huge_memory.c

	 * the dirty bit in the pud 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 pud to
	 * set the young bit, instead of the current set_pud_at.
	 */
	_pud = pud_mkyoung(pud_mkdirty(*pud));
	if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,
				pud, _pud,  1))
		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)
{
	unsigned long pfn = pud_pfn(*pud);
	struct mm_struct *mm = vma->vm_mm;
	struct dev_pagemap *pgmap;
	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);

	/*
	 * 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, NULL);
	if (!pgmap)
		return ERR_PTR(-EFAULT);
	page = pfn_to_page(pfn);
	get_page(page);
	put_dev_pagemap(pgmap);

	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 int 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 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, vma,
					       vmf->address, page_to_nid(page));
		if (unlikely(!pages[i] ||
			     mem_cgroup_try_charge(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();
	}

	mmun_start = haddr;
	mmun_end   = haddr + HPAGE_PMD_SIZE;
	mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end);

	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);

	pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
	/* leave pmd empty until pte is filled */

	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);

	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);

	ret |= VM_FAULT_WRITE;
	put_page(page);

out:
	return ret;

out_free_pages:
	spin_unlock(vmf->ptl);
	mmu_notifier_invalidate_range_end(vma->vm_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 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;
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */
	gfp_t huge_gfp;			/* for allocation and charge */
	int 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(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);

	if (!page)
		clear_huge_page(new_page, vmf->address, 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(vma->vm_mm, mmun_start, mmun_end);

	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);
		}
		ret |= VM_FAULT_WRITE;
	}
	spin_unlock(vmf->ptl);
out_mn:
	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
out:
	return ret;
out_unlock:
	spin_unlock(vmf->ptl);
	return ret;
}

/*
 * FOLL_FORCE can write to even unwritable pmd's, but only
 * after we've gone through a COW cycle and they are dirty.
 */
static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
{
	return pmd_write(pmd) ||
	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
}

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 && !can_follow_write_pmd(*pmd, flags))
		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) && !is_zone_device_page(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.
		 *
		 * For anon THP:
		 *
		 * 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.
		 *
		 * For file THP:
		 *
		 * We can expect PageDoubleMap() to be stable under page lock:
		 * for file pages we set it in page_add_file_rmap(), which
		 * requires page to be locked.
		 */

		if (PageAnon(page) && compound_mapcount(page) != 1)
			goto skip_mlock;
		if (PageDoubleMap(page) || !page->mapping)
			goto skip_mlock;
		if (!trylock_page(page))
			goto skip_mlock;
		lru_add_drain();
		if (page->mapping && !PageDoubleMap(page))
			mlock_vma_page(page);
		unlock_page(page);
	}
skip_mlock:
	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(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 vm_fault *vmf, pmd_t pmd)
{
	struct vm_area_struct *vma = vmf->vma;
	struct anon_vma *anon_vma = NULL;
	struct page *page;
	unsigned long haddr = vmf->address & 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;

	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
	if (unlikely(!pmd_same(pmd, *vmf->pmd)))
		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(*vmf->pmd))) {
		page = pmd_page(*vmf->pmd);
		if (!get_page_unless_zero(page))
			goto out_unlock;
		spin_unlock(vmf->ptl);
		wait_on_page_locked(page);
		put_page(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 (!pmd_savedwrite(pmd))
		flags |= TNF_NO_GROUP;

	/*
	 * Acquire the page lock to serialise THP migrations but avoid dropping
	 * page_table_lock if at all possible
	 */
	page_locked = trylock_page(page);
	target_nid = mpol_misplaced(page, vma, haddr);
	if (target_nid == -1) {
		/* If the page was locked, there are no parallel migrations */
		if (page_locked)
			goto clear_pmdnuma;
	}

	/* Migration could have started since the pmd_trans_migrating check */
	if (!page_locked) {
		page_nid = -1;
		if (!get_page_unless_zero(page))
			goto out_unlock;
		spin_unlock(vmf->ptl);
		wait_on_page_locked(page);
		put_page(page);
		goto out;
	}

	/*
	 * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
	 * to serialises splits
	 */
	get_page(page);
	spin_unlock(vmf->ptl);
	anon_vma = page_lock_anon_vma_read(page);

	/* Confirm the PMD did not change while page_table_lock was released */
	spin_lock(vmf->ptl);
	if (unlikely(!pmd_same(pmd, *vmf->pmd))) {
		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;
	}

	/*
	 * Since we took the NUMA fault, we must have observed the !accessible
	 * bit. Make sure all other CPUs agree with that, to avoid them
	 * modifying the page we're about to migrate.
	 *
	 * Must be done under PTL such that we'll observe the relevant
	 * inc_tlb_flush_pending().
	 *
	 * We are not sure a pending tlb flush here is for a huge page
	 * mapping or not. Hence use the tlb range variant
	 */
	if (mm_tlb_flush_pending(vma->vm_mm))
		flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);

	/*
	 * Migrate the THP to the requested node, returns with page unlocked
	 * and access rights restored.
	 */
	spin_unlock(vmf->ptl);

	migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma,
				vmf->pmd, pmd, vmf->address, 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_savedwrite(pmd);
	pmd = pmd_modify(pmd, vma->vm_page_prot);
	pmd = pmd_mkyoung(pmd);
	if (was_writable)
		pmd = pmd_mkwrite(pmd);
	set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
	update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
	unlock_page(page);
out_unlock:
	spin_unlock(vmf->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;
}

/*
 * Return true if we do MADV_FREE successfully on entire pmd page.
 * Otherwise, return false.
 */
bool 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;
	bool ret = false;

	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);

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

	orig_pmd = *pmd;
	if (is_huge_zero_pmd(orig_pmd))
		goto out;

	if (unlikely(!pmd_present(orig_pmd))) {
		VM_BUG_ON(thp_migration_supported() &&
				  !is_pmd_migration_entry(orig_pmd));
		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);
		split_huge_page(page);
		unlock_page(page);
		put_page(page);
		goto out_unlocked;
	}

	if (PageDirty(page))
		ClearPageDirty(page);
	unlock_page(page);

	if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
		pmdp_invalidate(vma, addr, pmd);
		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);
	}

	mark_page_lazyfree(page);
	ret = true;
out:
	spin_unlock(ptl);
out_unlocked:
	return ret;
}

static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
{
	pgtable_t pgtable;

	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
	pte_free(mm, pgtable);
	atomic_long_dec(&mm->nr_ptes);
}

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;

	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);

	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)) {
		if (arch_needs_pgtable_deposit())
			zap_deposited_table(tlb->mm, pmd);
		spin_unlock(ptl);
		if (is_huge_zero_pmd(orig_pmd))
			tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);
	} else if (is_huge_zero_pmd(orig_pmd)) {
		zap_deposited_table(tlb->mm, pmd);
		spin_unlock(ptl);
		tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);
	} else {
		struct page *page = NULL;
		int flush_needed = 1;

		if (pmd_present(orig_pmd)) {
			page = pmd_page(orig_pmd);
			page_remove_rmap(page, true);
			VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
			VM_BUG_ON_PAGE(!PageHead(page), page);
		} else if (thp_migration_supported()) {
			swp_entry_t entry;

			VM_BUG_ON(!is_pmd_migration_entry(orig_pmd));
			entry = pmd_to_swp_entry(orig_pmd);
			page = pfn_to_page(swp_offset(entry));
			flush_needed = 0;
		} else
			WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");

		if (PageAnon(page)) {
			zap_deposited_table(tlb->mm, pmd);
			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
		} else {
			if (arch_needs_pgtable_deposit())
				zap_deposited_table(tlb->mm, pmd);
			add_mm_counter(tlb->mm, MM_FILEPAGES, -HPAGE_PMD_NR);
		}

		spin_unlock(ptl);
		if (flush_needed)
			tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE);
	}
	return 1;
}

#ifndef pmd_move_must_withdraw
static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl,
					 spinlock_t *old_pmd_ptl,
					 struct vm_area_struct *vma)
{
	/*
	 * With split pmd lock we also need to move preallocated
	 * PTE page table if new_pmd is on different PMD page table.
	 *
	 * We also don't deposit and withdraw tables for file pages.
	 */
	return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma);
}
#endif

static pmd_t move_soft_dirty_pmd(pmd_t pmd)
{
#ifdef CONFIG_MEM_SOFT_DIRTY
	if (unlikely(is_pmd_migration_entry(pmd)))
		pmd = pmd_swp_mksoft_dirty(pmd);
	else if (pmd_present(pmd))
		pmd = pmd_mksoft_dirty(pmd);
#endif
	return pmd;
}

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, bool *need_flush)
{
	spinlock_t *old_ptl, *new_ptl;
	pmd_t pmd;
	struct mm_struct *mm = vma->vm_mm;
	bool force_flush = false;

	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);
		if (pmd_present(pmd) && pmd_dirty(pmd))
			force_flush = true;
		VM_BUG_ON(!pmd_none(*new_pmd));

		if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) {
			pgtable_t pgtable;
			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
		}
		pmd = move_soft_dirty_pmd(pmd);
		set_pmd_at(mm, new_addr, new_pmd, pmd);
		if (new_ptl != old_ptl)
			spin_unlock(new_ptl);
		if (force_flush)
			flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
		else
			*need_flush = true;
		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
 */
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;
	pmd_t entry;
	bool preserve_write;
	int ret;

	ptl = __pmd_trans_huge_lock(pmd, vma);
	if (!ptl)
		return 0;

	preserve_write = prot_numa && pmd_write(*pmd);
	ret = 1;

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
	if (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)) {
			pmd_t newpmd;
			/*
			 * A protection check is difficult so
			 * just be safe and disable write
			 */
			make_migration_entry_read(&entry);
			newpmd = swp_entry_to_pmd(entry);
			if (pmd_swp_soft_dirty(*pmd))
				newpmd = pmd_swp_mksoft_dirty(newpmd);
			set_pmd_at(mm, addr, pmd, newpmd);
		}
		goto unlock;
	}
#endif

	/*
	 * 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))
		goto unlock;

	if (prot_numa && pmd_protnone(*pmd))
		goto unlock;

	/*
	 * In case prot_numa, we are under down_read(mmap_sem). It's critical
	 * to not clear pmd intermittently to avoid race with MADV_DONTNEED
	 * which is also under down_read(mmap_sem):
	 *
	 *	CPU0:				CPU1:
	 *				change_huge_pmd(prot_numa=1)
	 *				 pmdp_huge_get_and_clear_notify()
	 * madvise_dontneed()
	 *  zap_pmd_range()
	 *   pmd_trans_huge(*pmd) == 0 (without ptl)
	 *   // skip the pmd
	 *				 set_pmd_at();
	 *				 // pmd is re-established
	 *
	 * The race makes MADV_DONTNEED miss the huge pmd and don't clear it
	 * which may break userspace.
	 *
	 * pmdp_invalidate() is required to make sure we don't miss
	 * dirty/young flags set by hardware.
	 */
	entry = *pmd;
	pmdp_invalidate(vma, addr, pmd);

	/*
	 * Recover dirty/young flags.  It relies on pmdp_invalidate to not
	 * corrupt them.
	 */
	if (pmd_dirty(*pmd))
		entry = pmd_mkdirty(entry);
	if (pmd_young(*pmd))
		entry = pmd_mkyoung(entry);

	entry = pmd_modify(entry, newprot);
	if (preserve_write)
		entry = pmd_mk_savedwrite(entry);
	ret = HPAGE_PMD_NR;
	set_pmd_at(mm, addr, pmd, entry);
	BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
unlock:
	spin_unlock(ptl);
	return ret;
}

/*
 * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise.
 *
 * Note that if it returns page table lock pointer, this routine returns without
 * unlocking page table lock. So callers must unlock it.
 */
spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
{
	spinlock_t *ptl;
	ptl = pmd_lock(vma->vm_mm, pmd);
	if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) ||
			pmd_devmap(*pmd)))
		return ptl;
	spin_unlock(ptl);
	return NULL;
}

/*
 * Returns true if a given pud maps a thp, false otherwise.
 *
 * Note that if it returns true, this routine returns without unlocking page
 * table lock. So callers must unlock it.
 */
spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma)
{
	spinlock_t *ptl;

	ptl = pud_lock(vma->vm_mm, pud);
	if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
		return ptl;
	spin_unlock(ptl);
	return NULL;
}

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
		 pud_t *pud, unsigned long addr)
{
	pud_t orig_pud;
	spinlock_t *ptl;

	ptl = __pud_trans_huge_lock(pud, vma);
	if (!ptl)
		return 0;
	/*
	 * For architectures like ppc64 we look at deposited pgtable
	 * when calling pudp_huge_get_and_clear. So do the
	 * pgtable_trans_huge_withdraw after finishing pudp related
	 * operations.
	 */
	orig_pud = pudp_huge_get_and_clear_full(tlb->mm, addr, pud,
			tlb->fullmm);
	tlb_remove_pud_tlb_entry(tlb, pud, addr);
	if (vma_is_dax(vma)) {
		spin_unlock(ptl);
		/* No zero page support yet */
	} else {
		/* No support for anonymous PUD pages yet */
		BUG();
	}
	return 1;
}

static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
		unsigned long haddr)
{
	VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
	VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));

	count_vm_event(THP_SPLIT_PUD);

	pudp_huge_clear_flush_notify(vma, haddr, pud);
}