huge_memory.c

/*
 * 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)
{
	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.
	 */
	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);
}

void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
		unsigned long address)
{
	spinlock_t *ptl;
	struct mmu_notifier_range range;

	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
				address & HPAGE_PUD_MASK,
				(address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE);
	mmu_notifier_invalidate_range_start(&range);
	ptl = pud_lock(vma->vm_mm, pud);
	if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
		goto out;
	__split_huge_pud_locked(vma, pud, range.start);

out:
	spin_unlock(ptl);
	/*
	 * No need to double call mmu_notifier->invalidate_range() callback as
	 * the above pudp_huge_clear_flush_notify() did already call it.
	 */
	mmu_notifier_invalidate_range_only_end(&range);
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
		unsigned long haddr, pmd_t *pmd)
{
	struct mm_struct *mm = vma->vm_mm;
	pgtable_t pgtable;
	pmd_t _pmd;
	int i;

	/*
	 * Leave pmd empty until pte is filled note that it is fine to delay
	 * notification until mmu_notifier_invalidate_range_end() as we are
	 * replacing a zero pmd write protected page with a zero pte write
	 * protected page.
	 *
	 * See Documentation/vm/mmu_notifier.rst
	 */
	pmdp_huge_clear_flush(vma, haddr, pmd);

	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 = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
		entry = pte_mkspecial(entry);
		pte = pte_offset_map(&_pmd, haddr);
		VM_BUG_ON(!pte_none(*pte));
		set_pte_at(mm, haddr, pte, entry);
		pte_unmap(pte);
	}
	smp_wmb(); /* make pte visible before pmd */
	pmd_populate(mm, pmd, pgtable);
}

static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long haddr, bool freeze)
{
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	pgtable_t pgtable;
	pmd_t old_pmd, _pmd;
	bool young, write, soft_dirty, pmd_migration = false;
	unsigned long addr;
	int i;

	VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
	VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd)
				&& !pmd_devmap(*pmd));

	count_vm_event(THP_SPLIT_PMD);

	if (!vma_is_anonymous(vma)) {
		_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
		/*
		 * We are going to unmap this huge page. So
		 * just go ahead and zap it
		 */
		if (arch_needs_pgtable_deposit())
			zap_deposited_table(mm, pmd);
		if (vma_is_dax(vma))
			return;
		page = pmd_page(_pmd);
		if (!PageDirty(page) && pmd_dirty(_pmd))
			set_page_dirty(page);
		if (!PageReferenced(page) && pmd_young(_pmd))
			SetPageReferenced(page);
		page_remove_rmap(page, true);
		put_page(page);
		add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
		return;
	} else if (is_huge_zero_pmd(*pmd)) {
		/*
		 * FIXME: Do we want to invalidate secondary mmu by calling
		 * mmu_notifier_invalidate_range() see comments below inside
		 * __split_huge_pmd() ?
		 *
		 * We are going from a zero huge page write protected to zero
		 * small page also write protected so it does not seems useful
		 * to invalidate secondary mmu at this time.
		 */
		return __split_huge_zero_page_pmd(vma, haddr, pmd);
	}

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

	pmd_migration = is_pmd_migration_entry(old_pmd);
	if (unlikely(pmd_migration)) {
		swp_entry_t entry;

		entry = pmd_to_swp_entry(old_pmd);
		page = pfn_to_page(swp_offset(entry));
		write = is_write_migration_entry(entry);
		young = false;
		soft_dirty = pmd_swp_soft_dirty(old_pmd);
	} else {
		page = pmd_page(old_pmd);
		if (pmd_dirty(old_pmd))
			SetPageDirty(page);
		write = pmd_write(old_pmd);
		young = pmd_young(old_pmd);
		soft_dirty = pmd_soft_dirty(old_pmd);
	}
	VM_BUG_ON_PAGE(!page_count(page), page);
	page_ref_add(page, HPAGE_PMD_NR - 1);

	/*
	 * Withdraw the table only after we mark the pmd entry invalid.
	 * This's critical for some architectures (Power).
	 */
	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
	pmd_populate(mm, &_pmd, pgtable);

	for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
		pte_t entry, *pte;
		/*
		 * Note that NUMA hinting access restrictions are not
		 * transferred to avoid any possibility of altering
		 * permissions across VMAs.
		 */
		if (freeze || pmd_migration) {
			swp_entry_t swp_entry;
			swp_entry = make_migration_entry(page + i, write);
			entry = swp_entry_to_pte(swp_entry);
			if (soft_dirty)
				entry = pte_swp_mksoft_dirty(entry);
		} else {
			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
			entry = maybe_mkwrite(entry, vma);
			if (!write)
				entry = pte_wrprotect(entry);
			if (!young)
				entry = pte_mkold(entry);
			if (soft_dirty)
				entry = pte_mksoft_dirty(entry);
		}
		pte = pte_offset_map(&_pmd, addr);
		BUG_ON(!pte_none(*pte));
		set_pte_at(mm, addr, pte, entry);
		atomic_inc(&page[i]._mapcount);
		pte_unmap(pte);
	}

	/*
	 * Set PG_double_map before dropping compound_mapcount to avoid
	 * false-negative page_mapped().
	 */
	if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
		for (i = 0; i < HPAGE_PMD_NR; i++)
			atomic_inc(&page[i]._mapcount);
	}

	if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
		/* Last compound_mapcount is gone. */
		__dec_node_page_state(page, NR_ANON_THPS);
		if (TestClearPageDoubleMap(page)) {
			/* No need in mapcount reference anymore */
			for (i = 0; i < HPAGE_PMD_NR; i++)
				atomic_dec(&page[i]._mapcount);
		}
	}

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

	if (freeze) {
		for (i = 0; i < HPAGE_PMD_NR; i++) {
			page_remove_rmap(page + i, false);
			put_page(page + i);
		}
	}
}

void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long address, bool freeze, struct page *page)
{
	spinlock_t *ptl;
	struct mmu_notifier_range range;

	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
				address & HPAGE_PMD_MASK,
				(address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE);
	mmu_notifier_invalidate_range_start(&range);
	ptl = pmd_lock(vma->vm_mm, pmd);

	/*
	 * If caller asks to setup a migration entries, we need a page to check
	 * pmd against. Otherwise we can end up replacing wrong page.
	 */
	VM_BUG_ON(freeze && !page);
	if (page && page != pmd_page(*pmd))
	        goto out;

	if (pmd_trans_huge(*pmd)) {
		page = pmd_page(*pmd);
		if (PageMlocked(page))
			clear_page_mlock(page);
	} else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
		goto out;
	__split_huge_pmd_locked(vma, pmd, range.start, freeze);
out:
	spin_unlock(ptl);
	/*
	 * No need to double call mmu_notifier->invalidate_range() callback.
	 * They are 3 cases to consider inside __split_huge_pmd_locked():
	 *  1) pmdp_huge_clear_flush_notify() call invalidate_range() obvious
	 *  2) __split_huge_zero_page_pmd() read only zero page and any write
	 *    fault will trigger a flush_notify before pointing to a new page
	 *    (it is fine if the secondary mmu keeps pointing to the old zero
	 *    page in the meantime)
	 *  3) Split a huge pmd into pte pointing to the same page. No need
	 *     to invalidate secondary tlb entry they are all still valid.
	 *     any further changes to individual pte will notify. So no need
	 *     to call mmu_notifier->invalidate_range()
	 */
	mmu_notifier_invalidate_range_only_end(&range);
}

void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
		bool freeze, struct page *page)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;

	pgd = pgd_offset(vma->vm_mm, address);
	if (!pgd_present(*pgd))
		return;

	p4d = p4d_offset(pgd, address);
	if (!p4d_present(*p4d))
		return;

	pud = pud_offset(p4d, address);
	if (!pud_present(*pud))
		return;

	pmd = pmd_offset(pud, address);

	__split_huge_pmd(vma, pmd, address, freeze, page);
}

void vma_adjust_trans_huge(struct vm_area_struct *vma,
			     unsigned long start,
			     unsigned long end,
			     long adjust_next)
{
	/*
	 * If the new start address isn't hpage aligned and it could
	 * previously contain an hugepage: check if we need to split
	 * an huge pmd.
	 */
	if (start & ~HPAGE_PMD_MASK &&
	    (start & HPAGE_PMD_MASK) >= vma->vm_start &&
	    (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
		split_huge_pmd_address(vma, start, false, NULL);

	/*
	 * If the new end address isn't hpage aligned and it could
	 * previously contain an hugepage: check if we need to split
	 * an huge pmd.
	 */
	if (end & ~HPAGE_PMD_MASK &&
	    (end & HPAGE_PMD_MASK) >= vma->vm_start &&
	    (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
		split_huge_pmd_address(vma, end, false, NULL);

	/*
	 * If we're also updating the vma->vm_next->vm_start, if the new
	 * vm_next->vm_start isn't page aligned and it could previously
	 * contain an hugepage: check if we need to split an huge pmd.
	 */
	if (adjust_next > 0) {
		struct vm_area_struct *next = vma->vm_next;
		unsigned long nstart = next->vm_start;
		nstart += adjust_next << PAGE_SHIFT;
		if (nstart & ~HPAGE_PMD_MASK &&
		    (nstart & HPAGE_PMD_MASK) >= next->vm_start &&
		    (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end)
			split_huge_pmd_address(next, nstart, false, NULL);
	}
}

static void unmap_page(struct page *page)
{
	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
	bool unmap_success;

	VM_BUG_ON_PAGE(!PageHead(page), page);

	if (PageAnon(page))
		ttu_flags |= TTU_SPLIT_FREEZE;

	unmap_success = try_to_unmap(page, ttu_flags);
	VM_BUG_ON_PAGE(!unmap_success, page);
}

static void remap_page(struct page *page)
{
	int i;
	if (PageTransHuge(page)) {
		remove_migration_ptes(page, page, true);
	} else {
		for (i = 0; i < HPAGE_PMD_NR; i++)
			remove_migration_ptes(page + i, page + i, true);
	}
}

static void __split_huge_page_tail(struct page *head, int tail,
		struct lruvec *lruvec, struct list_head *list)
{
	struct page *page_tail = head + tail;

	VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);

	/*
	 * Clone page flags before unfreezing refcount.
	 *
	 * After successful get_page_unless_zero() might follow flags change,
	 * for exmaple lock_page() which set PG_waiters.
	 */
	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
	page_tail->flags |= (head->flags &
			((1L << PG_referenced) |
			 (1L << PG_swapbacked) |
			 (1L << PG_swapcache) |
			 (1L << PG_mlocked) |
			 (1L << PG_uptodate) |
			 (1L << PG_active) |
			 (1L << PG_workingset) |
			 (1L << PG_locked) |
			 (1L << PG_unevictable) |
			 (1L << PG_dirty)));

	/* ->mapping in first tail page is compound_mapcount */
	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
			page_tail);
	page_tail->mapping = head->mapping;
	page_tail->index = head->index + tail;

	/* Page flags must be visible before we make the page non-compound. */
	smp_wmb();

	/*
	 * Clear PageTail before unfreezing page refcount.
	 *
	 * After successful get_page_unless_zero() might follow put_page()
	 * which needs correct compound_head().
	 */
	clear_compound_head(page_tail);

	/* Finally unfreeze refcount. Additional reference from page cache. */
	page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) ||
					  PageSwapCache(head)));

	if (page_is_young(head))
		set_page_young(page_tail);
	if (page_is_idle(head))
		set_page_idle(page_tail);

	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));

	/*
	 * always add to the tail because some iterators expect new
	 * pages to show after the currently processed elements - e.g.
	 * migrate_pages
	 */
	lru_add_page_tail(head, page_tail, lruvec, list);
}

static void __split_huge_page(struct page *page, struct list_head *list,
		pgoff_t end, unsigned long flags)
{
	struct page *head = compound_head(page);
	pg_data_t *pgdat = page_pgdat(head);
	struct lruvec *lruvec;
	int i;

	lruvec = mem_cgroup_page_lruvec(head, pgdat);

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

	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
		__split_huge_page_tail(head, i, lruvec, list);
		/* Some pages can be beyond i_size: drop them from page cache */
		if (head[i].index >= end) {
			ClearPageDirty(head + i);
			__delete_from_page_cache(head + i, NULL);
			if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
				shmem_uncharge(head->mapping->host, 1);
			put_page(head + i);
		}
	}

	ClearPageCompound(head);
	/* See comment in __split_huge_page_tail() */
	if (PageAnon(head)) {
		/* Additional pin to swap cache */
		if (PageSwapCache(head))
			page_ref_add(head, 2);
		else
			page_ref_inc(head);
	} else {
		/* Additional pin to page cache */
		page_ref_add(head, 2);
		xa_unlock(&head->mapping->i_pages);
	}

	spin_unlock_irqrestore(&pgdat->lru_lock, flags);

	remap_page(head);

	for (i = 0; i < HPAGE_PMD_NR; i++) {
		struct page *subpage = head + i;
		if (subpage == page)
			continue;
		unlock_page(subpage);

		/*
		 * Subpages may be freed if there wasn't any mapping
		 * like if add_to_swap() is running on a lru page that
		 * had its mapping zapped. And freeing these pages
		 * requires taking the lru_lock so we do the put_page
		 * of the tail pages after the split is complete.
		 */
		put_page(subpage);
	}
}

int total_mapcount(struct page *page)
{
	int i, compound, ret;

	VM_BUG_ON_PAGE(PageTail(page), page);

	if (likely(!PageCompound(page)))
		return atomic_read(&page->_mapcount) + 1;

	compound = compound_mapcount(page);
	if (PageHuge(page))
		return compound;
	ret = compound;
	for (i = 0; i < HPAGE_PMD_NR; i++)
		ret += atomic_read(&page[i]._mapcount) + 1;
	/* File pages has compound_mapcount included in _mapcount */
	if (!PageAnon(page))
		return ret - compound * HPAGE_PMD_NR;
	if (PageDoubleMap(page))
		ret -= HPAGE_PMD_NR;
	return ret;
}

/*
 * This calculates accurately how many mappings a transparent hugepage
 * has (unlike page_mapcount() which isn't fully accurate). This full
 * accuracy is primarily needed to know if copy-on-write faults can
 * reuse the page and change the mapping to read-write instead of
 * copying them. At the same time this returns the total_mapcount too.
 *
 * The function returns the highest mapcount any one of the subpages
 * has. If the return value is one, even if different processes are
 * mapping different subpages of the transparent hugepage, they can
 * all reuse it, because each process is reusing a different subpage.
 *
 * The total_mapcount is instead counting all virtual mappings of the
 * subpages. If the total_mapcount is equal to "one", it tells the
 * caller all mappings belong to the same "mm" and in turn the
 * anon_vma of the transparent hugepage can become the vma->anon_vma
 * local one as no other process may be mapping any of the subpages.
 *
 * It would be more accurate to replace page_mapcount() with
 * page_trans_huge_mapcount(), however we only use
 * page_trans_huge_mapcount() in the copy-on-write faults where we
 * need full accuracy to avoid breaking page pinning, because
 * page_trans_huge_mapcount() is slower than page_mapcount().
 */
int page_trans_huge_mapcount(struct page *page, int *total_mapcount)
{
	int i, ret, _total_mapcount, mapcount;

	/* hugetlbfs shouldn't call it */
	VM_BUG_ON_PAGE(PageHuge(page), page);

	if (likely(!PageTransCompound(page))) {
		mapcount = atomic_read(&page->_mapcount) + 1;
		if (total_mapcount)
			*total_mapcount = mapcount;
		return mapcount;
	}

	page = compound_head(page);

	_total_mapcount = ret = 0;
	for (i = 0; i < HPAGE_PMD_NR; i++) {
		mapcount = atomic_read(&page[i]._mapcount) + 1;
		ret = max(ret, mapcount);
		_total_mapcount += mapcount;
	}
	if (PageDoubleMap(page)) {
		ret -= 1;
		_total_mapcount -= HPAGE_PMD_NR;
	}
	mapcount = compound_mapcount(page);
	ret += mapcount;
	_total_mapcount += mapcount;
	if (total_mapcount)
		*total_mapcount = _total_mapcount;
	return ret;
}

/* Racy check whether the huge page can be split */
bool can_split_huge_page(struct page *page, int *pextra_pins)
{
	int extra_pins;

	/* Additional pins from page cache */
	if (PageAnon(page))
		extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0;
	else
		extra_pins = HPAGE_PMD_NR;
	if (pextra_pins)
		*pextra_pins = extra_pins;
	return total_mapcount(page) == page_count(page) - extra_pins - 1;
}

/*
 * This function splits huge page into normal pages. @page can point to any
 * subpage of huge page to split. Split doesn't change the position of @page.
 *
 * Only caller must hold pin on the @page, otherwise split fails with -EBUSY.
 * The huge page must be locked.
 *
 * If @list is null, tail pages will be added to LRU list, otherwise, to @list.
 *
 * Both head page and tail pages will inherit mapping, flags, and so on from
 * the hugepage.
 *
 * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if
 * they are not mapped.
 *
 * Returns 0 if the hugepage is split successfully.
 * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under
 * us.
 */
int split_huge_page_to_list(struct page *page, struct list_head *list)
{
	struct page *head = compound_head(page);
	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
	struct anon_vma *anon_vma = NULL;
	struct address_space *mapping = NULL;
	int count, mapcount, extra_pins, ret;
	bool mlocked;
	unsigned long flags;
	pgoff_t end;

	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
	VM_BUG_ON_PAGE(!PageLocked(page), page);
	VM_BUG_ON_PAGE(!PageCompound(page), page);

	if (PageWriteback(page))
		return -EBUSY;

	if (PageAnon(head)) {
		/*
		 * The caller does not necessarily hold an mmap_sem that would
		 * prevent the anon_vma disappearing so we first we take a
		 * reference to it and then lock the anon_vma for write. This
		 * is similar to page_lock_anon_vma_read except the write lock
		 * is taken to serialise against parallel split or collapse
		 * operations.
		 */
		anon_vma = page_get_anon_vma(head);
		if (!anon_vma) {
			ret = -EBUSY;
			goto out;
		}
		end = -1;
		mapping = NULL;
		anon_vma_lock_write(anon_vma);
	} else {
		mapping = head->mapping;

		/* Truncated ? */
		if (!mapping) {
			ret = -EBUSY;
			goto out;
		}

		anon_vma = NULL;
		i_mmap_lock_read(mapping);

		/*
		 *__split_huge_page() may need to trim off pages beyond EOF:
		 * but on 32-bit, i_size_read() takes an irq-unsafe seqlock,
		 * which cannot be nested inside the page tree lock. So note
		 * end now: i_size itself may be changed at any moment, but
		 * head page lock is good enough to serialize the trimming.
		 */
		end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
	}

	/*
	 * Racy check if we can split the page, before unmap_page() will
	 * split PMDs
	 */
	if (!can_split_huge_page(head, &extra_pins)) {
		ret = -EBUSY;
		goto out_unlock;
	}

	mlocked = PageMlocked(page);
	unmap_page(head);
	VM_BUG_ON_PAGE(compound_mapcount(head), head);

	/* Make sure the page is not on per-CPU pagevec as it takes pin */
	if (mlocked)
		lru_add_drain();

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

	if (mapping) {
		XA_STATE(xas, &mapping->i_pages, page_index(head));

		/*
		 * Check if the head page is present in page cache.
		 * We assume all tail are present too, if head is there.
		 */
		xa_lock(&mapping->i_pages);
		if (xas_load(&xas) != head)
			goto fail;
	}

	/* Prevent deferred_split_scan() touching ->_refcount */
	spin_lock(&pgdata->split_queue_lock);
	count = page_count(head);
	mapcount = total_mapcount(head);
	if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
		if (!list_empty(page_deferred_list(head))) {
			pgdata->split_queue_len--;
			list_del(page_deferred_list(head));
		}
		if (mapping)
			__dec_node_page_state(page, NR_SHMEM_THPS);
		spin_unlock(&pgdata->split_queue_lock);
		__split_huge_page(page, list, end, flags);
		if (PageSwapCache(head)) {
			swp_entry_t entry = { .val = page_private(head) };

			ret = split_swap_cluster(entry);
		} else
			ret = 0;
	} else {
		if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
			pr_alert("total_mapcount: %u, page_count(): %u\n",
					mapcount, count);
			if (PageTail(page))
				dump_page(head, NULL);
			dump_page(page, "total_mapcount(head) > 0");
			BUG();
		}
		spin_unlock(&pgdata->split_queue_lock);
fail:		if (mapping)
			xa_unlock(&mapping->i_pages);
		spin_unlock_irqrestore(&pgdata->lru_lock, flags);
		remap_page(head);
		ret = -EBUSY;
	}

out_unlock:
	if (anon_vma) {
		anon_vma_unlock_write(anon_vma);
		put_anon_vma(anon_vma);
	}
	if (mapping)
		i_mmap_unlock_read(mapping);
out:
	count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);
	return ret;
}

void free_transhuge_page(struct page *page)
{
	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
	unsigned long flags;

	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
	if (!list_empty(page_deferred_list(page))) {
		pgdata->split_queue_len--;
		list_del(page_deferred_list(page));
	}
	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
	free_compound_page(page);
}

void deferred_split_huge_page(struct page *page)
{
	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
	unsigned long flags;

	VM_BUG_ON_PAGE(!PageTransHuge(page), page);

	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
	if (list_empty(page_deferred_list(page))) {
		count_vm_event(THP_DEFERRED_SPLIT_PAGE);
		list_add_tail(page_deferred_list(page), &pgdata->split_queue);
		pgdata->split_queue_len++;
	}
	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
}

static unsigned long deferred_split_count(struct shrinker *shrink,
		struct shrink_control *sc)
{
	struct pglist_data *pgdata = NODE_DATA(sc->nid);
	return READ_ONCE(pgdata->split_queue_len);
}

static unsigned long deferred_split_scan(struct shrinker *shrink,
		struct shrink_control *sc)
{
	struct pglist_data *pgdata = NODE_DATA(sc->nid);
	unsigned long flags;
	LIST_HEAD(list), *pos, *next;
	struct page *page;
	int split = 0;

	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
	/* Take pin on all head pages to avoid freeing them under us */
	list_for_each_safe(pos, next, &pgdata->split_queue) {
		page = list_entry((void *)pos, struct page, mapping);
		page = compound_head(page);
		if (get_page_unless_zero(page)) {
			list_move(page_deferred_list(page), &list);
		} else {
			/* We lost race with put_compound_page() */
			list_del_init(page_deferred_list(page));
			pgdata->split_queue_len--;
		}
		if (!--sc->nr_to_scan)
			break;
	}
	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);

	list_for_each_safe(pos, next, &list) {
		page = list_entry((void *)pos, struct page, mapping);
		if (!trylock_page(page))
			goto next;
		/* split_huge_page() removes page from list on success */
		if (!split_huge_page(page))
			split++;
		unlock_page(page);
next:
		put_page(page);
	}

	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
	list_splice_tail(&list, &pgdata->split_queue);
	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);

	/*
	 * Stop shrinker if we didn't split any page, but the queue is empty.
	 * This can happen if pages were freed under us.
	 */
	if (!split && list_empty(&pgdata->split_queue))
		return SHRINK_STOP;
	return split;
}

static struct shrinker deferred_split_shrinker = {
	.count_objects = deferred_split_count,
	.scan_objects = deferred_split_scan,
	.seeks = DEFAULT_SEEKS,
	.flags = SHRINKER_NUMA_AWARE,
};

#ifdef CONFIG_DEBUG_FS
static int split_huge_pages_set(void *data, u64 val)
{
	struct zone *zone;
	struct page *page;
	unsigned long pfn, max_zone_pfn;
	unsigned long total = 0, split = 0;

	if (val != 1)
		return -EINVAL;

	for_each_populated_zone(zone) {
		max_zone_pfn = zone_end_pfn(zone);
		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
			if (!pfn_valid(pfn))
				continue;

			page = pfn_to_page(pfn);
			if (!get_page_unless_zero(page))
				continue;

			if (zone != page_zone(page))
				goto next;

			if (!PageHead(page) || PageHuge(page) || !PageLRU(page))
				goto next;

			total++;
			lock_page(page);
			if (!split_huge_page(page))
				split++;
			unlock_page(page);
next:
			put_page(page);
		}
	}

	pr_info("%lu of %lu THP split\n", split, total);

	return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set,
		"%llu\n");

static int __init split_huge_pages_debugfs(void)
{
	debugfs_create_file("split_huge_pages", 0200, NULL, NULL,
			    &split_huge_pages_fops);
	return 0;
}
late_initcall(split_huge_pages_debugfs);
#endif

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
		struct page *page)
{
	struct vm_area_struct *vma = pvmw->vma;
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address = pvmw->address;
	pmd_t pmdval;
	swp_entry_t entry;
	pmd_t pmdswp;

	if (!(pvmw->pmd && !pvmw->pte))
		return;

	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
	pmdval = *pvmw->pmd;
	pmdp_invalidate(vma, address, pvmw->pmd);
	if (pmd_dirty(pmdval))
		set_page_dirty(page);
	entry = make_migration_entry(page, pmd_write(pmdval));
	pmdswp = swp_entry_to_pmd(entry);
	if (pmd_soft_dirty(pmdval))
		pmdswp = pmd_swp_mksoft_dirty(pmdswp);
	set_pmd_at(mm, address, pvmw->pmd, pmdswp);
	page_remove_rmap(page, true);
	put_page(page);
}

void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
{
	struct vm_area_struct *vma = pvmw->vma;
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address = pvmw->address;
	unsigned long mmun_start = address & HPAGE_PMD_MASK;
	pmd_t pmde;
	swp_entry_t entry;

	if (!(pvmw->pmd && !pvmw->pte))
		return;

	entry = pmd_to_swp_entry(*pvmw->pmd);
	get_page(new);
	pmde = pmd_mkold(mk_huge_pmd(new, vma->vm_page_prot));
	if (pmd_swp_soft_dirty(*pvmw->pmd))
		pmde = pmd_mksoft_dirty(pmde);
	if (is_write_migration_entry(entry))
		pmde = maybe_pmd_mkwrite(pmde, vma);