migrate.c

	else if (unlikely(__is_movable_balloon_page(newpage))) {
		/* drop our reference, page already in the balloon */
		put_page(newpage);
	} else
		putback_lru_page(newpage);

	if (result) {
		if (rc)
			*result = rc;
		else
			*result = page_to_nid(newpage);
	}
	return rc;
}

/*
 * Counterpart of unmap_and_move_page() for hugepage migration.
 *
 * This function doesn't wait the completion of hugepage I/O
 * because there is no race between I/O and migration for hugepage.
 * Note that currently hugepage I/O occurs only in direct I/O
 * where no lock is held and PG_writeback is irrelevant,
 * and writeback status of all subpages are counted in the reference
 * count of the head page (i.e. if all subpages of a 2MB hugepage are
 * under direct I/O, the reference of the head page is 512 and a bit more.)
 * This means that when we try to migrate hugepage whose subpages are
 * doing direct I/O, some references remain after try_to_unmap() and
 * hugepage migration fails without data corruption.
 *
 * There is also no race when direct I/O is issued on the page under migration,
 * because then pte is replaced with migration swap entry and direct I/O code
 * will wait in the page fault for migration to complete.
 */
static int unmap_and_move_huge_page(new_page_t get_new_page,
				free_page_t put_new_page, unsigned long private,
				struct page *hpage, int force,
				enum migrate_mode mode, int reason)
{
	int rc = -EAGAIN;
	int *result = NULL;
	int page_was_mapped = 0;
	struct page *new_hpage;
	struct anon_vma *anon_vma = NULL;

	/*
	 * Movability of hugepages depends on architectures and hugepage size.
	 * This check is necessary because some callers of hugepage migration
	 * like soft offline and memory hotremove don't walk through page
	 * tables or check whether the hugepage is pmd-based or not before
	 * kicking migration.
	 */
	if (!hugepage_migration_supported(page_hstate(hpage))) {
		putback_active_hugepage(hpage);
		return -ENOSYS;
	}

	new_hpage = get_new_page(hpage, private, &result);
	if (!new_hpage)
		return -ENOMEM;

	if (!trylock_page(hpage)) {
		if (!force || mode != MIGRATE_SYNC)
			goto out;
		lock_page(hpage);
	}

	if (PageAnon(hpage))
		anon_vma = page_get_anon_vma(hpage);

	if (unlikely(!trylock_page(new_hpage)))
		goto put_anon;

	if (page_mapped(hpage)) {
		try_to_unmap(hpage,
			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
		page_was_mapped = 1;
	}

	if (!page_mapped(hpage))
		rc = move_to_new_page(new_hpage, hpage, mode);

	if (page_was_mapped)
		remove_migration_ptes(hpage,
			rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false);

	unlock_page(new_hpage);

put_anon:
	if (anon_vma)
		put_anon_vma(anon_vma);

	if (rc == MIGRATEPAGE_SUCCESS) {
		hugetlb_cgroup_migrate(hpage, new_hpage);
		put_new_page = NULL;
		set_page_owner_migrate_reason(new_hpage, reason);
	}

	unlock_page(hpage);
out:
	if (rc != -EAGAIN)
		putback_active_hugepage(hpage);

	/*
	 * If migration was not successful and there's a freeing callback, use
	 * it.  Otherwise, put_page() will drop the reference grabbed during
	 * isolation.
	 */
	if (put_new_page)
		put_new_page(new_hpage, private);
	else
		putback_active_hugepage(new_hpage);

	if (result) {
		if (rc)
			*result = rc;
		else
			*result = page_to_nid(new_hpage);
	}
	return rc;
}

/*
 * migrate_pages - migrate the pages specified in a list, to the free pages
 *		   supplied as the target for the page migration
 *
 * @from:		The list of pages to be migrated.
 * @get_new_page:	The function used to allocate free pages to be used
 *			as the target of the page migration.
 * @put_new_page:	The function used to free target pages if migration
 *			fails, or NULL if no special handling is necessary.
 * @private:		Private data to be passed on to get_new_page()
 * @mode:		The migration mode that specifies the constraints for
 *			page migration, if any.
 * @reason:		The reason for page migration.
 *
 * The function returns after 10 attempts or if no pages are movable any more
 * because the list has become empty or no retryable pages exist any more.
 * The caller should call putback_movable_pages() to return pages to the LRU
 * or free list only if ret != 0.
 *
 * Returns the number of pages that were not migrated, or an error code.
 */
int migrate_pages(struct list_head *from, new_page_t get_new_page,
		free_page_t put_new_page, unsigned long private,
		enum migrate_mode mode, int reason)
{
	int retry = 1;
	int nr_failed = 0;
	int nr_succeeded = 0;
	int pass = 0;
	struct page *page;
	struct page *page2;
	int swapwrite = current->flags & PF_SWAPWRITE;
	int rc;

	if (!swapwrite)
		current->flags |= PF_SWAPWRITE;

	for(pass = 0; pass < 10 && retry; pass++) {
		retry = 0;

		list_for_each_entry_safe(page, page2, from, lru) {
			cond_resched();

			if (PageHuge(page))
				rc = unmap_and_move_huge_page(get_new_page,
						put_new_page, private, page,
						pass > 2, mode, reason);
			else
				rc = unmap_and_move(get_new_page, put_new_page,
						private, page, pass > 2, mode,
						reason);

			switch(rc) {
			case -ENOMEM:
				nr_failed++;
				goto out;
			case -EAGAIN:
				retry++;
				break;
			case MIGRATEPAGE_SUCCESS:
				nr_succeeded++;
				break;
			default:
				/*
				 * Permanent failure (-EBUSY, -ENOSYS, etc.):
				 * unlike -EAGAIN case, the failed page is
				 * removed from migration page list and not
				 * retried in the next outer loop.
				 */
				nr_failed++;
				break;
			}
		}
	}
	nr_failed += retry;
	rc = nr_failed;
out:
	if (nr_succeeded)
		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
	if (nr_failed)
		count_vm_events(PGMIGRATE_FAIL, nr_failed);
	trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);

	if (!swapwrite)
		current->flags &= ~PF_SWAPWRITE;

	return rc;
}

#ifdef CONFIG_NUMA
/*
 * Move a list of individual pages
 */
struct page_to_node {
	unsigned long addr;
	struct page *page;
	int node;
	int status;
};

static struct page *new_page_node(struct page *p, unsigned long private,
		int **result)
{
	struct page_to_node *pm = (struct page_to_node *)private;

	while (pm->node != MAX_NUMNODES && pm->page != p)
		pm++;

	if (pm->node == MAX_NUMNODES)
		return NULL;

	*result = &pm->status;

	if (PageHuge(p))
		return alloc_huge_page_node(page_hstate(compound_head(p)),
					pm->node);
	else
		return __alloc_pages_node(pm->node,
				GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
}

/*
 * Move a set of pages as indicated in the pm array. The addr
 * field must be set to the virtual address of the page to be moved
 * and the node number must contain a valid target node.
 * The pm array ends with node = MAX_NUMNODES.
 */
static int do_move_page_to_node_array(struct mm_struct *mm,
				      struct page_to_node *pm,
				      int migrate_all)
{
	int err;
	struct page_to_node *pp;
	LIST_HEAD(pagelist);

	down_read(&mm->mmap_sem);

	/*
	 * Build a list of pages to migrate
	 */
	for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
		struct vm_area_struct *vma;
		struct page *page;

		err = -EFAULT;
		vma = find_vma(mm, pp->addr);
		if (!vma || pp->addr < vma->vm_start || !vma_migratable(vma))
			goto set_status;

		/* FOLL_DUMP to ignore special (like zero) pages */
		page = follow_page(vma, pp->addr,
				FOLL_GET | FOLL_SPLIT | FOLL_DUMP);

		err = PTR_ERR(page);
		if (IS_ERR(page))
			goto set_status;

		err = -ENOENT;
		if (!page)
			goto set_status;

		pp->page = page;
		err = page_to_nid(page);

		if (err == pp->node)
			/*
			 * Node already in the right place
			 */
			goto put_and_set;

		err = -EACCES;
		if (page_mapcount(page) > 1 &&
				!migrate_all)
			goto put_and_set;

		if (PageHuge(page)) {
			if (PageHead(page))
				isolate_huge_page(page, &pagelist);
			goto put_and_set;
		}

		err = isolate_lru_page(page);
		if (!err) {
			list_add_tail(&page->lru, &pagelist);
			inc_zone_page_state(page, NR_ISOLATED_ANON +
					    page_is_file_cache(page));
		}
put_and_set:
		/*
		 * Either remove the duplicate refcount from
		 * isolate_lru_page() or drop the page ref if it was
		 * not isolated.
		 */
		put_page(page);
set_status:
		pp->status = err;
	}

	err = 0;
	if (!list_empty(&pagelist)) {
		err = migrate_pages(&pagelist, new_page_node, NULL,
				(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
		if (err)
			putback_movable_pages(&pagelist);
	}

	up_read(&mm->mmap_sem);
	return err;
}

/*
 * Migrate an array of page address onto an array of nodes and fill
 * the corresponding array of status.
 */
static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
			 unsigned long nr_pages,
			 const void __user * __user *pages,
			 const int __user *nodes,
			 int __user *status, int flags)
{
	struct page_to_node *pm;
	unsigned long chunk_nr_pages;
	unsigned long chunk_start;
	int err;

	err = -ENOMEM;
	pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
	if (!pm)
		goto out;

	migrate_prep();

	/*
	 * Store a chunk of page_to_node array in a page,
	 * but keep the last one as a marker
	 */
	chunk_nr_pages = (PAGE_SIZE / sizeof(struct page_to_node)) - 1;

	for (chunk_start = 0;
	     chunk_start < nr_pages;
	     chunk_start += chunk_nr_pages) {
		int j;

		if (chunk_start + chunk_nr_pages > nr_pages)
			chunk_nr_pages = nr_pages - chunk_start;

		/* fill the chunk pm with addrs and nodes from user-space */
		for (j = 0; j < chunk_nr_pages; j++) {
			const void __user *p;
			int node;

			err = -EFAULT;
			if (get_user(p, pages + j + chunk_start))
				goto out_pm;
			pm[j].addr = (unsigned long) p;

			if (get_user(node, nodes + j + chunk_start))
				goto out_pm;

			err = -ENODEV;
			if (node < 0 || node >= MAX_NUMNODES)
				goto out_pm;

			if (!node_state(node, N_MEMORY))
				goto out_pm;

			err = -EACCES;
			if (!node_isset(node, task_nodes))
				goto out_pm;

			pm[j].node = node;
		}

		/* End marker for this chunk */
		pm[chunk_nr_pages].node = MAX_NUMNODES;

		/* Migrate this chunk */
		err = do_move_page_to_node_array(mm, pm,
						 flags & MPOL_MF_MOVE_ALL);
		if (err < 0)
			goto out_pm;

		/* Return status information */
		for (j = 0; j < chunk_nr_pages; j++)
			if (put_user(pm[j].status, status + j + chunk_start)) {
				err = -EFAULT;
				goto out_pm;
			}
	}
	err = 0;

out_pm:
	free_page((unsigned long)pm);
out:
	return err;
}

/*
 * Determine the nodes of an array of pages and store it in an array of status.
 */
static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
				const void __user **pages, int *status)
{
	unsigned long i;

	down_read(&mm->mmap_sem);

	for (i = 0; i < nr_pages; i++) {
		unsigned long addr = (unsigned long)(*pages);
		struct vm_area_struct *vma;
		struct page *page;
		int err = -EFAULT;

		vma = find_vma(mm, addr);
		if (!vma || addr < vma->vm_start)
			goto set_status;

		/* FOLL_DUMP to ignore special (like zero) pages */
		page = follow_page(vma, addr, FOLL_DUMP);

		err = PTR_ERR(page);
		if (IS_ERR(page))
			goto set_status;

		err = page ? page_to_nid(page) : -ENOENT;
set_status:
		*status = err;

		pages++;
		status++;
	}

	up_read(&mm->mmap_sem);
}

/*
 * Determine the nodes of a user array of pages and store it in
 * a user array of status.
 */
static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
			 const void __user * __user *pages,
			 int __user *status)
{
#define DO_PAGES_STAT_CHUNK_NR 16
	const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
	int chunk_status[DO_PAGES_STAT_CHUNK_NR];

	while (nr_pages) {
		unsigned long chunk_nr;

		chunk_nr = nr_pages;
		if (chunk_nr > DO_PAGES_STAT_CHUNK_NR)
			chunk_nr = DO_PAGES_STAT_CHUNK_NR;

		if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages)))
			break;

		do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status);

		if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status)))
			break;

		pages += chunk_nr;
		status += chunk_nr;
		nr_pages -= chunk_nr;
	}
	return nr_pages ? -EFAULT : 0;
}

/*
 * Move a list of pages in the address space of the currently executing
 * process.
 */
SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
		const void __user * __user *, pages,
		const int __user *, nodes,
		int __user *, status, int, flags)
{
	const struct cred *cred = current_cred(), *tcred;
	struct task_struct *task;
	struct mm_struct *mm;
	int err;
	nodemask_t task_nodes;

	/* Check flags */
	if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
		return -EINVAL;

	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
		return -EPERM;

	/* Find the mm_struct */
	rcu_read_lock();
	task = pid ? find_task_by_vpid(pid) : current;
	if (!task) {
		rcu_read_unlock();
		return -ESRCH;
	}
	get_task_struct(task);

	/*
	 * Check if this process has the right to modify the specified
	 * process. The right exists if the process has administrative
	 * capabilities, superuser privileges or the same
	 * userid as the target process.
	 */
	tcred = __task_cred(task);
	if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
	    !uid_eq(cred->uid,  tcred->suid) && !uid_eq(cred->uid,  tcred->uid) &&
	    !capable(CAP_SYS_NICE)) {
		rcu_read_unlock();
		err = -EPERM;
		goto out;
	}
	rcu_read_unlock();

 	err = security_task_movememory(task);
 	if (err)
		goto out;

	task_nodes = cpuset_mems_allowed(task);
	mm = get_task_mm(task);
	put_task_struct(task);

	if (!mm)
		return -EINVAL;

	if (nodes)
		err = do_pages_move(mm, task_nodes, nr_pages, pages,
				    nodes, status, flags);
	else
		err = do_pages_stat(mm, nr_pages, pages, status);

	mmput(mm);
	return err;

out:
	put_task_struct(task);
	return err;
}

#ifdef CONFIG_NUMA_BALANCING
/*
 * Returns true if this is a safe migration target node for misplaced NUMA
 * pages. Currently it only checks the watermarks which crude
 */
static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
				   unsigned long nr_migrate_pages)
{
	int z;
	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
		struct zone *zone = pgdat->node_zones + z;

		if (!populated_zone(zone))
			continue;

		if (!zone_reclaimable(zone))
			continue;

		/* Avoid waking kswapd by allocating pages_to_migrate pages. */
		if (!zone_watermark_ok(zone, 0,
				       high_wmark_pages(zone) +
				       nr_migrate_pages,
				       0, 0))
			continue;
		return true;
	}
	return false;
}

static struct page *alloc_misplaced_dst_page(struct page *page,
					   unsigned long data,
					   int **result)
{
	int nid = (int) data;
	struct page *newpage;

	newpage = __alloc_pages_node(nid,
					 (GFP_HIGHUSER_MOVABLE |
					  __GFP_THISNODE | __GFP_NOMEMALLOC |
					  __GFP_NORETRY | __GFP_NOWARN) &
					 ~__GFP_RECLAIM, 0);

	return newpage;
}

/*
 * page migration rate limiting control.
 * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs
 * window of time. Default here says do not migrate more than 1280M per second.
 */
static unsigned int migrate_interval_millisecs __read_mostly = 100;
static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT);

/* Returns true if the node is migrate rate-limited after the update */
static bool numamigrate_update_ratelimit(pg_data_t *pgdat,
					unsigned long nr_pages)
{
	/*
	 * Rate-limit the amount of data that is being migrated to a node.
	 * Optimal placement is no good if the memory bus is saturated and
	 * all the time is being spent migrating!
	 */
	if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) {
		spin_lock(&pgdat->numabalancing_migrate_lock);
		pgdat->numabalancing_migrate_nr_pages = 0;
		pgdat->numabalancing_migrate_next_window = jiffies +
			msecs_to_jiffies(migrate_interval_millisecs);
		spin_unlock(&pgdat->numabalancing_migrate_lock);
	}
	if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) {
		trace_mm_numa_migrate_ratelimit(current, pgdat->node_id,
								nr_pages);
		return true;
	}

	/*
	 * This is an unlocked non-atomic update so errors are possible.
	 * The consequences are failing to migrate when we potentiall should
	 * have which is not severe enough to warrant locking. If it is ever
	 * a problem, it can be converted to a per-cpu counter.
	 */
	pgdat->numabalancing_migrate_nr_pages += nr_pages;
	return false;
}

static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
{
	int page_lru;

	VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page);

	/* Avoid migrating to a node that is nearly full */
	if (!migrate_balanced_pgdat(pgdat, 1UL << compound_order(page)))
		return 0;

	if (isolate_lru_page(page))
		return 0;

	/*
	 * migrate_misplaced_transhuge_page() skips page migration's usual
	 * check on page_count(), so we must do it here, now that the page
	 * has been isolated: a GUP pin, or any other pin, prevents migration.
	 * The expected page count is 3: 1 for page's mapcount and 1 for the
	 * caller's pin and 1 for the reference taken by isolate_lru_page().
	 */
	if (PageTransHuge(page) && page_count(page) != 3) {
		putback_lru_page(page);
		return 0;
	}

	page_lru = page_is_file_cache(page);
	mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru,
				hpage_nr_pages(page));

	/*
	 * Isolating the page has taken another reference, so the
	 * caller's reference can be safely dropped without the page
	 * disappearing underneath us during migration.
	 */
	put_page(page);
	return 1;
}

bool pmd_trans_migrating(pmd_t pmd)
{
	struct page *page = pmd_page(pmd);
	return PageLocked(page);
}

/*
 * Attempt to migrate a misplaced page to the specified destination
 * node. Caller is expected to have an elevated reference count on
 * the page that will be dropped by this function before returning.
 */
int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
			   int node)
{
	pg_data_t *pgdat = NODE_DATA(node);
	int isolated;
	int nr_remaining;
	LIST_HEAD(migratepages);

	/*
	 * Don't migrate file pages that are mapped in multiple processes
	 * with execute permissions as they are probably shared libraries.
	 */
	if (page_mapcount(page) != 1 && page_is_file_cache(page) &&
	    (vma->vm_flags & VM_EXEC))
		goto out;

	/*
	 * Rate-limit the amount of data that is being migrated to a node.
	 * Optimal placement is no good if the memory bus is saturated and
	 * all the time is being spent migrating!
	 */
	if (numamigrate_update_ratelimit(pgdat, 1))
		goto out;

	isolated = numamigrate_isolate_page(pgdat, page);
	if (!isolated)
		goto out;

	list_add(&page->lru, &migratepages);
	nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
				     NULL, node, MIGRATE_ASYNC,
				     MR_NUMA_MISPLACED);
	if (nr_remaining) {
		if (!list_empty(&migratepages)) {
			list_del(&page->lru);
			dec_zone_page_state(page, NR_ISOLATED_ANON +
					page_is_file_cache(page));
			putback_lru_page(page);
		}
		isolated = 0;
	} else
		count_vm_numa_event(NUMA_PAGE_MIGRATE);
	BUG_ON(!list_empty(&migratepages));
	return isolated;

out:
	put_page(page);
	return 0;
}
#endif /* CONFIG_NUMA_BALANCING */

#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
/*
 * Migrates a THP to a given target node. page must be locked and is unlocked
 * before returning.
 */
int migrate_misplaced_transhuge_page(struct mm_struct *mm,
				struct vm_area_struct *vma,
				pmd_t *pmd, pmd_t entry,
				unsigned long address,
				struct page *page, int node)
{
	spinlock_t *ptl;
	pg_data_t *pgdat = NODE_DATA(node);
	int isolated = 0;
	struct page *new_page = NULL;
	int page_lru = page_is_file_cache(page);
	unsigned long mmun_start = address & HPAGE_PMD_MASK;
	unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
	pmd_t orig_entry;

	/*
	 * Rate-limit the amount of data that is being migrated to a node.
	 * Optimal placement is no good if the memory bus is saturated and
	 * all the time is being spent migrating!
	 */
	if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR))
		goto out_dropref;

	new_page = alloc_pages_node(node,
		(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_RECLAIM,
		HPAGE_PMD_ORDER);
	if (!new_page)
		goto out_fail;
	prep_transhuge_page(new_page);

	isolated = numamigrate_isolate_page(pgdat, page);
	if (!isolated) {
		put_page(new_page);
		goto out_fail;
	}
	/*
	 * 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(mm))
		flush_tlb_range(vma, mmun_start, mmun_end);

	/* Prepare a page as a migration target */
	__SetPageLocked(new_page);
	__SetPageSwapBacked(new_page);

	/* anon mapping, we can simply copy page->mapping to the new page: */
	new_page->mapping = page->mapping;
	new_page->index = page->index;
	migrate_page_copy(new_page, page);
	WARN_ON(PageLRU(new_page));

	/* Recheck the target PMD */
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
	ptl = pmd_lock(mm, pmd);
	if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) {
fail_putback:
		spin_unlock(ptl);
		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

		/* Reverse changes made by migrate_page_copy() */
		if (TestClearPageActive(new_page))
			SetPageActive(page);
		if (TestClearPageUnevictable(new_page))
			SetPageUnevictable(page);

		unlock_page(new_page);
		put_page(new_page);		/* Free it */

		/* Retake the callers reference and putback on LRU */
		get_page(page);
		putback_lru_page(page);
		mod_zone_page_state(page_zone(page),
			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);

		goto out_unlock;
	}

	orig_entry = *pmd;
	entry = mk_pmd(new_page, vma->vm_page_prot);
	entry = pmd_mkhuge(entry);
	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);

	/*
	 * Clear the old entry under pagetable lock and establish the new PTE.
	 * Any parallel GUP will either observe the old page blocking on the
	 * page lock, block on the page table lock or observe the new page.
	 * The SetPageUptodate on the new page and page_add_new_anon_rmap
	 * guarantee the copy is visible before the pagetable update.
	 */
	flush_cache_range(vma, mmun_start, mmun_end);
	page_add_anon_rmap(new_page, vma, mmun_start, true);
	pmdp_huge_clear_flush_notify(vma, mmun_start, pmd);
	set_pmd_at(mm, mmun_start, pmd, entry);
	update_mmu_cache_pmd(vma, address, &entry);

	if (page_count(page) != 2) {
		set_pmd_at(mm, mmun_start, pmd, orig_entry);
		flush_pmd_tlb_range(vma, mmun_start, mmun_end);
		mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
		update_mmu_cache_pmd(vma, address, &entry);
		page_remove_rmap(new_page, true);
		goto fail_putback;
	}

	mlock_migrate_page(new_page, page);
	page_remove_rmap(page, true);
	set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED);

	spin_unlock(ptl);
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

	/* Take an "isolate" reference and put new page on the LRU. */
	get_page(new_page);
	putback_lru_page(new_page);

	unlock_page(new_page);
	unlock_page(page);
	put_page(page);			/* Drop the rmap reference */
	put_page(page);			/* Drop the LRU isolation reference */

	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);

	mod_zone_page_state(page_zone(page),
			NR_ISOLATED_ANON + page_lru,
			-HPAGE_PMD_NR);
	return isolated;

out_fail:
	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
out_dropref:
	ptl = pmd_lock(mm, pmd);
	if (pmd_same(*pmd, entry)) {
		entry = pmd_modify(entry, vma->vm_page_prot);
		set_pmd_at(mm, mmun_start, pmd, entry);
		update_mmu_cache_pmd(vma, address, &entry);
	}
	spin_unlock(ptl);

out_unlock:
	unlock_page(page);
	put_page(page);
	return 0;
}
#endif /* CONFIG_NUMA_BALANCING */

#endif /* CONFIG_NUMA */