buf)
  {
  	return sprintf(buf, "%u
  ", khugepaged_alloc_sleep_millisecs);
  }
  
  static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj,
  					   struct kobj_attribute *attr,
  					   const char *buf, size_t count)
  {
  	unsigned long msecs;
  	int err;

  	err = kstrtoul(buf, 10, &msecs);

  	if (err || msecs > UINT_MAX)
  		return -EINVAL;
  
  	khugepaged_alloc_sleep_millisecs = msecs;
  	wake_up_interruptible(&khugepaged_wait);
  
  	return count;
  }
  static struct kobj_attribute alloc_sleep_millisecs_attr =
  	__ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show,
  	       alloc_sleep_millisecs_store);
  
  static ssize_t pages_to_scan_show(struct kobject *kobj,
  				  struct kobj_attribute *attr,
  				  char *buf)
  {
  	return sprintf(buf, "%u
  ", khugepaged_pages_to_scan);
  }
  static ssize_t pages_to_scan_store(struct kobject *kobj,
  				   struct kobj_attribute *attr,
  				   const char *buf, size_t count)
  {
  	int err;
  	unsigned long pages;

  	err = kstrtoul(buf, 10, &pages);

  	if (err || !pages || pages > UINT_MAX)
  		return -EINVAL;
  
  	khugepaged_pages_to_scan = pages;
  
  	return count;
  }
  static struct kobj_attribute pages_to_scan_attr =
  	__ATTR(pages_to_scan, 0644, pages_to_scan_show,
  	       pages_to_scan_store);
  
  static ssize_t pages_collapsed_show(struct kobject *kobj,
  				    struct kobj_attribute *attr,
  				    char *buf)
  {
  	return sprintf(buf, "%u
  ", khugepaged_pages_collapsed);
  }
  static struct kobj_attribute pages_collapsed_attr =
  	__ATTR_RO(pages_collapsed);
  
  static ssize_t full_scans_show(struct kobject *kobj,
  			       struct kobj_attribute *attr,
  			       char *buf)
  {
  	return sprintf(buf, "%u
  ", khugepaged_full_scans);
  }
  static struct kobj_attribute full_scans_attr =
  	__ATTR_RO(full_scans);
  
  static ssize_t khugepaged_defrag_show(struct kobject *kobj,
  				      struct kobj_attribute *attr, char *buf)
  {
  	return single_flag_show(kobj, attr, buf,
  				TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
  }
  static ssize_t khugepaged_defrag_store(struct kobject *kobj,
  				       struct kobj_attribute *attr,
  				       const char *buf, size_t count)
  {
  	return single_flag_store(kobj, attr, buf, count,
  				 TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
  }
  static struct kobj_attribute khugepaged_defrag_attr =
  	__ATTR(defrag, 0644, khugepaged_defrag_show,
  	       khugepaged_defrag_store);
  
  /*
   * max_ptes_none controls if khugepaged should collapse hugepages over
   * any unmapped ptes in turn potentially increasing the memory
   * footprint of the vmas. When max_ptes_none is 0 khugepaged will not
   * reduce the available free memory in the system as it
   * runs. Increasing max_ptes_none will instead potentially reduce the
   * free memory in the system during the khugepaged scan.
   */
  static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj,
  					     struct kobj_attribute *attr,
  					     char *buf)
  {
  	return sprintf(buf, "%u
  ", khugepaged_max_ptes_none);
  }
  static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj,
  					      struct kobj_attribute *attr,
  					      const char *buf, size_t count)
  {
  	int err;
  	unsigned long max_ptes_none;

  	err = kstrtoul(buf, 10, &max_ptes_none);

  	if (err || max_ptes_none > HPAGE_PMD_NR-1)
  		return -EINVAL;
  
  	khugepaged_max_ptes_none = max_ptes_none;
  
  	return count;
  }
  static struct kobj_attribute khugepaged_max_ptes_none_attr =
  	__ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show,
  	       khugepaged_max_ptes_none_store);
  
  static struct attribute *khugepaged_attr[] = {
  	&khugepaged_defrag_attr.attr,
  	&khugepaged_max_ptes_none_attr.attr,
  	&pages_to_scan_attr.attr,
  	&pages_collapsed_attr.attr,
  	&full_scans_attr.attr,
  	&scan_sleep_millisecs_attr.attr,
  	&alloc_sleep_millisecs_attr.attr,
  	NULL,
  };
  
  static struct attribute_group khugepaged_attr_group = {
  	.attrs = khugepaged_attr,
  	.name = "khugepaged",

  };

  static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)

  {

  	int err;

  	*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
  	if (unlikely(!*hugepage_kobj)) {

  		printk(KERN_ERR "hugepage: failed to create transparent hugepage kobject
  ");

  		return -ENOMEM;

  	}

  	err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);

  	if (err) {

  		printk(KERN_ERR "hugepage: failed to register transparent hugepage group
  ");

  		goto delete_obj;

  	}

  	err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);

  	if (err) {

  		printk(KERN_ERR "hugepage: failed to register transparent hugepage group
  ");

  		goto remove_hp_group;

  	}

  
  	return 0;
  
  remove_hp_group:
  	sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group);
  delete_obj:
  	kobject_put(*hugepage_kobj);
  	return err;
  }
  
  static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj)
  {
  	sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group);
  	sysfs_remove_group(hugepage_kobj, &hugepage_attr_group);
  	kobject_put(hugepage_kobj);
  }
  #else
  static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj)
  {
  	return 0;
  }
  
  static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj)
  {
  }
  #endif /* CONFIG_SYSFS */
  
  static int __init hugepage_init(void)
  {
  	int err;
  	struct kobject *hugepage_kobj;
  
  	if (!has_transparent_hugepage()) {
  		transparent_hugepage_flags = 0;
  		return -EINVAL;
  	}
  
  	err = hugepage_init_sysfs(&hugepage_kobj);
  	if (err)
  		return err;

  
  	err = khugepaged_slab_init();
  	if (err)
  		goto out;

  	register_shrinker(&huge_zero_page_shrinker);

  	/*
  	 * By default disable transparent hugepages on smaller systems,
  	 * where the extra memory used could hurt more than TLB overhead
  	 * is likely to save.  The admin can still enable it through /sys.
  	 */
  	if (totalram_pages < (512 << (20 - PAGE_SHIFT)))
  		transparent_hugepage_flags = 0;

  	start_khugepaged();

  	return 0;

  out:

  	hugepage_exit_sysfs(hugepage_kobj);

  	return err;

  }

  subsys_initcall(hugepage_init);

  
  static int __init setup_transparent_hugepage(char *str)
  {
  	int ret = 0;
  	if (!str)
  		goto out;
  	if (!strcmp(str, "always")) {
  		set_bit(TRANSPARENT_HUGEPAGE_FLAG,
  			&transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
  			  &transparent_hugepage_flags);
  		ret = 1;
  	} else if (!strcmp(str, "madvise")) {
  		clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
  			  &transparent_hugepage_flags);
  		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
  			&transparent_hugepage_flags);
  		ret = 1;
  	} else if (!strcmp(str, "never")) {
  		clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
  			  &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
  			  &transparent_hugepage_flags);
  		ret = 1;
  	}
  out:
  	if (!ret)
  		printk(KERN_WARNING
  		       "transparent_hugepage= cannot parse, ignored
  ");
  	return ret;
  }
  __setup("transparent_hugepage=", setup_transparent_hugepage);

  pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)

  {
  	if (likely(vma->vm_flags & VM_WRITE))
  		pmd = pmd_mkwrite(pmd);
  	return pmd;
  }

  static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)

  {
  	pmd_t entry;

  	entry = mk_pmd(page, prot);

  	entry = pmd_mkhuge(entry);
  	return entry;
  }

  static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
  					struct vm_area_struct *vma,
  					unsigned long haddr, pmd_t *pmd,
  					struct page *page)
  {

  	pgtable_t pgtable;

  	spinlock_t *ptl;

  	VM_BUG_ON_PAGE(!PageCompound(page), page);

  	pgtable = pte_alloc_one(mm, haddr);

  	if (unlikely(!pgtable))

  		return VM_FAULT_OOM;

  
  	clear_huge_page(page, haddr, HPAGE_PMD_NR);

  	/*
  	 * The memory barrier inside __SetPageUptodate makes sure that
  	 * clear_huge_page writes become visible before the set_pmd_at()
  	 * write.
  	 */

  	__SetPageUptodate(page);

  	ptl = pmd_lock(mm, pmd);

  	if (unlikely(!pmd_none(*pmd))) {

  		spin_unlock(ptl);

  		mem_cgroup_uncharge_page(page);

  		put_page(page);
  		pte_free(mm, pgtable);
  	} else {
  		pmd_t entry;

  		entry = mk_huge_pmd(page, vma->vm_page_prot);
  		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);

  		page_add_new_anon_rmap(page, vma, haddr);

  		pgtable_trans_huge_deposit(mm, pmd, pgtable);

  		set_pmd_at(mm, haddr, pmd, entry);

  		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);

  		atomic_long_inc(&mm->nr_ptes);

  		spin_unlock(ptl);

  	}

  	return 0;

  }

  static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)

  {

  	return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp;

  }
  
  static inline struct page *alloc_hugepage_vma(int defrag,
  					      struct vm_area_struct *vma,

  					      unsigned long haddr, int nd,
  					      gfp_t extra_gfp)

  {

  	return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp),

  			       HPAGE_PMD_ORDER, vma, haddr, nd);

  }

  /* Caller must hold page table lock. */

  static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,

  		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,

  		struct page *zero_page)

  {
  	pmd_t entry;

  	if (!pmd_none(*pmd))
  		return false;

  	entry = mk_pmd(zero_page, vma->vm_page_prot);

  	entry = pmd_wrprotect(entry);
  	entry = pmd_mkhuge(entry);

  	pgtable_trans_huge_deposit(mm, pmd, pgtable);

  	set_pmd_at(mm, haddr, pmd, entry);

  	atomic_long_inc(&mm->nr_ptes);

  	return true;

  }

  int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
  			       unsigned long address, pmd_t *pmd,
  			       unsigned int flags)
  {
  	struct page *page;
  	unsigned long haddr = address & HPAGE_PMD_MASK;

  	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)

  		return VM_FAULT_FALLBACK;

  	if (unlikely(anon_vma_prepare(vma)))
  		return VM_FAULT_OOM;
  	if (unlikely(khugepaged_enter(vma)))
  		return VM_FAULT_OOM;
  	if (!(flags & FAULT_FLAG_WRITE) &&
  			transparent_hugepage_use_zero_page()) {

  		spinlock_t *ptl;

  		pgtable_t pgtable;
  		struct page *zero_page;
  		bool set;
  		pgtable = pte_alloc_one(mm, haddr);
  		if (unlikely(!pgtable))

  			return VM_FAULT_OOM;

  		zero_page = get_huge_zero_page();
  		if (unlikely(!zero_page)) {
  			pte_free(mm, pgtable);

  			count_vm_event(THP_FAULT_FALLBACK);

  			return VM_FAULT_FALLBACK;

  		}

  		ptl = pmd_lock(mm, pmd);

  		set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
  				zero_page);

  		spin_unlock(ptl);

  		if (!set) {
  			pte_free(mm, pgtable);
  			put_huge_zero_page();

  		}

  		return 0;

  	}

  	page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
  			vma, haddr, numa_node_id(), 0);
  	if (unlikely(!page)) {
  		count_vm_event(THP_FAULT_FALLBACK);

  		return VM_FAULT_FALLBACK;

  	}

  	if (unlikely(mem_cgroup_charge_anon(page, mm, GFP_KERNEL))) {

  		put_page(page);

  		count_vm_event(THP_FAULT_FALLBACK);

  		return VM_FAULT_FALLBACK;

  	}
  	if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
  		mem_cgroup_uncharge_page(page);
  		put_page(page);

  		count_vm_event(THP_FAULT_FALLBACK);

  		return VM_FAULT_FALLBACK;

  	}

  	count_vm_event(THP_FAULT_ALLOC);

  	return 0;

  }
  
  int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
  		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
  		  struct vm_area_struct *vma)
  {

  	spinlock_t *dst_ptl, *src_ptl;

  	struct page *src_page;
  	pmd_t pmd;
  	pgtable_t pgtable;
  	int ret;
  
  	ret = -ENOMEM;
  	pgtable = pte_alloc_one(dst_mm, addr);
  	if (unlikely(!pgtable))
  		goto out;

  	dst_ptl = pmd_lock(dst_mm, dst_pmd);
  	src_ptl = pmd_lockptr(src_mm, src_pmd);
  	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);

  
  	ret = -EAGAIN;
  	pmd = *src_pmd;
  	if (unlikely(!pmd_trans_huge(pmd))) {
  		pte_free(dst_mm, pgtable);
  		goto out_unlock;
  	}

  	/*

  	 * When page table lock is held, the huge zero pmd should not be

  	 * under splitting since we don't split the page itself, only pmd to
  	 * a page table.
  	 */
  	if (is_huge_zero_pmd(pmd)) {

  		struct page *zero_page;

  		bool set;

  		/*
  		 * get_huge_zero_page() will never allocate a new page here,
  		 * since we already have a zero page to copy. It just takes a
  		 * reference.
  		 */

  		zero_page = get_huge_zero_page();

  		set = set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,

  				zero_page);

  		BUG_ON(!set); /* unexpected !pmd_none(dst_pmd) */

  		ret = 0;
  		goto out_unlock;
  	}

  	if (unlikely(pmd_trans_splitting(pmd))) {
  		/* split huge page running from under us */

  		spin_unlock(src_ptl);
  		spin_unlock(dst_ptl);

  		pte_free(dst_mm, pgtable);
  
  		wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */
  		goto out;
  	}
  	src_page = pmd_page(pmd);

  	VM_BUG_ON_PAGE(!PageHead(src_page), src_page);

  	get_page(src_page);
  	page_dup_rmap(src_page);
  	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
  
  	pmdp_set_wrprotect(src_mm, addr, src_pmd);
  	pmd = pmd_mkold(pmd_wrprotect(pmd));

  	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);

  	set_pmd_at(dst_mm, addr, dst_pmd, pmd);

  	atomic_long_inc(&dst_mm->nr_ptes);

  
  	ret = 0;
  out_unlock:

  	spin_unlock(src_ptl);
  	spin_unlock(dst_ptl);

  out:
  	return ret;
  }

  void huge_pmd_set_accessed(struct mm_struct *mm,
  			   struct vm_area_struct *vma,
  			   unsigned long address,
  			   pmd_t *pmd, pmd_t orig_pmd,
  			   int dirty)
  {

  	spinlock_t *ptl;

  	pmd_t entry;
  	unsigned long haddr;

  	ptl = pmd_lock(mm, pmd);

  	if (unlikely(!pmd_same(*pmd, orig_pmd)))
  		goto unlock;
  
  	entry = pmd_mkyoung(orig_pmd);
  	haddr = address & HPAGE_PMD_MASK;
  	if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty))
  		update_mmu_cache_pmd(vma, address, pmd);
  
  unlock:

  	spin_unlock(ptl);

  }

  static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
  					struct vm_area_struct *vma,
  					unsigned long address,
  					pmd_t *pmd, pmd_t orig_pmd,
  					struct page *page,
  					unsigned long haddr)
  {

  	spinlock_t *ptl;

  	pgtable_t pgtable;
  	pmd_t _pmd;
  	int ret = 0, i;
  	struct page **pages;

  	unsigned long mmun_start;	/* For mmu_notifiers */
  	unsigned long mmun_end;		/* For mmu_notifiers */

  
  	pages = kmalloc(sizeof(struct page *) * HPAGE_PMD_NR,
  			GFP_KERNEL);
  	if (unlikely(!pages)) {
  		ret |= VM_FAULT_OOM;
  		goto out;
  	}
  
  	for (i = 0; i < HPAGE_PMD_NR; i++) {

  		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE |
  					       __GFP_OTHER_NODE,

  					       vma, address, page_to_nid(page));

  		if (unlikely(!pages[i] ||

  			     mem_cgroup_charge_anon(pages[i], mm,

  						       GFP_KERNEL))) {
  			if (pages[i])

  				put_page(pages[i]);

  			mem_cgroup_uncharge_start();
  			while (--i >= 0) {
  				mem_cgroup_uncharge_page(pages[i]);
  				put_page(pages[i]);
  			}
  			mem_cgroup_uncharge_end();

  			kfree(pages);
  			ret |= VM_FAULT_OOM;
  			goto out;
  		}
  	}
  
  	for (i = 0; i < HPAGE_PMD_NR; i++) {
  		copy_user_highpage(pages[i], page + i,

  				   haddr + PAGE_SIZE * i, vma);

  		__SetPageUptodate(pages[i]);
  		cond_resched();
  	}

  	mmun_start = haddr;
  	mmun_end   = haddr + HPAGE_PMD_SIZE;
  	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

  	ptl = pmd_lock(mm, pmd);

  	if (unlikely(!pmd_same(*pmd, orig_pmd)))
  		goto out_free_pages;

  	VM_BUG_ON_PAGE(!PageHead(page), page);

  	pmdp_clear_flush(vma, haddr, pmd);

  	/* leave pmd empty until pte is filled */

  	pgtable = pgtable_trans_huge_withdraw(mm, pmd);

  	pmd_populate(mm, &_pmd, pgtable);
  
  	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
  		pte_t *pte, entry;
  		entry = mk_pte(pages[i], vma->vm_page_prot);
  		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
  		page_add_new_anon_rmap(pages[i], vma, haddr);
  		pte = pte_offset_map(&_pmd, haddr);
  		VM_BUG_ON(!pte_none(*pte));
  		set_pte_at(mm, haddr, pte, entry);
  		pte_unmap(pte);
  	}
  	kfree(pages);

  	smp_wmb(); /* make pte visible before pmd */
  	pmd_populate(mm, pmd, pgtable);
  	page_remove_rmap(page);

  	spin_unlock(ptl);

  	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

  	ret |= VM_FAULT_WRITE;
  	put_page(page);
  
  out:
  	return ret;
  
  out_free_pages:

  	spin_unlock(ptl);

  	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

  	mem_cgroup_uncharge_start();
  	for (i = 0; i < HPAGE_PMD_NR; i++) {
  		mem_cgroup_uncharge_page(pages[i]);

  		put_page(pages[i]);

  	}
  	mem_cgroup_uncharge_end();

  	kfree(pages);
  	goto out;
  }
  
  int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
  			unsigned long address, pmd_t *pmd, pmd_t orig_pmd)
  {

  	spinlock_t *ptl;

  	int ret = 0;

  	struct page *page = NULL, *new_page;

  	unsigned long haddr;

  	unsigned long mmun_start;	/* For mmu_notifiers */
  	unsigned long mmun_end;		/* For mmu_notifiers */

  	ptl = pmd_lockptr(mm, pmd);

  	VM_BUG_ON(!vma->anon_vma);

  	haddr = address & HPAGE_PMD_MASK;
  	if (is_huge_zero_pmd(orig_pmd))
  		goto alloc;

  	spin_lock(ptl);

  	if (unlikely(!pmd_same(*pmd, orig_pmd)))
  		goto out_unlock;
  
  	page = pmd_page(orig_pmd);

  	VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page);

  	if (page_mapcount(page) == 1) {
  		pmd_t entry;
  		entry = pmd_mkyoung(orig_pmd);
  		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
  		if (pmdp_set_access_flags(vma, haddr, pmd, entry,  1))

  			update_mmu_cache_pmd(vma, address, pmd);

  		ret |= VM_FAULT_WRITE;
  		goto out_unlock;
  	}
  	get_page(page);

  	spin_unlock(ptl);

  alloc:

  	if (transparent_hugepage_enabled(vma) &&
  	    !transparent_hugepage_debug_cow())

  		new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),

  					      vma, haddr, numa_node_id(), 0);

  	else
  		new_page = NULL;
  
  	if (unlikely(!new_page)) {

  		if (!page) {

  			split_huge_page_pmd(vma, address, pmd);
  			ret |= VM_FAULT_FALLBACK;

  		} else {
  			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
  					pmd, orig_pmd, page, haddr);

  			if (ret & VM_FAULT_OOM) {

  				split_huge_page(page);

  				ret |= VM_FAULT_FALLBACK;
  			}

  			put_page(page);
  		}

  		count_vm_event(THP_FAULT_FALLBACK);

  		goto out;
  	}

  	if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) {

  		put_page(new_page);

  		if (page) {
  			split_huge_page(page);
  			put_page(page);

  		} else
  			split_huge_page_pmd(vma, address, pmd);
  		ret |= VM_FAULT_FALLBACK;

  		count_vm_event(THP_FAULT_FALLBACK);

  		goto out;
  	}

  	count_vm_event(THP_FAULT_ALLOC);

  	if (!page)

  		clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
  	else
  		copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);

  	__SetPageUptodate(new_page);

  	mmun_start = haddr;
  	mmun_end   = haddr + HPAGE_PMD_SIZE;
  	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

  	spin_lock(ptl);

  	if (page)
  		put_page(page);

  	if (unlikely(!pmd_same(*pmd, orig_pmd))) {

  		spin_unlock(ptl);

  		mem_cgroup_uncharge_page(new_page);

  		put_page(new_page);

  		goto out_mn;

  	} else {

  		pmd_t entry;

  		entry = mk_huge_pmd(new_page, vma->vm_page_prot);
  		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);

  		pmdp_clear_flush(vma, haddr, pmd);

  		page_add_new_anon_rmap(new_page, vma, haddr);
  		set_pmd_at(mm, haddr, pmd, entry);

  		update_mmu_cache_pmd(vma, address, pmd);

  		if (!page) {

  			add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);

  			put_huge_zero_page();
  		} else {

  			VM_BUG_ON_PAGE(!PageHead(page), page);

  			page_remove_rmap(page);
  			put_page(page);
  		}

  		ret |= VM_FAULT_WRITE;
  	}

  	spin_unlock(ptl);

  out_mn:
  	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

  out:
  	return ret;

  out_unlock:

  	spin_unlock(ptl);

  	return ret;

  }

  struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,

  				   unsigned long addr,
  				   pmd_t *pmd,
  				   unsigned int flags)
  {

  	struct mm_struct *mm = vma->vm_mm;

  	struct page *page = NULL;

  	assert_spin_locked(pmd_lockptr(mm, pmd));

  
  	if (flags & FOLL_WRITE && !pmd_write(*pmd))
  		goto out;

  	/* Avoid dumping huge zero page */
  	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
  		return ERR_PTR(-EFAULT);

  	/* Full NUMA hinting faults to serialise migration in fault paths */
  	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
  		goto out;

  	page = pmd_page(*pmd);

  	VM_BUG_ON_PAGE(!PageHead(page), page);

  	if (flags & FOLL_TOUCH) {
  		pmd_t _pmd;
  		/*
  		 * We should set the dirty bit only for FOLL_WRITE but
  		 * for now the dirty bit in the pmd is meaningless.
  		 * And if the dirty bit will become meaningful and
  		 * we'll only set it with FOLL_WRITE, an atomic
  		 * set_bit will be required on the pmd to set the
  		 * young bit, instead of the current set_pmd_at.
  		 */
  		_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));

  		if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
  					  pmd, _pmd,  1))
  			update_mmu_cache_pmd(vma, addr, pmd);

  	}

  	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
  		if (page->mapping && trylock_page(page)) {
  			lru_add_drain();
  			if (page->mapping)
  				mlock_vma_page(page);
  			unlock_page(page);
  		}
  	}

  	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;

  	VM_BUG_ON_PAGE(!PageCompound(page), page);

  	if (flags & FOLL_GET)

  		get_page_foll(page);

  
  out:
  	return page;
  }

  /* NUMA hinting page fault entry point for trans huge pmds */

  int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
  				unsigned long addr, pmd_t pmd, pmd_t *pmdp)

  {

  	spinlock_t *ptl;

  	struct anon_vma *anon_vma = NULL;

  	struct page *page;

  	unsigned long haddr = addr & HPAGE_PMD_MASK;

  	int page_nid = -1, this_nid = numa_node_id();

  	int target_nid, last_cpupid = -1;

  	bool page_locked;
  	bool migrated = false;

  	int flags = 0;

  	ptl = pmd_lock(mm, pmdp);

  	if (unlikely(!pmd_same(pmd, *pmdp)))
  		goto out_unlock;

  	/*
  	 * If there are potential migrations, wait for completion and retry
  	 * without disrupting NUMA hinting information. Do not relock and
  	 * check_same as the page may no longer be mapped.
  	 */
  	if (unlikely(pmd_trans_migrating(*pmdp))) {
  		spin_unlock(ptl);
  		wait_migrate_huge_page(vma->anon_vma, pmdp);
  		goto out;
  	}

  	page = pmd_page(pmd);

  	BUG_ON(is_huge_zero_page(page));

  	page_nid = page_to_nid(page);

  	last_cpupid = page_cpupid_last(page);

  	count_vm_numa_event(NUMA_HINT_FAULTS);

  	if (page_nid == this_nid) {

  		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);

  		flags |= TNF_FAULT_LOCAL;
  	}

  	/*

  	 * Avoid grouping on DSO/COW pages in specific and RO pages
  	 * in general, RO pages shouldn't hurt as much anyway since
  	 * they can be in shared cache state.
  	 */
  	if (!pmd_write(pmd))
  		flags |= TNF_NO_GROUP;
  
  	/*

  	 * Acquire the page lock to serialise THP migrations but avoid dropping
  	 * page_table_lock if at all possible
  	 */

  	page_locked = trylock_page(page);
  	target_nid = mpol_misplaced(page, vma, haddr);
  	if (target_nid == -1) {
  		/* If the page was locked, there are no parallel migrations */

  		if (page_locked)

  			goto clear_pmdnuma;

  	}

  	/* Migration could have started since the pmd_trans_migrating check */

  	if (!page_locked) {

  		spin_unlock(ptl);

  		wait_on_page_locked(page);

  		page_nid = -1;

  		goto out;
  	}

  	/*
  	 * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
  	 * to serialises splits
  	 */

  	get_page(page);

  	spin_unlock(ptl);

  	anon_vma = page_lock_anon_vma_read(page);

  	/* Confirm the PMD did not change while page_table_lock was released */

  	spin_lock(ptl);

  	if (unlikely(!pmd_same(pmd, *pmdp))) {
  		unlock_page(page);
  		put_page(page);

  		page_nid = -1;

  		goto out_unlock;

  	}

  	/* Bail if we fail to protect against THP splits for any reason */
  	if (unlikely(!anon_vma)) {
  		put_page(page);
  		page_nid = -1;
  		goto clear_pmdnuma;
  	}

  	/*
  	 * Migrate the THP to the requested node, returns with page unlocked
  	 * and pmd_numa cleared.
  	 */

  	spin_unlock(ptl);

  	migrated = migrate_misplaced_transhuge_page(mm, vma,

  				pmdp, pmd, addr, page, target_nid);

  	if (migrated) {
  		flags |= TNF_MIGRATED;

  		page_nid = target_nid;

  	}

  	goto out;

  clear_pmdnuma:

  	BUG_ON(!PageLocked(page));

  	pmd = pmd_mknonnuma(pmd);
  	set_pmd_at(mm, haddr, pmdp, pmd);
  	VM_BUG_ON(pmd_numa(*pmdp));
  	update_mmu_cache_pmd(vma, addr, pmdp);

  	unlock_page(page);

  out_unlock:

  	spin_unlock(ptl);

  
  out:
  	if (anon_vma)
  		page_unlock_anon_vma_read(anon_vma);

  	if (page_nid != -1)

  		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags);

  	return 0;
  }

  int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,

  		 pmd_t *pmd, unsigned long addr)

  {

  	spinlock_t *ptl;

  	int ret = 0;

  	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {

  		struct page *page;
  		pgtable_t pgtable;

  		pmd_t orig_pmd;

  		/*
  		 * For architectures like ppc64 we look at deposited pgtable
  		 * when calling pmdp_get_and_clear. So do the
  		 * pgtable_trans_huge_withdraw after finishing pmdp related
  		 * operations.
  		 */

  		orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);

  		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);

  		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);

  		if (is_huge_zero_pmd(orig_pmd)) {

  			atomic_long_dec(&tlb->mm->nr_ptes);

  			spin_unlock(ptl);

  			put_huge_zero_page();

  		} else {
  			page = pmd_page(orig_pmd);
  			page_remove_rmap(page);

  			VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);

  			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);

  			VM_BUG_ON_PAGE(!PageHead(page), page);

  			atomic_long_dec(&tlb->mm->nr_ptes);

  			spin_unlock(ptl);

  			tlb_remove_page(tlb, page);
  		}

  		pte_free(tlb->mm, pgtable);
  		ret = 1;
  	}

  	return ret;
  }

  int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
  		unsigned long addr, unsigned long end,
  		unsigned char *vec)
  {

  	spinlock_t *ptl;

  	int ret = 0;

  	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {

  		/*
  		 * All logical pages in the range are present
  		 * if backed by a huge page.
  		 */

  		spin_unlock(ptl);

  		memset(vec, 1, (end - addr) >> PAGE_SHIFT);
  		ret = 1;
  	}

  
  	return ret;
  }

  int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
  		  unsigned long old_addr,
  		  unsigned long new_addr, unsigned long old_end,
  		  pmd_t *old_pmd, pmd_t *new_pmd)
  {

  	spinlock_t *old_ptl, *new_ptl;

  	int ret = 0;
  	pmd_t pmd;
  
  	struct mm_struct *mm = vma->vm_mm;
  
  	if ((old_addr & ~HPAGE_PMD_MASK) ||
  	    (new_addr & ~HPAGE_PMD_MASK) ||
  	    old_end - old_addr < HPAGE_PMD_SIZE ||
  	    (new_vma->vm_flags & VM_NOHUGEPAGE))
  		goto out;
  
  	/*
  	 * The destination pmd shouldn't be established, free_pgtables()
  	 * should have release it.
  	 */
  	if (WARN_ON(!pmd_none(*new_pmd))) {
  		VM_BUG_ON(pmd_trans_huge(*new_pmd));
  		goto out;
  	}

  	/*
  	 * We don't have to worry about the ordering of src and dst
  	 * ptlocks because exclusive mmap_sem prevents deadlock.
  	 */
  	ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl);

  	if (ret == 1) {

  		new_ptl = pmd_lockptr(mm, new_pmd);
  		if (new_ptl != old_ptl)
  			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);

  		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
  		VM_BUG_ON(!pmd_none(*new_pmd));

  		if (pmd_move_must_withdraw(new_ptl, old_ptl)) {
  			pgtable_t pgtable;

  			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
  			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);

  		}

  		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
  		if (new_ptl != old_ptl)
  			spin_unlock(new_ptl);

  		spin_unlock(old_ptl);

  	}
  out:
  	return ret;
  }

  /*
   * Returns
   *  - 0 if PMD could not be locked
   *  - 1 if PMD was locked but protections unchange and TLB flush unnecessary
   *  - HPAGE_PMD_NR is protections changed and TLB flush necessary
   */

  int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,

  		unsigned long addr, pgprot_t newprot, int prot_numa)

  {
  	struct mm_struct *mm = vma->vm_mm;

  	spinlock_t *ptl;

  	int ret = 0;

  	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {

  		pmd_t entry;

  		ret = 1;

  		if (!prot_numa) {

  			entry = pmdp_get_and_clear(mm, addr, pmd);

  			if (pmd_numa(entry))
  				entry = pmd_mknonnuma(entry);

  			entry = pmd_modify(entry, newprot);

  			ret = HPAGE_PMD_NR;

  			set_pmd_at(mm, addr, pmd, entry);

  			BUG_ON(pmd_write(entry));
  		} else {

  			struct page *page = pmd_page(*pmd);

  			/*

  			 * Do not trap faults against the zero page. The
  			 * read-only data is likely to be read-cached on the
  			 * local CPU cache and it is less useful to know about
  			 * local vs remote hits on the zero page.

  			 */

  			if (!is_huge_zero_page(page) &&

  			    !pmd_numa(*pmd)) {

  				pmdp_set_numa(mm, addr, pmd);

  				ret = HPAGE_PMD_NR;

  			}
  		}

  		spin_unlock(ptl);

  	}
  
  	return ret;
  }
  
  /*
   * Returns 1 if a given pmd maps a stable (not under splitting) thp.
   * Returns -1 if it maps a thp under splitting. Returns 0 otherwise.
   *
   * Note that if it returns 1, this routine returns without unlocking page
   * table locks. So callers must unlock them.
   */

  int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
  		spinlock_t **ptl)

  {

  	*ptl = pmd_lock(vma->vm_mm, pmd);

  	if (likely(pmd_trans_huge(*pmd))) {
  		if (unlikely(pmd_trans_splitting(*pmd))) {

  			spin_unlock(*ptl);

  			wait_split_huge_page(vma->anon_vma, pmd);

  			return -1;

  		} else {

  			/* Thp mapped by 'pmd' is stable, so we can
  			 * handle it as it is. */
  			return 1;

  		}

  	}

  	spin_unlock(*ptl);

  	return 0;

  }

  /*
   * This function returns whether a given @page is mapped onto the @address
   * in the virtual space of @mm.
   *
   * When it's true, this function returns *pmd with holding the page table lock
   * and passing it back to the caller via @ptl.
   * If it's false, returns NULL without holding the page table lock.
   */

  pmd_t *page_check_address_pmd(struct page *page,
  			      struct mm_struct *mm,
  			      unsigned long address,

  			      enum page_check_address_pmd_flag flag,
  			      spinlock_t **ptl)

  {

  	pgd_t *pgd;
  	pud_t *pud;

  	pmd_t *pmd;

  
  	if (address & ~HPAGE_PMD_MASK)

  		return NULL;

  	pgd = pgd_offset(mm, address);
  	if (!pgd_present(*pgd))

  		return NULL;

  	pud = pud_offset(pgd, address);
  	if (!pud_present(*pud))
  		return NULL;
  	pmd = pmd_offset(pud, address);

  	*ptl = pmd_lock(mm, pmd);

  	if (!pmd_present(*pmd))

  		goto unlock;

  	if (pmd_page(*pmd) != page)

  		goto unlock;

  	/*
  	 * split_vma() may create temporary aliased mappings. There is
  	 * no risk as long as all huge pmd are found and have their
  	 * splitting bit set before __split_huge_page_refcount
  	 * runs. Finding the same huge pmd more than once during the
  	 * same rmap walk is not a problem.
  	 */
  	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
  	    pmd_trans_splitting(*pmd))

  		goto unlock;

  	if (pmd_trans_huge(*pmd)) {
  		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
  			  !pmd_trans_splitting(*pmd));

  		return pmd;

  	}

  unlock:
  	spin_unlock(*ptl);
  	return NULL;

  }
  
  static int __split_huge_page_splitting(struct page *page,
  				       struct vm_area_struct *vma,
  				       unsigned long address)
  {
  	struct mm_struct *mm = vma->vm_mm;

  	spinlock_t *ptl;

  	pmd_t *pmd;
  	int ret = 0;

  	/* For mmu_notifiers */
  	const unsigned long mmun_start = address;
  	const unsigned long mmun_end   = address + HPAGE_PMD_SIZE;

  	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

  	pmd = page_check_address_pmd(page, mm, address,

  			PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, &ptl);

  	if (pmd) {
  		/*
  		 * We can't temporarily set the pmd to null in order
  		 * to split it, the pmd must remain marked huge at all
  		 * times or the VM won't take the pmd_trans_huge paths

  		 * and it won't wait on the anon_vma->root->rwsem to

  		 * serialize against split_huge_page*.
  		 */

  		pmdp_splitting_flush(vma, address, pmd);

  		ret = 1;

  		spin_unlock(ptl);

  	}

  	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

  
  	return ret;
  }

  static void __split_huge_page_refcount(struct page *page,
  				       struct list_head *list)

  {
  	int i;

  	struct zone *zone = page_zone(page);

  	struct lruvec *lruvec;

  	int tail_count = 0;

  
  	/* prevent PageLRU to go away from under us, and freeze lru stats */
  	spin_lock_irq(&zone->lru_lock);

  	lruvec = mem_cgroup_page_lruvec(page, zone);

  	compound_lock(page);

  	/* complete memcg works before add pages to LRU */
  	mem_cgroup_split_huge_fixup(page);

  	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {

  		struct page *page_tail = page + i;

  		/* tail_page->_mapcount cannot change */
  		BUG_ON(page_mapcount(page_tail) < 0);
  		tail_count += page_mapcount(page_tail);
  		/* check for overflow */
  		BUG_ON(tail_count < 0);
  		BUG_ON(atomic_read(&page_tail->_count) != 0);
  		/*
  		 * tail_page->_count is zero and not changing from
  		 * under us. But get_page_unless_zero() may be running
  		 * from under us on the tail_page. If we used
  		 * atomic_set() below instead of atomic_add(), we
  		 * would then run atomic_set() concurrently with
  		 * get_page_unless_zero(), and atomic_set() is
  		 * implemented in C not using locked ops. spin_unlock
  		 * on x86 sometime uses locked ops because of PPro
  		 * errata 66, 92, so unless somebody can guarantee
  		 * atomic_set() here would be safe on all archs (and
  		 * not only on x86), it's safer to use atomic_add().
  		 */
  		atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1,
  			   &page_tail->_count);

  
  		/* after clearing PageTail the gup refcount can be released */
  		smp_mb();

  		/*
  		 * retain hwpoison flag of the poisoned tail page:
  		 *   fix for the unsuitable process killed on Guest Machine(KVM)
  		 *   by the memory-failure.
  		 */
  		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;

  		page_tail->flags |= (page->flags &
  				     ((1L << PG_referenced) |
  				      (1L << PG_swapbacked) |
  				      (1L << PG_mlocked) |

  				      (1L << PG_uptodate) |
  				      (1L << PG_active) |
  				      (1L << PG_unevictable)));

  		page_tail->flags |= (1L << PG_dirty);

  		/* clear PageTail before overwriting first_page */

  		smp_wmb();
  
  		/*
  		 * __split_huge_page_splitting() already set the
  		 * splitting bit in all pmd that could map this
  		 * hugepage, that will ensure no CPU can alter the
  		 * mapcount on the head page. The mapcount is only
  		 * accounted in the head page and it has to be
  		 * transferred to all tail pages in the below code. So
  		 * for this code to be safe, the split the mapcount
  		 * can't change. But that doesn't mean userland can't
  		 * keep changing and reading the page contents while
  		 * we transfer the mapcount, so the pmd splitting
  		 * status is achieved setting a reserved bit in the
  		 * pmd, not by clearing the present bit.
  		*/

  		page_tail->_mapcount = page->_mapcount;
  
  		BUG_ON(page_tail->mapping);
  		page_tail->mapping = page->mapping;

  		page_tail->index = page->index + i;

  		page_cpupid_xchg_last(page_tail, page_cpupid_last(page));

  
  		BUG_ON(!PageAnon(page_tail));
  		BUG_ON(!PageUptodate(page_tail));
  		BUG_ON(!PageDirty(page_tail));
  		BUG_ON(!PageSwapBacked(page_tail));

  		lru_add_page_tail(page, page_tail, lruvec, list);

  	}

  	atomic_sub(tail_count, &page->_count);
  	BUG_ON(atomic_read(&page->_count) <= 0);

  	__mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1);

  	ClearPageCompound(page);
  	compound_unlock(page);
  	spin_unlock_irq(&zone->lru_lock);
  
  	for (i = 1; i < HPAGE_PMD_NR; i++) {
  		struct page *page_tail = page + i;
  		BUG_ON(page_count(page_tail) <= 0);
  		/*
  		 * Tail pages may be freed if there wasn't any mapping
  		 * like if add_to_swap() is running on a lru page that
  		 * had its mapping zapped. And freeing these pages
  		 * requires taking the lru_lock so we do the put_page
  		 * of the tail pages after the split is complete.
  		 */
  		put_page(page_tail);
  	}
  
  	/*
  	 * Only the head page (now become a regular page) is required
  	 * to be pinned by the caller.
  	 */
  	BUG_ON(page_count(page) <= 0);
  }
  
  static int __split_huge_page_map(struct page *page,
  				 struct vm_area_struct *vma,
  				 unsigned long address)
  {
  	struct mm_struct *mm = vma->vm_mm;

  	spinlock_t *ptl;

  	pmd_t *pmd, _pmd;
  	int ret = 0, i;
  	pgtable_t pgtable;
  	unsigned long haddr;

  	pmd = page_check_address_pmd(page, mm, address,

  			PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, &ptl);

  	if (pmd) {

  		pgtable = pgtable_trans_huge_withdraw(mm, pmd);

  		pmd_populate(mm, &_pmd, pgtable);

  		haddr = address;
  		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {

  			pte_t *pte, entry;
  			BUG_ON(PageCompound(page+i));
  			entry = mk_pte(page + i, vma->vm_page_prot);
  			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
  			if (!pmd_write(*pmd))
  				entry = pte_wrprotect(entry);
  			else
  				BUG_ON(page_mapcount(page) != 1);
  			if (!pmd_young(*pmd))
  				entry = pte_mkold(entry);

  			if (pmd_numa(*pmd))
  				entry = pte_mknuma(entry);

  			pte = pte_offset_map(&_pmd, haddr);
  			BUG_ON(!pte_none(*pte));
  			set_pte_at(mm, haddr, pte, entry);
  			pte_unmap(pte);
  		}

  		smp_wmb(); /* make pte visible before pmd */
  		/*
  		 * Up to this point the pmd is present and huge and
  		 * userland has the whole access to the hugepage
  		 * during the split (which happens in place). If we
  		 * overwrite the pmd with the not-huge version
  		 * pointing to the pte here (which of course we could
  		 * if all CPUs were bug free), userland could trigger
  		 * a small page size TLB miss on the small sized TLB
  		 * while the hugepage TLB entry is still established
  		 * in the huge TLB. Some CPU doesn't like that. See
  		 * http://support.amd.com/us/Processor_TechDocs/41322.pdf,
  		 * Erratum 383 on page 93. Intel should be safe but is
  		 * also warns that it's only safe if the permission
  		 * and cache attributes of the two entries loaded in
  		 * the two TLB is identical (which should be the case
  		 * here). But it is generally safer to never allow
  		 * small and huge TLB entries for the same virtual
  		 * address to be loaded simultaneously. So instead of
  		 * doing "pmd_populate(); flush_tlb_range();" we first
  		 * mark the current pmd notpresent (atomically because
  		 * here the pmd_trans_huge and pmd_trans_splitting
  		 * must remain set at all times on the pmd until the
  		 * split is complete for this pmd), then we flush the
  		 * SMP TLB and finally we write the non-huge version
  		 * of the pmd entry with pmd_populate.
  		 */

  		pmdp_invalidate(vma, address, pmd);

  		pmd_populate(mm, pmd, pgtable);
  		ret = 1;

  		spin_unlock(ptl);

  	}

  
  	return ret;
  }

  /* must be called with anon_vma->root->rwsem held */

  static void __split_huge_page(struct page *page,

  			      struct anon_vma *anon_vma,
  			      struct list_head *list)

  {
  	int mapcount, mapcount2;

  	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);

  	struct anon_vma_chain *avc;
  
  	BUG_ON(!PageHead(page));
  	BUG_ON(PageTail(page));
  
  	mapcount = 0;

  	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {

  		struct vm_area_struct *vma = avc->vma;
  		unsigned long addr = vma_address(page, vma);
  		BUG_ON(is_vma_temporary_stack(vma));

  		mapcount += __split_huge_page_splitting(page, vma, addr);
  	}

  	/*
  	 * It is critical that new vmas are added to the tail of the
  	 * anon_vma list. This guarantes that if copy_huge_pmd() runs
  	 * and establishes a child pmd before
  	 * __split_huge_page_splitting() freezes the parent pmd (so if
  	 * we fail to prevent copy_huge_pmd() from running until the
  	 * whole __split_huge_page() is complete), we will still see
  	 * the newly established pmd of the child later during the
  	 * walk, to be able to set it as pmd_trans_splitting too.
  	 */
  	if (mapcount != page_mapcount(page))
  		printk(KERN_ERR "mapcount %d page_mapcount %d
  ",
  		       mapcount, page_mapcount(page));

  	BUG_ON(mapcount != page_mapcount(page));

  	__split_huge_page_refcount(page, list);

  
  	mapcount2 = 0;

  	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {

  		struct vm_area_struct *vma = avc->vma;
  		unsigned long addr = vma_address(page, vma);
  		BUG_ON(is_vma_temporary_stack(vma));

  		mapcount2 += __split_huge_page_map(page, vma, addr);
  	}

  	if (mapcount != mapcount2)
  		printk(KERN_ERR "mapcount %d mapcount2 %d page_mapcount %d
  ",
  		       mapcount, mapcount2, page_mapcount(page));

  	BUG_ON(mapcount != mapcount2);
  }

  /*
   * Split a hugepage into normal pages. This doesn't change the position of head
   * page. If @list is null, tail pages will be added to LRU list, otherwise, to
   * @list. Both head page and tail pages will inherit mapping, flags, and so on
   * from the hugepage.
   * Return 0 if the hugepage is split successfully otherwise return 1.
   */
  int split_huge_page_to_list(struct page *page, struct list_head *list)

  {
  	struct anon_vma *anon_vma;
  	int ret = 1;

  	BUG_ON(is_huge_zero_page(page));

  	BUG_ON(!PageAnon(page));

  
  	/*
  	 * The caller does not necessarily hold an mmap_sem that would prevent
  	 * the anon_vma disappearing so we first we take a reference to it
  	 * and then lock the anon_vma for write. This is similar to
  	 * page_lock_anon_vma_read except the write lock is taken to serialise
  	 * against parallel split or collapse operations.
  	 */
  	anon_vma = page_get_anon_vma(page);

  	if (!anon_vma)
  		goto out;

  	anon_vma_lock_write(anon_vma);

  	ret = 0;
  	if (!PageCompound(page))
  		goto out_unlock;
  
  	BUG_ON(!PageSwapBacked(page));

  	__split_huge_page(page, anon_vma, list);

  	count_vm_event(THP_SPLIT);

  
  	BUG_ON(PageCompound(page));
  out_unlock: