vmscan.c

/*
 *  linux/mm/vmscan.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Swap reorganised 29.12.95, Stephen Tweedie.
 *  kswapd added: 7.1.96  sct
 *  Removed kswapd_ctl limits, and swap out as many pages as needed
 *  to bring the system back to freepages.high: 2.4.97, Rik van Riel.
 *  Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
 *  Multiqueue VM started 5.8.00, Rik van Riel.
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>	/* for try_to_release_page(),
					buffer_heads_over_limit */
#include <linux/mm_inline.h>
#include <linux/pagevec.h>
#include <linux/backing-dev.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>

#include <asm/tlbflush.h>
#include <asm/div64.h>

#include <linux/swapops.h>

#include "internal.h"

/* possible outcome of pageout() */
typedef enum {
	/* failed to write page out, page is locked */
	PAGE_KEEP,
	/* move page to the active list, page is locked */
	PAGE_ACTIVATE,
	/* page has been sent to the disk successfully, page is unlocked */
	PAGE_SUCCESS,
	/* page is clean and locked */
	PAGE_CLEAN,
} pageout_t;

struct scan_control {
	/* Incremented by the number of inactive pages that were scanned */
	unsigned long nr_scanned;

	unsigned long nr_mapped;	/* From page_state */

	/* This context's GFP mask */
	gfp_t gfp_mask;

	int may_writepage;

	/* Can pages be swapped as part of reclaim? */
	int may_swap;

	/* This context's SWAP_CLUSTER_MAX. If freeing memory for
	 * suspend, we effectively ignore SWAP_CLUSTER_MAX.
	 * In this context, it doesn't matter that we scan the
	 * whole list at once. */
	int swap_cluster_max;
};

/*
 * The list of shrinker callbacks used by to apply pressure to
 * ageable caches.
 */
struct shrinker {
	shrinker_t		shrinker;
	struct list_head	list;
	int			seeks;	/* seeks to recreate an obj */
	long			nr;	/* objs pending delete */
};

#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))

#ifdef ARCH_HAS_PREFETCH
#define prefetch_prev_lru_page(_page, _base, _field)			\
	do {								\
		if ((_page)->lru.prev != _base) {			\
			struct page *prev;				\
									\
			prev = lru_to_page(&(_page->lru));		\
			prefetch(&prev->_field);			\
		}							\
	} while (0)
#else
#define prefetch_prev_lru_page(_page, _base, _field) do { } while (0)
#endif

#ifdef ARCH_HAS_PREFETCHW
#define prefetchw_prev_lru_page(_page, _base, _field)			\
	do {								\
		if ((_page)->lru.prev != _base) {			\
			struct page *prev;				\
									\
			prev = lru_to_page(&(_page->lru));		\
			prefetchw(&prev->_field);			\
		}							\
	} while (0)
#else
#define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0)
#endif

/*
 * From 0 .. 100.  Higher means more swappy.
 */
int vm_swappiness = 60;
static long total_memory;

static LIST_HEAD(shrinker_list);
static DECLARE_RWSEM(shrinker_rwsem);

/*
 * Add a shrinker callback to be called from the vm
 */
struct shrinker *set_shrinker(int seeks, shrinker_t theshrinker)
{
        struct shrinker *shrinker;

        shrinker = kmalloc(sizeof(*shrinker), GFP_KERNEL);
        if (shrinker) {
	        shrinker->shrinker = theshrinker;
	        shrinker->seeks = seeks;
	        shrinker->nr = 0;
	        down_write(&shrinker_rwsem);
	        list_add_tail(&shrinker->list, &shrinker_list);
	        up_write(&shrinker_rwsem);
	}
	return shrinker;
}
EXPORT_SYMBOL(set_shrinker);

/*
 * Remove one
 */
void remove_shrinker(struct shrinker *shrinker)
{
	down_write(&shrinker_rwsem);
	list_del(&shrinker->list);
	up_write(&shrinker_rwsem);
	kfree(shrinker);
}
EXPORT_SYMBOL(remove_shrinker);

#define SHRINK_BATCH 128
/*
 * Call the shrink functions to age shrinkable caches
 *
 * Here we assume it costs one seek to replace a lru page and that it also
 * takes a seek to recreate a cache object.  With this in mind we age equal
 * percentages of the lru and ageable caches.  This should balance the seeks
 * generated by these structures.
 *
 * If the vm encounted mapped pages on the LRU it increase the pressure on
 * slab to avoid swapping.
 *
 * We do weird things to avoid (scanned*seeks*entries) overflowing 32 bits.
 *
 * `lru_pages' represents the number of on-LRU pages in all the zones which
 * are eligible for the caller's allocation attempt.  It is used for balancing
 * slab reclaim versus page reclaim.
 *
 * Returns the number of slab objects which we shrunk.
 */
unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
			unsigned long lru_pages)
{
	struct shrinker *shrinker;
	unsigned long ret = 0;

	if (scanned == 0)
		scanned = SWAP_CLUSTER_MAX;

	if (!down_read_trylock(&shrinker_rwsem))
		return 1;	/* Assume we'll be able to shrink next time */

	list_for_each_entry(shrinker, &shrinker_list, list) {
		unsigned long long delta;
		unsigned long total_scan;
		unsigned long max_pass = (*shrinker->shrinker)(0, gfp_mask);

		delta = (4 * scanned) / shrinker->seeks;
		delta *= max_pass;
		do_div(delta, lru_pages + 1);
		shrinker->nr += delta;
		if (shrinker->nr < 0) {
			printk(KERN_ERR "%s: nr=%ld\n",
					__FUNCTION__, shrinker->nr);
			shrinker->nr = max_pass;
		}

		/*
		 * Avoid risking looping forever due to too large nr value:
		 * never try to free more than twice the estimate number of
		 * freeable entries.
		 */
		if (shrinker->nr > max_pass * 2)
			shrinker->nr = max_pass * 2;

		total_scan = shrinker->nr;
		shrinker->nr = 0;

		while (total_scan >= SHRINK_BATCH) {
			long this_scan = SHRINK_BATCH;
			int shrink_ret;
			int nr_before;

			nr_before = (*shrinker->shrinker)(0, gfp_mask);
			shrink_ret = (*shrinker->shrinker)(this_scan, gfp_mask);
			if (shrink_ret == -1)
				break;
			if (shrink_ret < nr_before)
				ret += nr_before - shrink_ret;
			mod_page_state(slabs_scanned, this_scan);
			total_scan -= this_scan;

			cond_resched();
		}

		shrinker->nr += total_scan;
	}
	up_read(&shrinker_rwsem);
	return ret;
}

/* Called without lock on whether page is mapped, so answer is unstable */
static inline int page_mapping_inuse(struct page *page)
{
	struct address_space *mapping;

	/* Page is in somebody's page tables. */
	if (page_mapped(page))
		return 1;

	/* Be more reluctant to reclaim swapcache than pagecache */
	if (PageSwapCache(page))
		return 1;

	mapping = page_mapping(page);
	if (!mapping)
		return 0;

	/* File is mmap'd by somebody? */
	return mapping_mapped(mapping);
}

static inline int is_page_cache_freeable(struct page *page)
{
	return page_count(page) - !!PagePrivate(page) == 2;
}

static int may_write_to_queue(struct backing_dev_info *bdi)
{
	if (current->flags & PF_SWAPWRITE)
		return 1;
	if (!bdi_write_congested(bdi))
		return 1;
	if (bdi == current->backing_dev_info)
		return 1;
	return 0;
}

/*
 * We detected a synchronous write error writing a page out.  Probably
 * -ENOSPC.  We need to propagate that into the address_space for a subsequent
 * fsync(), msync() or close().
 *
 * The tricky part is that after writepage we cannot touch the mapping: nothing
 * prevents it from being freed up.  But we have a ref on the page and once
 * that page is locked, the mapping is pinned.
 *
 * We're allowed to run sleeping lock_page() here because we know the caller has
 * __GFP_FS.
 */
static void handle_write_error(struct address_space *mapping,
				struct page *page, int error)
{
	lock_page(page);
	if (page_mapping(page) == mapping) {
		if (error == -ENOSPC)
			set_bit(AS_ENOSPC, &mapping->flags);
		else
			set_bit(AS_EIO, &mapping->flags);
	}
	unlock_page(page);
}

/*
 * pageout is called by shrink_page_list() for each dirty page.
 * Calls ->writepage().
 */
static pageout_t pageout(struct page *page, struct address_space *mapping)
{
	/*
	 * If the page is dirty, only perform writeback if that write
	 * will be non-blocking.  To prevent this allocation from being
	 * stalled by pagecache activity.  But note that there may be
	 * stalls if we need to run get_block().  We could test
	 * PagePrivate for that.
	 *
	 * If this process is currently in generic_file_write() against
	 * this page's queue, we can perform writeback even if that
	 * will block.
	 *
	 * If the page is swapcache, write it back even if that would
	 * block, for some throttling. This happens by accident, because
	 * swap_backing_dev_info is bust: it doesn't reflect the
	 * congestion state of the swapdevs.  Easy to fix, if needed.
	 * See swapfile.c:page_queue_congested().
	 */
	if (!is_page_cache_freeable(page))
		return PAGE_KEEP;
	if (!mapping) {
		/*
		 * Some data journaling orphaned pages can have
		 * page->mapping == NULL while being dirty with clean buffers.
		 */
		if (PagePrivate(page)) {
			if (try_to_free_buffers(page)) {
				ClearPageDirty(page);
				printk("%s: orphaned page\n", __FUNCTION__);
				return PAGE_CLEAN;
			}
		}
		return PAGE_KEEP;
	}
	if (mapping->a_ops->writepage == NULL)
		return PAGE_ACTIVATE;
	if (!may_write_to_queue(mapping->backing_dev_info))
		return PAGE_KEEP;

	if (clear_page_dirty_for_io(page)) {
		int res;
		struct writeback_control wbc = {
			.sync_mode = WB_SYNC_NONE,
			.nr_to_write = SWAP_CLUSTER_MAX,
			.nonblocking = 1,
			.for_reclaim = 1,
		};

		SetPageReclaim(page);
		res = mapping->a_ops->writepage(page, &wbc);
		if (res < 0)
			handle_write_error(mapping, page, res);
		if (res == AOP_WRITEPAGE_ACTIVATE) {
			ClearPageReclaim(page);
			return PAGE_ACTIVATE;
		}
		if (!PageWriteback(page)) {
			/* synchronous write or broken a_ops? */
			ClearPageReclaim(page);
		}

		return PAGE_SUCCESS;
	}

	return PAGE_CLEAN;
}

static int remove_mapping(struct address_space *mapping, struct page *page)
{
	if (!mapping)
		return 0;		/* truncate got there first */

	write_lock_irq(&mapping->tree_lock);

	/*
	 * The non-racy check for busy page.  It is critical to check
	 * PageDirty _after_ making sure that the page is freeable and
	 * not in use by anybody. 	(pagecache + us == 2)
	 */
	if (unlikely(page_count(page) != 2))
		goto cannot_free;
	smp_rmb();
	if (unlikely(PageDirty(page)))
		goto cannot_free;

	if (PageSwapCache(page)) {
		swp_entry_t swap = { .val = page_private(page) };
		__delete_from_swap_cache(page);
		write_unlock_irq(&mapping->tree_lock);
		swap_free(swap);
		__put_page(page);	/* The pagecache ref */
		return 1;
	}

	__remove_from_page_cache(page);
	write_unlock_irq(&mapping->tree_lock);
	__put_page(page);
	return 1;

cannot_free:
	write_unlock_irq(&mapping->tree_lock);
	return 0;
}

/*
 * shrink_page_list() returns the number of reclaimed pages
 */
static unsigned long shrink_page_list(struct list_head *page_list,
					struct scan_control *sc)
{
	LIST_HEAD(ret_pages);
	struct pagevec freed_pvec;
	int pgactivate = 0;
	unsigned long nr_reclaimed = 0;

	cond_resched();

	pagevec_init(&freed_pvec, 1);
	while (!list_empty(page_list)) {
		struct address_space *mapping;
		struct page *page;
		int may_enter_fs;
		int referenced;

		cond_resched();

		page = lru_to_page(page_list);
		list_del(&page->lru);

		if (TestSetPageLocked(page))
			goto keep;

		BUG_ON(PageActive(page));

		sc->nr_scanned++;

		if (!sc->may_swap && page_mapped(page))
			goto keep_locked;

		/* Double the slab pressure for mapped and swapcache pages */
		if (page_mapped(page) || PageSwapCache(page))
			sc->nr_scanned++;

		if (PageWriteback(page))
			goto keep_locked;

		referenced = page_referenced(page, 1);
		/* In active use or really unfreeable?  Activate it. */
		if (referenced && page_mapping_inuse(page))
			goto activate_locked;

#ifdef CONFIG_SWAP
		/*
		 * Anonymous process memory has backing store?
		 * Try to allocate it some swap space here.
		 */
		if (PageAnon(page) && !PageSwapCache(page)) {
			if (!sc->may_swap)
				goto keep_locked;
			if (!add_to_swap(page, GFP_ATOMIC))
				goto activate_locked;
		}
#endif /* CONFIG_SWAP */

		mapping = page_mapping(page);
		may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));

		/*
		 * The page is mapped into the page tables of one or more
		 * processes. Try to unmap it here.
		 */
		if (page_mapped(page) && mapping) {
			/*
			 * No unmapping if we do not swap
			 */
			if (!sc->may_swap)
				goto keep_locked;

			switch (try_to_unmap(page, 0)) {
			case SWAP_FAIL:
				goto activate_locked;
			case SWAP_AGAIN:
				goto keep_locked;
			case SWAP_SUCCESS:
				; /* try to free the page below */
			}
		}

		if (PageDirty(page)) {
			if (referenced)
				goto keep_locked;
			if (!may_enter_fs)
				goto keep_locked;
			if (!sc->may_writepage)
				goto keep_locked;

			/* Page is dirty, try to write it out here */
			switch(pageout(page, mapping)) {
			case PAGE_KEEP:
				goto keep_locked;
			case PAGE_ACTIVATE:
				goto activate_locked;
			case PAGE_SUCCESS:
				if (PageWriteback(page) || PageDirty(page))
					goto keep;
				/*
				 * A synchronous write - probably a ramdisk.  Go
				 * ahead and try to reclaim the page.
				 */
				if (TestSetPageLocked(page))
					goto keep;
				if (PageDirty(page) || PageWriteback(page))
					goto keep_locked;
				mapping = page_mapping(page);
			case PAGE_CLEAN:
				; /* try to free the page below */
			}
		}

		/*
		 * If the page has buffers, try to free the buffer mappings
		 * associated with this page. If we succeed we try to free
		 * the page as well.
		 *
		 * We do this even if the page is PageDirty().
		 * try_to_release_page() does not perform I/O, but it is
		 * possible for a page to have PageDirty set, but it is actually
		 * clean (all its buffers are clean).  This happens if the
		 * buffers were written out directly, with submit_bh(). ext3
		 * will do this, as well as the blockdev mapping. 
		 * try_to_release_page() will discover that cleanness and will
		 * drop the buffers and mark the page clean - it can be freed.
		 *
		 * Rarely, pages can have buffers and no ->mapping.  These are
		 * the pages which were not successfully invalidated in
		 * truncate_complete_page().  We try to drop those buffers here
		 * and if that worked, and the page is no longer mapped into
		 * process address space (page_count == 1) it can be freed.
		 * Otherwise, leave the page on the LRU so it is swappable.
		 */
		if (PagePrivate(page)) {
			if (!try_to_release_page(page, sc->gfp_mask))
				goto activate_locked;
			if (!mapping && page_count(page) == 1)
				goto free_it;
		}

		if (!remove_mapping(mapping, page))
			goto keep_locked;

free_it:
		unlock_page(page);
		nr_reclaimed++;
		if (!pagevec_add(&freed_pvec, page))
			__pagevec_release_nonlru(&freed_pvec);
		continue;

activate_locked:
		SetPageActive(page);
		pgactivate++;
keep_locked:
		unlock_page(page);
keep:
		list_add(&page->lru, &ret_pages);
		BUG_ON(PageLRU(page));
	}
	list_splice(&ret_pages, page_list);
	if (pagevec_count(&freed_pvec))
		__pagevec_release_nonlru(&freed_pvec);
	mod_page_state(pgactivate, pgactivate);
	return nr_reclaimed;
}

#ifdef CONFIG_MIGRATION
static inline void move_to_lru(struct page *page)
{
	list_del(&page->lru);
	if (PageActive(page)) {
		/*
		 * lru_cache_add_active checks that
		 * the PG_active bit is off.
		 */
		ClearPageActive(page);
		lru_cache_add_active(page);
	} else {
		lru_cache_add(page);
	}
	put_page(page);
}

/*
 * Add isolated pages on the list back to the LRU.
 *
 * returns the number of pages put back.
 */
unsigned long putback_lru_pages(struct list_head *l)
{
	struct page *page;
	struct page *page2;
	unsigned long count = 0;

	list_for_each_entry_safe(page, page2, l, lru) {
		move_to_lru(page);
		count++;
	}
	return count;
}

/*
 * Non migratable page
 */
int fail_migrate_page(struct page *newpage, struct page *page)
{
	return -EIO;
}
EXPORT_SYMBOL(fail_migrate_page);

/*
 * swapout a single page
 * page is locked upon entry, unlocked on exit
 */
static int swap_page(struct page *page)
{
	struct address_space *mapping = page_mapping(page);

	if (page_mapped(page) && mapping)
		if (try_to_unmap(page, 1) != SWAP_SUCCESS)
			goto unlock_retry;

	if (PageDirty(page)) {
		/* Page is dirty, try to write it out here */
		switch(pageout(page, mapping)) {
		case PAGE_KEEP:
		case PAGE_ACTIVATE:
			goto unlock_retry;

		case PAGE_SUCCESS:
			goto retry;

		case PAGE_CLEAN:
			; /* try to free the page below */
		}
	}

	if (PagePrivate(page)) {
		if (!try_to_release_page(page, GFP_KERNEL) ||
		    (!mapping && page_count(page) == 1))
			goto unlock_retry;
	}

	if (remove_mapping(mapping, page)) {
		/* Success */
		unlock_page(page);
		return 0;
	}

unlock_retry:
	unlock_page(page);

retry:
	return -EAGAIN;
}
EXPORT_SYMBOL(swap_page);

/*
 * 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 <clameter@sgi.com>
 */

/*
 * Remove references for a page and establish the new page with the correct
 * basic settings to be able to stop accesses to the page.
 */
int migrate_page_remove_references(struct page *newpage,
				struct page *page, int nr_refs)
{
	struct address_space *mapping = page_mapping(page);
	struct page **radix_pointer;

	/*
	 * Avoid doing any of the following work if the page count
	 * indicates that the page is in use or truncate has removed
	 * the page.
	 */
	if (!mapping || page_mapcount(page) + nr_refs != page_count(page))
		return -EAGAIN;

	/*
	 * Establish swap ptes for anonymous pages or destroy pte
	 * maps for files.
	 *
	 * In order to reestablish file backed mappings the fault handlers
	 * will take the radix tree_lock which may then be used to stop
  	 * processses from accessing this page until the new page is ready.
	 *
	 * A process accessing via a swap pte (an anonymous page) will take a
	 * page_lock on the old page which will block the process until the
	 * migration attempt is complete. At that time the PageSwapCache bit
	 * will be examined. If the page was migrated then the PageSwapCache
	 * bit will be clear and the operation to retrieve the page will be
	 * retried which will find the new page in the radix tree. Then a new
	 * direct mapping may be generated based on the radix tree contents.
	 *
	 * If the page was not migrated then the PageSwapCache bit
	 * is still set and the operation may continue.
	 */
	if (try_to_unmap(page, 1) == SWAP_FAIL)
		/* A vma has VM_LOCKED set -> Permanent failure */
		return -EPERM;

	/*
	 * Give up if we were unable to remove all mappings.
	 */
	if (page_mapcount(page))
		return -EAGAIN;

	write_lock_irq(&mapping->tree_lock);

	radix_pointer = (struct page **)radix_tree_lookup_slot(
						&mapping->page_tree,
						page_index(page));

	if (!page_mapping(page) || page_count(page) != nr_refs ||
			*radix_pointer != page) {
		write_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	/*
	 * Now we know that no one else is looking at the page.
	 *
	 * Certain minimal information about a page must be available
	 * in order for other subsystems to properly handle the page if they
	 * find it through the radix tree update before we are finished
	 * copying the page.
	 */
	get_page(newpage);
	newpage->index = page->index;
	newpage->mapping = page->mapping;
	if (PageSwapCache(page)) {
		SetPageSwapCache(newpage);
		set_page_private(newpage, page_private(page));
	}

	*radix_pointer = newpage;
	__put_page(page);
	write_unlock_irq(&mapping->tree_lock);

	return 0;
}
EXPORT_SYMBOL(migrate_page_remove_references);

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

	if (PageError(page))
		SetPageError(newpage);
	if (PageReferenced(page))
		SetPageReferenced(newpage);
	if (PageUptodate(page))
		SetPageUptodate(newpage);
	if (PageActive(page))
		SetPageActive(newpage);
	if (PageChecked(page))
		SetPageChecked(newpage);
	if (PageMappedToDisk(page))
		SetPageMappedToDisk(newpage);

	if (PageDirty(page)) {
		clear_page_dirty_for_io(page);
		set_page_dirty(newpage);
 	}

	ClearPageSwapCache(page);
	ClearPageActive(page);
	ClearPagePrivate(page);
	set_page_private(page, 0);
	page->mapping = NULL;

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

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

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

	rc = migrate_page_remove_references(newpage, page, 2);

	if (rc)
		return rc;

	migrate_page_copy(newpage, page);

	/*
	 * Remove auxiliary swap entries and replace
	 * them with real ptes.
	 *
	 * Note that a real pte entry will allow processes that are not
	 * waiting on the page lock to use the new page via the page tables
	 * before the new page is unlocked.
	 */
	remove_from_swap(newpage);
	return 0;
}
EXPORT_SYMBOL(migrate_page);

/*
 * migrate_pages
 *
 * Two lists are passed to this function. The first list
 * contains the pages isolated from the LRU to be migrated.
 * The second list contains new pages that the pages isolated
 * can be moved to. If the second list is NULL then all
 * pages are swapped out.
 *
 * The function returns after 10 attempts or if no pages
 * are movable anymore because to has become empty
 * or no retryable pages exist anymore.
 *
 * Return: Number of pages not migrated when "to" ran empty.
 */
unsigned long migrate_pages(struct list_head *from, struct list_head *to,
		  struct list_head *moved, struct list_head *failed)
{
	unsigned long retry;
	unsigned long nr_failed = 0;
	int pass = 0;
	struct page *page;
	struct page *page2;
	int swapwrite = current->flags & PF_SWAPWRITE;
	int rc;

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

redo:
	retry = 0;

	list_for_each_entry_safe(page, page2, from, lru) {
		struct page *newpage = NULL;
		struct address_space *mapping;

		cond_resched();

		rc = 0;
		if (page_count(page) == 1)
			/* page was freed from under us. So we are done. */
			goto next;

		if (to && list_empty(to))
			break;

		/*
		 * Skip locked pages during the first two passes to give the
		 * functions holding the lock time to release the page. Later we
		 * use lock_page() to have a higher chance of acquiring the
		 * lock.
		 */
		rc = -EAGAIN;
		if (pass > 2)
			lock_page(page);
		else
			if (TestSetPageLocked(page))
				goto next;

		/*
		 * Only wait on writeback if we have already done a pass where
		 * we we may have triggered writeouts for lots of pages.
		 */
		if (pass > 0) {
			wait_on_page_writeback(page);
		} else {
			if (PageWriteback(page))
				goto unlock_page;
		}

		/*
		 * Anonymous pages must have swap cache references otherwise
		 * the information contained in the page maps cannot be
		 * preserved.
		 */
		if (PageAnon(page) && !PageSwapCache(page)) {
			if (!add_to_swap(page, GFP_KERNEL)) {
				rc = -ENOMEM;
				goto unlock_page;
			}
		}

		if (!to) {
			rc = swap_page(page);
			goto next;
		}

		newpage = lru_to_page(to);
		lock_page(newpage);

		/*
		 * Pages are properly locked and writeback is complete.
		 * Try to migrate the page.
		 */
		mapping = page_mapping(page);
		if (!mapping)
			goto unlock_both;

		if (mapping->a_ops->migratepage) {
			/*
			 * Most pages have a mapping and most filesystems
			 * should provide a migration function. Anonymous
			 * pages are part of swap space which also has its
			 * own migration function. This is the most common
			 * path for page migration.
			 */
			rc = mapping->a_ops->migratepage(newpage, page);
			goto unlock_both;
                }

		/*
		 * Default handling if a filesystem does not provide
		 * a migration function. We can only migrate clean
		 * pages so try to write out any dirty pages first.
		 */
		if (PageDirty(page)) {
			switch (pageout(page, mapping)) {
			case PAGE_KEEP:
			case PAGE_ACTIVATE:
				goto unlock_both;

			case PAGE_SUCCESS:
				unlock_page(newpage);
				goto next;

			case PAGE_CLEAN:
				; /* try to migrate the page below */
			}
                }

		/*
		 * Buffers are managed in a filesystem specific way.
		 * We must have no buffers or drop them.
		 */
		if (!page_has_buffers(page) ||
		    try_to_release_page(page, GFP_KERNEL)) {
			rc = migrate_page(newpage, page);
			goto unlock_both;
		}

		/*
		 * On early passes with mapped pages simply
		 * retry. There may be a lock held for some
		 * buffers that may go away. Later
		 * swap them out.
		 */
		if (pass > 4) {
			/*
			 * Persistently unable to drop buffers..... As a
			 * measure of last resort we fall back to
			 * swap_page().
			 */
			unlock_page(newpage);
			newpage = NULL;
			rc = swap_page(page);
			goto next;
		}

unlock_both:
		unlock_page(newpage);

unlock_page:
		unlock_page(page);