swapfile.c

/*
 *  linux/mm/swapfile.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 */

#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/shm.h>
#include <linux/blkdev.h>
#include <linux/random.h>
#include <linux/writeback.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/backing-dev.h>
#include <linux/mutex.h>
#include <linux/capability.h>
#include <linux/syscalls.h>
#include <linux/memcontrol.h>

#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>

static DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
long nr_swap_pages;
long total_swap_pages;
static int swap_overflow;
static int least_priority;

static const char Bad_file[] = "Bad swap file entry ";
static const char Unused_file[] = "Unused swap file entry ";
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";

static struct swap_list_t swap_list = {-1, -1};

static struct swap_info_struct swap_info[MAX_SWAPFILES];

static DEFINE_MUTEX(swapon_mutex);

/*
 * We need this because the bdev->unplug_fn can sleep and we cannot
 * hold swap_lock while calling the unplug_fn. And swap_lock
 * cannot be turned into a mutex.
 */
static DECLARE_RWSEM(swap_unplug_sem);

void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page)
{
	swp_entry_t entry;

	down_read(&swap_unplug_sem);
	entry.val = page_private(page);
	if (PageSwapCache(page)) {
		struct block_device *bdev = swap_info[swp_type(entry)].bdev;
		struct backing_dev_info *bdi;

		/*
		 * If the page is removed from swapcache from under us (with a
		 * racy try_to_unuse/swapoff) we need an additional reference
		 * count to avoid reading garbage from page_private(page) above.
		 * If the WARN_ON triggers during a swapoff it maybe the race
		 * condition and it's harmless. However if it triggers without
		 * swapoff it signals a problem.
		 */
		WARN_ON(page_count(page) <= 1);

		bdi = bdev->bd_inode->i_mapping->backing_dev_info;
		blk_run_backing_dev(bdi, page);
	}
	up_read(&swap_unplug_sem);
}

/*
 * swapon tell device that all the old swap contents can be discarded,
 * to allow the swap device to optimize its wear-levelling.
 */
static int discard_swap(struct swap_info_struct *si)
{
	struct swap_extent *se;
	int err = 0;

	list_for_each_entry(se, &si->extent_list, list) {
		sector_t start_block = se->start_block << (PAGE_SHIFT - 9);
		sector_t nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);

		if (se->start_page == 0) {
			/* Do not discard the swap header page! */
			start_block += 1 << (PAGE_SHIFT - 9);
			nr_blocks -= 1 << (PAGE_SHIFT - 9);
			if (!nr_blocks)
				continue;
		}

		err = blkdev_issue_discard(si->bdev, start_block,
						nr_blocks, GFP_KERNEL);
		if (err)
			break;

		cond_resched();
	}
	return err;		/* That will often be -EOPNOTSUPP */
}

/*
 * swap allocation tell device that a cluster of swap can now be discarded,
 * to allow the swap device to optimize its wear-levelling.
 */
static void discard_swap_cluster(struct swap_info_struct *si,
				 pgoff_t start_page, pgoff_t nr_pages)
{
	struct swap_extent *se = si->curr_swap_extent;
	int found_extent = 0;

	while (nr_pages) {
		struct list_head *lh;

		if (se->start_page <= start_page &&
		    start_page < se->start_page + se->nr_pages) {
			pgoff_t offset = start_page - se->start_page;
			sector_t start_block = se->start_block + offset;
			sector_t nr_blocks = se->nr_pages - offset;

			if (nr_blocks > nr_pages)
				nr_blocks = nr_pages;
			start_page += nr_blocks;
			nr_pages -= nr_blocks;

			if (!found_extent++)
				si->curr_swap_extent = se;

			start_block <<= PAGE_SHIFT - 9;
			nr_blocks <<= PAGE_SHIFT - 9;
			if (blkdev_issue_discard(si->bdev, start_block,
							nr_blocks, GFP_NOIO))
				break;
		}

		lh = se->list.next;
		if (lh == &si->extent_list)
			lh = lh->next;
		se = list_entry(lh, struct swap_extent, list);
	}
}

static int wait_for_discard(void *word)
{
	schedule();
	return 0;
}

#define SWAPFILE_CLUSTER	256
#define LATENCY_LIMIT		256

static inline unsigned long scan_swap_map(struct swap_info_struct *si)
{
	unsigned long offset;
	unsigned long scan_base;
	unsigned long last_in_cluster = 0;
	int latency_ration = LATENCY_LIMIT;
	int found_free_cluster = 0;

	/*
	 * We try to cluster swap pages by allocating them sequentially
	 * in swap.  Once we've allocated SWAPFILE_CLUSTER pages this
	 * way, however, we resort to first-free allocation, starting
	 * a new cluster.  This prevents us from scattering swap pages
	 * all over the entire swap partition, so that we reduce
	 * overall disk seek times between swap pages.  -- sct
	 * But we do now try to find an empty cluster.  -Andrea
	 * And we let swap pages go all over an SSD partition.  Hugh
	 */

	si->flags += SWP_SCANNING;
	scan_base = offset = si->cluster_next;

	if (unlikely(!si->cluster_nr--)) {
		if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
			si->cluster_nr = SWAPFILE_CLUSTER - 1;
			goto checks;
		}
		if (si->flags & SWP_DISCARDABLE) {
			/*
			 * Start range check on racing allocations, in case
			 * they overlap the cluster we eventually decide on
			 * (we scan without swap_lock to allow preemption).
			 * It's hardly conceivable that cluster_nr could be
			 * wrapped during our scan, but don't depend on it.
			 */
			if (si->lowest_alloc)
				goto checks;
			si->lowest_alloc = si->max;
			si->highest_alloc = 0;
		}
		spin_unlock(&swap_lock);

		/*
		 * If seek is expensive, start searching for new cluster from
		 * start of partition, to minimize the span of allocated swap.
		 * But if seek is cheap, search from our current position, so
		 * that swap is allocated from all over the partition: if the
		 * Flash Translation Layer only remaps within limited zones,
		 * we don't want to wear out the first zone too quickly.
		 */
		if (!(si->flags & SWP_SOLIDSTATE))
			scan_base = offset = si->lowest_bit;
		last_in_cluster = offset + SWAPFILE_CLUSTER - 1;

		/* Locate the first empty (unaligned) cluster */
		for (; last_in_cluster <= si->highest_bit; offset++) {
			if (si->swap_map[offset])
				last_in_cluster = offset + SWAPFILE_CLUSTER;
			else if (offset == last_in_cluster) {
				spin_lock(&swap_lock);
				offset -= SWAPFILE_CLUSTER - 1;
				si->cluster_next = offset;
				si->cluster_nr = SWAPFILE_CLUSTER - 1;
				found_free_cluster = 1;
				goto checks;
			}
			if (unlikely(--latency_ration < 0)) {
				cond_resched();
				latency_ration = LATENCY_LIMIT;
			}
		}

		offset = si->lowest_bit;
		last_in_cluster = offset + SWAPFILE_CLUSTER - 1;

		/* Locate the first empty (unaligned) cluster */
		for (; last_in_cluster < scan_base; offset++) {
			if (si->swap_map[offset])
				last_in_cluster = offset + SWAPFILE_CLUSTER;
			else if (offset == last_in_cluster) {
				spin_lock(&swap_lock);
				offset -= SWAPFILE_CLUSTER - 1;
				si->cluster_next = offset;
				si->cluster_nr = SWAPFILE_CLUSTER - 1;
				found_free_cluster = 1;
				goto checks;
			}
			if (unlikely(--latency_ration < 0)) {
				cond_resched();
				latency_ration = LATENCY_LIMIT;
			}
		}

		offset = scan_base;
		spin_lock(&swap_lock);
		si->cluster_nr = SWAPFILE_CLUSTER - 1;
		si->lowest_alloc = 0;
	}

checks:
	if (!(si->flags & SWP_WRITEOK))
		goto no_page;
	if (!si->highest_bit)
		goto no_page;
	if (offset > si->highest_bit)
		scan_base = offset = si->lowest_bit;
	if (si->swap_map[offset])
		goto scan;

	if (offset == si->lowest_bit)
		si->lowest_bit++;
	if (offset == si->highest_bit)
		si->highest_bit--;
	si->inuse_pages++;
	if (si->inuse_pages == si->pages) {
		si->lowest_bit = si->max;
		si->highest_bit = 0;
	}
	si->swap_map[offset] = 1;
	si->cluster_next = offset + 1;
	si->flags -= SWP_SCANNING;

	if (si->lowest_alloc) {
		/*
		 * Only set when SWP_DISCARDABLE, and there's a scan
		 * for a free cluster in progress or just completed.
		 */
		if (found_free_cluster) {
			/*
			 * To optimize wear-levelling, discard the
			 * old data of the cluster, taking care not to
			 * discard any of its pages that have already
			 * been allocated by racing tasks (offset has
			 * already stepped over any at the beginning).
			 */
			if (offset < si->highest_alloc &&
			    si->lowest_alloc <= last_in_cluster)
				last_in_cluster = si->lowest_alloc - 1;
			si->flags |= SWP_DISCARDING;
			spin_unlock(&swap_lock);

			if (offset < last_in_cluster)
				discard_swap_cluster(si, offset,
					last_in_cluster - offset + 1);

			spin_lock(&swap_lock);
			si->lowest_alloc = 0;
			si->flags &= ~SWP_DISCARDING;

			smp_mb();	/* wake_up_bit advises this */
			wake_up_bit(&si->flags, ilog2(SWP_DISCARDING));

		} else if (si->flags & SWP_DISCARDING) {
			/*
			 * Delay using pages allocated by racing tasks
			 * until the whole discard has been issued. We
			 * could defer that delay until swap_writepage,
			 * but it's easier to keep this self-contained.
			 */
			spin_unlock(&swap_lock);
			wait_on_bit(&si->flags, ilog2(SWP_DISCARDING),
				wait_for_discard, TASK_UNINTERRUPTIBLE);
			spin_lock(&swap_lock);
		} else {
			/*
			 * Note pages allocated by racing tasks while
			 * scan for a free cluster is in progress, so
			 * that its final discard can exclude them.
			 */
			if (offset < si->lowest_alloc)
				si->lowest_alloc = offset;
			if (offset > si->highest_alloc)
				si->highest_alloc = offset;
		}
	}
	return offset;

scan:
	spin_unlock(&swap_lock);
	while (++offset <= si->highest_bit) {
		if (!si->swap_map[offset]) {
			spin_lock(&swap_lock);
			goto checks;
		}
		if (unlikely(--latency_ration < 0)) {
			cond_resched();
			latency_ration = LATENCY_LIMIT;
		}
	}
	offset = si->lowest_bit;
	while (++offset < scan_base) {
		if (!si->swap_map[offset]) {
			spin_lock(&swap_lock);
			goto checks;
		}
		if (unlikely(--latency_ration < 0)) {
			cond_resched();
			latency_ration = LATENCY_LIMIT;
		}
	}
	spin_lock(&swap_lock);

no_page:
	si->flags -= SWP_SCANNING;
	return 0;
}

swp_entry_t get_swap_page(void)
{
	struct swap_info_struct *si;
	pgoff_t offset;
	int type, next;
	int wrapped = 0;

	spin_lock(&swap_lock);
	if (nr_swap_pages <= 0)
		goto noswap;
	nr_swap_pages--;

	for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
		si = swap_info + type;
		next = si->next;
		if (next < 0 ||
		    (!wrapped && si->prio != swap_info[next].prio)) {
			next = swap_list.head;
			wrapped++;
		}

		if (!si->highest_bit)
			continue;
		if (!(si->flags & SWP_WRITEOK))
			continue;

		swap_list.next = next;
		offset = scan_swap_map(si);
		if (offset) {
			spin_unlock(&swap_lock);
			return swp_entry(type, offset);
		}
		next = swap_list.next;
	}

	nr_swap_pages++;
noswap:
	spin_unlock(&swap_lock);
	return (swp_entry_t) {0};
}

swp_entry_t get_swap_page_of_type(int type)
{
	struct swap_info_struct *si;
	pgoff_t offset;

	spin_lock(&swap_lock);
	si = swap_info + type;
	if (si->flags & SWP_WRITEOK) {
		nr_swap_pages--;
		offset = scan_swap_map(si);
		if (offset) {
			spin_unlock(&swap_lock);
			return swp_entry(type, offset);
		}
		nr_swap_pages++;
	}
	spin_unlock(&swap_lock);
	return (swp_entry_t) {0};
}

static struct swap_info_struct * swap_info_get(swp_entry_t entry)
{
	struct swap_info_struct * p;
	unsigned long offset, type;

	if (!entry.val)
		goto out;
	type = swp_type(entry);
	if (type >= nr_swapfiles)
		goto bad_nofile;
	p = & swap_info[type];
	if (!(p->flags & SWP_USED))
		goto bad_device;
	offset = swp_offset(entry);
	if (offset >= p->max)
		goto bad_offset;
	if (!p->swap_map[offset])
		goto bad_free;
	spin_lock(&swap_lock);
	return p;

bad_free:
	printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val);
	goto out;
bad_offset:
	printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val);
	goto out;
bad_device:
	printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val);
	goto out;
bad_nofile:
	printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
out:
	return NULL;
}

static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
{
	int count = p->swap_map[offset];

	if (count < SWAP_MAP_MAX) {
		count--;
		p->swap_map[offset] = count;
		if (!count) {
			if (offset < p->lowest_bit)
				p->lowest_bit = offset;
			if (offset > p->highest_bit)
				p->highest_bit = offset;
			if (p->prio > swap_info[swap_list.next].prio)
				swap_list.next = p - swap_info;
			nr_swap_pages++;
			p->inuse_pages--;
		}
	}
	return count;
}

/*
 * Caller has made sure that the swapdevice corresponding to entry
 * is still around or has not been recycled.
 */
void swap_free(swp_entry_t entry)
{
	struct swap_info_struct * p;

	p = swap_info_get(entry);
	if (p) {
		swap_entry_free(p, swp_offset(entry));
		spin_unlock(&swap_lock);
	}
}

/*
 * How many references to page are currently swapped out?
 */
static inline int page_swapcount(struct page *page)
{
	int count = 0;
	struct swap_info_struct *p;
	swp_entry_t entry;

	entry.val = page_private(page);
	p = swap_info_get(entry);
	if (p) {
		/* Subtract the 1 for the swap cache itself */
		count = p->swap_map[swp_offset(entry)] - 1;
		spin_unlock(&swap_lock);
	}
	return count;
}

/*
 * We can write to an anon page without COW if there are no other references
 * to it.  And as a side-effect, free up its swap: because the old content
 * on disk will never be read, and seeking back there to write new content
 * later would only waste time away from clustering.
 */
int reuse_swap_page(struct page *page)
{
	int count;

	VM_BUG_ON(!PageLocked(page));
	count = page_mapcount(page);
	if (count <= 1 && PageSwapCache(page)) {
		count += page_swapcount(page);
		if (count == 1 && !PageWriteback(page)) {
			delete_from_swap_cache(page);
			SetPageDirty(page);
		}
	}
	return count == 1;
}

/*
 * If swap is getting full, or if there are no more mappings of this page,
 * then try_to_free_swap is called to free its swap space.
 */
int try_to_free_swap(struct page *page)
{
	VM_BUG_ON(!PageLocked(page));

	if (!PageSwapCache(page))
		return 0;
	if (PageWriteback(page))
		return 0;
	if (page_swapcount(page))
		return 0;

	delete_from_swap_cache(page);
	SetPageDirty(page);
	return 1;
}

/*
 * Free the swap entry like above, but also try to
 * free the page cache entry if it is the last user.
 */
int free_swap_and_cache(swp_entry_t entry)
{
	struct swap_info_struct *p;
	struct page *page = NULL;

	if (is_migration_entry(entry))
		return 1;

	p = swap_info_get(entry);
	if (p) {
		if (swap_entry_free(p, swp_offset(entry)) == 1) {
			page = find_get_page(&swapper_space, entry.val);
			if (page && !trylock_page(page)) {
				page_cache_release(page);
				page = NULL;
			}
		}
		spin_unlock(&swap_lock);
	}
	if (page) {
		/*
		 * Not mapped elsewhere, or swap space full? Free it!
		 * Also recheck PageSwapCache now page is locked (above).
		 */
		if (PageSwapCache(page) && !PageWriteback(page) &&
				(!page_mapped(page) || vm_swap_full())) {
			delete_from_swap_cache(page);
			SetPageDirty(page);
		}
		unlock_page(page);
		page_cache_release(page);
	}
	return p != NULL;
}

#ifdef CONFIG_HIBERNATION
/*
 * Find the swap type that corresponds to given device (if any).
 *
 * @offset - number of the PAGE_SIZE-sized block of the device, starting
 * from 0, in which the swap header is expected to be located.
 *
 * This is needed for the suspend to disk (aka swsusp).
 */
int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
{
	struct block_device *bdev = NULL;
	int i;

	if (device)
		bdev = bdget(device);

	spin_lock(&swap_lock);
	for (i = 0; i < nr_swapfiles; i++) {
		struct swap_info_struct *sis = swap_info + i;

		if (!(sis->flags & SWP_WRITEOK))
			continue;

		if (!bdev) {
			if (bdev_p)
				*bdev_p = sis->bdev;

			spin_unlock(&swap_lock);
			return i;
		}
		if (bdev == sis->bdev) {
			struct swap_extent *se;

			se = list_entry(sis->extent_list.next,
					struct swap_extent, list);
			if (se->start_block == offset) {
				if (bdev_p)
					*bdev_p = sis->bdev;

				spin_unlock(&swap_lock);
				bdput(bdev);
				return i;
			}
		}
	}
	spin_unlock(&swap_lock);
	if (bdev)
		bdput(bdev);

	return -ENODEV;
}

/*
 * Return either the total number of swap pages of given type, or the number
 * of free pages of that type (depending on @free)
 *
 * This is needed for software suspend
 */
unsigned int count_swap_pages(int type, int free)
{
	unsigned int n = 0;

	if (type < nr_swapfiles) {
		spin_lock(&swap_lock);
		if (swap_info[type].flags & SWP_WRITEOK) {
			n = swap_info[type].pages;
			if (free)
				n -= swap_info[type].inuse_pages;
		}
		spin_unlock(&swap_lock);
	}
	return n;
}
#endif

/*
 * No need to decide whether this PTE shares the swap entry with others,
 * just let do_wp_page work it out if a write is requested later - to
 * force COW, vm_page_prot omits write permission from any private vma.
 */
static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long addr, swp_entry_t entry, struct page *page)
{
	spinlock_t *ptl;
	pte_t *pte;
	int ret = 1;

	if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
		ret = -ENOMEM;

	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
		if (ret > 0)
			mem_cgroup_uncharge_page(page);
		ret = 0;
		goto out;
	}

	inc_mm_counter(vma->vm_mm, anon_rss);
	get_page(page);
	set_pte_at(vma->vm_mm, addr, pte,
		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
	page_add_anon_rmap(page, vma, addr);
	swap_free(entry);
	/*
	 * Move the page to the active list so it is not
	 * immediately swapped out again after swapon.
	 */
	activate_page(page);
out:
	pte_unmap_unlock(pte, ptl);
	return ret;
}

static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
				unsigned long addr, unsigned long end,
				swp_entry_t entry, struct page *page)
{
	pte_t swp_pte = swp_entry_to_pte(entry);
	pte_t *pte;
	int ret = 0;

	/*
	 * We don't actually need pte lock while scanning for swp_pte: since
	 * we hold page lock and mmap_sem, swp_pte cannot be inserted into the
	 * page table while we're scanning; though it could get zapped, and on
	 * some architectures (e.g. x86_32 with PAE) we might catch a glimpse
	 * of unmatched parts which look like swp_pte, so unuse_pte must
	 * recheck under pte lock.  Scanning without pte lock lets it be
	 * preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE.
	 */
	pte = pte_offset_map(pmd, addr);
	do {
		/*
		 * swapoff spends a _lot_ of time in this loop!
		 * Test inline before going to call unuse_pte.
		 */
		if (unlikely(pte_same(*pte, swp_pte))) {
			pte_unmap(pte);
			ret = unuse_pte(vma, pmd, addr, entry, page);
			if (ret)
				goto out;
			pte = pte_offset_map(pmd, addr);
		}
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap(pte - 1);
out:
	return ret;
}

static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
				unsigned long addr, unsigned long end,
				swp_entry_t entry, struct page *page)
{
	pmd_t *pmd;
	unsigned long next;
	int ret;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		ret = unuse_pte_range(vma, pmd, addr, next, entry, page);
		if (ret)
			return ret;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
				unsigned long addr, unsigned long end,
				swp_entry_t entry, struct page *page)
{
	pud_t *pud;
	unsigned long next;
	int ret;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		ret = unuse_pmd_range(vma, pud, addr, next, entry, page);
		if (ret)
			return ret;
	} while (pud++, addr = next, addr != end);
	return 0;
}

static int unuse_vma(struct vm_area_struct *vma,
				swp_entry_t entry, struct page *page)
{
	pgd_t *pgd;
	unsigned long addr, end, next;
	int ret;

	if (page->mapping) {
		addr = page_address_in_vma(page, vma);
		if (addr == -EFAULT)
			return 0;
		else
			end = addr + PAGE_SIZE;
	} else {
		addr = vma->vm_start;
		end = vma->vm_end;
	}

	pgd = pgd_offset(vma->vm_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		ret = unuse_pud_range(vma, pgd, addr, next, entry, page);
		if (ret)
			return ret;
	} while (pgd++, addr = next, addr != end);
	return 0;
}

static int unuse_mm(struct mm_struct *mm,
				swp_entry_t entry, struct page *page)
{
	struct vm_area_struct *vma;
	int ret = 0;

	if (!down_read_trylock(&mm->mmap_sem)) {
		/*
		 * Activate page so shrink_inactive_list is unlikely to unmap
		 * its ptes while lock is dropped, so swapoff can make progress.
		 */
		activate_page(page);
		unlock_page(page);
		down_read(&mm->mmap_sem);
		lock_page(page);
	}
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		if (vma->anon_vma && (ret = unuse_vma(vma, entry, page)))
			break;
	}
	up_read(&mm->mmap_sem);
	return (ret < 0)? ret: 0;
}

/*
 * Scan swap_map from current position to next entry still in use.
 * Recycle to start on reaching the end, returning 0 when empty.
 */
static unsigned int find_next_to_unuse(struct swap_info_struct *si,
					unsigned int prev)
{
	unsigned int max = si->max;
	unsigned int i = prev;
	int count;

	/*
	 * No need for swap_lock here: we're just looking
	 * for whether an entry is in use, not modifying it; false
	 * hits are okay, and sys_swapoff() has already prevented new
	 * allocations from this area (while holding swap_lock).
	 */
	for (;;) {
		if (++i >= max) {
			if (!prev) {
				i = 0;
				break;
			}
			/*
			 * No entries in use at top of swap_map,
			 * loop back to start and recheck there.
			 */
			max = prev + 1;
			prev = 0;
			i = 1;
		}
		count = si->swap_map[i];
		if (count && count != SWAP_MAP_BAD)
			break;
	}
	return i;
}

/*
 * We completely avoid races by reading each swap page in advance,
 * and then search for the process using it.  All the necessary
 * page table adjustments can then be made atomically.
 */
static int try_to_unuse(unsigned int type)
{
	struct swap_info_struct * si = &swap_info[type];
	struct mm_struct *start_mm;
	unsigned short *swap_map;
	unsigned short swcount;
	struct page *page;
	swp_entry_t entry;
	unsigned int i = 0;
	int retval = 0;
	int reset_overflow = 0;
	int shmem;

	/*
	 * When searching mms for an entry, a good strategy is to
	 * start at the first mm we freed the previous entry from
	 * (though actually we don't notice whether we or coincidence
	 * freed the entry).  Initialize this start_mm with a hold.
	 *
	 * A simpler strategy would be to start at the last mm we
	 * freed the previous entry from; but that would take less
	 * advantage of mmlist ordering, which clusters forked mms
	 * together, child after parent.  If we race with dup_mmap(), we
	 * prefer to resolve parent before child, lest we miss entries
	 * duplicated after we scanned child: using last mm would invert
	 * that.  Though it's only a serious concern when an overflowed
	 * swap count is reset from SWAP_MAP_MAX, preventing a rescan.
	 */
	start_mm = &init_mm;
	atomic_inc(&init_mm.mm_users);

	/*
	 * Keep on scanning until all entries have gone.  Usually,
	 * one pass through swap_map is enough, but not necessarily:
	 * there are races when an instance of an entry might be missed.
	 */
	while ((i = find_next_to_unuse(si, i)) != 0) {
		if (signal_pending(current)) {
			retval = -EINTR;
			break;
		}

		/*
		 * Get a page for the entry, using the existing swap
		 * cache page if there is one.  Otherwise, get a clean
		 * page and read the swap into it.
		 */
		swap_map = &si->swap_map[i];
		entry = swp_entry(type, i);
		page = read_swap_cache_async(entry,
					GFP_HIGHUSER_MOVABLE, NULL, 0);
		if (!page) {
			/*
			 * Either swap_duplicate() failed because entry
			 * has been freed independently, and will not be
			 * reused since sys_swapoff() already disabled
			 * allocation from here, or alloc_page() failed.
			 */
			if (!*swap_map)
				continue;
			retval = -ENOMEM;
			break;
		}

		/*
		 * Don't hold on to start_mm if it looks like exiting.
		 */
		if (atomic_read(&start_mm->mm_users) == 1) {
			mmput(start_mm);
			start_mm = &init_mm;
			atomic_inc(&init_mm.mm_users);
		}

		/*
		 * Wait for and lock page.  When do_swap_page races with
		 * try_to_unuse, do_swap_page can handle the fault much
		 * faster than try_to_unuse can locate the entry.  This
		 * apparently redundant "wait_on_page_locked" lets try_to_unuse
		 * defer to do_swap_page in such a case - in some tests,
		 * do_swap_page and try_to_unuse repeatedly compete.
		 */
		wait_on_page_locked(page);
		wait_on_page_writeback(page);
		lock_page(page);
		wait_on_page_writeback(page);

		/*
		 * Remove all references to entry.
		 * Whenever we reach init_mm, there's no address space
		 * to search, but use it as a reminder to search shmem.
		 */
		shmem = 0;
		swcount = *swap_map;
		if (swcount > 1) {
			if (start_mm == &init_mm)
				shmem = shmem_unuse(entry, page);
			else
				retval = unuse_mm(start_mm, entry, page);
		}
		if (*swap_map > 1) {
			int set_start_mm = (*swap_map >= swcount);
			struct list_head *p = &start_mm->mmlist;
			struct mm_struct *new_start_mm = start_mm;
			struct mm_struct *prev_mm = start_mm;