migrate.c

/*
 * Memory Migration functionality - linux/mm/migration.c
 *
 * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter
 *
 * Page migration was first developed in the context of the memory hotplug
 * project. The main authors of the migration code are:
 *
 * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
 * Hirokazu Takahashi <taka@valinux.co.jp>
 * Dave Hansen <haveblue@us.ibm.com>
 * Christoph Lameter
 */

#include <linux/migrate.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/mm_inline.h>
#include <linux/nsproxy.h>
#include <linux/pagevec.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/writeback.h>
#include <linux/mempolicy.h>
#include <linux/vmalloc.h>
#include <linux/security.h>
#include <linux/memcontrol.h>
#include <linux/syscalls.h>
#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>
#include <linux/balloon_compaction.h>
#include <linux/mmu_notifier.h>

#include <asm/tlbflush.h>

#define CREATE_TRACE_POINTS
#include <trace/events/migrate.h>

#include "internal.h"

/*
 * migrate_prep() needs to be called before we start compiling a list of pages
 * to be migrated using isolate_lru_page(). If scheduling work on other CPUs is
 * undesirable, use migrate_prep_local()
 */
int migrate_prep(void)
{
	/*
	 * Clear the LRU lists so pages can be isolated.
	 * Note that pages may be moved off the LRU after we have
	 * drained them. Those pages will fail to migrate like other
	 * pages that may be busy.
	 */
	lru_add_drain_all();

	return 0;
}

/* Do the necessary work of migrate_prep but not if it involves other CPUs */
int migrate_prep_local(void)
{
	lru_add_drain();

	return 0;
}

/*
 * Put previously isolated pages back onto the appropriate lists
 * from where they were once taken off for compaction/migration.
 *
 * This function shall be used whenever the isolated pageset has been
 * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range()
 * and isolate_huge_page().
 */
void putback_movable_pages(struct list_head *l)
{
	struct page *page;
	struct page *page2;

	list_for_each_entry_safe(page, page2, l, lru) {
		if (unlikely(PageHuge(page))) {
			putback_active_hugepage(page);
			continue;
		}
		list_del(&page->lru);
		dec_zone_page_state(page, NR_ISOLATED_ANON +
				page_is_file_cache(page));
		if (unlikely(isolated_balloon_page(page)))
			balloon_page_putback(page);
		else
			putback_lru_page(page);
	}
}

/*
 * Restore a potential migration pte to a working pte entry
 */
static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
				 unsigned long addr, void *old)
{
	struct mm_struct *mm = vma->vm_mm;
	swp_entry_t entry;
 	pmd_t *pmd;
	pte_t *ptep, pte;
 	spinlock_t *ptl;

	if (unlikely(PageHuge(new))) {
		ptep = huge_pte_offset(mm, addr);
		if (!ptep)
			goto out;
		ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep);
	} else {
		pmd = mm_find_pmd(mm, addr);
		if (!pmd)
			goto out;

		ptep = pte_offset_map(pmd, addr);

		/*
		 * Peek to check is_swap_pte() before taking ptlock?  No, we
		 * can race mremap's move_ptes(), which skips anon_vma lock.
		 */

		ptl = pte_lockptr(mm, pmd);
	}

 	spin_lock(ptl);
	pte = *ptep;
	if (!is_swap_pte(pte))
		goto unlock;

	entry = pte_to_swp_entry(pte);

	if (!is_migration_entry(entry) ||
	    migration_entry_to_page(entry) != old)
		goto unlock;

	get_page(new);
	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
	if (pte_swp_soft_dirty(*ptep))
		pte = pte_mksoft_dirty(pte);

	/* Recheck VMA as permissions can change since migration started  */
	if (is_write_migration_entry(entry))
		pte = maybe_mkwrite(pte, vma);

#ifdef CONFIG_HUGETLB_PAGE
	if (PageHuge(new)) {
		pte = pte_mkhuge(pte);
		pte = arch_make_huge_pte(pte, vma, new, 0);
	}
#endif
	flush_dcache_page(new);
	set_pte_at(mm, addr, ptep, pte);

	if (PageHuge(new)) {
		if (PageAnon(new))
			hugepage_add_anon_rmap(new, vma, addr);
		else
			page_dup_rmap(new);
	} else if (PageAnon(new))
		page_add_anon_rmap(new, vma, addr);
	else
		page_add_file_rmap(new);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, addr, ptep);
unlock:
	pte_unmap_unlock(ptep, ptl);
out:
	return SWAP_AGAIN;
}

/*
 * Get rid of all migration entries and replace them by
 * references to the indicated page.
 */
static void remove_migration_ptes(struct page *old, struct page *new)
{
	struct rmap_walk_control rwc = {
		.rmap_one = remove_migration_pte,
		.arg = old,
	};

	rmap_walk(new, &rwc);
}

/*
 * Something used the pte of a page under migration. We need to
 * get to the page and wait until migration is finished.
 * When we return from this function the fault will be retried.
 */
void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
				spinlock_t *ptl)
{
	pte_t pte;
	swp_entry_t entry;
	struct page *page;

	spin_lock(ptl);
	pte = *ptep;
	if (!is_swap_pte(pte))
		goto out;

	entry = pte_to_swp_entry(pte);
	if (!is_migration_entry(entry))
		goto out;

	page = migration_entry_to_page(entry);

	/*
	 * Once radix-tree replacement of page migration started, page_count
	 * *must* be zero. And, we don't want to call wait_on_page_locked()
	 * against a page without get_page().
	 * So, we use get_page_unless_zero(), here. Even failed, page fault
	 * will occur again.
	 */
	if (!get_page_unless_zero(page))
		goto out;
	pte_unmap_unlock(ptep, ptl);
	wait_on_page_locked(page);
	put_page(page);
	return;
out:
	pte_unmap_unlock(ptep, ptl);
}

void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
				unsigned long address)
{
	spinlock_t *ptl = pte_lockptr(mm, pmd);
	pte_t *ptep = pte_offset_map(pmd, address);
	__migration_entry_wait(mm, ptep, ptl);
}

void migration_entry_wait_huge(struct vm_area_struct *vma,
		struct mm_struct *mm, pte_t *pte)
{
	spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte);
	__migration_entry_wait(mm, pte, ptl);
}

#ifdef CONFIG_BLOCK
/* Returns true if all buffers are successfully locked */
static bool buffer_migrate_lock_buffers(struct buffer_head *head,
							enum migrate_mode mode)
{
	struct buffer_head *bh = head;

	/* Simple case, sync compaction */
	if (mode != MIGRATE_ASYNC) {
		do {
			get_bh(bh);
			lock_buffer(bh);
			bh = bh->b_this_page;

		} while (bh != head);

		return true;
	}

	/* async case, we cannot block on lock_buffer so use trylock_buffer */
	do {
		get_bh(bh);
		if (!trylock_buffer(bh)) {
			/*
			 * We failed to lock the buffer and cannot stall in
			 * async migration. Release the taken locks
			 */
			struct buffer_head *failed_bh = bh;
			put_bh(failed_bh);
			bh = head;
			while (bh != failed_bh) {
				unlock_buffer(bh);
				put_bh(bh);
				bh = bh->b_this_page;
			}
			return false;
		}

		bh = bh->b_this_page;
	} while (bh != head);
	return true;
}
#else
static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
							enum migrate_mode mode)
{
	return true;
}
#endif /* CONFIG_BLOCK */

/*
 * Replace the page in the mapping.
 *
 * The number of remaining references must be:
 * 1 for anonymous pages without a mapping
 * 2 for pages with a mapping
 * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
 */
int migrate_page_move_mapping(struct address_space *mapping,
		struct page *newpage, struct page *page,
		struct buffer_head *head, enum migrate_mode mode,
		int extra_count)
{
	int expected_count = 1 + extra_count;
	void **pslot;

	if (!mapping) {
		/* Anonymous page without mapping */
		if (page_count(page) != expected_count)
			return -EAGAIN;
		return MIGRATEPAGE_SUCCESS;
	}

	spin_lock_irq(&mapping->tree_lock);

	pslot = radix_tree_lookup_slot(&mapping->page_tree,
 					page_index(page));

	expected_count += 1 + page_has_private(page);
	if (page_count(page) != expected_count ||
		radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	if (!page_freeze_refs(page, expected_count)) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	/*
	 * In the async migration case of moving a page with buffers, lock the
	 * buffers using trylock before the mapping is moved. If the mapping
	 * was moved, we later failed to lock the buffers and could not move
	 * the mapping back due to an elevated page count, we would have to
	 * block waiting on other references to be dropped.
	 */
	if (mode == MIGRATE_ASYNC && head &&
			!buffer_migrate_lock_buffers(head, mode)) {
		page_unfreeze_refs(page, expected_count);
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	/*
	 * Now we know that no one else is looking at the page.
	 */
	get_page(newpage);	/* add cache reference */
	if (PageSwapCache(page)) {
		SetPageSwapCache(newpage);
		set_page_private(newpage, page_private(page));
	}

	radix_tree_replace_slot(pslot, newpage);

	/*
	 * Drop cache reference from old page by unfreezing
	 * to one less reference.
	 * We know this isn't the last reference.
	 */
	page_unfreeze_refs(page, expected_count - 1);

	/*
	 * If moved to a different zone then also account
	 * the page for that zone. Other VM counters will be
	 * taken care of when we establish references to the
	 * new page and drop references to the old page.
	 *
	 * Note that anonymous pages are accounted for
	 * via NR_FILE_PAGES and NR_ANON_PAGES if they
	 * are mapped to swap space.
	 */
	__dec_zone_page_state(page, NR_FILE_PAGES);
	__inc_zone_page_state(newpage, NR_FILE_PAGES);
	if (!PageSwapCache(page) && PageSwapBacked(page)) {
		__dec_zone_page_state(page, NR_SHMEM);
		__inc_zone_page_state(newpage, NR_SHMEM);
	}
	spin_unlock_irq(&mapping->tree_lock);

	return MIGRATEPAGE_SUCCESS;
}

/*
 * The expected number of remaining references is the same as that
 * of migrate_page_move_mapping().
 */
int migrate_huge_page_move_mapping(struct address_space *mapping,
				   struct page *newpage, struct page *page)
{
	int expected_count;
	void **pslot;

	if (!mapping) {
		if (page_count(page) != 1)
			return -EAGAIN;
		return MIGRATEPAGE_SUCCESS;
	}

	spin_lock_irq(&mapping->tree_lock);

	pslot = radix_tree_lookup_slot(&mapping->page_tree,
					page_index(page));

	expected_count = 2 + page_has_private(page);
	if (page_count(page) != expected_count ||
		radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	if (!page_freeze_refs(page, expected_count)) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	get_page(newpage);

	radix_tree_replace_slot(pslot, newpage);

	page_unfreeze_refs(page, expected_count - 1);

	spin_unlock_irq(&mapping->tree_lock);
	return MIGRATEPAGE_SUCCESS;
}

/*
 * Gigantic pages are so large that we do not guarantee that page++ pointer
 * arithmetic will work across the entire page.  We need something more
 * specialized.
 */
static void __copy_gigantic_page(struct page *dst, struct page *src,
				int nr_pages)
{
	int i;
	struct page *dst_base = dst;
	struct page *src_base = src;

	for (i = 0; i < nr_pages; ) {
		cond_resched();
		copy_highpage(dst, src);

		i++;
		dst = mem_map_next(dst, dst_base, i);
		src = mem_map_next(src, src_base, i);
	}
}

static void copy_huge_page(struct page *dst, struct page *src)
{
	int i;
	int nr_pages;

	if (PageHuge(src)) {
		/* hugetlbfs page */
		struct hstate *h = page_hstate(src);
		nr_pages = pages_per_huge_page(h);

		if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
			__copy_gigantic_page(dst, src, nr_pages);
			return;
		}
	} else {
		/* thp page */
		BUG_ON(!PageTransHuge(src));
		nr_pages = hpage_nr_pages(src);
	}

	for (i = 0; i < nr_pages; i++) {
		cond_resched();
		copy_highpage(dst + i, src + i);
	}
}

/*
 * Copy the page to its new location
 */
void migrate_page_copy(struct page *newpage, struct page *page)
{
	int cpupid;

	if (PageHuge(page) || PageTransHuge(page))
		copy_huge_page(newpage, page);
	else
		copy_highpage(newpage, page);

	if (PageError(page))
		SetPageError(newpage);
	if (PageReferenced(page))
		SetPageReferenced(newpage);
	if (PageUptodate(page))
		SetPageUptodate(newpage);
	if (TestClearPageActive(page)) {
		VM_BUG_ON_PAGE(PageUnevictable(page), page);
		SetPageActive(newpage);
	} else if (TestClearPageUnevictable(page))
		SetPageUnevictable(newpage);
	if (PageChecked(page))
		SetPageChecked(newpage);
	if (PageMappedToDisk(page))
		SetPageMappedToDisk(newpage);

	if (PageDirty(page)) {
		clear_page_dirty_for_io(page);
		/*
		 * Want to mark the page and the radix tree as dirty, and
		 * redo the accounting that clear_page_dirty_for_io undid,
		 * but we can't use set_page_dirty because that function
		 * is actually a signal that all of the page has become dirty.
		 * Whereas only part of our page may be dirty.
		 */
		if (PageSwapBacked(page))
			SetPageDirty(newpage);
		else
			__set_page_dirty_nobuffers(newpage);
 	}

	/*
	 * Copy NUMA information to the new page, to prevent over-eager
	 * future migrations of this same page.
	 */
	cpupid = page_cpupid_xchg_last(page, -1);
	page_cpupid_xchg_last(newpage, cpupid);

	mlock_migrate_page(newpage, page);
	ksm_migrate_page(newpage, page);
	/*
	 * Please do not reorder this without considering how mm/ksm.c's
	 * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
	 */
	ClearPageSwapCache(page);
	ClearPagePrivate(page);
	set_page_private(page, 0);

	/*
	 * If any waiters have accumulated on the new page then
	 * wake them up.
	 */
	if (PageWriteback(newpage))
		end_page_writeback(newpage);
}

/************************************************************
 *                    Migration functions
 ***********************************************************/

/*
 * Common logic to directly migrate a single page suitable for
 * pages that do not use PagePrivate/PagePrivate2.
 *
 * Pages are locked upon entry and exit.
 */
int migrate_page(struct address_space *mapping,
		struct page *newpage, struct page *page,
		enum migrate_mode mode)
{
	int rc;

	BUG_ON(PageWriteback(page));	/* Writeback must be complete */

	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);

	if (rc != MIGRATEPAGE_SUCCESS)
		return rc;

	migrate_page_copy(newpage, page);
	return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(migrate_page);

#ifdef CONFIG_BLOCK
/*
 * Migration function for pages with buffers. This function can only be used
 * if the underlying filesystem guarantees that no other references to "page"
 * exist.
 */
int buffer_migrate_page(struct address_space *mapping,
		struct page *newpage, struct page *page, enum migrate_mode mode)
{
	struct buffer_head *bh, *head;
	int rc;

	if (!page_has_buffers(page))
		return migrate_page(mapping, newpage, page, mode);

	head = page_buffers(page);

	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode, 0);

	if (rc != MIGRATEPAGE_SUCCESS)
		return rc;

	/*
	 * In the async case, migrate_page_move_mapping locked the buffers
	 * with an IRQ-safe spinlock held. In the sync case, the buffers
	 * need to be locked now
	 */
	if (mode != MIGRATE_ASYNC)
		BUG_ON(!buffer_migrate_lock_buffers(head, mode));

	ClearPagePrivate(page);
	set_page_private(newpage, page_private(page));
	set_page_private(page, 0);
	put_page(page);
	get_page(newpage);

	bh = head;
	do {
		set_bh_page(bh, newpage, bh_offset(bh));
		bh = bh->b_this_page;

	} while (bh != head);

	SetPagePrivate(newpage);

	migrate_page_copy(newpage, page);

	bh = head;
	do {
		unlock_buffer(bh);
 		put_bh(bh);
		bh = bh->b_this_page;

	} while (bh != head);

	return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(buffer_migrate_page);
#endif

/*
 * Writeback a page to clean the dirty state
 */
static int writeout(struct address_space *mapping, struct page *page)
{
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_NONE,
		.nr_to_write = 1,
		.range_start = 0,
		.range_end = LLONG_MAX,
		.for_reclaim = 1
	};
	int rc;

	if (!mapping->a_ops->writepage)
		/* No write method for the address space */
		return -EINVAL;

	if (!clear_page_dirty_for_io(page))
		/* Someone else already triggered a write */
		return -EAGAIN;

	/*
	 * A dirty page may imply that the underlying filesystem has
	 * the page on some queue. So the page must be clean for
	 * migration. Writeout may mean we loose the lock and the
	 * page state is no longer what we checked for earlier.
	 * At this point we know that the migration attempt cannot
	 * be successful.
	 */
	remove_migration_ptes(page, page);

	rc = mapping->a_ops->writepage(page, &wbc);

	if (rc != AOP_WRITEPAGE_ACTIVATE)
		/* unlocked. Relock */
		lock_page(page);

	return (rc < 0) ? -EIO : -EAGAIN;
}

/*
 * Default handling if a filesystem does not provide a migration function.
 */
static int fallback_migrate_page(struct address_space *mapping,
	struct page *newpage, struct page *page, enum migrate_mode mode)
{
	if (PageDirty(page)) {
		/* Only writeback pages in full synchronous migration */
		if (mode != MIGRATE_SYNC)
			return -EBUSY;
		return writeout(mapping, page);
	}

	/*
	 * Buffers may be managed in a filesystem specific way.
	 * We must have no buffers or drop them.
	 */
	if (page_has_private(page) &&
	    !try_to_release_page(page, GFP_KERNEL))
		return -EAGAIN;

	return migrate_page(mapping, newpage, page, mode);
}

/*
 * Move a page to a newly allocated page
 * The page is locked and all ptes have been successfully removed.
 *
 * The new page will have replaced the old page if this function
 * is successful.
 *
 * Return value:
 *   < 0 - error code
 *  MIGRATEPAGE_SUCCESS - success
 */
static int move_to_new_page(struct page *newpage, struct page *page,
				int page_was_mapped, enum migrate_mode mode)
{
	struct address_space *mapping;
	int rc;

	/*
	 * Block others from accessing the page when we get around to
	 * establishing additional references. We are the only one
	 * holding a reference to the new page at this point.
	 */
	if (!trylock_page(newpage))
		BUG();

	/* Prepare mapping for the new page.*/
	newpage->index = page->index;
	newpage->mapping = page->mapping;
	if (PageSwapBacked(page))
		SetPageSwapBacked(newpage);

	mapping = page_mapping(page);
	if (!mapping)
		rc = migrate_page(mapping, newpage, page, mode);
	else if (mapping->a_ops->migratepage)
		/*
		 * Most pages have a mapping and most filesystems provide a
		 * migratepage callback. Anonymous pages are part of swap
		 * space which also has its own migratepage callback. This
		 * is the most common path for page migration.
		 */
		rc = mapping->a_ops->migratepage(mapping,
						newpage, page, mode);
	else
		rc = fallback_migrate_page(mapping, newpage, page, mode);

	if (rc != MIGRATEPAGE_SUCCESS) {
		newpage->mapping = NULL;
	} else {
		mem_cgroup_migrate(page, newpage, false);
		if (page_was_mapped)
			remove_migration_ptes(page, newpage);
		page->mapping = NULL;
	}

	unlock_page(newpage);

	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;

	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
		 */
		if (mode != MIGRATE_SYNC) {
			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.
	 */
	if (PageAnon(page) && !PageKsm(page)) {
		/*
		 * Only page_lock_anon_vma_read() understands the subtleties of
		 * getting a hold on an anon_vma from outside one of its mms.
		 */
		anon_vma = page_get_anon_vma(page);
		if (anon_vma) {
			/*
			 * Anon page
			 */
		} else if (PageSwapCache(page)) {
			/*
			 * We cannot be sure that the anon_vma of an unmapped
			 * swapcache page is safe to use because we don't
			 * know in advance if the VMA that this page belonged
			 * to still exists. If the VMA and others sharing the
			 * data have been freed, then the anon_vma could
			 * already be invalid.
			 *
			 * To avoid this possibility, swapcache pages get
			 * migrated but are not remapped when migration
			 * completes
			 */
		} else {
			goto out_unlock;
		}
	}

	if (unlikely(isolated_balloon_page(page))) {
		/*
		 * A ballooned page does not need any special attention from
		 * physical to virtual reverse mapping procedures.
		 * Skip any attempt to unmap PTEs or to remap swap cache,
		 * in order to avoid burning cycles at rmap level, and perform
		 * the page migration right away (proteced by page lock).
		 */
		rc = balloon_page_migrate(newpage, page, mode);
		goto out_unlock;
	}

	/*
	 * 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;
		}
		goto skip_unmap;
	}

	/* Establish migration ptes or remove ptes */
	if (page_mapped(page)) {
		try_to_unmap(page,
			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
		page_was_mapped = 1;
	}

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

	if (rc && page_was_mapped)
		remove_migration_ptes(page, page);

	/* Drop an anon_vma reference if we took one */
	if (anon_vma)
		put_anon_vma(anon_vma);

out_unlock:
	unlock_page(page);
out:
	return rc;
}

/*
 * Obtain the lock on page, remove all ptes and migrate the page
 * to the newly allocated page in newpage.
 */
static 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)
{
	int rc = 0;
	int *result = NULL;
	struct page *newpage = get_new_page(page, private, &result);

	if (!newpage)
		return -ENOMEM;

	if (page_count(page) == 1) {
		/* page was freed from under us. So we are done. */
		goto out;
	}

	if (unlikely(PageTransHuge(page)))
		if (unlikely(split_huge_page(page)))
			goto out;

	rc = __unmap_and_move(page, newpage, force, mode);

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);
		dec_zone_page_state(page, NR_ISOLATED_ANON +
				page_is_file_cache(page));
		putback_lru_page(page);
	}

	/*
	 * If migration was not successful and there's a freeing callback, use
	 * it.  Otherwise, putback_lru_page() will drop the reference grabbed
	 * during isolation.
	 */
	if (rc != MIGRATEPAGE_SUCCESS && put_new_page) {
		ClearPageSwapBacked(newpage);
		put_new_page(newpage, private);
	} 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 rc = 0;
	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.