/*
   *  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.
   */

  #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

  #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/swapops.h>

  #include <linux/dax.h>

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

  #include <linux/freezer.h>

  #include <linux/pfn_t.h>

  #include <linux/mman.h>

  #include <linux/memremap.h>

  #include <linux/pagemap.h>

  #include <linux/debugfs.h>

  #include <linux/migrate.h>

  #include <linux/hashtable.h>

  #include <linux/userfaultfd_k.h>

  #include <linux/page_idle.h>

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

  enum scan_result {
  	SCAN_FAIL,
  	SCAN_SUCCEED,
  	SCAN_PMD_NULL,
  	SCAN_EXCEED_NONE_PTE,
  	SCAN_PTE_NON_PRESENT,
  	SCAN_PAGE_RO,
  	SCAN_NO_REFERENCED_PAGE,
  	SCAN_PAGE_NULL,
  	SCAN_SCAN_ABORT,
  	SCAN_PAGE_COUNT,
  	SCAN_PAGE_LRU,
  	SCAN_PAGE_LOCK,
  	SCAN_PAGE_ANON,

  	SCAN_PAGE_COMPOUND,

  	SCAN_ANY_PROCESS,
  	SCAN_VMA_NULL,
  	SCAN_VMA_CHECK,
  	SCAN_ADDRESS_RANGE,
  	SCAN_SWAP_CACHE_PAGE,
  	SCAN_DEL_PAGE_LRU,
  	SCAN_ALLOC_HUGE_PAGE_FAIL,
  	SCAN_CGROUP_CHARGE_FAIL
  };
  
  #define CREATE_TRACE_POINTS
  #include <trace/events/huge_memory.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_REQ_MADV_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;

  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;

  
  static int khugepaged(void *none);

  static int khugepaged_slab_init(void);

  static void khugepaged_slab_exit(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 struct shrinker deferred_split_shrinker;

  static void set_recommended_min_free_kbytes(void)

  {
  	struct zone *zone;
  	int nr_zones = 0;
  	unsigned long recommended_min;

  	for_each_populated_zone(zone)
  		nr_zones++;

  	/* Ensure 2 pageblocks are free to assist fragmentation avoidance */

  	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();

  }

  static int start_stop_khugepaged(void)

  {
  	int err = 0;
  	if (khugepaged_enabled()) {

  		if (!khugepaged_thread)
  			khugepaged_thread = kthread_run(khugepaged, NULL,
  							"khugepaged");

  		if (IS_ERR(khugepaged_thread)) {

  			pr_err("khugepaged: kthread_run(khugepaged) failed
  ");

  			err = PTR_ERR(khugepaged_thread);
  			khugepaged_thread = NULL;

  			goto fail;

  		}

  
  		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;
  	}

  fail:

  	return err;
  }

  static atomic_t huge_zero_refcount;

  struct page *huge_zero_page __read_mostly;

  struct page *get_huge_zero_page(void)

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

  		return READ_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_pages(zero_page, compound_order(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 READ_ONCE(huge_zero_page);

  }

  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_pages(zero_page, compound_order(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 triple_flag_store(struct kobject *kobj,

  				 struct kobj_attribute *attr,
  				 const char *buf, size_t count,
  				 enum transparent_hugepage_flag enabled,

  				 enum transparent_hugepage_flag deferred,

  				 enum transparent_hugepage_flag req_madv)
  {

  	if (!memcmp("defer", buf,
  		    min(sizeof("defer")-1, count))) {
  		if (enabled == deferred)
  			return -EINVAL;
  		clear_bit(enabled, &transparent_hugepage_flags);
  		clear_bit(req_madv, &transparent_hugepage_flags);
  		set_bit(deferred, &transparent_hugepage_flags);
  	} else if (!memcmp("always", buf,

  		    min(sizeof("always")-1, count))) {

  		clear_bit(deferred, &transparent_hugepage_flags);

  		clear_bit(req_madv, &transparent_hugepage_flags);

  		set_bit(enabled, &transparent_hugepage_flags);

  	} else if (!memcmp("madvise", buf,
  			   min(sizeof("madvise")-1, count))) {
  		clear_bit(enabled, &transparent_hugepage_flags);

  		clear_bit(deferred, &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);

  		clear_bit(deferred, &transparent_hugepage_flags);

  	} else
  		return -EINVAL;
  
  	return count;
  }
  
  static ssize_t enabled_show(struct kobject *kobj,
  			    struct kobj_attribute *attr, char *buf)
  {

  	if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags))
  		return sprintf(buf, "[always] madvise never
  ");
  	else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags))
  		return sprintf(buf, "always [madvise] never
  ");
  	else
  		return sprintf(buf, "always madvise [never]
  ");

  }

  static ssize_t enabled_store(struct kobject *kobj,
  			     struct kobj_attribute *attr,
  			     const char *buf, size_t count)
  {

  	ssize_t ret;

  	ret = triple_flag_store(kobj, attr, buf, count,
  				TRANSPARENT_HUGEPAGE_FLAG,

  				TRANSPARENT_HUGEPAGE_FLAG,
  				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
  
  	if (ret > 0) {

  		int err;
  
  		mutex_lock(&khugepaged_mutex);

  		err = start_stop_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)
  {

  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
  		return sprintf(buf, "[always] defer madvise never
  ");
  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
  		return sprintf(buf, "always [defer] madvise never
  ");
  	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
  		return sprintf(buf, "always defer [madvise] never
  ");
  	else
  		return sprintf(buf, "always defer madvise [never]
  ");

  }
  static ssize_t defrag_store(struct kobject *kobj,
  			    struct kobj_attribute *attr,
  			    const char *buf, size_t count)
  {

  	return triple_flag_store(kobj, attr, buf, count,
  				 TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
  				 TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_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)) {

  		pr_err("failed to create transparent hugepage kobject
  ");

  		return -ENOMEM;

  	}

  	err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);

  	if (err) {

  		pr_err("failed to register transparent hugepage group
  ");

  		goto delete_obj;

  	}

  	err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);

  	if (err) {

  		pr_err("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;
  	}

  	khugepaged_pages_to_scan = HPAGE_PMD_NR * 8;
  	khugepaged_max_ptes_none = HPAGE_PMD_NR - 1;
  	/*
  	 * hugepages can't be allocated by the buddy allocator
  	 */
  	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER >= MAX_ORDER);
  	/*
  	 * we use page->mapping and page->index in second tail page
  	 * as list_head: assuming THP order >= 2
  	 */
  	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER < 2);

  	err = hugepage_init_sysfs(&hugepage_kobj);
  	if (err)

  		goto err_sysfs;

  
  	err = khugepaged_slab_init();
  	if (err)

  		goto err_slab;

  	err = register_shrinker(&huge_zero_page_shrinker);
  	if (err)
  		goto err_hzp_shrinker;

  	err = register_shrinker(&deferred_split_shrinker);
  	if (err)
  		goto err_split_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;

  		return 0;
  	}

  	err = start_stop_khugepaged();

  	if (err)
  		goto err_khugepaged;

  	return 0;

  err_khugepaged:

  	unregister_shrinker(&deferred_split_shrinker);
  err_split_shrinker:

  	unregister_shrinker(&huge_zero_page_shrinker);
  err_hzp_shrinker:
  	khugepaged_slab_exit();
  err_slab:

  	hugepage_exit_sysfs(hugepage_kobj);

  err_sysfs:

  	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)

  		pr_warn("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 inline struct list_head *page_deferred_list(struct page *page)
  {
  	/*
  	 * ->lru in the tail pages is occupied by compound_head.
  	 * Let's use ->mapping + ->index in the second tail page as list_head.
  	 */
  	return (struct list_head *)&page[2].mapping;
  }
  
  void prep_transhuge_page(struct page *page)
  {
  	/*
  	 * we use page->mapping and page->indexlru in second tail page
  	 * as list_head: assuming THP order >= 2
  	 */

  
  	INIT_LIST_HEAD(page_deferred_list(page));
  	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
  }

  static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
  					struct vm_area_struct *vma,

  					unsigned long address, pmd_t *pmd,

  					struct page *page, gfp_t gfp,
  					unsigned int flags)

  {

  	struct mem_cgroup *memcg;

  	pgtable_t pgtable;

  	spinlock_t *ptl;

  	unsigned long haddr = address & HPAGE_PMD_MASK;

  	VM_BUG_ON_PAGE(!PageCompound(page), page);

  	if (mem_cgroup_try_charge(page, mm, gfp, &memcg, true)) {

  		put_page(page);
  		count_vm_event(THP_FAULT_FALLBACK);
  		return VM_FAULT_FALLBACK;
  	}

  	pgtable = pte_alloc_one(mm, haddr);

  	if (unlikely(!pgtable)) {

  		mem_cgroup_cancel_charge(page, memcg, true);

  		put_page(page);

  		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_cancel_charge(page, memcg, true);

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

  
  		/* Deliver the page fault to userland */
  		if (userfaultfd_missing(vma)) {
  			int ret;
  
  			spin_unlock(ptl);

  			mem_cgroup_cancel_charge(page, memcg, true);

  			put_page(page);
  			pte_free(mm, pgtable);

  			ret = handle_userfault(vma, address, flags,

  					       VM_UFFD_MISSING);
  			VM_BUG_ON(ret & VM_FAULT_FALLBACK);
  			return ret;
  		}

  		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, true);

  		mem_cgroup_commit_charge(page, memcg, false, true);

  		lru_cache_add_active_or_unevictable(page, vma);

  		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);

  		count_vm_event(THP_FAULT_ALLOC);

  	}

  	return 0;

  }

  /*
   * If THP is set to always then directly reclaim/compact as necessary
   * If set to defer then do no reclaim and defer to khugepaged
   * If set to madvise and the VMA is flagged then directly reclaim/compact
   */
  static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
  {
  	gfp_t reclaim_flags = 0;
  
  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags) &&
  	    (vma->vm_flags & VM_HUGEPAGE))
  		reclaim_flags = __GFP_DIRECT_RECLAIM;
  	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
  		reclaim_flags = __GFP_KSWAPD_RECLAIM;
  	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
  		reclaim_flags = __GFP_DIRECT_RECLAIM;
  
  	return GFP_TRANSHUGE | reclaim_flags;
  }
  
  /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */
  static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void)

  {

  	return GFP_TRANSHUGE | (khugepaged_defrag() ? __GFP_DIRECT_RECLAIM : 0);

  }

  /* 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_mkhuge(entry);

  	if (pgtable)
  		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)
  {

  	gfp_t gfp;

  	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, vma->vm_flags)))

  		return VM_FAULT_OOM;

  	if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm) &&

  			transparent_hugepage_use_zero_page()) {

  		spinlock_t *ptl;

  		pgtable_t pgtable;
  		struct page *zero_page;
  		bool set;

  		int ret;

  		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);

  		ret = 0;
  		set = false;
  		if (pmd_none(*pmd)) {
  			if (userfaultfd_missing(vma)) {
  				spin_unlock(ptl);

  				ret = handle_userfault(vma, address, flags,

  						       VM_UFFD_MISSING);
  				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
  			} else {
  				set_huge_zero_page(pgtable, mm, vma,
  						   haddr, pmd,
  						   zero_page);
  				spin_unlock(ptl);
  				set = true;
  			}
  		} else
  			spin_unlock(ptl);

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

  		}

  		return ret;

  	}

  	gfp = alloc_hugepage_direct_gfpmask(vma);

  	page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);

  	if (unlikely(!page)) {
  		count_vm_event(THP_FAULT_FALLBACK);

  		return VM_FAULT_FALLBACK;

  	}

  	prep_transhuge_page(page);

  	return __do_huge_pmd_anonymous_page(mm, vma, address, pmd, page, gfp,
  					    flags);

  }

  static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,

  		pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write)

  {
  	struct mm_struct *mm = vma->vm_mm;
  	pmd_t entry;
  	spinlock_t *ptl;
  
  	ptl = pmd_lock(mm, pmd);

  	entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
  	if (pfn_t_devmap(pfn))
  		entry = pmd_mkdevmap(entry);

  	if (write) {
  		entry = pmd_mkyoung(pmd_mkdirty(entry));
  		entry = maybe_pmd_mkwrite(entry, vma);

  	}

  	set_pmd_at(mm, addr, pmd, entry);
  	update_mmu_cache_pmd(vma, addr, pmd);

  	spin_unlock(ptl);

  }
  
  int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,

  			pmd_t *pmd, pfn_t pfn, bool write)

  {
  	pgprot_t pgprot = vma->vm_page_prot;
  	/*
  	 * If we had pmd_special, we could avoid all these restrictions,
  	 * but we need to be consistent with PTEs and architectures that
  	 * can't support a 'special' bit.
  	 */
  	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
  	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
  						(VM_PFNMAP|VM_MIXEDMAP));
  	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));

  	BUG_ON(!pfn_t_devmap(pfn));

  
  	if (addr < vma->vm_start || addr >= vma->vm_end)
  		return VM_FAULT_SIGBUS;
  	if (track_pfn_insert(vma, &pgprot, pfn))
  		return VM_FAULT_SIGBUS;

  	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
  	return VM_FAULT_NOPAGE;

  }

  static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
  		pmd_t *pmd)
  {
  	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);
  }
  
  struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
  		pmd_t *pmd, int flags)
  {
  	unsigned long pfn = pmd_pfn(*pmd);
  	struct mm_struct *mm = vma->vm_mm;
  	struct dev_pagemap *pgmap;
  	struct page *page;
  
  	assert_spin_locked(pmd_lockptr(mm, pmd));
  
  	if (flags & FOLL_WRITE && !pmd_write(*pmd))
  		return NULL;
  
  	if (pmd_present(*pmd) && pmd_devmap(*pmd))
  		/* pass */;
  	else
  		return NULL;
  
  	if (flags & FOLL_TOUCH)
  		touch_pmd(vma, addr, pmd);
  
  	/*
  	 * device mapped pages can only be returned if the
  	 * caller will manage the page reference count.
  	 */
  	if (!(flags & FOLL_GET))
  		return ERR_PTR(-EEXIST);
  
  	pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
  	pgmap = get_dev_pagemap(pfn, NULL);
  	if (!pgmap)
  		return ERR_PTR(-EFAULT);
  	page = pfn_to_page(pfn);
  	get_page(page);
  	put_dev_pagemap(pgmap);
  
  	return page;
  }

  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 = NULL;

  	int ret;

  	if (!vma_is_dax(vma)) {
  		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) && !pmd_devmap(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;

  		/*
  		 * 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_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,

  				zero_page);

  		ret = 0;
  		goto out_unlock;
  	}

  	if (!vma_is_dax(vma)) {

  		/* thp accounting separate from pmd_devmap accounting */
  		src_page = pmd_page(pmd);
  		VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
  		get_page(src_page);
  		page_dup_rmap(src_page, true);
  		add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
  		atomic_long_inc(&dst_mm->nr_ptes);
  		pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
  	}

  
  	pmdp_set_wrprotect(src_mm, addr, src_pmd);
  	pmd = pmd_mkold(pmd_wrprotect(pmd));
  	set_pmd_at(dst_mm, addr, dst_pmd, pmd);

  
  	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)
  {

  	struct mem_cgroup *memcg;

  	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_try_charge(pages[i], mm, GFP_KERNEL,

  						   &memcg, false))) {

  			if (pages[i])

  				put_page(pages[i]);

  			while (--i >= 0) {

  				memcg = (void *)page_private(pages[i]);
  				set_page_private(pages[i], 0);

  				mem_cgroup_cancel_charge(pages[i], memcg,
  						false);

  				put_page(pages[i]);
  			}

  			kfree(pages);
  			ret |= VM_FAULT_OOM;
  			goto out;
  		}

  		set_page_private(pages[i], (unsigned long)memcg);

  	}
  
  	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_huge_clear_flush_notify(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);

  		memcg = (void *)page_private(pages[i]);
  		set_page_private(pages[i], 0);

  		page_add_new_anon_rmap(pages[i], vma, haddr, false);

  		mem_cgroup_commit_charge(pages[i], memcg, false, false);

  		lru_cache_add_active_or_unevictable(pages[i], vma);

  		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, true);

  	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);

  	for (i = 0; i < HPAGE_PMD_NR; i++) {

  		memcg = (void *)page_private(pages[i]);
  		set_page_private(pages[i], 0);

  		mem_cgroup_cancel_charge(pages[i], memcg, false);

  		put_page(pages[i]);

  	}

  	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;

  	struct mem_cgroup *memcg;

  	unsigned long haddr;

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

  	gfp_t huge_gfp;			/* for allocation and charge */

  	ptl = pmd_lockptr(mm, pmd);

  	VM_BUG_ON_VMA(!vma->anon_vma, 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);

  	/*
  	 * We can only reuse the page if nobody else maps the huge page or it's

  	 * part.

  	 */

  	if (page_trans_huge_mapcount(page, NULL) == 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()) {

  		huge_gfp = alloc_hugepage_direct_gfpmask(vma);

  		new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);

  	} else

  		new_page = NULL;

  	if (likely(new_page)) {
  		prep_transhuge_page(new_page);
  	} else {

  		if (!page) {

  			split_huge_pmd(vma, pmd, address);

  			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_pmd(vma, pmd, address);

  				ret |= VM_FAULT_FALLBACK;
  			}

  			put_page(page);

  		}

  		count_vm_event(THP_FAULT_FALLBACK);

  		goto out;
  	}

  	if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg,
  					   true))) {

  		put_page(new_page);

  		if (page) {

  			split_huge_pmd(vma, pmd, address);

  			put_page(page);

  		} else

  			split_huge_pmd(vma, pmd, address);

  		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_cancel_charge(new_page, memcg, true);

  		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_huge_clear_flush_notify(vma, haddr, pmd);

  		page_add_new_anon_rmap(new_page, vma, haddr, true);

  		mem_cgroup_commit_charge(new_page, memcg, false, true);

  		lru_cache_add_active_or_unevictable(new_page, vma);

  		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, true);

  			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_protnone(*pmd))

  		goto out;

  	page = pmd_page(*pmd);

  	VM_BUG_ON_PAGE(!PageHead(page), page);

  	if (flags & FOLL_TOUCH)
  		touch_pmd(vma, addr, pmd);

  	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {

  		/*
  		 * We don't mlock() pte-mapped THPs. This way we can avoid
  		 * leaking mlocked pages into non-VM_LOCKED VMAs.
  		 *
  		 * In most cases the pmd is the only mapping of the page as we
  		 * break COW for the mlock() -- see gup_flags |= FOLL_WRITE for
  		 * writable private mappings in populate_vma_page_range().
  		 *
  		 * The only scenario when we have the page shared here is if we
  		 * mlocking read-only mapping shared over fork(). We skip
  		 * mlocking such pages.
  		 */
  		if (compound_mapcount(page) == 1 && !PageDoubleMap(page) &&
  				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(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;

  	bool was_writable;

  	int flags = 0;

  	/* A PROT_NONE fault should not end up here */
  	BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)));

  	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))) {

  		page = pmd_page(*pmdp);

  		spin_unlock(ptl);

  		wait_on_page_locked(page);

  		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;
  	}

  	/* See similar comment in do_numa_page for explanation */
  	if (!(vma->vm_flags & VM_WRITE))

  		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 access rights restored.

  	 */

  	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;

  	} else
  		flags |= TNF_MIGRATE_FAIL;

  	goto out;

  clear_pmdnuma:

  	BUG_ON(!PageLocked(page));

  	was_writable = pmd_write(pmd);

  	pmd = pmd_modify(pmd, vma->vm_page_prot);

  	pmd = pmd_mkyoung(pmd);

  	if (was_writable)
  		pmd = pmd_mkwrite(pmd);

  	set_pmd_at(mm, haddr, pmdp, pmd);

  	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 madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
  		pmd_t *pmd, unsigned long addr, unsigned long next)
  
  {
  	spinlock_t *ptl;
  	pmd_t orig_pmd;
  	struct page *page;
  	struct mm_struct *mm = tlb->mm;
  	int ret = 0;

  	ptl = pmd_trans_huge_lock(pmd, vma);
  	if (!ptl)

  		goto out_unlocked;

  
  	orig_pmd = *pmd;
  	if (is_huge_zero_pmd(orig_pmd)) {
  		ret = 1;
  		goto out;
  	}
  
  	page = pmd_page(orig_pmd);
  	/*
  	 * If other processes are mapping this page, we couldn't discard
  	 * the page unless they all do MADV_FREE so let's skip the page.
  	 */
  	if (page_mapcount(page) != 1)
  		goto out;
  
  	if (!trylock_page(page))
  		goto out;
  
  	/*
  	 * If user want to discard part-pages of THP, split it so MADV_FREE
  	 * will deactivate only them.
  	 */
  	if (next - addr != HPAGE_PMD_SIZE) {
  		get_page(page);
  		spin_unlock(ptl);
  		if (split_huge_page(page)) {
  			put_page(page);
  			unlock_page(page);
  			goto out_unlocked;
  		}
  		put_page(page);
  		unlock_page(page);
  		ret = 1;
  		goto out_unlocked;
  	}
  
  	if (PageDirty(page))
  		ClearPageDirty(page);
  	unlock_page(page);
  
  	if (PageActive(page))
  		deactivate_page(page);
  
  	if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
  		orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
  			tlb->fullmm);
  		orig_pmd = pmd_mkold(orig_pmd);
  		orig_pmd = pmd_mkclean(orig_pmd);
  
  		set_pmd_at(mm, addr, pmd, orig_pmd);
  		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
  	}
  	ret = 1;
  out:
  	spin_unlock(ptl);
  out_unlocked:
  	return ret;
  }

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

  		 pmd_t *pmd, unsigned long addr)

  {

  	pmd_t orig_pmd;

  	spinlock_t *ptl;

  	ptl = __pmd_trans_huge_lock(pmd, vma);
  	if (!ptl)

  		return 0;
  	/*
  	 * For architectures like ppc64 we look at deposited pgtable
  	 * when calling pmdp_huge_get_and_clear. So do the
  	 * pgtable_trans_huge_withdraw after finishing pmdp related
  	 * operations.
  	 */
  	orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
  			tlb->fullmm);
  	tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
  	if (vma_is_dax(vma)) {
  		spin_unlock(ptl);
  		if (is_huge_zero_pmd(orig_pmd))

  			tlb_remove_page(tlb, pmd_page(orig_pmd));

  	} else if (is_huge_zero_pmd(orig_pmd)) {
  		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
  		atomic_long_dec(&tlb->mm->nr_ptes);
  		spin_unlock(ptl);

  		tlb_remove_page(tlb, pmd_page(orig_pmd));

  	} else {
  		struct page *page = pmd_page(orig_pmd);

  		page_remove_rmap(page, true);

  		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);
  		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
  		atomic_long_dec(&tlb->mm->nr_ptes);
  		spin_unlock(ptl);
  		tlb_remove_page(tlb, page);

  	}

  	return 1;

  }

  bool move_huge_pmd(struct vm_area_struct *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;

  	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)

  		return false;

  
  	/*
  	 * 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));

  		return false;

  	}

  	/*
  	 * We don't have to worry about the ordering of src and dst
  	 * ptlocks because exclusive mmap_sem prevents deadlock.
  	 */

  	old_ptl = __pmd_trans_huge_lock(old_pmd, vma);
  	if (old_ptl) {

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

  		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);

  		VM_BUG_ON(!pmd_none(*new_pmd));

  		if (pmd_move_must_withdraw(new_ptl, old_ptl) &&
  				vma_is_anonymous(vma)) {

  			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);

  		return true;

  	}

  	return false;

  }

  /*
   * 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
   */