huge_memory.c

	ret |= VM_FAULT_WRITE;
out:
	return ret;
out_free_page:
	spin_unlock(&mm->page_table_lock);
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
	mem_cgroup_uncharge_page(page);
	put_page(page);
	goto out;
}

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)
{
	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_newpage_charge(pages[i], mm,
						       GFP_KERNEL))) {
			if (pages[i])
				put_page(pages[i]);
			mem_cgroup_uncharge_start();
			while (--i >= 0) {
				mem_cgroup_uncharge_page(pages[i]);
				put_page(pages[i]);
			}
			mem_cgroup_uncharge_end();
			kfree(pages);
			ret |= VM_FAULT_OOM;
			goto out;
		}
	}

	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);

	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(*pmd, orig_pmd)))
		goto out_free_pages;
	VM_BUG_ON(!PageHead(page));

	pmdp_clear_flush(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);
		page_add_new_anon_rmap(pages[i], vma, haddr);
		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);
	spin_unlock(&mm->page_table_lock);

	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(&mm->page_table_lock);
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
	mem_cgroup_uncharge_start();
	for (i = 0; i < HPAGE_PMD_NR; i++) {
		mem_cgroup_uncharge_page(pages[i]);
		put_page(pages[i]);
	}
	mem_cgroup_uncharge_end();
	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)
{
	int ret = 0;
	struct page *page = NULL, *new_page;
	unsigned long haddr;
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */

	VM_BUG_ON(!vma->anon_vma);
	haddr = address & HPAGE_PMD_MASK;
	if (is_huge_zero_pmd(orig_pmd))
		goto alloc;
	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(*pmd, orig_pmd)))
		goto out_unlock;

	page = pmd_page(orig_pmd);
	VM_BUG_ON(!PageCompound(page) || !PageHead(page));
	if (page_mapcount(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_page(page);
	spin_unlock(&mm->page_table_lock);
alloc:
	if (transparent_hugepage_enabled(vma) &&
	    !transparent_hugepage_debug_cow())
		new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
					      vma, haddr, numa_node_id(), 0);
	else
		new_page = NULL;

	if (unlikely(!new_page)) {
		if (is_huge_zero_pmd(orig_pmd)) {
			ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
					address, pmd, orig_pmd, haddr);
		} else {
			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
					pmd, orig_pmd, page, haddr);
			if (ret & VM_FAULT_OOM)
				split_huge_page(page);
			put_page(page);
		}
		count_vm_event(THP_FAULT_FALLBACK);
		goto out;
	}

	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
		put_page(new_page);
		if (page) {
			split_huge_page(page);
			put_page(page);
		}
		count_vm_event(THP_FAULT_FALLBACK);
		ret |= VM_FAULT_OOM;
		goto out;
	}

	count_vm_event(THP_FAULT_ALLOC);

	if (is_huge_zero_pmd(orig_pmd))
		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(&mm->page_table_lock);
	if (page)
		put_page(page);
	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
		spin_unlock(&mm->page_table_lock);
		mem_cgroup_uncharge_page(new_page);
		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_clear_flush(vma, haddr, pmd);
		page_add_new_anon_rmap(new_page, vma, haddr);
		set_pmd_at(mm, haddr, pmd, entry);
		update_mmu_cache_pmd(vma, address, pmd);
		if (is_huge_zero_pmd(orig_pmd)) {
			add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
			put_huge_zero_page();
		} else {
			VM_BUG_ON(!PageHead(page));
			page_remove_rmap(page);
			put_page(page);
		}
		ret |= VM_FAULT_WRITE;
	}
	spin_unlock(&mm->page_table_lock);
out_mn:
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out:
	return ret;
out_unlock:
	spin_unlock(&mm->page_table_lock);
	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(&mm->page_table_lock);

	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);

	page = pmd_page(*pmd);
	VM_BUG_ON(!PageHead(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(!PageCompound(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)
{
	struct page *page;
	unsigned long haddr = addr & HPAGE_PMD_MASK;
	int target_nid;
	int current_nid = -1;
	bool migrated;

	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(pmd, *pmdp)))
		goto out_unlock;

	page = pmd_page(pmd);
	get_page(page);
	current_nid = page_to_nid(page);
	count_vm_numa_event(NUMA_HINT_FAULTS);
	if (current_nid == numa_node_id())
		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);

	target_nid = mpol_misplaced(page, vma, haddr);
	if (target_nid == -1) {
		put_page(page);
		goto clear_pmdnuma;
	}

	/* Acquire the page lock to serialise THP migrations */
	spin_unlock(&mm->page_table_lock);
	lock_page(page);

	/* Confirm the PTE did not while locked */
	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(pmd, *pmdp))) {
		unlock_page(page);
		put_page(page);
		goto out_unlock;
	}
	spin_unlock(&mm->page_table_lock);

	/* Migrate the THP to the requested node */
	migrated = migrate_misplaced_transhuge_page(mm, vma,
				pmdp, pmd, addr, page, target_nid);
	if (!migrated)
		goto check_same;

	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
	return 0;

check_same:
	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(pmd, *pmdp)))
		goto out_unlock;
clear_pmdnuma:
	pmd = pmd_mknonnuma(pmd);
	set_pmd_at(mm, haddr, pmdp, pmd);
	VM_BUG_ON(pmd_numa(*pmdp));
	update_mmu_cache_pmd(vma, addr, pmdp);
out_unlock:
	spin_unlock(&mm->page_table_lock);
	if (current_nid != -1)
		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
	return 0;
}

int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
		 pmd_t *pmd, unsigned long addr)
{
	int ret = 0;

	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
		struct page *page;
		pgtable_t pgtable;
		pmd_t orig_pmd;
		/*
		 * For architectures like ppc64 we look at deposited pgtable
		 * when calling pmdp_get_and_clear. So do the
		 * pgtable_trans_huge_withdraw after finishing pmdp related
		 * operations.
		 */
		orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
		if (is_huge_zero_pmd(orig_pmd)) {
			tlb->mm->nr_ptes--;
			spin_unlock(&tlb->mm->page_table_lock);
			put_huge_zero_page();
		} else {
			page = pmd_page(orig_pmd);
			page_remove_rmap(page);
			VM_BUG_ON(page_mapcount(page) < 0);
			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
			VM_BUG_ON(!PageHead(page));
			tlb->mm->nr_ptes--;
			spin_unlock(&tlb->mm->page_table_lock);
			tlb_remove_page(tlb, page);
		}
		pte_free(tlb->mm, pgtable);
		ret = 1;
	}
	return ret;
}

int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long addr, unsigned long end,
		unsigned char *vec)
{
	int ret = 0;

	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
		/*
		 * All logical pages in the range are present
		 * if backed by a huge page.
		 */
		spin_unlock(&vma->vm_mm->page_table_lock);
		memset(vec, 1, (end - addr) >> PAGE_SHIFT);
		ret = 1;
	}

	return ret;
}

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)
{
	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;
	}

	ret = __pmd_trans_huge_lock(old_pmd, vma);
	if (ret == 1) {
		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
		VM_BUG_ON(!pmd_none(*new_pmd));
		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
		spin_unlock(&mm->page_table_lock);
	}
out:
	return ret;
}

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;
	int ret = 0;

	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
		pmd_t entry;
		entry = pmdp_get_and_clear(mm, addr, pmd);
		if (!prot_numa) {
			entry = pmd_modify(entry, newprot);
			BUG_ON(pmd_write(entry));
		} else {
			struct page *page = pmd_page(*pmd);

			/* only check non-shared pages */
			if (page_mapcount(page) == 1 &&
			    !pmd_numa(*pmd)) {
				entry = pmd_mknuma(entry);
			}
		}
		set_pmd_at(mm, addr, pmd, entry);
		spin_unlock(&vma->vm_mm->page_table_lock);
		ret = 1;
	}

	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)
{
	spin_lock(&vma->vm_mm->page_table_lock);
	if (likely(pmd_trans_huge(*pmd))) {
		if (unlikely(pmd_trans_splitting(*pmd))) {
			spin_unlock(&vma->vm_mm->page_table_lock);
			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(&vma->vm_mm->page_table_lock);
	return 0;
}

pmd_t *page_check_address_pmd(struct page *page,
			      struct mm_struct *mm,
			      unsigned long address,
			      enum page_check_address_pmd_flag flag)
{
	pmd_t *pmd, *ret = NULL;

	if (address & ~HPAGE_PMD_MASK)
		goto out;

	pmd = mm_find_pmd(mm, address);
	if (!pmd)
		goto out;
	if (pmd_none(*pmd))
		goto out;
	if (pmd_page(*pmd) != page)
		goto out;
	/*
	 * 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 out;
	if (pmd_trans_huge(*pmd)) {
		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
			  !pmd_trans_splitting(*pmd));
		ret = pmd;
	}
out:
	return ret;
}

static int __split_huge_page_splitting(struct page *page,
				       struct vm_area_struct *vma,
				       unsigned long address)
{
	struct mm_struct *mm = vma->vm_mm;
	pmd_t *pmd;
	int ret = 0;
	/* For mmu_notifiers */
	const unsigned long mmun_start = address;
	const unsigned long mmun_end   = address + HPAGE_PMD_SIZE;

	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
	spin_lock(&mm->page_table_lock);
	pmd = page_check_address_pmd(page, mm, address,
				     PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG);
	if (pmd) {
		/*
		 * We can't temporarily set the pmd to null in order
		 * to split it, the pmd must remain marked huge at all
		 * times or the VM won't take the pmd_trans_huge paths
		 * and it won't wait on the anon_vma->root->rwsem to
		 * serialize against split_huge_page*.
		 */
		pmdp_splitting_flush(vma, address, pmd);
		ret = 1;
	}
	spin_unlock(&mm->page_table_lock);
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

	return ret;
}

static void __split_huge_page_refcount(struct page *page,
				       struct list_head *list)
{
	int i;
	struct zone *zone = page_zone(page);
	struct lruvec *lruvec;
	int tail_count = 0;

	/* prevent PageLRU to go away from under us, and freeze lru stats */
	spin_lock_irq(&zone->lru_lock);
	lruvec = mem_cgroup_page_lruvec(page, zone);

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

	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
		struct page *page_tail = page + i;

		/* tail_page->_mapcount cannot change */
		BUG_ON(page_mapcount(page_tail) < 0);
		tail_count += page_mapcount(page_tail);
		/* check for overflow */
		BUG_ON(tail_count < 0);
		BUG_ON(atomic_read(&page_tail->_count) != 0);
		/*
		 * tail_page->_count is zero and not changing from
		 * under us. But get_page_unless_zero() may be running
		 * from under us on the tail_page. If we used
		 * atomic_set() below instead of atomic_add(), we
		 * would then run atomic_set() concurrently with
		 * get_page_unless_zero(), and atomic_set() is
		 * implemented in C not using locked ops. spin_unlock
		 * on x86 sometime uses locked ops because of PPro
		 * errata 66, 92, so unless somebody can guarantee
		 * atomic_set() here would be safe on all archs (and
		 * not only on x86), it's safer to use atomic_add().
		 */
		atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1,
			   &page_tail->_count);

		/* after clearing PageTail the gup refcount can be released */
		smp_mb();

		/*
		 * retain hwpoison flag of the poisoned tail page:
		 *   fix for the unsuitable process killed on Guest Machine(KVM)
		 *   by the memory-failure.
		 */
		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;
		page_tail->flags |= (page->flags &
				     ((1L << PG_referenced) |
				      (1L << PG_swapbacked) |
				      (1L << PG_mlocked) |
				      (1L << PG_uptodate) |
				      (1L << PG_active) |
				      (1L << PG_unevictable)));
		page_tail->flags |= (1L << PG_dirty);

		/* clear PageTail before overwriting first_page */
		smp_wmb();

		/*
		 * __split_huge_page_splitting() already set the
		 * splitting bit in all pmd that could map this
		 * hugepage, that will ensure no CPU can alter the
		 * mapcount on the head page. The mapcount is only
		 * accounted in the head page and it has to be
		 * transferred to all tail pages in the below code. So
		 * for this code to be safe, the split the mapcount
		 * can't change. But that doesn't mean userland can't
		 * keep changing and reading the page contents while
		 * we transfer the mapcount, so the pmd splitting
		 * status is achieved setting a reserved bit in the
		 * pmd, not by clearing the present bit.
		*/
		page_tail->_mapcount = page->_mapcount;

		BUG_ON(page_tail->mapping);
		page_tail->mapping = page->mapping;

		page_tail->index = page->index + i;
		page_nid_xchg_last(page_tail, page_nid_last(page));

		BUG_ON(!PageAnon(page_tail));
		BUG_ON(!PageUptodate(page_tail));
		BUG_ON(!PageDirty(page_tail));
		BUG_ON(!PageSwapBacked(page_tail));

		lru_add_page_tail(page, page_tail, lruvec, list);
	}
	atomic_sub(tail_count, &page->_count);
	BUG_ON(atomic_read(&page->_count) <= 0);

	__mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1);

	ClearPageCompound(page);
	compound_unlock(page);
	spin_unlock_irq(&zone->lru_lock);

	for (i = 1; i < HPAGE_PMD_NR; i++) {
		struct page *page_tail = page + i;
		BUG_ON(page_count(page_tail) <= 0);
		/*
		 * Tail pages 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(page_tail);
	}

	/*
	 * Only the head page (now become a regular page) is required
	 * to be pinned by the caller.
	 */
	BUG_ON(page_count(page) <= 0);
}

static int __split_huge_page_map(struct page *page,
				 struct vm_area_struct *vma,
				 unsigned long address)
{
	struct mm_struct *mm = vma->vm_mm;
	pmd_t *pmd, _pmd;
	int ret = 0, i;
	pgtable_t pgtable;
	unsigned long haddr;

	spin_lock(&mm->page_table_lock);
	pmd = page_check_address_pmd(page, mm, address,
				     PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
	if (pmd) {
		pgtable = pgtable_trans_huge_withdraw(mm, pmd);
		pmd_populate(mm, &_pmd, pgtable);

		haddr = address;
		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
			pte_t *pte, entry;
			BUG_ON(PageCompound(page+i));
			entry = mk_pte(page + i, vma->vm_page_prot);
			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
			if (!pmd_write(*pmd))
				entry = pte_wrprotect(entry);
			else
				BUG_ON(page_mapcount(page) != 1);
			if (!pmd_young(*pmd))
				entry = pte_mkold(entry);
			if (pmd_numa(*pmd))
				entry = pte_mknuma(entry);
			pte = pte_offset_map(&_pmd, haddr);
			BUG_ON(!pte_none(*pte));
			set_pte_at(mm, haddr, pte, entry);
			pte_unmap(pte);
		}

		smp_wmb(); /* make pte visible before 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_tlb_range();" we first
		 * mark the current pmd notpresent (atomically because
		 * here the pmd_trans_huge and pmd_trans_splitting
		 * 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.
		 */
		pmdp_invalidate(vma, address, pmd);
		pmd_populate(mm, pmd, pgtable);
		ret = 1;
	}
	spin_unlock(&mm->page_table_lock);

	return ret;
}

/* must be called with anon_vma->root->rwsem held */
static void __split_huge_page(struct page *page,
			      struct anon_vma *anon_vma,
			      struct list_head *list)
{
	int mapcount, mapcount2;
	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
	struct anon_vma_chain *avc;

	BUG_ON(!PageHead(page));
	BUG_ON(PageTail(page));

	mapcount = 0;
	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
		struct vm_area_struct *vma = avc->vma;
		unsigned long addr = vma_address(page, vma);
		BUG_ON(is_vma_temporary_stack(vma));
		mapcount += __split_huge_page_splitting(page, vma, addr);
	}
	/*
	 * It is critical that new vmas are added to the tail of the
	 * anon_vma list. This guarantes that if copy_huge_pmd() runs
	 * and establishes a child pmd before
	 * __split_huge_page_splitting() freezes the parent pmd (so if
	 * we fail to prevent copy_huge_pmd() from running until the
	 * whole __split_huge_page() is complete), we will still see
	 * the newly established pmd of the child later during the
	 * walk, to be able to set it as pmd_trans_splitting too.
	 */
	if (mapcount != page_mapcount(page))
		printk(KERN_ERR "mapcount %d page_mapcount %d\n",
		       mapcount, page_mapcount(page));
	BUG_ON(mapcount != page_mapcount(page));

	__split_huge_page_refcount(page, list);

	mapcount2 = 0;
	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
		struct vm_area_struct *vma = avc->vma;
		unsigned long addr = vma_address(page, vma);
		BUG_ON(is_vma_temporary_stack(vma));
		mapcount2 += __split_huge_page_map(page, vma, addr);
	}
	if (mapcount != mapcount2)
		printk(KERN_ERR "mapcount %d mapcount2 %d page_mapcount %d\n",
		       mapcount, mapcount2, page_mapcount(page));
	BUG_ON(mapcount != mapcount2);
}

/*
 * Split a hugepage into normal pages. This doesn't change the position of head
 * page. 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.
 * Return 0 if the hugepage is split successfully otherwise return 1.
 */
int split_huge_page_to_list(struct page *page, struct list_head *list)
{
	struct anon_vma *anon_vma;
	int ret = 1;

	BUG_ON(is_huge_zero_page(page));
	BUG_ON(!PageAnon(page));

	/*
	 * 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(page);
	if (!anon_vma)
		goto out;
	anon_vma_lock_write(anon_vma);

	ret = 0;
	if (!PageCompound(page))
		goto out_unlock;

	BUG_ON(!PageSwapBacked(page));
	__split_huge_page(page, anon_vma, list);
	count_vm_event(THP_SPLIT);

	BUG_ON(PageCompound(page));
out_unlock:
	anon_vma_unlock_write(anon_vma);
	put_anon_vma(anon_vma);
out:
	return ret;
}

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

int hugepage_madvise(struct vm_area_struct *vma,
		     unsigned long *vm_flags, int advice)
{
	struct mm_struct *mm = vma->vm_mm;

	switch (advice) {
	case MADV_HUGEPAGE:
		/*
		 * Be somewhat over-protective like KSM for now!
		 */
		if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP))
			return -EINVAL;
		if (mm->def_flags & VM_NOHUGEPAGE)
			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)))
			return -ENOMEM;
		break;
	case MADV_NOHUGEPAGE:
		/*
		 * Be somewhat over-protective like KSM for now!
		 */
		if (*vm_flags & (VM_NOHUGEPAGE | 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 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(khugepaged_test_exit(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 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);
	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
	hend = vma->vm_end & HPAGE_PMD_MASK;
	if (hstart < hend)
		return khugepaged_enter(vma);
	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) {