// SPDX-License-Identifier: GPL-2.0-only

  /*
   *  Copyright (C) 2009  Red Hat, Inc.

   */

  #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

  #include <linux/mm.h>
  #include <linux/sched.h>

  #include <linux/sched/coredump.h>

  #include <linux/sched/numa_balancing.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/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 <linux/shmem_fs.h>

  #include <linux/oom.h>

  #include <linux/numa.h>

  #include <linux/page_owner.h>

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

  /*

   * By default, transparent hugepage support is disabled in order to avoid
   * risking an increased memory footprint for applications that are not
   * guaranteed to benefit from it. When transparent hugepage support is
   * enabled, it 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);

  static struct shrinker deferred_split_shrinker;

  static atomic_t huge_zero_refcount;

  struct page *huge_zero_page __read_mostly;

  bool transparent_hugepage_enabled(struct vm_area_struct *vma)
  {

  	/* The addr is used to check if the vma size fits */
  	unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE;
  
  	if (!transhuge_vma_suitable(vma, addr))
  		return false;

  	if (vma_is_anonymous(vma))
  		return __transparent_hugepage_enabled(vma);

  	if (vma_is_shmem(vma))
  		return shmem_huge_enabled(vma);

  
  	return false;
  }

  static 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);

  }

  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));

  }

  struct page *mm_get_huge_zero_page(struct mm_struct *mm)
  {
  	if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
  		return READ_ONCE(huge_zero_page);
  
  	if (!get_huge_zero_page())
  		return NULL;
  
  	if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
  		put_huge_zero_page();
  
  	return READ_ONCE(huge_zero_page);
  }
  
  void mm_put_huge_zero_page(struct mm_struct *mm)
  {
  	if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
  		put_huge_zero_page();
  }

  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 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 = count;

  	if (sysfs_streq(buf, "always")) {

  		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
  		set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);

  	} else if (sysfs_streq(buf, "madvise")) {

  		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
  		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);

  	} else if (sysfs_streq(buf, "never")) {

  		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
  	} else
  		ret = -EINVAL;

  
  	if (ret > 0) {

  		int err = start_stop_khugepaged();

  		if (err)
  			ret = err;
  	}

  	return ret;

  }
  static struct kobj_attribute enabled_attr =
  	__ATTR(enabled, 0644, enabled_show, enabled_store);

  ssize_t single_hugepage_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));

  }

  ssize_t single_hugepage_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;
  }

  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 defer+madvise madvise never
  ");

  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))

  		return sprintf(buf, "always [defer] defer+madvise madvise never
  ");
  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
  		return sprintf(buf, "always defer [defer+madvise] madvise never
  ");
  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
  		return sprintf(buf, "always defer defer+madvise [madvise] never
  ");
  	return sprintf(buf, "always defer defer+madvise madvise [never]
  ");

  }

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

  	if (sysfs_streq(buf, "always")) {

  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
  		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);

  	} else if (sysfs_streq(buf, "defer+madvise")) {

  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
  		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);

  	} else if (sysfs_streq(buf, "defer")) {

  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
  		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);

  	} else if (sysfs_streq(buf, "madvise")) {

  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
  		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);

  	} else if (sysfs_streq(buf, "never")) {

  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
  		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
  	} else
  		return -EINVAL;
  
  	return count;

  }
  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_hugepage_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_hugepage_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);

  
  static ssize_t hpage_pmd_size_show(struct kobject *kobj,
  		struct kobj_attribute *attr, char *buf)
  {
  	return sprintf(buf, "%lu
  ", HPAGE_PMD_SIZE);
  }
  static struct kobj_attribute hpage_pmd_size_attr =
  	__ATTR_RO(hpage_pmd_size);

  #ifdef CONFIG_DEBUG_VM
  static ssize_t debug_cow_show(struct kobject *kobj,
  				struct kobj_attribute *attr, char *buf)
  {

  	return single_hugepage_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_hugepage_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,

  	&hpage_pmd_size_attr.attr,

  #if defined(CONFIG_SHMEM) && defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE)

  	&shmem_enabled_attr.attr,
  #endif

  #ifdef CONFIG_DEBUG_VM
  	&debug_cow_attr.attr,
  #endif
  	NULL,
  };

  static const struct attribute_group hugepage_attr_group = {

  	.attrs = hugepage_attr,

  };

  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;
  	}

  	/*
  	 * 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_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_destroy();

  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;
  }

  #ifdef CONFIG_MEMCG
  static inline struct deferred_split *get_deferred_split_queue(struct page *page)

  {

  	struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
  	struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
  
  	if (memcg)
  		return &memcg->deferred_split_queue;
  	else
  		return &pgdat->deferred_split_queue;

  }

  #else
  static inline struct deferred_split *get_deferred_split_queue(struct page *page)
  {
  	struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
  
  	return &pgdat->deferred_split_queue;
  }
  #endif

  
  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 unsigned long __thp_get_unmapped_area(struct file *filp,
  		unsigned long addr, unsigned long len,

  		loff_t off, unsigned long flags, unsigned long size)
  {

  	loff_t off_end = off + len;
  	loff_t off_align = round_up(off, size);

  	unsigned long len_pad, ret;

  
  	if (off_end <= off_align || (off_end - off_align) < size)
  		return 0;
  
  	len_pad = len + size;
  	if (len_pad < len || (off + len_pad) < off)
  		return 0;

  	ret = current->mm->get_unmapped_area(filp, addr, len_pad,

  					      off >> PAGE_SHIFT, flags);

  
  	/*
  	 * The failure might be due to length padding. The caller will retry
  	 * without the padding.
  	 */
  	if (IS_ERR_VALUE(ret))

  		return 0;

  	/*
  	 * Do not try to align to THP boundary if allocation at the address
  	 * hint succeeds.
  	 */
  	if (ret == addr)
  		return addr;
  
  	ret += (off - ret) & (size - 1);
  	return ret;

  }
  
  unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
  		unsigned long len, unsigned long pgoff, unsigned long flags)
  {

  	unsigned long ret;

  	loff_t off = (loff_t)pgoff << PAGE_SHIFT;

  	if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD))
  		goto out;

  	ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE);
  	if (ret)
  		return ret;
  out:

  	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
  }
  EXPORT_SYMBOL_GPL(thp_get_unmapped_area);

  static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
  			struct page *page, gfp_t gfp)

  {

  	struct vm_area_struct *vma = vmf->vma;

  	struct mem_cgroup *memcg;

  	pgtable_t pgtable;

  	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;

  	vm_fault_t ret = 0;

  	VM_BUG_ON_PAGE(!PageCompound(page), page);

  	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {

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

  	pgtable = pte_alloc_one(vma->vm_mm);

  	if (unlikely(!pgtable)) {

  		ret = VM_FAULT_OOM;
  		goto release;

  	}

  	clear_huge_page(page, vmf->address, 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);

  	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
  	if (unlikely(!pmd_none(*vmf->pmd))) {

  		goto unlock_release;

  	} else {
  		pmd_t entry;

  		ret = check_stable_address_space(vma->vm_mm);
  		if (ret)
  			goto unlock_release;

  		/* Deliver the page fault to userland */
  		if (userfaultfd_missing(vma)) {

  			vm_fault_t ret2;

  			spin_unlock(vmf->ptl);

  			mem_cgroup_cancel_charge(page, memcg, true);

  			put_page(page);

  			pte_free(vma->vm_mm, pgtable);

  			ret2 = handle_userfault(vmf, VM_UFFD_MISSING);
  			VM_BUG_ON(ret2 & VM_FAULT_FALLBACK);
  			return ret2;

  		}

  		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(vma->vm_mm, vmf->pmd, pgtable);
  		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);

  		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);

  		mm_inc_nr_ptes(vma->vm_mm);

  		spin_unlock(vmf->ptl);

  		count_vm_event(THP_FAULT_ALLOC);

  		count_memcg_events(memcg, THP_FAULT_ALLOC, 1);

  	}

  	return 0;

  unlock_release:
  	spin_unlock(vmf->ptl);
  release:
  	if (pgtable)
  		pte_free(vma->vm_mm, pgtable);
  	mem_cgroup_cancel_charge(page, memcg, true);
  	put_page(page);
  	return ret;

  }

  /*

   * always: directly stall for all thp allocations
   * defer: wake kswapd and fail if not immediately available
   * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise
   *		  fail if not immediately available
   * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately
   *	    available
   * never: never stall for any thp allocation

   */

  static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)

  {

  	const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);

  	/* Always do synchronous compaction */

  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
  		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);

  
  	/* Kick kcompactd and fail quickly */

  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))

  		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;

  
  	/* Synchronous compaction if madvised, otherwise kick kcompactd */

  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))

  		return GFP_TRANSHUGE_LIGHT |
  			(vma_madvised ? __GFP_DIRECT_RECLAIM :
  					__GFP_KSWAPD_RECLAIM);

  
  	/* Only do synchronous compaction if madvised */

  	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))

  		return GFP_TRANSHUGE_LIGHT |
  		       (vma_madvised ? __GFP_DIRECT_RECLAIM : 0);

  	return GFP_TRANSHUGE_LIGHT;

  }

  /* 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);

  	mm_inc_nr_ptes(mm);

  	return true;

  }

  vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)

  {

  	struct vm_area_struct *vma = vmf->vma;

  	gfp_t gfp;

  	struct page *page;

  	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;

  	if (!transhuge_vma_suitable(vma, haddr))

  		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 (!(vmf->flags & FAULT_FLAG_WRITE) &&

  			!mm_forbids_zeropage(vma->vm_mm) &&

  			transparent_hugepage_use_zero_page()) {
  		pgtable_t pgtable;
  		struct page *zero_page;
  		bool set;

  		vm_fault_t ret;

  		pgtable = pte_alloc_one(vma->vm_mm);

  		if (unlikely(!pgtable))

  			return VM_FAULT_OOM;

  		zero_page = mm_get_huge_zero_page(vma->vm_mm);

  		if (unlikely(!zero_page)) {

  			pte_free(vma->vm_mm, pgtable);

  			count_vm_event(THP_FAULT_FALLBACK);

  			return VM_FAULT_FALLBACK;

  		}

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

  		ret = 0;
  		set = false;

  		if (pmd_none(*vmf->pmd)) {

  			ret = check_stable_address_space(vma->vm_mm);
  			if (ret) {
  				spin_unlock(vmf->ptl);
  			} else if (userfaultfd_missing(vma)) {

  				spin_unlock(vmf->ptl);
  				ret = handle_userfault(vmf, VM_UFFD_MISSING);

  				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
  			} else {

  				set_huge_zero_page(pgtable, vma->vm_mm, vma,

  						   haddr, vmf->pmd, zero_page);
  				spin_unlock(vmf->ptl);

  				set = true;
  			}
  		} else

  			spin_unlock(vmf->ptl);

  		if (!set)

  			pte_free(vma->vm_mm, pgtable);

  		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(vmf, page, gfp);

  }

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

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

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

  	if (!pmd_none(*pmd)) {
  		if (write) {
  			if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
  				WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
  				goto out_unlock;
  			}
  			entry = pmd_mkyoung(*pmd);
  			entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
  			if (pmdp_set_access_flags(vma, addr, pmd, entry, 1))
  				update_mmu_cache_pmd(vma, addr, pmd);
  		}
  
  		goto out_unlock;
  	}

  	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);

  	}

  
  	if (pgtable) {
  		pgtable_trans_huge_deposit(mm, pmd, pgtable);

  		mm_inc_nr_ptes(mm);

  		pgtable = NULL;

  	}

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

  
  out_unlock:

  	spin_unlock(ptl);

  	if (pgtable)
  		pte_free(mm, pgtable);

  }

  vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)

  {

  	unsigned long addr = vmf->address & PMD_MASK;
  	struct vm_area_struct *vma = vmf->vma;

  	pgprot_t pgprot = vma->vm_page_prot;

  	pgtable_t pgtable = NULL;

  	/*
  	 * 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)) &&
  			!pfn_t_devmap(pfn));

  	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));

  
  	if (addr < vma->vm_start || addr >= vma->vm_end)
  		return VM_FAULT_SIGBUS;

  	if (arch_needs_pgtable_deposit()) {

  		pgtable = pte_alloc_one(vma->vm_mm);

  		if (!pgtable)
  			return VM_FAULT_OOM;
  	}

  	track_pfn_insert(vma, &pgprot, pfn);

  	insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable);

  	return VM_FAULT_NOPAGE;

  }

  EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);

  #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD

  static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)

  {

  	if (likely(vma->vm_flags & VM_WRITE))

  		pud = pud_mkwrite(pud);
  	return pud;
  }
  
  static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
  		pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
  {
  	struct mm_struct *mm = vma->vm_mm;
  	pud_t entry;
  	spinlock_t *ptl;
  
  	ptl = pud_lock(mm, pud);

  	if (!pud_none(*pud)) {
  		if (write) {
  			if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) {
  				WARN_ON_ONCE(!is_huge_zero_pud(*pud));
  				goto out_unlock;
  			}
  			entry = pud_mkyoung(*pud);
  			entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
  			if (pudp_set_access_flags(vma, addr, pud, entry, 1))
  				update_mmu_cache_pud(vma, addr, pud);
  		}
  		goto out_unlock;
  	}

  	entry = pud_mkhuge(pfn_t_pud(pfn, prot));
  	if (pfn_t_devmap(pfn))
  		entry = pud_mkdevmap(entry);
  	if (write) {

  		entry = pud_mkyoung(pud_mkdirty(entry));
  		entry = maybe_pud_mkwrite(entry, vma);

  	}
  	set_pud_at(mm, addr, pud, entry);
  	update_mmu_cache_pud(vma, addr, pud);

  
  out_unlock:

  	spin_unlock(ptl);
  }

  vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)

  {

  	unsigned long addr = vmf->address & PUD_MASK;
  	struct vm_area_struct *vma = vmf->vma;

  	pgprot_t pgprot = vma->vm_page_prot;

  	/*
  	 * If we had pud_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)) &&
  			!pfn_t_devmap(pfn));

  	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));

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

  	insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);

  	return VM_FAULT_NOPAGE;
  }
  EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
  #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

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

  		pmd_t *pmd, int flags)

  {
  	pmd_t _pmd;

  	_pmd = pmd_mkyoung(*pmd);
  	if (flags & FOLL_WRITE)
  		_pmd = pmd_mkdirty(_pmd);

  	if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,

  				pmd, _pmd, flags & FOLL_WRITE))

  		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, struct dev_pagemap **pgmap)

  {
  	unsigned long pfn = pmd_pfn(*pmd);
  	struct mm_struct *mm = vma->vm_mm;

  	struct page *page;
  
  	assert_spin_locked(pmd_lockptr(mm, pmd));

  	/*
  	 * When we COW a devmap PMD entry, we split it into PTEs, so we should
  	 * not be in this function with `flags & FOLL_COW` set.
  	 */
  	WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");

  	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, flags);

  
  	/*
  	 * 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, *pgmap);
  	if (!*pgmap)

  		return ERR_PTR(-EFAULT);
  	page = pfn_to_page(pfn);
  	get_page(page);

  
  	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 = -ENOMEM;

  	/* Skip if can be re-fill on fault */
  	if (!vma_is_anonymous(vma))
  		return 0;

  	pgtable = pte_alloc_one(dst_mm);

  	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;

  
  #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
  	if (unlikely(is_swap_pmd(pmd))) {
  		swp_entry_t entry = pmd_to_swp_entry(pmd);
  
  		VM_BUG_ON(!is_pmd_migration_entry(pmd));
  		if (is_write_migration_entry(entry)) {
  			make_migration_entry_read(&entry);
  			pmd = swp_entry_to_pmd(entry);

  			if (pmd_swp_soft_dirty(*src_pmd))
  				pmd = pmd_swp_mksoft_dirty(pmd);

  			set_pmd_at(src_mm, addr, src_pmd, pmd);
  		}

  		add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);

  		mm_inc_nr_ptes(dst_mm);

  		pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);

  		set_pmd_at(dst_mm, addr, dst_pmd, pmd);
  		ret = 0;
  		goto out_unlock;
  	}
  #endif

  	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;

  		/*
  		 * 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 = mm_get_huge_zero_page(dst_mm);

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

  				zero_page);

  		ret = 0;
  		goto out_unlock;
  	}

  	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);

  	mm_inc_nr_ptes(dst_mm);

  	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;
  }

  #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
  static void touch_pud(struct vm_area_struct *vma, unsigned long addr,

  		pud_t *pud, int flags)

  {
  	pud_t _pud;

  	_pud = pud_mkyoung(*pud);
  	if (flags & FOLL_WRITE)
  		_pud = pud_mkdirty(_pud);

  	if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,

  				pud, _pud, flags & FOLL_WRITE))

  		update_mmu_cache_pud(vma, addr, pud);
  }
  
  struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,

  		pud_t *pud, int flags, struct dev_pagemap **pgmap)

  {
  	unsigned long pfn = pud_pfn(*pud);
  	struct mm_struct *mm = vma->vm_mm;

  	struct page *page;
  
  	assert_spin_locked(pud_lockptr(mm, pud));

  	if (flags & FOLL_WRITE && !pud_write(*pud))

  		return NULL;
  
  	if (pud_present(*pud) && pud_devmap(*pud))
  		/* pass */;
  	else
  		return NULL;
  
  	if (flags & FOLL_TOUCH)

  		touch_pud(vma, addr, pud, flags);

  
  	/*
  	 * 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 & ~PUD_MASK) >> PAGE_SHIFT;

  	*pgmap = get_dev_pagemap(pfn, *pgmap);
  	if (!*pgmap)

  		return ERR_PTR(-EFAULT);
  	page = pfn_to_page(pfn);
  	get_page(page);

  
  	return page;
  }
  
  int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
  		  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
  		  struct vm_area_struct *vma)
  {
  	spinlock_t *dst_ptl, *src_ptl;
  	pud_t pud;
  	int ret;
  
  	dst_ptl = pud_lock(dst_mm, dst_pud);
  	src_ptl = pud_lockptr(src_mm, src_pud);
  	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
  
  	ret = -EAGAIN;
  	pud = *src_pud;
  	if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud)))
  		goto out_unlock;
  
  	/*
  	 * When page table lock is held, the huge zero pud should not be
  	 * under splitting since we don't split the page itself, only pud to
  	 * a page table.
  	 */
  	if (is_huge_zero_pud(pud)) {
  		/* No huge zero pud yet */
  	}
  
  	pudp_set_wrprotect(src_mm, addr, src_pud);
  	pud = pud_mkold(pud_wrprotect(pud));
  	set_pud_at(dst_mm, addr, dst_pud, pud);
  
  	ret = 0;
  out_unlock:
  	spin_unlock(src_ptl);
  	spin_unlock(dst_ptl);
  	return ret;
  }
  
  void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
  {
  	pud_t entry;
  	unsigned long haddr;
  	bool write = vmf->flags & FAULT_FLAG_WRITE;
  
  	vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud);
  	if (unlikely(!pud_same(*vmf->pud, orig_pud)))
  		goto unlock;
  
  	entry = pud_mkyoung(orig_pud);
  	if (write)
  		entry = pud_mkdirty(entry);
  	haddr = vmf->address & HPAGE_PUD_MASK;
  	if (pudp_set_access_flags(vmf->vma, haddr, vmf->pud, entry, write))
  		update_mmu_cache_pud(vmf->vma, vmf->address, vmf->pud);
  
  unlock:
  	spin_unlock(vmf->ptl);
  }
  #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

  void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd)

  {
  	pmd_t entry;
  	unsigned long haddr;

  	bool write = vmf->flags & FAULT_FLAG_WRITE;

  	vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
  	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))

  		goto unlock;
  
  	entry = pmd_mkyoung(orig_pmd);

  	if (write)
  		entry = pmd_mkdirty(entry);

  	haddr = vmf->address & HPAGE_PMD_MASK;

  	if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, write))

  		update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd);

  
  unlock:

  	spin_unlock(vmf->ptl);

  }

  static vm_fault_t do_huge_pmd_wp_page_fallback(struct vm_fault *vmf,
  			pmd_t orig_pmd, struct page *page)

  {

  	struct vm_area_struct *vma = vmf->vma;
  	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;

  	struct mem_cgroup *memcg;

  	pgtable_t pgtable;
  	pmd_t _pmd;

  	int i;
  	vm_fault_t ret = 0;

  	struct page **pages;

  	struct mmu_notifier_range range;

  	pages = kmalloc_array(HPAGE_PMD_NR, sizeof(struct page *),
  			      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, vma,

  					       vmf->address, page_to_nid(page));

  		if (unlikely(!pages[i] ||

  			     mem_cgroup_try_charge_delay(pages[i], vma->vm_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();
  	}

  	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
  				haddr, haddr + HPAGE_PMD_SIZE);

  	mmu_notifier_invalidate_range_start(&range);

  	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
  	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))

  		goto out_free_pages;

  	VM_BUG_ON_PAGE(!PageHead(page), page);

  	/*
  	 * Leave pmd empty until pte is filled note we must notify here as
  	 * concurrent CPU thread might write to new page before the call to
  	 * mmu_notifier_invalidate_range_end() happens which can lead to a
  	 * device seeing memory write in different order than CPU.
  	 *

  	 * See Documentation/vm/mmu_notifier.rst

  	 */

  	pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);

  	pgtable = pgtable_trans_huge_withdraw(vma->vm_mm, vmf->pmd);

  	pmd_populate(vma->vm_mm, &_pmd, pgtable);

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

  		pte_t 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], vmf->vma, haddr, false);

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

  		lru_cache_add_active_or_unevictable(pages[i], vma);

  		vmf->pte = pte_offset_map(&_pmd, haddr);
  		VM_BUG_ON(!pte_none(*vmf->pte));
  		set_pte_at(vma->vm_mm, haddr, vmf->pte, entry);
  		pte_unmap(vmf->pte);

  	}
  	kfree(pages);

  	smp_wmb(); /* make pte visible before pmd */

  	pmd_populate(vma->vm_mm, vmf->pmd, pgtable);

  	page_remove_rmap(page, true);

  	spin_unlock(vmf->ptl);

  	/*
  	 * No need to double call mmu_notifier->invalidate_range() callback as
  	 * the above pmdp_huge_clear_flush_notify() did already call it.
  	 */

  	mmu_notifier_invalidate_range_only_end(&range);

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

  	spin_unlock(vmf->ptl);

  	mmu_notifier_invalidate_range_end(&range);

  	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;
  }

  vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)

  {

  	struct vm_area_struct *vma = vmf->vma;

  	struct page *page = NULL, *new_page;

  	struct mem_cgroup *memcg;

  	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;

  	struct mmu_notifier_range range;

  	gfp_t huge_gfp;			/* for allocation and charge */

  	vm_fault_t ret = 0;

  	vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);

  	VM_BUG_ON_VMA(!vma->anon_vma, vma);

  	if (is_huge_zero_pmd(orig_pmd))
  		goto alloc;

  	spin_lock(vmf->ptl);
  	if (unlikely(!pmd_same(*vmf->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 (!trylock_page(page)) {
  		get_page(page);
  		spin_unlock(vmf->ptl);
  		lock_page(page);
  		spin_lock(vmf->ptl);
  		if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
  			unlock_page(page);
  			put_page(page);
  			goto out_unlock;
  		}
  		put_page(page);
  	}
  	if (reuse_swap_page(page, NULL)) {

  		pmd_t entry;
  		entry = pmd_mkyoung(orig_pmd);

  		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);

  		if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry,  1))
  			update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);

  		ret |= VM_FAULT_WRITE;

  		unlock_page(page);

  		goto out_unlock;
  	}

  	unlock_page(page);

  	get_page(page);

  	spin_unlock(vmf->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, vmf->pmd, vmf->address);

  			ret |= VM_FAULT_FALLBACK;

  		} else {

  			ret = do_huge_pmd_wp_page_fallback(vmf, orig_pmd, page);

  			if (ret & VM_FAULT_OOM) {

  				split_huge_pmd(vma, vmf->pmd, vmf->address);

  				ret |= VM_FAULT_FALLBACK;
  			}

  			put_page(page);

  		}

  		count_vm_event(THP_FAULT_FALLBACK);

  		goto out;
  	}

  	if (unlikely(mem_cgroup_try_charge_delay(new_page, vma->vm_mm,

  					huge_gfp, &memcg, true))) {

  		put_page(new_page);

  		split_huge_pmd(vma, vmf->pmd, vmf->address);

  		if (page)

  			put_page(page);

  		ret |= VM_FAULT_FALLBACK;

  		count_vm_event(THP_FAULT_FALLBACK);

  		goto out;
  	}

  	count_vm_event(THP_FAULT_ALLOC);

  	count_memcg_events(memcg, THP_FAULT_ALLOC, 1);

  	if (!page)

  		clear_huge_page(new_page, vmf->address, HPAGE_PMD_NR);

  	else

  		copy_user_huge_page(new_page, page, vmf->address,
  				    vma, HPAGE_PMD_NR);

  	__SetPageUptodate(new_page);

  	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
  				haddr, haddr + HPAGE_PMD_SIZE);

  	mmu_notifier_invalidate_range_start(&range);

  	spin_lock(vmf->ptl);

  	if (page)

  		put_page(page);

  	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
  		spin_unlock(vmf->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, vmf->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(vma->vm_mm, haddr, vmf->pmd, entry);
  		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);

  		if (!page) {

  			add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);

  		} else {

  			VM_BUG_ON_PAGE(!PageHead(page), page);

  			page_remove_rmap(page, true);

  			put_page(page);
  		}