migrate.c

	return rc;
}

static int __unmap_and_move(struct page *page, struct page *newpage,
				int force, enum migrate_mode mode)
{
	int rc = -EAGAIN;
	int page_was_mapped = 0;
	struct anon_vma *anon_vma = NULL;
	bool is_lru = !__PageMovable(page);

	if (!trylock_page(page)) {
		if (!force || mode == MIGRATE_ASYNC)
			goto out;

		/*
		 * It's not safe for direct compaction to call lock_page.
		 * For example, during page readahead pages are added locked
		 * to the LRU. Later, when the IO completes the pages are
		 * marked uptodate and unlocked. However, the queueing
		 * could be merging multiple pages for one bio (e.g.
		 * mpage_readpages). If an allocation happens for the
		 * second or third page, the process can end up locking
		 * the same page twice and deadlocking. Rather than
		 * trying to be clever about what pages can be locked,
		 * avoid the use of lock_page for direct compaction
		 * altogether.
		 */
		if (current->flags & PF_MEMALLOC)
			goto out;

		lock_page(page);
	}

	if (PageWriteback(page)) {
		/*
		 * Only in the case of a full synchronous migration is it
		 * necessary to wait for PageWriteback. In the async case,
		 * the retry loop is too short and in the sync-light case,
		 * the overhead of stalling is too much
		 */
		switch (mode) {
		case MIGRATE_SYNC:
		case MIGRATE_SYNC_NO_COPY:
			break;
		default:
			rc = -EBUSY;
			goto out_unlock;
		}
		if (!force)
			goto out_unlock;
		wait_on_page_writeback(page);
	}

	/*
	 * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
	 * we cannot notice that anon_vma is freed while we migrates a page.
	 * This get_anon_vma() delays freeing anon_vma pointer until the end
	 * of migration. File cache pages are no problem because of page_lock()
	 * File Caches may use write_page() or lock_page() in migration, then,
	 * just care Anon page here.
	 *
	 * Only page_get_anon_vma() understands the subtleties of
	 * getting a hold on an anon_vma from outside one of its mms.
	 * But if we cannot get anon_vma, then we won't need it anyway,
	 * because that implies that the anon page is no longer mapped
	 * (and cannot be remapped so long as we hold the page lock).
	 */
	if (PageAnon(page) && !PageKsm(page))
		anon_vma = page_get_anon_vma(page);

	/*
	 * Block others from accessing the new page when we get around to
	 * establishing additional references. We are usually the only one
	 * holding a reference to newpage at this point. We used to have a BUG
	 * here if trylock_page(newpage) fails, but would like to allow for
	 * cases where there might be a race with the previous use of newpage.
	 * This is much like races on refcount of oldpage: just don't BUG().
	 */
	if (unlikely(!trylock_page(newpage)))
		goto out_unlock;

	if (unlikely(!is_lru)) {
		rc = move_to_new_page(newpage, page, mode);
		goto out_unlock_both;
	}

	/*
	 * Corner case handling:
	 * 1. When a new swap-cache page is read into, it is added to the LRU
	 * and treated as swapcache but it has no rmap yet.
	 * Calling try_to_unmap() against a page->mapping==NULL page will
	 * trigger a BUG.  So handle it here.
	 * 2. An orphaned page (see truncate_complete_page) might have
	 * fs-private metadata. The page can be picked up due to memory
	 * offlining.  Everywhere else except page reclaim, the page is
	 * invisible to the vm, so the page can not be migrated.  So try to
	 * free the metadata, so the page can be freed.
	 */
	if (!page->mapping) {
		VM_BUG_ON_PAGE(PageAnon(page), page);
		if (page_has_private(page)) {
			try_to_free_buffers(page);
			goto out_unlock_both;
		}
	} else if (page_mapped(page)) {
		/* Establish migration ptes */
		VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
				page);
		try_to_unmap(page,
			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
		page_was_mapped = 1;
	}

	if (!page_mapped(page))
		rc = move_to_new_page(newpage, page, mode);

	if (page_was_mapped)
		remove_migration_ptes(page,
			rc == MIGRATEPAGE_SUCCESS ? newpage : page, false);

out_unlock_both:
	unlock_page(newpage);
out_unlock:
	/* Drop an anon_vma reference if we took one */
	if (anon_vma)
		put_anon_vma(anon_vma);
	unlock_page(page);
out:
	/*
	 * If migration is successful, decrease refcount of the newpage
	 * which will not free the page because new page owner increased
	 * refcounter. As well, if it is LRU page, add the page to LRU
	 * list in here. Use the old state of the isolated source page to
	 * determine if we migrated a LRU page. newpage was already unlocked
	 * and possibly modified by its owner - don't rely on the page
	 * state.
	 */
	if (rc == MIGRATEPAGE_SUCCESS) {
		if (unlikely(!is_lru))
			put_page(newpage);
		else
			putback_lru_page(newpage);
	}

	return rc;
}

/*
 * gcc 4.7 and 4.8 on arm get an ICEs when inlining unmap_and_move().  Work
 * around it.
 */
#if defined(CONFIG_ARM) && \
	defined(GCC_VERSION) && GCC_VERSION < 40900 && GCC_VERSION >= 40700
#define ICE_noinline noinline
#else
#define ICE_noinline
#endif

/*
 * Obtain the lock on page, remove all ptes and migrate the page
 * to the newly allocated page in newpage.
 */
static ICE_noinline int unmap_and_move(new_page_t get_new_page,
				   free_page_t put_new_page,
				   unsigned long private, struct page *page,
				   int force, enum migrate_mode mode,
				   enum migrate_reason reason)
{
	int rc = MIGRATEPAGE_SUCCESS;
	struct page *newpage;

	if (!thp_migration_supported() && PageTransHuge(page))
		return -ENOMEM;

	newpage = get_new_page(page, private);
	if (!newpage)
		return -ENOMEM;

	if (page_count(page) == 1) {
		/* page was freed from under us. So we are done. */
		ClearPageActive(page);
		ClearPageUnevictable(page);
		if (unlikely(__PageMovable(page))) {
			lock_page(page);
			if (!PageMovable(page))
				__ClearPageIsolated(page);
			unlock_page(page);
		}
		if (put_new_page)
			put_new_page(newpage, private);
		else
			put_page(newpage);
		goto out;
	}

	rc = __unmap_and_move(page, newpage, force, mode);
	if (rc == MIGRATEPAGE_SUCCESS)
		set_page_owner_migrate_reason(newpage, reason);

out:
	if (rc != -EAGAIN) {
		/*
		 * A page that has been migrated has all references
		 * removed and will be freed. A page that has not been
		 * migrated will have kepts its references and be
		 * restored.
		 */
		list_del(&page->lru);

		/*
		 * Compaction can migrate also non-LRU pages which are
		 * not accounted to NR_ISOLATED_*. They can be recognized
		 * as __PageMovable
		 */
		if (likely(!__PageMovable(page)))
			mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
					page_is_file_cache(page), -hpage_nr_pages(page));
	}

	/*
	 * If migration is successful, releases reference grabbed during
	 * isolation. Otherwise, restore the page to right list unless
	 * we want to retry.
	 */
	if (rc == MIGRATEPAGE_SUCCESS) {
		put_page(page);
		if (reason == MR_MEMORY_FAILURE) {
			/*
			 * Set PG_HWPoison on just freed page
			 * intentionally. Although it's rather weird,
			 * it's how HWPoison flag works at the moment.
			 */
			if (set_hwpoison_free_buddy_page(page))
				num_poisoned_pages_inc();
		}
	} else {
		if (rc != -EAGAIN) {
			if (likely(!__PageMovable(page))) {
				putback_lru_page(page);
				goto put_new;
			}

			lock_page(page);
			if (PageMovable(page))
				putback_movable_page(page);
			else
				__ClearPageIsolated(page);
			unlock_page(page);
			put_page(page);
		}
put_new:
		if (put_new_page)
			put_new_page(newpage, private);
		else
			put_page(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 page_was_mapped = 0;
	struct page *new_hpage;
	struct anon_vma *anon_vma = NULL;

	/*
	 * Migratability of hugepages depends on architectures and their 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);
	if (!new_hpage)
		return -ENOMEM;

	if (!trylock_page(hpage)) {
		if (!force)
			goto out;
		switch (mode) {
		case MIGRATE_SYNC:
		case MIGRATE_SYNC_NO_COPY:
			break;
		default:
			goto out;
		}
		lock_page(hpage);
	}

	/*
	 * Check for pages which are in the process of being freed.  Without
	 * page_mapping() set, hugetlbfs specific move page routine will not
	 * be called and we could leak usage counts for subpools.
	 */
	if (page_private(hpage) && !page_mapping(hpage)) {
		rc = -EBUSY;
		goto out_unlock;
	}

	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) {
		move_hugetlb_state(hpage, new_hpage, reason);
		put_new_page = NULL;
	}

out_unlock:
	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);

	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) {
retry:
			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:
				/*
				 * THP migration might be unsupported or the
				 * allocation could've failed so we should
				 * retry on the same page with the THP split
				 * to base pages.
				 *
				 * Head page is retried immediately and tail
				 * pages are added to the tail of the list so
				 * we encounter them after the rest of the list
				 * is processed.
				 */
				if (PageTransHuge(page) && !PageHuge(page)) {
					lock_page(page);
					rc = split_huge_page_to_list(page, from);
					unlock_page(page);
					if (!rc) {
						list_safe_reset_next(page, page2, lru);
						goto retry;
					}
				}
				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

static int store_status(int __user *status, int start, int value, int nr)
{
	while (nr-- > 0) {
		if (put_user(value, status + start))
			return -EFAULT;
		start++;
	}

	return 0;
}

static int do_move_pages_to_node(struct mm_struct *mm,
		struct list_head *pagelist, int node)
{
	int err;

	if (list_empty(pagelist))
		return 0;

	err = migrate_pages(pagelist, alloc_new_node_page, NULL, node,
			MIGRATE_SYNC, MR_SYSCALL);
	if (err)
		putback_movable_pages(pagelist);
	return err;
}

/*
 * Resolves the given address to a struct page, isolates it from the LRU and
 * puts it to the given pagelist.
 * Returns -errno if the page cannot be found/isolated or 0 when it has been
 * queued or the page doesn't need to be migrated because it is already on
 * the target node
 */
static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
		int node, struct list_head *pagelist, bool migrate_all)
{
	struct vm_area_struct *vma;
	struct page *page;
	unsigned int follflags;
	int err;

	down_read(&mm->mmap_sem);
	err = -EFAULT;
	vma = find_vma(mm, addr);
	if (!vma || addr < vma->vm_start || !vma_migratable(vma))
		goto out;

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

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

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

	err = 0;
	if (page_to_nid(page) == node)
		goto out_putpage;

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

	if (PageHuge(page)) {
		if (PageHead(page)) {
			isolate_huge_page(page, pagelist);
			err = 0;
		}
	} else {
		struct page *head;

		head = compound_head(page);
		err = isolate_lru_page(head);
		if (err)
			goto out_putpage;

		err = 0;
		list_add_tail(&head->lru, pagelist);
		mod_node_page_state(page_pgdat(head),
			NR_ISOLATED_ANON + page_is_file_cache(head),
			hpage_nr_pages(head));
	}
out_putpage:
	/*
	 * Either remove the duplicate refcount from
	 * isolate_lru_page() or drop the page ref if it was
	 * not isolated.
	 */
	put_page(page);
out:
	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)
{
	int current_node = NUMA_NO_NODE;
	LIST_HEAD(pagelist);
	int start, i;
	int err = 0, err1;

	migrate_prep();

	for (i = start = 0; i < nr_pages; i++) {
		const void __user *p;
		unsigned long addr;
		int node;

		err = -EFAULT;
		if (get_user(p, pages + i))
			goto out_flush;
		if (get_user(node, nodes + i))
			goto out_flush;
		addr = (unsigned long)p;

		err = -ENODEV;
		if (node < 0 || node >= MAX_NUMNODES)
			goto out_flush;
		if (!node_state(node, N_MEMORY))
			goto out_flush;

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

		if (current_node == NUMA_NO_NODE) {
			current_node = node;
			start = i;
		} else if (node != current_node) {
			err = do_move_pages_to_node(mm, &pagelist, current_node);
			if (err)
				goto out;
			err = store_status(status, start, current_node, i - start);
			if (err)
				goto out;
			start = i;
			current_node = node;
		}

		/*
		 * Errors in the page lookup or isolation are not fatal and we simply
		 * report them via status
		 */
		err = add_page_for_migration(mm, addr, current_node,
				&pagelist, flags & MPOL_MF_MOVE_ALL);
		if (!err)
			continue;

		err = store_status(status, i, err, 1);
		if (err)
			goto out_flush;

		err = do_move_pages_to_node(mm, &pagelist, current_node);
		if (err)
			goto out;
		if (i > start) {
			err = store_status(status, start, current_node, i - start);
			if (err)
				goto out;
		}
		current_node = NUMA_NO_NODE;
	}
out_flush:
	if (list_empty(&pagelist))
		return err;

	/* Make sure we do not overwrite the existing error */
	err1 = do_move_pages_to_node(mm, &pagelist, current_node);
	if (!err1)
		err1 = store_status(status, start, current_node, i - start);
	if (!err)
		err = err1;
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.
 */
static int kernel_move_pages(pid_t pid, unsigned long nr_pages,
			     const void __user * __user *pages,
			     const int __user *nodes,
			     int __user *status, int flags)
{
	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. Use the regular "ptrace_may_access()" checks.
	 */
	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
		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;
}

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)
{
	return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
}

#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
		       compat_uptr_t __user *, pages32,
		       const int __user *, nodes,
		       int __user *, status,
		       int, flags)
{
	const void __user * __user *pages;
	int i;

	pages = compat_alloc_user_space(nr_pages * sizeof(void *));
	for (i = 0; i < nr_pages; i++) {
		compat_uptr_t p;

		if (get_user(p, pages32 + i) ||
			put_user(compat_ptr(p), pages + i))
			return -EFAULT;
	}
	return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
}
#endif /* CONFIG_COMPAT */

#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;

		/* 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 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;
}

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, compound_nr(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_node_page_state(page_pgdat(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;

	/*
	 * Also do not migrate dirty pages as not all filesystems can move
	 * dirty pages in MIGRATE_ASYNC mode which is a waste of cycles.
	 */
	if (page_is_file_cache(page) && PageDirty(page))
		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_node_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;