mm/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 <linux/freezer.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);
		__mod_zone_page_state(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_zone_vm_events(PGSTEAL, zone, 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_page_state(zone, NR_ACTIVE)
				+ zone_page_state(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;
	__mod_zone_page_state(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)) {
			__mod_zone_page_state(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);
		}
	}
	__mod_zone_page_state(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)) {
			__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
			pgmoved = 0;
			spin_unlock_irq(&zone->lru_lock);
			__pagevec_release(&pvec);
			spin_lock_irq(&zone->lru_lock);
		}
	}
	__mod_zone_page_state(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_page_state(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_page_state(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(sc->gfp_mask);

	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_hardwall(zone, GFP_KERNEL))
			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;
}
 
/*
 * This is the main entry point to direct page reclaim.
 *
 * If a full scan of the inactive list fails to free enough memory then we
 * are "out of memory" and something needs to be killed.
 *
 * If the caller is !__GFP_FS then the probability of a failure is reasonably
 * high - the zone may be full of dirty or under-writeback pages, which this
 * caller can't do much about.  We kick pdflush and take explicit naps in the
 * hope that some of these pages can be written.  But if the allocating task
 * holds filesystem locks which prevent writeout this might not work, and the
 * allocation attempt will fail.
 */
unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
{
	int priority;
	int ret = 0;
	unsigned long total_scanned = 0;
	unsigned long nr_reclaimed = 0;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	unsigned long lru_pages = 0;
	int i;
	struct scan_control sc = {
		.gfp_mask = gfp_mask,
		.may_writepage = !laptop_mode,
		.swap_cluster_max = SWAP_CLUSTER_MAX,
		.may_swap = 1,
		.swappiness = vm_swappiness,
	};

	count_vm_event(ALLOCSTALL);

	for (i = 0; zones[i] != NULL; i++) {
		struct zone *zone = zones[i];

		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
			continue;

		lru_pages += zone_page_state(zone, NR_ACTIVE)
				+ zone_page_state(zone, NR_INACTIVE);
	}

	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
		sc.nr_scanned = 0;
		if (!priority)
			disable_swap_token();
		nr_reclaimed += shrink_zones(priority, zones, &sc);
		shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
		if (reclaim_state) {
			nr_reclaimed += reclaim_state->reclaimed_slab;
			reclaim_state->reclaimed_slab = 0;
		}
		total_scanned += sc.nr_scanned;
		if (nr_reclaimed >= sc.swap_cluster_max) {
			ret = 1;
			goto out;
		}

		/*
		 * Try to write back as many pages as we just scanned.  This
		 * tends to cause slow streaming writers to write data to the
		 * disk smoothly, at the dirtying rate, which is nice.   But
		 * that's undesirable in laptop mode, where we *want* lumpy
		 * writeout.  So in laptop mode, write out the whole world.
		 */
		if (total_scanned > sc.swap_cluster_max +
					sc.swap_cluster_max / 2) {
			wakeup_pdflush(laptop_mode ? 0 : total_scanned);
			sc.may_writepage = 1;
		}

		/* Take a nap, wait for some writeback to complete */
		if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
			congestion_wait(WRITE, HZ/10);
	}
	/* top priority shrink_caches still had more to do? don't OOM, then */
	if (!sc.all_unreclaimable)
		ret = 1;
out:
	/*
	 * Now that we've scanned all the zones at this priority level, note
	 * that level within the zone so that the next thread which performs
	 * scanning of this zone will immediately start out at this priority
	 * level.  This affects only the decision whether or not to bring
	 * mapped pages onto the inactive list.
	 */
	if (priority < 0)
		priority = 0;
	for (i = 0; zones[i] != 0; i++) {
		struct zone *zone = zones[i];

		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
			continue;

		zone->prev_priority = priority;
	}
	return ret;
}

/*
 * For kswapd, balance_pgdat() will work across all this node's zones until
 * they are all at pages_high.
 *
 * Returns the number of pages which were actually freed.
 *
 * There is special handling here for zones which are full of pinned pages.
 * This can happen if the pages are all mlocked, or if they are all used by
 * device drivers (say, ZONE_DMA).  Or if they are all in use by hugetlb.
 * What we do is to detect the case where all pages in the zone have been
 * scanned twice and there has been zero successful reclaim.  Mark the zone as
 * dead and from now on, only perform a short scan.  Basically we're polling
 * the zone for when the problem goes away.
 *
 * kswapd scans the zones in the highmem->normal->dma direction.  It skips
 * zones which have free_pages > pages_high, but once a zone is found to have
 * free_pages <= pages_high, we scan that zone and the lower zones regardless
 * of the number of free pages in the lower zones.  This interoperates with
 * the page allocator fallback scheme to ensure that aging of pages is balanced
 * across the zones.
 */
static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
{
	int all_zones_ok;
	int priority;
	int i;
	unsigned long total_scanned;
	unsigned long nr_reclaimed;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_swap = 1,
		.swap_cluster_max = SWAP_CLUSTER_MAX,
		.swappiness = vm_swappiness,
	};
	/*
	 * temp_priority is used to remember the scanning priority at which
	 * this zone was successfully refilled to free_pages == pages_high.
	 */
	int temp_priority[MAX_NR_ZONES];

loop_again:
	total_scanned = 0;
	nr_reclaimed = 0;
	sc.may_writepage = !laptop_mode;
	count_vm_event(PAGEOUTRUN);

	for (i = 0; i < pgdat->nr_zones; i++)
		temp_priority[i] = DEF_PRIORITY;

	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
		unsigned long lru_pages = 0;

		/* The swap token gets in the way of swapout... */
		if (!priority)
			disable_swap_token();

		all_zones_ok = 1;

		/*
		 * Scan in the highmem->dma direction for the highest
		 * zone which needs scanning
		 */
		for (i = pgdat->nr_zones - 1; i >= 0; i--) {
			struct zone *zone = pgdat->node_zones + i;

			if (!populated_zone(zone))
				continue;

			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
				continue;

			if (!zone_watermark_ok(zone, order, zone->pages_high,
					       0, 0)) {
				end_zone = i;
				break;
			}
		}
		if (i < 0)
			goto out;

		for (i = 0; i <= end_zone; i++) {
			struct zone *zone = pgdat->node_zones + i;

			lru_pages += zone_page_state(zone, NR_ACTIVE)
					+ zone_page_state(zone, NR_INACTIVE);
		}

		/*
		 * Now scan the zone in the dma->highmem direction, stopping
		 * at the last zone which needs scanning.
		 *
		 * We do this because the page allocator works in the opposite
		 * direction.  This prevents the page allocator from allocating
		 * pages behind kswapd's direction of progress, which would
		 * cause too much scanning of the lower zones.
		 */
		for (i = 0; i <= end_zone; i++) {
			struct zone *zone = pgdat->node_zones + i;
			int nr_slab;

			if (!populated_zone(zone))
				continue;

			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
				continue;

			if (!zone_watermark_ok(zone, order, zone->pages_high,
					       end_zone, 0))
				all_zones_ok = 0;
			temp_priority[i] = priority;
			sc.nr_scanned = 0;
			note_zone_scanning_priority(zone, priority);
			nr_reclaimed += shrink_zone(priority, zone, &sc);
			reclaim_state->reclaimed_slab = 0;
			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
						lru_pages);
			nr_reclaimed += reclaim_state->reclaimed_slab;
			total_scanned += sc.nr_scanned;
			if (zone->all_unreclaimable)
				continue;
			if (nr_slab == 0 && zone->pages_scanned >=
				(zone_page_state(zone, NR_ACTIVE)
				+ zone_page_state(zone, NR_INACTIVE)) * 6)
					zone->all_unreclaimable = 1;
			/*
			 * If we've done a decent amount of scanning and
			 * the reclaim ratio is low, start doing writepage
			 * even in laptop mode
			 */
			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
			    total_scanned > nr_reclaimed + nr_reclaimed / 2)
				sc.may_writepage = 1;
		}
		if (all_zones_ok)
			break;		/* kswapd: all done */
		/*
		 * OK, kswapd is getting into trouble.  Take a nap, then take
		 * another pass across the zones.
		 */
		if (total_scanned && priority < DEF_PRIORITY - 2)
			congestion_wait(WRITE, HZ/10);

		/*
		 * We do this so kswapd doesn't build up large priorities for
		 * example when it is freeing in parallel with allocators. It
		 * matches the direct reclaim path behaviour in terms of impact
		 * on zone->*_priority.
		 */
		if (nr_reclaimed >= SWAP_CLUSTER_MAX)
			break;
	}
out:
	/*
	 * Note within each zone the priority level at which this zone was
	 * brought into a happy state.  So that the next thread which scans this
	 * zone will start out at that priority level.
	 */
	for (i = 0; i < pgdat->nr_zones; i++) {
		struct zone *zone = pgdat->node_zones + i;

		zone->prev_priority = temp_priority[i];
	}
	if (!all_zones_ok) {
		cond_resched();

		try_to_freeze();

		goto loop_again;
	}

	return nr_reclaimed;
}

/*
 * The background pageout daemon, started as a kernel thread
 * from the init process. 
 *
 * This basically trickles out pages so that we have _some_
 * free memory available even if there is no other activity
 * that frees anything up. This is needed for things like routing
 * etc, where we otherwise might have all activity going on in
 * asynchronous contexts that cannot page things out.
 *
 * If there are applications that are active memory-allocators
 * (most normal use), this basically shouldn't matter.
 */
static int kswapd(void *p)
{
	unsigned long order;
	pg_data_t *pgdat = (pg_data_t*)p;
	struct task_struct *tsk = current;
	DEFINE_WAIT(wait);
	struct reclaim_state reclaim_state = {
		.reclaimed_slab = 0,
	};
	cpumask_t cpumask;

	cpumask = node_to_cpumask(pgdat->node_id);
	if (!cpus_empty(cpumask))
		set_cpus_allowed(tsk, cpumask);
	current->reclaim_state = &reclaim_state;

	/*
	 * Tell the memory management that we're a "memory allocator",
	 * and that if we need more memory we should get access to it
	 * regardless (see "__alloc_pages()"). "kswapd" should
	 * never get caught in the normal page freeing logic.
	 *
	 * (Kswapd normally doesn't need memory anyway, but sometimes
	 * you need a small amount of memory in order to be able to
	 * page out something else, and this flag essentially protects
	 * us from recursively trying to free more memory as we're
	 * trying to free the first piece of memory in the first place).
	 */
	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;

	order = 0;
	for ( ; ; ) {
		unsigned long new_order;

		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
		new_order = pgdat->kswapd_max_order;
		pgdat->kswapd_max_order = 0;
		if (order < new_order) {
			/*
			 * Don't sleep if someone wants a larger 'order'
			 * allocation
			 */
			order = new_order;
		} else {
			if (!freezing(current))
				schedule();

			order = pgdat->kswapd_max_order;
		}
		finish_wait(&pgdat->kswapd_wait, &wait);

		if (!try_to_freeze()) {
			/* We can speed up thawing tasks if we don't call
			 * balance_pgdat after returning from the refrigerator
			 */
			balance_pgdat(pgdat, order);
		}
	}
	return 0;
}

/*
 * A zone is low on free memory, so wake its kswapd task to service it.
 */
void wakeup_kswapd(struct zone *zone, int order)
{
	pg_data_t *pgdat;

	if (!populated_zone(zone))
		return;

	pgdat = zone->zone_pgdat;
	if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
		return;
	if (pgdat->kswapd_max_order < order)
		pgdat->kswapd_max_order = order;
	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
		return;
	if (!waitqueue_active(&pgdat->kswapd_wait))
		return;
	wake_up_interruptible(&pgdat->kswapd_wait);
}

#ifdef CONFIG_PM
/*
 * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
 * from LRU lists system-wide, for given pass and priority, and returns the
 * number of reclaimed pages
 *
 * For pass > 3 we also try to shrink the LRU lists that contain a few pages
 */
static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
				      int pass, struct scan_control *sc)
{
	struct zone *zone;
	unsigned long nr_to_scan, ret = 0;

	for_each_zone(zone) {

		if (!populated_zone(zone))
			continue;

		if (zone->all_unreclaimable && prio != DEF_PRIORITY)
			continue;

		/* For pass = 0 we don't shrink the active list */
		if (pass > 0) {
			zone->nr_scan_active +=
				(zone_page_state(zone, NR_ACTIVE) >> prio) + 1;
			if (zone->nr_scan_active >= nr_pages || pass > 3) {
				zone->nr_scan_active = 0;
				nr_to_scan = min(nr_pages,
					zone_page_state(zone, NR_ACTIVE));
				shrink_active_list(nr_to_scan, zone, sc, prio);
			}
		}

		zone->nr_scan_inactive +=
			(zone_page_state(zone, NR_INACTIVE) >> prio) + 1;
		if (zone->nr_scan_inactive >= nr_pages || pass > 3) {
			zone->nr_scan_inactive = 0;
			nr_to_scan = min(nr_pages,
				zone_page_state(zone, NR_INACTIVE));
			ret += shrink_inactive_list(nr_to_scan, zone, sc);
			if (ret >= nr_pages)
				return ret;
		}
	}

	return ret;
}

static unsigned long count_lru_pages(void)
{
	return global_page_state(NR_ACTIVE) + global_page_state(NR_INACTIVE);
}

/*
 * Try to free `nr_pages' of memory, system-wide, and return the number of
 * freed pages.
 *
 * Rather than trying to age LRUs the aim is to preserve the overall
 * LRU order by reclaiming preferentially
 * inactive > active > active referenced > active mapped
 */
unsigned long shrink_all_memory(unsigned long nr_pages)
{
	unsigned long lru_pages, nr_slab;
	unsigned long ret = 0;
	int pass;
	struct reclaim_state reclaim_state;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_swap = 0,
		.swap_cluster_max = nr_pages,
		.may_writepage = 1,
		.swappiness = vm_swappiness,
	};

	current->reclaim_state = &reclaim_state;

	lru_pages = count_lru_pages();
	nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
	/* If slab caches are huge, it's better to hit them first */
	while (nr_slab >= lru_pages) {
		reclaim_state.reclaimed_slab = 0;
		shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
		if (!reclaim_state.reclaimed_slab)
			break;

		ret += reclaim_state.reclaimed_slab;
		if (ret >= nr_pages)
			goto out;

		nr_slab -= reclaim_state.reclaimed_slab;
	}

	/*
	 * We try to shrink LRUs in 5 passes:
	 * 0 = Reclaim from inactive_list only
	 * 1 = Reclaim from active list but don't reclaim mapped
	 * 2 = 2nd pass of type 1
	 * 3 = Reclaim mapped (normal reclaim)
	 * 4 = 2nd pass of type 3
	 */
	for (pass = 0; pass < 5; pass++) {
		int prio;

		/* Force reclaiming mapped pages in the passes #3 and #4 */
		if (pass > 2) {
			sc.may_swap = 1;
			sc.swappiness = 100;
		}

		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
			unsigned long nr_to_scan = nr_pages - ret;

			sc.nr_scanned = 0;
			ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
			if (ret >= nr_pages)
				goto out;

			reclaim_state.reclaimed_slab = 0;
			shrink_slab(sc.nr_scanned, sc.gfp_mask,
					count_lru_pages());
			ret += reclaim_state.reclaimed_slab;
			if (ret >= nr_pages)
				goto out;

			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
				congestion_wait(WRITE, HZ / 10);
		}
	}

	/*
	 * If ret = 0, we could not shrink LRUs, but there may be something
	 * in slab caches
	 */
	if (!ret) {
		do {
			reclaim_state.reclaimed_slab = 0;
			shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages());
			ret += reclaim_state.reclaimed_slab;
		} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
	}

out:
	current->reclaim_state = NULL;

	return ret;
}
#endif

/* It's optimal to keep kswapds on the same CPUs as their memory, but
   not required for correctness.  So if the last cpu in a node goes
   away, we get changed to run anywhere: as the first one comes back,
   restore their cpu bindings. */
static int __devinit cpu_callback(struct notifier_block *nfb,
				  unsigned long action, void *hcpu)
{
	pg_data_t *pgdat;
	cpumask_t mask;

	if (action == CPU_ONLINE) {
		for_each_online_pgdat(pgdat) {
			mask = node_to_cpumask(pgdat->node_id);
			if (any_online_cpu(mask) != NR_CPUS)
				/* One of our CPUs online: restore mask */
				set_cpus_allowed(pgdat->kswapd, mask);
		}
	}
	return NOTIFY_OK;
}

/*
 * This kswapd start function will be called by init and node-hot-add.
 * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
 */
int kswapd_run(int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);
	int ret = 0;

	if (pgdat->kswapd)
		return 0;

	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
	if (IS_ERR(pgdat->kswapd)) {
		/* failure at boot is fatal */
		BUG_ON(system_state == SYSTEM_BOOTING);
		printk("Failed to start kswapd on node %d\n",nid);
		ret = -1;
	}
	return ret;
}

static int __init kswapd_init(void)
{
	int nid;

	swap_setup();
	for_each_online_node(nid)
 		kswapd_run(nid);
	hotcpu_notifier(cpu_callback, 0);
	return 0;
}

module_init(kswapd_init)

#ifdef CONFIG_NUMA
/*
 * Zone reclaim mode
 *
 * If non-zero call zone_reclaim when the number of free pages falls below
 * the watermarks.
 */
int zone_reclaim_mode __read_mostly;

#define RECLAIM_OFF 0
#define RECLAIM_ZONE (1<<0)	/* Run shrink_cache on the zone */
#define RECLAIM_WRITE (1<<1)	/* Writeout pages during reclaim */
#define RECLAIM_SWAP (1<<2)	/* Swap pages out during reclaim */

/*
 * Priority for ZONE_RECLAIM. This determines the fraction of pages
 * of a node considered for each zone_reclaim. 4 scans 1/16th of
 * a zone.
 */
#define ZONE_RECLAIM_PRIORITY 4

/*
 * Percentage of pages in a zone that must be unmapped for zone_reclaim to
 * occur.
 */
int sysctl_min_unmapped_ratio = 1;

/*
 * If the number of slab pages in a zone grows beyond this percentage then
 * slab reclaim needs to occur.
 */
int sysctl_min_slab_ratio = 5;

/*
 * Try to free up some pages from this zone through reclaim.
 */
static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
{
	/* Minimum pages needed in order to stay on node */
	const unsigned long nr_pages = 1 << order;
	struct task_struct *p = current;
	struct reclaim_state reclaim_state;
	int priority;
	unsigned long nr_reclaimed = 0;
	struct scan_control sc = {
		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
		.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
		.swap_cluster_max = max_t(unsigned long, nr_pages,
					SWAP_CLUSTER_MAX),
		.gfp_mask = gfp_mask,
		.swappiness = vm_swappiness,
	};
	unsigned long slab_reclaimable;

	disable_swap_token();
	cond_resched();
	/*
	 * We need to be able to allocate from the reserves for RECLAIM_SWAP
	 * and we also need to be able to write out pages for RECLAIM_WRITE
	 * and RECLAIM_SWAP.
	 */
	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

	if (zone_page_state(zone, NR_FILE_PAGES) -
		zone_page_state(zone, NR_FILE_MAPPED) >
		zone->min_unmapped_pages) {
		/*
		 * Free memory by calling shrink zone with increasing
		 * priorities until we have enough memory freed.
		 */
		priority = ZONE_RECLAIM_PRIORITY;
		do {
			note_zone_scanning_priority(zone, priority);
			nr_reclaimed += shrink_zone(priority, zone, &sc);
			priority--;
		} while (priority >= 0 && nr_reclaimed < nr_pages);
	}

	slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
	if (slab_reclaimable > zone->min_slab_pages) {
		/*
		 * shrink_slab() does not currently allow us to determine how
		 * many pages were freed in this zone. So we take the current
		 * number of slab pages and shake the slab until it is reduced
		 * by the same nr_pages that we used for reclaiming unmapped
		 * pages.
		 *
		 * Note that shrink_slab will free memory on all zones and may
		 * take a long time.
		 */
		while (shrink_slab(sc.nr_scanned, gfp_mask, order) &&
			zone_page_state(zone, NR_SLAB_RECLAIMABLE) >
				slab_reclaimable - nr_pages)
			;

		/*
		 * Update nr_reclaimed by the number of slab pages we
		 * reclaimed from this zone.
		 */
		nr_reclaimed += slab_reclaimable -
			zone_page_state(zone, NR_SLAB_RECLAIMABLE);
	}

	p->reclaim_state = NULL;
	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
	return nr_reclaimed >= nr_pages;
}

int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
{
	cpumask_t mask;
	int node_id;

	/*
	 * Zone reclaim reclaims unmapped file backed pages and
	 * slab pages if we are over the defined limits.
	 *
	 * A small portion of unmapped file backed pages is needed for
	 * file I/O otherwise pages read by file I/O will be immediately
	 * thrown out if the zone is overallocated. So we do not reclaim
	 * if less than a specified percentage of the zone is used by
	 * unmapped file backed pages.
	 */
	if (zone_page_state(zone, NR_FILE_PAGES) -
	    zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages
	    && zone_page_state(zone, NR_SLAB_RECLAIMABLE)
			<= zone->min_slab_pages)
		return 0;

	/*
	 * Avoid concurrent zone reclaims, do not reclaim in a zone that does
	 * not have reclaimable pages and if we should not delay the allocation
	 * then do not scan.
	 */
	if (!(gfp_mask & __GFP_WAIT) ||
		zone->all_unreclaimable ||
		atomic_read(&zone->reclaim_in_progress) > 0 ||
		(current->flags & PF_MEMALLOC))
			return 0;

	/*
	 * Only run zone reclaim on the local zone or on zones that do not
	 * have associated processors. This will favor the local processor
	 * over remote processors and spread off node memory allocations
	 * as wide as possible.
	 */
	node_id = zone_to_nid(zone);
	mask = node_to_cpumask(node_id);
	if (!cpus_empty(mask) && node_id != numa_node_id())
		return 0;
	return __zone_reclaim(zone, gfp_mask, order);
}
#endif