huge_memory.c

	page_dup_rmap(src_page);
	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);

	pmdp_set_wrprotect(src_mm, addr, src_pmd);
	pmd = pmd_mkold(pmd_wrprotect(pmd));
	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
	atomic_long_inc(&dst_mm->nr_ptes);

	ret = 0;
out_unlock:
	spin_unlock(src_ptl);
	spin_unlock(dst_ptl);
out:
	return ret;
}

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

	ptl = pmd_lock(mm, pmd);
	if (unlikely(!pmd_same(*pmd, orig_pmd)))
		goto unlock;

	entry = pmd_mkyoung(orig_pmd);
	haddr = address & HPAGE_PMD_MASK;
	if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty))
		update_mmu_cache_pmd(vma, address, pmd);

unlock:
	spin_unlock(ptl);
}

/*
 * Save CONFIG_DEBUG_PAGEALLOC from faulting falsely on tail pages
 * during copy_user_huge_page()'s copy_page_rep(): in the case when
 * the source page gets split and a tail freed before copy completes.
 * Called under pmd_lock of checked pmd, so safe from splitting itself.
 */
static void get_user_huge_page(struct page *page)
{
	if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
		struct page *endpage = page + HPAGE_PMD_NR;

		atomic_add(HPAGE_PMD_NR, &page->_count);
		while (++page < endpage)
			get_huge_page_tail(page);
	} else {
		get_page(page);
	}
}

static void put_user_huge_page(struct page *page)
{
	if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
		struct page *endpage = page + HPAGE_PMD_NR;

		while (page < endpage)
			put_page(page++);
	} else {
		put_page(page);
	}
}

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. We can do it by checking page_mapcount() on each sub-page, but
	 * it's expensive.
	 * The cheaper way is to check page_count() to be equal 1: every
	 * mapcount takes page reference reference, so this way we can
	 * guarantee, that the PMD is the only mapping.
	 * This can give false negative if somebody pinned the page, but that's
	 * fine.
	 */
	if (page_mapcount(page) == 1 && page_count(page) == 1) {
		pmd_t entry;
		entry = pmd_mkyoung(orig_pmd);
		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
		if (pmdp_set_access_flags(vma, haddr, pmd, entry,  1))
			update_mmu_cache_pmd(vma, address, pmd);
		ret |= VM_FAULT_WRITE;
		goto out_unlock;
	}
	get_user_huge_page(page);
	spin_unlock(ptl);
alloc:
	if (transparent_hugepage_enabled(vma) &&
	    !transparent_hugepage_debug_cow()) {
		huge_gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0);
		new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
	} else
		new_page = NULL;

	if (unlikely(!new_page)) {
		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_user_huge_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_user_huge_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_user_huge_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) {
		pmd_t _pmd;
		/*
		 * We should set the dirty bit only for FOLL_WRITE but
		 * for now the dirty bit in the pmd is meaningless.
		 * And if the dirty bit will become meaningful and
		 * we'll only set it with FOLL_WRITE, an atomic
		 * set_bit will be required on the pmd to set the
		 * young bit, instead of the current set_pmd_at.
		 */
		_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
		if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
					  pmd, _pmd,  1))
			update_mmu_cache_pmd(vma, addr, pmd);
	}
	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
		if (page->mapping && trylock_page(page)) {
			lru_add_drain();
			if (page->mapping)
				mlock_vma_page(page);
			unlock_page(page);
		}
	}
	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
	VM_BUG_ON_PAGE(!PageCompound(page), page);
	if (flags & FOLL_GET)
		get_page_foll(page);

out:
	return page;
}

/* NUMA hinting page fault entry point for trans huge pmds */
int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
{
	spinlock_t *ptl;
	struct anon_vma *anon_vma = NULL;
	struct page *page;
	unsigned long haddr = addr & HPAGE_PMD_MASK;
	int page_nid = -1, this_nid = numa_node_id();
	int target_nid, last_cpupid = -1;
	bool page_locked;
	bool migrated = false;
	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 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;

	if (__pmd_trans_huge_lock(pmd, vma, &ptl) != 1)
		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))
			put_huge_zero_page();
	} 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);
		put_huge_zero_page();
	} 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;
}

int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
		  unsigned long old_addr,
		  unsigned long new_addr, unsigned long old_end,
		  pmd_t *old_pmd, pmd_t *new_pmd)
{
	spinlock_t *old_ptl, *new_ptl;
	int ret = 0;
	pmd_t pmd;

	struct mm_struct *mm = vma->vm_mm;

	if ((old_addr & ~HPAGE_PMD_MASK) ||
	    (new_addr & ~HPAGE_PMD_MASK) ||
	    old_end - old_addr < HPAGE_PMD_SIZE ||
	    (new_vma->vm_flags & VM_NOHUGEPAGE))
		goto out;

	/*
	 * The destination pmd shouldn't be established, free_pgtables()
	 * should have release it.
	 */
	if (WARN_ON(!pmd_none(*new_pmd))) {
		VM_BUG_ON(pmd_trans_huge(*new_pmd));
		goto out;
	}

	/*
	 * We don't have to worry about the ordering of src and dst
	 * ptlocks because exclusive mmap_sem prevents deadlock.
	 */
	ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl);
	if (ret == 1) {
		new_ptl = pmd_lockptr(mm, new_pmd);
		if (new_ptl != old_ptl)
			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
		pmd = pmdp_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)) {
			pgtable_t pgtable;
			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
		}
		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
		if (new_ptl != old_ptl)
			spin_unlock(new_ptl);
		spin_unlock(old_ptl);
	}
out:
	return ret;
}

/*
 * Returns
 *  - 0 if PMD could not be locked
 *  - 1 if PMD was locked but protections unchange and TLB flush unnecessary
 *  - HPAGE_PMD_NR is protections changed and TLB flush necessary
 */
int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long addr, pgprot_t newprot, int prot_numa)
{
	struct mm_struct *mm = vma->vm_mm;
	spinlock_t *ptl;
	int ret = 0;

	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
		pmd_t entry;
		bool preserve_write = prot_numa && pmd_write(*pmd);
		ret = 1;

		/*
		 * Avoid trapping faults against the zero page. The read-only
		 * data is likely to be read-cached on the local CPU and
		 * local/remote hits to the zero page are not interesting.
		 */
		if (prot_numa && is_huge_zero_pmd(*pmd)) {
			spin_unlock(ptl);
			return ret;
		}

		if (!prot_numa || !pmd_protnone(*pmd)) {
			entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd);
			entry = pmd_modify(entry, newprot);
			if (preserve_write)
				entry = pmd_mkwrite(entry);
			ret = HPAGE_PMD_NR;
			set_pmd_at(mm, addr, pmd, entry);
			BUG_ON(!preserve_write && pmd_write(entry));
		}
		spin_unlock(ptl);
	}

	return ret;
}

/*
 * Returns 1 if a given pmd maps a stable (not under splitting) thp.
 * Returns -1 if it maps a thp under splitting. Returns 0 otherwise.
 *
 * Note that if it returns 1, this routine returns without unlocking page
 * table locks. So callers must unlock them.
 */
int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
		spinlock_t **ptl)
{
	*ptl = pmd_lock(vma->vm_mm, pmd);
	if (likely(pmd_trans_huge(*pmd))) {
		if (unlikely(pmd_trans_splitting(*pmd))) {
			spin_unlock(*ptl);
			wait_split_huge_page(vma->anon_vma, pmd);
			return -1;
		} else {
			/* Thp mapped by 'pmd' is stable, so we can
			 * handle it as it is. */
			return 1;
		}
	}
	spin_unlock(*ptl);
	return 0;
}

/*
 * This function returns whether a given @page is mapped onto the @address
 * in the virtual space of @mm.
 *
 * When it's true, this function returns *pmd with holding the page table lock
 * and passing it back to the caller via @ptl.
 * If it's false, returns NULL without holding the page table lock.
 */
pmd_t *page_check_address_pmd(struct page *page,
			      struct mm_struct *mm,
			      unsigned long address,
			      enum page_check_address_pmd_flag flag,
			      spinlock_t **ptl)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	if (address & ~HPAGE_PMD_MASK)
		return NULL;

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

	*ptl = pmd_lock(mm, pmd);
	if (!pmd_present(*pmd))
		goto unlock;
	if (pmd_page(*pmd) != page)
		goto unlock;
	/*
	 * split_vma() may create temporary aliased mappings. There is
	 * no risk as long as all huge pmd are found and have their
	 * splitting bit set before __split_huge_page_refcount
	 * runs. Finding the same huge pmd more than once during the
	 * same rmap walk is not a problem.
	 */
	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
	    pmd_trans_splitting(*pmd))
		goto unlock;
	if (pmd_trans_huge(*pmd)) {
		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
			  !pmd_trans_splitting(*pmd));
		return pmd;
	}
unlock:
	spin_unlock(*ptl);
	return NULL;
}

#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)

int hugepage_madvise(struct vm_area_struct *vma,
		     unsigned long *vm_flags, int advice)
{
	switch (advice) {
	case MADV_HUGEPAGE:
#ifdef CONFIG_S390
		/*
		 * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390
		 * can't handle this properly after s390_enable_sie, so we simply
		 * ignore the madvise to prevent qemu from causing a SIGSEGV.
		 */
		if (mm_has_pgste(vma->vm_mm))
			return 0;
#endif
		/*
		 * Be somewhat over-protective like KSM for now!
		 */
		if (*vm_flags & VM_NO_THP)
			return -EINVAL;
		*vm_flags &= ~VM_NOHUGEPAGE;
		*vm_flags |= VM_HUGEPAGE;
		/*
		 * If the vma become good for khugepaged to scan,
		 * register it here without waiting a page fault that
		 * may not happen any time soon.
		 */
		if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags)))
			return -ENOMEM;
		break;
	case MADV_NOHUGEPAGE:
		/*
		 * Be somewhat over-protective like KSM for now!
		 */
		if (*vm_flags & VM_NO_THP)
			return -EINVAL;
		*vm_flags &= ~VM_HUGEPAGE;
		*vm_flags |= VM_NOHUGEPAGE;
		/*
		 * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning
		 * this vma even if we leave the mm registered in khugepaged if
		 * it got registered before VM_NOHUGEPAGE was set.
		 */
		break;
	}

	return 0;
}

static int __init khugepaged_slab_init(void)
{
	mm_slot_cache = kmem_cache_create("khugepaged_mm_slot",
					  sizeof(struct mm_slot),
					  __alignof__(struct mm_slot), 0, NULL);
	if (!mm_slot_cache)
		return -ENOMEM;

	return 0;
}

static void __init khugepaged_slab_exit(void)
{
	kmem_cache_destroy(mm_slot_cache);
}

static inline struct mm_slot *alloc_mm_slot(void)
{
	if (!mm_slot_cache)	/* initialization failed */
		return NULL;
	return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL);
}

static inline void free_mm_slot(struct mm_slot *mm_slot)
{
	kmem_cache_free(mm_slot_cache, mm_slot);
}

static struct mm_slot *get_mm_slot(struct mm_struct *mm)
{
	struct mm_slot *mm_slot;

	hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm)
		if (mm == mm_slot->mm)
			return mm_slot;

	return NULL;
}

static void insert_to_mm_slots_hash(struct mm_struct *mm,
				    struct mm_slot *mm_slot)
{
	mm_slot->mm = mm;
	hash_add(mm_slots_hash, &mm_slot->hash, (long)mm);
}

static inline int khugepaged_test_exit(struct mm_struct *mm)
{
	return atomic_read(&mm->mm_users) == 0;
}

int __khugepaged_enter(struct mm_struct *mm)
{
	struct mm_slot *mm_slot;
	int wakeup;

	mm_slot = alloc_mm_slot();
	if (!mm_slot)
		return -ENOMEM;

	/* __khugepaged_exit() must not run from under us */
	VM_BUG_ON_MM(khugepaged_test_exit(mm), mm);
	if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) {
		free_mm_slot(mm_slot);
		return 0;
	}

	spin_lock(&khugepaged_mm_lock);
	insert_to_mm_slots_hash(mm, mm_slot);
	/*
	 * Insert just behind the scanning cursor, to let the area settle
	 * down a little.
	 */
	wakeup = list_empty(&khugepaged_scan.mm_head);
	list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head);
	spin_unlock(&khugepaged_mm_lock);

	atomic_inc(&mm->mm_count);
	if (wakeup)
		wake_up_interruptible(&khugepaged_wait);

	return 0;
}

int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
			       unsigned long vm_flags)
{
	unsigned long hstart, hend;
	if (!vma->anon_vma)
		/*
		 * Not yet faulted in so we will register later in the
		 * page fault if needed.
		 */
		return 0;
	if (vma->vm_ops)
		/* khugepaged not yet working on file or special mappings */
		return 0;
	VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma);
	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
	hend = vma->vm_end & HPAGE_PMD_MASK;
	if (hstart < hend)
		return khugepaged_enter(vma, vm_flags);
	return 0;
}

void __khugepaged_exit(struct mm_struct *mm)
{
	struct mm_slot *mm_slot;
	int free = 0;

	spin_lock(&khugepaged_mm_lock);
	mm_slot = get_mm_slot(mm);
	if (mm_slot && khugepaged_scan.mm_slot != mm_slot) {
		hash_del(&mm_slot->hash);
		list_del(&mm_slot->mm_node);
		free = 1;
	}
	spin_unlock(&khugepaged_mm_lock);

	if (free) {
		clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
		free_mm_slot(mm_slot);
		mmdrop(mm);
	} else if (mm_slot) {
		/*
		 * This is required to serialize against
		 * khugepaged_test_exit() (which is guaranteed to run
		 * under mmap sem read mode). Stop here (after we
		 * return all pagetables will be destroyed) until
		 * khugepaged has finished working on the pagetables
		 * under the mmap_sem.
		 */
		down_write(&mm->mmap_sem);
		up_write(&mm->mmap_sem);
	}
}

static void release_pte_page(struct page *page)
{
	/* 0 stands for page_is_file_cache(page) == false */
	dec_zone_page_state(page, NR_ISOLATED_ANON + 0);
	unlock_page(page);
	putback_lru_page(page);
}

static void release_pte_pages(pte_t *pte, pte_t *_pte)
{
	while (--_pte >= pte) {
		pte_t pteval = *_pte;
		if (!pte_none(pteval) && !is_zero_pfn(pte_pfn(pteval)))
			release_pte_page(pte_page(pteval));
	}
}

static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
					unsigned long address,
					pte_t *pte)
{
	struct page *page = NULL;
	pte_t *_pte;
	int none_or_zero = 0, result = 0;
	bool referenced = false, writable = false;

	for (_pte = pte; _pte < pte+HPAGE_PMD_NR;
	     _pte++, address += PAGE_SIZE) {
		pte_t pteval = *_pte;
		if (pte_none(pteval) || (pte_present(pteval) &&
				is_zero_pfn(pte_pfn(pteval)))) {
			if (!userfaultfd_armed(vma) &&
			    ++none_or_zero <= khugepaged_max_ptes_none) {
				continue;
			} else {
				result = SCAN_EXCEED_NONE_PTE;
				goto out;
			}
		}
		if (!pte_present(pteval)) {
			result = SCAN_PTE_NON_PRESENT;
			goto out;
		}
		page = vm_normal_page(vma, address, pteval);
		if (unlikely(!page)) {
			result = SCAN_PAGE_NULL;
			goto out;
		}

		VM_BUG_ON_PAGE(PageCompound(page), page);
		VM_BUG_ON_PAGE(!PageAnon(page), page);
		VM_BUG_ON_PAGE(!PageSwapBacked(page), page);

		/*
		 * We can do it before isolate_lru_page because the
		 * page can't be freed from under us. NOTE: PG_lock
		 * is needed to serialize against split_huge_page
		 * when invoked from the VM.
		 */
		if (!trylock_page(page)) {
			result = SCAN_PAGE_LOCK;
			goto out;
		}

		/*
		 * cannot use mapcount: can't collapse if there's a gup pin.
		 * The page must only be referenced by the scanned process
		 * and page swap cache.
		 */
		if (page_count(page) != 1 + !!PageSwapCache(page)) {
			unlock_page(page);
			result = SCAN_PAGE_COUNT;
			goto out;
		}
		if (pte_write(pteval)) {
			writable = true;
		} else {
			if (PageSwapCache(page) && !reuse_swap_page(page)) {
				unlock_page(page);
				result = SCAN_SWAP_CACHE_PAGE;
				goto out;
			}
			/*
			 * Page is not in the swap cache. It can be collapsed
			 * into a THP.
			 */
		}

		/*
		 * Isolate the page to avoid collapsing an hugepage
		 * currently in use by the VM.
		 */
		if (isolate_lru_page(page)) {
			unlock_page(page);
			result = SCAN_DEL_PAGE_LRU;
			goto out;
		}
		/* 0 stands for page_is_file_cache(page) == false */
		inc_zone_page_state(page, NR_ISOLATED_ANON + 0);
		VM_BUG_ON_PAGE(!PageLocked(page), page);
		VM_BUG_ON_PAGE(PageLRU(page), page);