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/vmstat.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 <linux/delay.h>
#include <linux/kthread.h>

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

#include <linux/swapops.h>

#include "internal.h"

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

	/* 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;

	int swappiness;

	int all_unreclaimable;
};

/*
 * 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;
long vm_total_pages;	/* The total number of pages which the VM controls */

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;
			count_vm_events(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);
}

/* 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;

/*
 * 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,
			.range_start = 0,
			.range_end = LLONG_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);
		}
		inc_zone_page_state(page, NR_VMSCAN_WRITE);
		return PAGE_SUCCESS;
	}

	return PAGE_CLEAN;
}

/*
 * Attempt to detach a locked page from its ->mapping.  If it is dirty or if
 * someone else has a ref on the page, abort and return 0.  If it was
 * successfully detached, return 1.  Assumes the caller has a single ref on
 * this page.
 */
int remove_mapping(struct address_space *mapping, struct page *page)
{
	BUG_ON(!PageLocked(page));
	BUG_ON(mapping != page_mapping(page));

	write_lock_irq(&mapping->tree_lock);
	/*
	 * The non racy check for a busy page.
	 *
	 * Must be careful with the order of the tests. When someone has
	 * a ref to the page, it may be possible that they dirty it then
	 * drop the reference. So if PageDirty is tested before page_count
	 * here, then the following race may occur:
	 *
	 * get_user_pages(&page);
	 * [user mapping goes away]
	 * write_to(page);
	 *				!PageDirty(page)    [good]
	 * SetPageDirty(page);
	 * put_page(page);
	 *				!page_count(page)   [good, discard it]
	 *
	 * [oops, our write_to data is lost]
	 *
	 * Reversing the order of the tests ensures such a situation cannot
	 * escape unnoticed. The smp_rmb is needed to ensure the page->flags
	 * load is not satisfied before that of page->_count.
	 *
	 * Note that if SetPageDirty is always performed via set_page_dirty,
	 * and thus under tree_lock, then this ordering is not required.
	 */
	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;

		VM_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 (!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) {
			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 (!mapping || !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);
		VM_BUG_ON(PageLRU(page));
	}
	list_splice(&ret_pages, page_list);
	if (pagevec_count(&freed_pvec))
		__pagevec_release_nonlru(&freed_pvec);
	count_vm_events(PGACTIVATE, pgactivate);
	return nr_reclaimed;
}

/*
 * zone->lru_lock is heavily contended.  Some of the functions that
 * shrink the lists perform better by taking out a batch of pages
 * and working on them outside the LRU lock.
 *
 * For pagecache intensive workloads, this function is the hottest
 * spot in the kernel (apart from copy_*_user functions).
 *
 * Appropriate locks must be held before calling this function.
 *
 * @nr_to_scan:	The number of pages to look through on the list.
 * @src:	The LRU list to pull pages off.
 * @dst:	The temp list to put pages on to.
 * @scanned:	The number of pages that were scanned.
 *
 * returns how many pages were moved onto *@dst.
 */
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
		struct list_head *src, struct list_head *dst,
		unsigned long *scanned)
{
	unsigned long nr_taken = 0;
	struct page *page;
	unsigned long scan;

	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
		struct list_head *target;
		page = lru_to_page(src);
		prefetchw_prev_lru_page(page, src, flags);

		VM_BUG_ON(!PageLRU(page));

		list_del(&page->lru);
		target = src;
		if (likely(get_page_unless_zero(page))) {
			/*
			 * Be careful not to clear PageLRU until after we're
			 * sure the page is not being freed elsewhere -- the
			 * page release code relies on it.
			 */
			ClearPageLRU(page);
			target = dst;
			nr_taken++;
		} /* else it is being freed elsewhere */

		list_add(&page->lru, target);
	}

	*scanned = scan;
	return nr_taken;
}

/*
 * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
 * of reclaimed pages
 */
static unsigned long shrink_inactive_list(unsigned long max_scan,
				struct zone *zone, struct scan_control *sc)
{
	LIST_HEAD(page_list);
	struct pagevec pvec;
	unsigned long nr_scanned = 0;
	unsigned long nr_reclaimed = 0;

	pagevec_init(&pvec, 1);

	lru_add_drain();
	spin_lock_irq(&zone->lru_lock);
	do {
		struct page *page;
		unsigned long nr_taken;
		unsigned long nr_scan;
		unsigned long nr_freed;

		nr_taken = isolate_lru_pages(sc->swap_cluster_max,
					     &zone->inactive_list,
					     &page_list, &nr_scan);
		zone->nr_inactive -= nr_taken;
		zone->pages_scanned += nr_scan;
		spin_unlock_irq(&zone->lru_lock);

		nr_scanned += nr_scan;
		nr_freed = shrink_page_list(&page_list, sc);
		nr_reclaimed += nr_freed;
		local_irq_disable();
		if (current_is_kswapd()) {
			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
			__count_vm_events(KSWAPD_STEAL, nr_freed);
		} else
			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
		__count_vm_events(PGACTIVATE, nr_freed);

		if (nr_taken == 0)
			goto done;

		spin_lock(&zone->lru_lock);
		/*
		 * Put back any unfreeable pages.
		 */
		while (!list_empty(&page_list)) {
			page = lru_to_page(&page_list);
			VM_BUG_ON(PageLRU(page));
			SetPageLRU(page);
			list_del(&page->lru);
			if (PageActive(page))
				add_page_to_active_list(zone, page);
			else
				add_page_to_inactive_list(zone, page);
			if (!pagevec_add(&pvec, page)) {
				spin_unlock_irq(&zone->lru_lock);
				__pagevec_release(&pvec);
				spin_lock_irq(&zone->lru_lock);
			}
		}
  	} while (nr_scanned < max_scan);
	spin_unlock(&zone->lru_lock);
done:
	local_irq_enable();
	pagevec_release(&pvec);
	return nr_reclaimed;
}

/*
 * We are about to scan this zone at a certain priority level.  If that priority
 * level is smaller (ie: more urgent) than the previous priority, then note
 * that priority level within the zone.  This is done so that when the next
 * process comes in to scan this zone, it will immediately start out at this
 * priority level rather than having to build up its own scanning priority.
 * Here, this priority affects only the reclaim-mapped threshold.
 */
static inline void note_zone_scanning_priority(struct zone *zone, int priority)
{
	if (priority < zone->prev_priority)
		zone->prev_priority = priority;
}

static inline int zone_is_near_oom(struct zone *zone)
{
	return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3;
}

/*
 * This moves pages from the active list to the inactive list.
 *
 * We move them the other way if the page is referenced by one or more
 * processes, from rmap.
 *
 * If the pages are mostly unmapped, the processing is fast and it is
 * appropriate to hold zone->lru_lock across the whole operation.  But if
 * the pages are mapped, the processing is slow (page_referenced()) so we
 * should drop zone->lru_lock around each page.  It's impossible to balance
 * this, so instead we remove the pages from the LRU while processing them.
 * It is safe to rely on PG_active against the non-LRU pages in here because
 * nobody will play with that bit on a non-LRU page.
 *
 * The downside is that we have to touch page->_count against each page.
 * But we had to alter page->flags anyway.
 */
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
				struct scan_control *sc, int priority)
{
	unsigned long pgmoved;
	int pgdeactivate = 0;
	unsigned long pgscanned;
	LIST_HEAD(l_hold);	/* The pages which were snipped off */
	LIST_HEAD(l_inactive);	/* Pages to go onto the inactive_list */
	LIST_HEAD(l_active);	/* Pages to go onto the active_list */
	struct page *page;
	struct pagevec pvec;
	int reclaim_mapped = 0;

	if (sc->may_swap) {
		long mapped_ratio;
		long distress;
		long swap_tendency;

		if (zone_is_near_oom(zone))
			goto force_reclaim_mapped;

		/*
		 * `distress' is a measure of how much trouble we're having
		 * reclaiming pages.  0 -> no problems.  100 -> great trouble.
		 */
		distress = 100 >> min(zone->prev_priority, priority);

		/*
		 * The point of this algorithm is to decide when to start
		 * reclaiming mapped memory instead of just pagecache.  Work out
		 * how much memory
		 * is mapped.
		 */
		mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
				global_page_state(NR_ANON_PAGES)) * 100) /
					vm_total_pages;

		/*
		 * Now decide how much we really want to unmap some pages.  The
		 * mapped ratio is downgraded - just because there's a lot of
		 * mapped memory doesn't necessarily mean that page reclaim
		 * isn't succeeding.
		 *
		 * The distress ratio is important - we don't want to start
		 * going oom.
		 *
		 * A 100% value of vm_swappiness overrides this algorithm
		 * altogether.
		 */
		swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;

		/*
		 * Now use this metric to decide whether to start moving mapped
		 * memory onto the inactive list.
		 */
		if (swap_tendency >= 100)
force_reclaim_mapped:
			reclaim_mapped = 1;
	}

	lru_add_drain();
	spin_lock_irq(&zone->lru_lock);
	pgmoved = isolate_lru_pages(nr_pages, &zone->active_list,
				    &l_hold, &pgscanned);
	zone->pages_scanned += pgscanned;
	zone->nr_active -= pgmoved;
	spin_unlock_irq(&zone->lru_lock);

	while (!list_empty(&l_hold)) {
		cond_resched();
		page = lru_to_page(&l_hold);
		list_del(&page->lru);
		if (page_mapped(page)) {
			if (!reclaim_mapped ||
			    (total_swap_pages == 0 && PageAnon(page)) ||
			    page_referenced(page, 0)) {
				list_add(&page->lru, &l_active);
				continue;
			}
		}
		list_add(&page->lru, &l_inactive);
	}

	pagevec_init(&pvec, 1);
	pgmoved = 0;
	spin_lock_irq(&zone->lru_lock);
	while (!list_empty(&l_inactive)) {
		page = lru_to_page(&l_inactive);
		prefetchw_prev_lru_page(page, &l_inactive, flags);
		VM_BUG_ON(PageLRU(page));
		SetPageLRU(page);
		VM_BUG_ON(!PageActive(page));
		ClearPageActive(page);

		list_move(&page->lru, &zone->inactive_list);
		pgmoved++;
		if (!pagevec_add(&pvec, page)) {
			zone->nr_inactive += pgmoved;
			spin_unlock_irq(&zone->lru_lock);
			pgdeactivate += pgmoved;
			pgmoved = 0;
			if (buffer_heads_over_limit)
				pagevec_strip(&pvec);
			__pagevec_release(&pvec);
			spin_lock_irq(&zone->lru_lock);
		}
	}
	zone->nr_inactive += pgmoved;
	pgdeactivate += pgmoved;
	if (buffer_heads_over_limit) {
		spin_unlock_irq(&zone->lru_lock);
		pagevec_strip(&pvec);
		spin_lock_irq(&zone->lru_lock);
	}

	pgmoved = 0;
	while (!list_empty(&l_active)) {
		page = lru_to_page(&l_active);
		prefetchw_prev_lru_page(page, &l_active, flags);
		VM_BUG_ON(PageLRU(page));
		SetPageLRU(page);
		VM_BUG_ON(!PageActive(page));
		list_move(&page->lru, &zone->active_list);
		pgmoved++;
		if (!pagevec_add(&pvec, page)) {
			zone->nr_active += pgmoved;
			pgmoved = 0;
			spin_unlock_irq(&zone->lru_lock);
			__pagevec_release(&pvec);
			spin_lock_irq(&zone->lru_lock);
		}
	}
	zone->nr_active += pgmoved;

	__count_zone_vm_events(PGREFILL, zone, pgscanned);
	__count_vm_events(PGDEACTIVATE, pgdeactivate);
	spin_unlock_irq(&zone->lru_lock);

	pagevec_release(&pvec);
}

/*
 * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
 */
static unsigned long shrink_zone(int priority, struct zone *zone,
				struct scan_control *sc)
{
	unsigned long nr_active;
	unsigned long nr_inactive;
	unsigned long nr_to_scan;
	unsigned long nr_reclaimed = 0;

	atomic_inc(&zone->reclaim_in_progress);

	/*
	 * Add one to `nr_to_scan' just to make sure that the kernel will
	 * slowly sift through the active list.
	 */
	zone->nr_scan_active += (zone->nr_active >> priority) + 1;
	nr_active = zone->nr_scan_active;
	if (nr_active >= sc->swap_cluster_max)
		zone->nr_scan_active = 0;
	else
		nr_active = 0;

	zone->nr_scan_inactive += (zone->nr_inactive >> priority) + 1;
	nr_inactive = zone->nr_scan_inactive;
	if (nr_inactive >= sc->swap_cluster_max)
		zone->nr_scan_inactive = 0;
	else
		nr_inactive = 0;

	while (nr_active || nr_inactive) {
		if (nr_active) {
			nr_to_scan = min(nr_active,
					(unsigned long)sc->swap_cluster_max);
			nr_active -= nr_to_scan;
			shrink_active_list(nr_to_scan, zone, sc, priority);
		}

		if (nr_inactive) {
			nr_to_scan = min(nr_inactive,
					(unsigned long)sc->swap_cluster_max);
			nr_inactive -= nr_to_scan;
			nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
								sc);
		}
	}

	throttle_vm_writeout();

	atomic_dec(&zone->reclaim_in_progress);
	return nr_reclaimed;
}

/*
 * This is the direct reclaim path, for page-allocating processes.  We only
 * try to reclaim pages from zones which will satisfy the caller's allocation
 * request.
 *
 * We reclaim from a zone even if that zone is over pages_high.  Because:
 * a) The caller may be trying to free *extra* pages to satisfy a higher-order
 *    allocation or
 * b) The zones may be over pages_high but they must go *over* pages_high to
 *    satisfy the `incremental min' zone defense algorithm.
 *
 * Returns the number of reclaimed pages.
 *
 * If a zone is deemed to be full of pinned pages then just give it a light
 * scan then give up on it.
 */
static unsigned long shrink_zones(int priority, struct zone **zones,
					struct scan_control *sc)
{
	unsigned long nr_reclaimed = 0;
	int i;

	sc->all_unreclaimable = 1;
	for (i = 0; zones[i] != NULL; i++) {
		struct zone *zone = zones[i];

		if (!populated_zone(zone))
			continue;

		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
			continue;

		note_zone_scanning_priority(zone, priority);

		if (zone->all_unreclaimable && priority != DEF_PRIORITY)
			continue;	/* Let kswapd poll it */

		sc->all_unreclaimable = 0;

		nr_reclaimed += shrink_zone(priority, zone, sc);
	}
	return nr_reclaimed;
}