/*
   *  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/shmem_fs.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/ksm.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 <linux/poll.h>

  #include <linux/oom.h>

  #include <linux/frontswap.h>
  #include <linux/swapfile.h>

  #include <linux/export.h>

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

  #include <linux/page_cgroup.h>

  static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
  				 unsigned char);
  static void free_swap_count_continuations(struct swap_info_struct *);

  static sector_t map_swap_entry(swp_entry_t, struct block_device**);

  DEFINE_SPINLOCK(swap_lock);

  static unsigned int nr_swapfiles;

  atomic_long_t nr_swap_pages;
  /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */

  long total_swap_pages;

  static int least_priority;

  static atomic_t highest_priority_index = ATOMIC_INIT(-1);

  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 ";

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

  struct swap_info_struct *swap_info[MAX_SWAPFILES];

  static DEFINE_MUTEX(swapon_mutex);

  static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait);
  /* Activity counter to indicate that a swapon or swapoff has occurred */
  static atomic_t proc_poll_event = ATOMIC_INIT(0);

  static inline unsigned char swap_count(unsigned char ent)

  {

  	return ent & ~SWAP_HAS_CACHE;	/* may include SWAP_HAS_CONT flag */

  }

  /* returns 1 if swap entry is freed */

  static int
  __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset)
  {

  	swp_entry_t entry = swp_entry(si->type, offset);

  	struct page *page;
  	int ret = 0;

  	page = find_get_page(swap_address_space(entry), entry.val);

  	if (!page)
  		return 0;
  	/*
  	 * This function is called from scan_swap_map() and it's called
  	 * by vmscan.c at reclaiming pages. So, we hold a lock on a page, here.
  	 * We have to use trylock for avoiding deadlock. This is a special
  	 * case and you should use try_to_free_swap() with explicit lock_page()
  	 * in usual operations.
  	 */
  	if (trylock_page(page)) {
  		ret = try_to_free_swap(page);
  		unlock_page(page);
  	}
  	page_cache_release(page);
  	return ret;
  }

  /*

   * 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;

  	sector_t start_block;
  	sector_t nr_blocks;

  	int err = 0;

  	/* Do not discard the swap header page! */
  	se = &si->first_swap_extent;
  	start_block = (se->start_block + 1) << (PAGE_SHIFT - 9);
  	nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9);
  	if (nr_blocks) {
  		err = blkdev_issue_discard(si->bdev, start_block,

  				nr_blocks, GFP_KERNEL, 0);

  		if (err)
  			return err;
  		cond_resched();
  	}

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

  
  		err = blkdev_issue_discard(si->bdev, start_block,

  				nr_blocks, GFP_KERNEL, 0);

  		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, 0))

  				break;
  		}
  
  		lh = se->list.next;

  		se = list_entry(lh, struct swap_extent, list);
  	}
  }

  #define SWAPFILE_CLUSTER	256
  #define LATENCY_LIMIT		256

  static inline void cluster_set_flag(struct swap_cluster_info *info,
  	unsigned int flag)
  {
  	info->flags = flag;
  }
  
  static inline unsigned int cluster_count(struct swap_cluster_info *info)
  {
  	return info->data;
  }
  
  static inline void cluster_set_count(struct swap_cluster_info *info,
  				     unsigned int c)
  {
  	info->data = c;
  }
  
  static inline void cluster_set_count_flag(struct swap_cluster_info *info,
  					 unsigned int c, unsigned int f)
  {
  	info->flags = f;
  	info->data = c;
  }
  
  static inline unsigned int cluster_next(struct swap_cluster_info *info)
  {
  	return info->data;
  }
  
  static inline void cluster_set_next(struct swap_cluster_info *info,
  				    unsigned int n)
  {
  	info->data = n;
  }
  
  static inline void cluster_set_next_flag(struct swap_cluster_info *info,
  					 unsigned int n, unsigned int f)
  {
  	info->flags = f;
  	info->data = n;
  }
  
  static inline bool cluster_is_free(struct swap_cluster_info *info)
  {
  	return info->flags & CLUSTER_FLAG_FREE;
  }
  
  static inline bool cluster_is_null(struct swap_cluster_info *info)
  {
  	return info->flags & CLUSTER_FLAG_NEXT_NULL;
  }
  
  static inline void cluster_set_null(struct swap_cluster_info *info)
  {
  	info->flags = CLUSTER_FLAG_NEXT_NULL;
  	info->data = 0;
  }

  /* Add a cluster to discard list and schedule it to do discard */
  static void swap_cluster_schedule_discard(struct swap_info_struct *si,
  		unsigned int idx)
  {
  	/*
  	 * If scan_swap_map() can't find a free cluster, it will check
  	 * si->swap_map directly. To make sure the discarding cluster isn't
  	 * taken by scan_swap_map(), mark the swap entries bad (occupied). It
  	 * will be cleared after discard
  	 */
  	memset(si->swap_map + idx * SWAPFILE_CLUSTER,
  			SWAP_MAP_BAD, SWAPFILE_CLUSTER);
  
  	if (cluster_is_null(&si->discard_cluster_head)) {
  		cluster_set_next_flag(&si->discard_cluster_head,
  						idx, 0);
  		cluster_set_next_flag(&si->discard_cluster_tail,
  						idx, 0);
  	} else {
  		unsigned int tail = cluster_next(&si->discard_cluster_tail);
  		cluster_set_next(&si->cluster_info[tail], idx);
  		cluster_set_next_flag(&si->discard_cluster_tail,
  						idx, 0);
  	}
  
  	schedule_work(&si->discard_work);
  }
  
  /*
   * Doing discard actually. After a cluster discard is finished, the cluster
   * will be added to free cluster list. caller should hold si->lock.
  */
  static void swap_do_scheduled_discard(struct swap_info_struct *si)
  {
  	struct swap_cluster_info *info;
  	unsigned int idx;
  
  	info = si->cluster_info;
  
  	while (!cluster_is_null(&si->discard_cluster_head)) {
  		idx = cluster_next(&si->discard_cluster_head);
  
  		cluster_set_next_flag(&si->discard_cluster_head,
  						cluster_next(&info[idx]), 0);
  		if (cluster_next(&si->discard_cluster_tail) == idx) {
  			cluster_set_null(&si->discard_cluster_head);
  			cluster_set_null(&si->discard_cluster_tail);
  		}
  		spin_unlock(&si->lock);
  
  		discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
  				SWAPFILE_CLUSTER);
  
  		spin_lock(&si->lock);
  		cluster_set_flag(&info[idx], CLUSTER_FLAG_FREE);
  		if (cluster_is_null(&si->free_cluster_head)) {
  			cluster_set_next_flag(&si->free_cluster_head,
  						idx, 0);
  			cluster_set_next_flag(&si->free_cluster_tail,
  						idx, 0);
  		} else {
  			unsigned int tail;
  
  			tail = cluster_next(&si->free_cluster_tail);
  			cluster_set_next(&info[tail], idx);
  			cluster_set_next_flag(&si->free_cluster_tail,
  						idx, 0);
  		}
  		memset(si->swap_map + idx * SWAPFILE_CLUSTER,
  				0, SWAPFILE_CLUSTER);
  	}
  }
  
  static void swap_discard_work(struct work_struct *work)
  {
  	struct swap_info_struct *si;
  
  	si = container_of(work, struct swap_info_struct, discard_work);
  
  	spin_lock(&si->lock);
  	swap_do_scheduled_discard(si);
  	spin_unlock(&si->lock);
  }

  /*
   * The cluster corresponding to page_nr will be used. The cluster will be
   * removed from free cluster list and its usage counter will be increased.
   */
  static void inc_cluster_info_page(struct swap_info_struct *p,
  	struct swap_cluster_info *cluster_info, unsigned long page_nr)
  {
  	unsigned long idx = page_nr / SWAPFILE_CLUSTER;
  
  	if (!cluster_info)
  		return;
  	if (cluster_is_free(&cluster_info[idx])) {
  		VM_BUG_ON(cluster_next(&p->free_cluster_head) != idx);
  		cluster_set_next_flag(&p->free_cluster_head,
  			cluster_next(&cluster_info[idx]), 0);
  		if (cluster_next(&p->free_cluster_tail) == idx) {
  			cluster_set_null(&p->free_cluster_tail);
  			cluster_set_null(&p->free_cluster_head);
  		}
  		cluster_set_count_flag(&cluster_info[idx], 0, 0);
  	}
  
  	VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER);
  	cluster_set_count(&cluster_info[idx],
  		cluster_count(&cluster_info[idx]) + 1);
  }
  
  /*
   * The cluster corresponding to page_nr decreases one usage. If the usage
   * counter becomes 0, which means no page in the cluster is in using, we can
   * optionally discard the cluster and add it to free cluster list.
   */
  static void dec_cluster_info_page(struct swap_info_struct *p,
  	struct swap_cluster_info *cluster_info, unsigned long page_nr)
  {
  	unsigned long idx = page_nr / SWAPFILE_CLUSTER;
  
  	if (!cluster_info)
  		return;
  
  	VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0);
  	cluster_set_count(&cluster_info[idx],
  		cluster_count(&cluster_info[idx]) - 1);
  
  	if (cluster_count(&cluster_info[idx]) == 0) {

  		/*
  		 * If the swap is discardable, prepare discard the cluster
  		 * instead of free it immediately. The cluster will be freed
  		 * after discard.
  		 */

  		if ((p->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
  				 (SWP_WRITEOK | SWP_PAGE_DISCARD)) {

  			swap_cluster_schedule_discard(p, idx);
  			return;
  		}

  		cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE);
  		if (cluster_is_null(&p->free_cluster_head)) {
  			cluster_set_next_flag(&p->free_cluster_head, idx, 0);
  			cluster_set_next_flag(&p->free_cluster_tail, idx, 0);
  		} else {
  			unsigned int tail = cluster_next(&p->free_cluster_tail);
  			cluster_set_next(&cluster_info[tail], idx);
  			cluster_set_next_flag(&p->free_cluster_tail, idx, 0);
  		}
  	}
  }
  
  /*
   * It's possible scan_swap_map() uses a free cluster in the middle of free
   * cluster list. Avoiding such abuse to avoid list corruption.
   */

  static bool
  scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,

  	unsigned long offset)
  {

  	struct percpu_cluster *percpu_cluster;
  	bool conflict;

  	offset /= SWAPFILE_CLUSTER;

  	conflict = !cluster_is_null(&si->free_cluster_head) &&

  		offset != cluster_next(&si->free_cluster_head) &&
  		cluster_is_free(&si->cluster_info[offset]);

  
  	if (!conflict)
  		return false;
  
  	percpu_cluster = this_cpu_ptr(si->percpu_cluster);
  	cluster_set_null(&percpu_cluster->index);
  	return true;
  }
  
  /*
   * Try to get a swap entry from current cpu's swap entry pool (a cluster). This
   * might involve allocating a new cluster for current CPU too.
   */
  static void scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
  	unsigned long *offset, unsigned long *scan_base)
  {
  	struct percpu_cluster *cluster;
  	bool found_free;
  	unsigned long tmp;
  
  new_cluster:
  	cluster = this_cpu_ptr(si->percpu_cluster);
  	if (cluster_is_null(&cluster->index)) {
  		if (!cluster_is_null(&si->free_cluster_head)) {
  			cluster->index = si->free_cluster_head;
  			cluster->next = cluster_next(&cluster->index) *
  					SWAPFILE_CLUSTER;
  		} else if (!cluster_is_null(&si->discard_cluster_head)) {
  			/*
  			 * we don't have free cluster but have some clusters in
  			 * discarding, do discard now and reclaim them
  			 */
  			swap_do_scheduled_discard(si);
  			*scan_base = *offset = si->cluster_next;
  			goto new_cluster;
  		} else
  			return;
  	}
  
  	found_free = false;
  
  	/*
  	 * Other CPUs can use our cluster if they can't find a free cluster,
  	 * check if there is still free entry in the cluster
  	 */
  	tmp = cluster->next;
  	while (tmp < si->max && tmp < (cluster_next(&cluster->index) + 1) *
  	       SWAPFILE_CLUSTER) {
  		if (!si->swap_map[tmp]) {
  			found_free = true;
  			break;
  		}
  		tmp++;
  	}
  	if (!found_free) {
  		cluster_set_null(&cluster->index);
  		goto new_cluster;
  	}
  	cluster->next = tmp + 1;
  	*offset = tmp;
  	*scan_base = tmp;

  }

  static unsigned long scan_swap_map(struct swap_info_struct *si,
  				   unsigned char usage)

  {

  	unsigned long offset;

  	unsigned long scan_base;

  	unsigned long last_in_cluster = 0;

  	int latency_ration = LATENCY_LIMIT;

  	/*

  	 * 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;

  	/* SSD algorithm */
  	if (si->cluster_info) {
  		scan_swap_map_try_ssd_cluster(si, &offset, &scan_base);
  		goto checks;
  	}

  	if (unlikely(!si->cluster_nr--)) {
  		if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
  			si->cluster_nr = SWAPFILE_CLUSTER - 1;
  			goto checks;
  		}

  		spin_unlock(&si->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(&si->lock);

  				offset -= SWAPFILE_CLUSTER - 1;
  				si->cluster_next = offset;
  				si->cluster_nr = SWAPFILE_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(&si->lock);

  				offset -= SWAPFILE_CLUSTER - 1;
  				si->cluster_next = offset;
  				si->cluster_nr = SWAPFILE_CLUSTER - 1;

  				goto checks;
  			}
  			if (unlikely(--latency_ration < 0)) {
  				cond_resched();
  				latency_ration = LATENCY_LIMIT;
  			}
  		}
  
  		offset = scan_base;

  		spin_lock(&si->lock);

  		si->cluster_nr = SWAPFILE_CLUSTER - 1;

  	}

  checks:

  	if (si->cluster_info) {
  		while (scan_swap_map_ssd_cluster_conflict(si, offset))
  			scan_swap_map_try_ssd_cluster(si, &offset, &scan_base);
  	}

  	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;

  	/* reuse swap entry of cache-only swap if not busy. */
  	if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {

  		int swap_was_freed;

  		spin_unlock(&si->lock);

  		swap_was_freed = __try_to_reclaim_swap(si, offset);

  		spin_lock(&si->lock);

  		/* entry was freed successfully, try to use this again */
  		if (swap_was_freed)
  			goto checks;
  		goto scan; /* check next one */
  	}

  	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] = usage;

  	inc_cluster_info_page(si, si->cluster_info, offset);

  	si->cluster_next = offset + 1;
  	si->flags -= SWP_SCANNING;

  	return offset;

  scan:

  	spin_unlock(&si->lock);

  	while (++offset <= si->highest_bit) {

  		if (!si->swap_map[offset]) {

  			spin_lock(&si->lock);

  			goto checks;
  		}

  		if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {

  			spin_lock(&si->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(&si->lock);

  			goto checks;
  		}

  		if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {

  			spin_lock(&si->lock);

  			goto checks;
  		}

  		if (unlikely(--latency_ration < 0)) {
  			cond_resched();
  			latency_ration = LATENCY_LIMIT;
  		}

  		offset++;

  	}

  	spin_lock(&si->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;

  	int hp_index;

  	spin_lock(&swap_lock);

  	if (atomic_long_read(&nr_swap_pages) <= 0)

  		goto noswap;

  	atomic_long_dec(&nr_swap_pages);

  
  	for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {

  		hp_index = atomic_xchg(&highest_priority_index, -1);
  		/*
  		 * highest_priority_index records current highest priority swap
  		 * type which just frees swap entries. If its priority is
  		 * higher than that of swap_list.next swap type, we use it.  It
  		 * isn't protected by swap_lock, so it can be an invalid value
  		 * if the corresponding swap type is swapoff. We double check
  		 * the flags here. It's even possible the swap type is swapoff
  		 * and swapon again and its priority is changed. In such rare
  		 * case, low prority swap type might be used, but eventually
  		 * high priority swap will be used after several rounds of
  		 * swap.
  		 */
  		if (hp_index != -1 && hp_index != type &&
  		    swap_info[type]->prio < swap_info[hp_index]->prio &&
  		    (swap_info[hp_index]->flags & SWP_WRITEOK)) {
  			type = hp_index;
  			swap_list.next = type;
  		}

  		si = swap_info[type];

  		next = si->next;
  		if (next < 0 ||

  		    (!wrapped && si->prio != swap_info[next]->prio)) {

  			next = swap_list.head;
  			wrapped++;

  		}

  		spin_lock(&si->lock);
  		if (!si->highest_bit) {
  			spin_unlock(&si->lock);

  			continue;

  		}
  		if (!(si->flags & SWP_WRITEOK)) {
  			spin_unlock(&si->lock);

  			continue;

  		}

  
  		swap_list.next = next;

  
  		spin_unlock(&swap_lock);

  		/* This is called for allocating swap entry for cache */

  		offset = scan_swap_map(si, SWAP_HAS_CACHE);

  		spin_unlock(&si->lock);
  		if (offset)

  			return swp_entry(type, offset);

  		spin_lock(&swap_lock);

  		next = swap_list.next;

  	}

  	atomic_long_inc(&nr_swap_pages);

  noswap:

  	spin_unlock(&swap_lock);

  	return (swp_entry_t) {0};

  }

  /* The only caller of this function is now suspend routine */

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

  	si = swap_info[type];

  	spin_lock(&si->lock);

  	if (si && (si->flags & SWP_WRITEOK)) {

  		atomic_long_dec(&nr_swap_pages);

  		/* This is called for allocating swap entry, not cache */
  		offset = scan_swap_map(si, 1);
  		if (offset) {

  			spin_unlock(&si->lock);

  			return swp_entry(type, offset);
  		}

  		atomic_long_inc(&nr_swap_pages);

  	}

  	spin_unlock(&si->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(&p->lock);

  	return p;
  
  bad_free:

  	pr_err("swap_free: %s%08lx
  ", Unused_offset, entry.val);

  	goto out;
  bad_offset:

  	pr_err("swap_free: %s%08lx
  ", Bad_offset, entry.val);

  	goto out;
  bad_device:

  	pr_err("swap_free: %s%08lx
  ", Unused_file, entry.val);

  	goto out;
  bad_nofile:

  	pr_err("swap_free: %s%08lx
  ", Bad_file, entry.val);

  out:
  	return NULL;

  }

  /*
   * This swap type frees swap entry, check if it is the highest priority swap
   * type which just frees swap entry. get_swap_page() uses
   * highest_priority_index to search highest priority swap type. The
   * swap_info_struct.lock can't protect us if there are multiple swap types
   * active, so we use atomic_cmpxchg.
   */
  static void set_highest_priority_index(int type)
  {
  	int old_hp_index, new_hp_index;
  
  	do {
  		old_hp_index = atomic_read(&highest_priority_index);
  		if (old_hp_index != -1 &&
  			swap_info[old_hp_index]->prio >= swap_info[type]->prio)
  			break;
  		new_hp_index = type;
  	} while (atomic_cmpxchg(&highest_priority_index,
  		old_hp_index, new_hp_index) != old_hp_index);
  }

  static unsigned char swap_entry_free(struct swap_info_struct *p,
  				     swp_entry_t entry, unsigned char usage)

  {

  	unsigned long offset = swp_offset(entry);

  	unsigned char count;
  	unsigned char has_cache;

  	count = p->swap_map[offset];
  	has_cache = count & SWAP_HAS_CACHE;
  	count &= ~SWAP_HAS_CACHE;

  	if (usage == SWAP_HAS_CACHE) {

  		VM_BUG_ON(!has_cache);

  		has_cache = 0;

  	} else if (count == SWAP_MAP_SHMEM) {
  		/*
  		 * Or we could insist on shmem.c using a special
  		 * swap_shmem_free() and free_shmem_swap_and_cache()...
  		 */
  		count = 0;

  	} else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) {
  		if (count == COUNT_CONTINUED) {
  			if (swap_count_continued(p, offset, count))
  				count = SWAP_MAP_MAX | COUNT_CONTINUED;
  			else
  				count = SWAP_MAP_MAX;
  		} else
  			count--;
  	}

  
  	if (!count)
  		mem_cgroup_uncharge_swap(entry);
  
  	usage = count | has_cache;
  	p->swap_map[offset] = usage;

  	/* free if no reference */

  	if (!usage) {

  		dec_cluster_info_page(p, p->cluster_info, offset);

  		if (offset < p->lowest_bit)
  			p->lowest_bit = offset;
  		if (offset > p->highest_bit)
  			p->highest_bit = offset;

  		set_highest_priority_index(p->type);
  		atomic_long_inc(&nr_swap_pages);

  		p->inuse_pages--;

  		frontswap_invalidate_page(p->type, offset);

  		if (p->flags & SWP_BLKDEV) {
  			struct gendisk *disk = p->bdev->bd_disk;
  			if (disk->fops->swap_slot_free_notify)
  				disk->fops->swap_slot_free_notify(p->bdev,
  								  offset);
  		}

  	}

  
  	return usage;

  }
  
  /*

   * Caller has made sure that the swap device 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, entry, 1);

  		spin_unlock(&p->lock);

  	}
  }
  
  /*

   * Called after dropping swapcache to decrease refcnt to swap entries.
   */
  void swapcache_free(swp_entry_t entry, struct page *page)
  {

  	struct swap_info_struct *p;

  	unsigned char count;

  	p = swap_info_get(entry);
  	if (p) {

  		count = swap_entry_free(p, entry, SWAP_HAS_CACHE);
  		if (page)
  			mem_cgroup_uncharge_swapcache(page, entry, count != 0);

  		spin_unlock(&p->lock);

  	}

  }
  
  /*

   * How many references to page are currently swapped out?

   * This does not give an exact answer when swap count is continued,
   * but does include the high COUNT_CONTINUED flag to allow for that.

   */

  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) {

  		count = swap_count(p->swap_map[swp_offset(entry)]);

  		spin_unlock(&p->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_PAGE(!PageLocked(page), page);

  	if (unlikely(PageKsm(page)))
  		return 0;

  	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_PAGE(!PageLocked(page), page);

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

  	if (page_swapcount(page))

  		return 0;

  	/*
  	 * Once hibernation has begun to create its image of memory,
  	 * there's a danger that one of the calls to try_to_free_swap()
  	 * - most probably a call from __try_to_reclaim_swap() while
  	 * hibernation is allocating its own swap pages for the image,
  	 * but conceivably even a call from memory reclaim - will free
  	 * the swap from a page which has already been recorded in the
  	 * image as a clean swapcache page, and then reuse its swap for
  	 * another page of the image.  On waking from hibernation, the
  	 * original page might be freed under memory pressure, then
  	 * later read back in from swap, now with the wrong data.
  	 *

  	 * Hibernation suspends storage while it is writing the image

  	 * to disk so check that here.

  	 */

  	if (pm_suspended_storage())

  		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 (non_swap_entry(entry))

  		return 1;

  	p = swap_info_get(entry);
  	if (p) {

  		if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) {

  			page = find_get_page(swap_address_space(entry),
  						entry.val);

  			if (page && !trylock_page(page)) {

  				page_cache_release(page);
  				page = NULL;
  			}
  		}

  		spin_unlock(&p->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 type;

  	if (device)
  		bdev = bdget(device);

  	spin_lock(&swap_lock);

  	for (type = 0; type < nr_swapfiles; type++) {
  		struct swap_info_struct *sis = swap_info[type];

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

  			continue;

  		if (!bdev) {

  			if (bdev_p)

  				*bdev_p = bdgrab(sis->bdev);

  			spin_unlock(&swap_lock);

  			return type;

  		}

  		if (bdev == sis->bdev) {

  			struct swap_extent *se = &sis->first_swap_extent;

  			if (se->start_block == offset) {

  				if (bdev_p)

  					*bdev_p = bdgrab(sis->bdev);

  				spin_unlock(&swap_lock);
  				bdput(bdev);

  				return type;

  			}

  		}
  	}
  	spin_unlock(&swap_lock);

  	if (bdev)
  		bdput(bdev);

  	return -ENODEV;
  }
  
  /*

   * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev
   * corresponding to given index in swap_info (swap type).
   */
  sector_t swapdev_block(int type, pgoff_t offset)
  {
  	struct block_device *bdev;
  
  	if ((unsigned int)type >= nr_swapfiles)
  		return 0;
  	if (!(swap_info[type]->flags & SWP_WRITEOK))
  		return 0;

  	return map_swap_entry(swp_entry(type, offset), &bdev);

  }
  
  /*

   * 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;

  	spin_lock(&swap_lock);
  	if ((unsigned int)type < nr_swapfiles) {
  		struct swap_info_struct *sis = swap_info[type];

  		spin_lock(&sis->lock);

  		if (sis->flags & SWP_WRITEOK) {
  			n = sis->pages;

  			if (free)

  				n -= sis->inuse_pages;

  		}

  		spin_unlock(&sis->lock);

  	}

  	spin_unlock(&swap_lock);

  	return n;
  }

  #endif /* CONFIG_HIBERNATION */

  static inline int maybe_same_pte(pte_t pte, pte_t swp_pte)
  {
  #ifdef CONFIG_MEM_SOFT_DIRTY
  	/*
  	 * When pte keeps soft dirty bit the pte generated
  	 * from swap entry does not has it, still it's same
  	 * pte from logical point of view.
  	 */
  	pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte);
  	return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty);
  #else
  	return pte_same(pte, swp_pte);
  #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)
  {

  	struct page *swapcache;

  	struct mem_cgroup *memcg;

  	spinlock_t *ptl;
  	pte_t *pte;
  	int ret = 1;

  	swapcache = page;
  	page = ksm_might_need_to_copy(page, vma, addr);
  	if (unlikely(!page))
  		return -ENOMEM;

  	if (mem_cgroup_try_charge_swapin(vma->vm_mm, page,
  					 GFP_KERNEL, &memcg)) {

  		ret = -ENOMEM;

  		goto out_nolock;
  	}

  
  	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);

  	if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {

  		mem_cgroup_cancel_charge_swapin(memcg);

  		ret = 0;
  		goto out;
  	}

  	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);

  	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);

  	get_page(page);
  	set_pte_at(vma->vm_mm, addr, pte,
  		   pte_mkold(mk_pte(page, vma->vm_page_prot)));

  	if (page == swapcache)
  		page_add_anon_rmap(page, vma, addr);
  	else /* ksm created a completely new copy */
  		page_add_new_anon_rmap(page, vma, addr);

  	mem_cgroup_commit_charge_swapin(page, memcg);

  	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);

  out_nolock:

  	if (page != swapcache) {
  		unlock_page(page);
  		put_page(page);
  	}

  	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

  	 * preemptable 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(maybe_same_pte(*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_trans_huge_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_anon_vma(page)) {

  		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 (or frontswap_map if frontswap parameter is true)
   * 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, bool frontswap)

  {

  	unsigned int max = si->max;
  	unsigned int i = prev;

  	unsigned char 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;
  		}

  		if (frontswap) {
  			if (frontswap_test(si, i))
  				break;
  			else
  				continue;
  		}

  		count = ACCESS_ONCE(si->swap_map[i]);

  		if (count && swap_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.

   *
   * if the boolean frontswap is true, only unuse pages_to_unuse pages;
   * pages_to_unuse==0 means all pages; ignored if frontswap is false

   */

  int try_to_unuse(unsigned int type, bool frontswap,
  		 unsigned long pages_to_unuse)

  {

  	struct swap_info_struct *si = swap_info[type];

  	struct mm_struct *start_mm;

  	volatile unsigned char *swap_map; /* swap_map is accessed without
  					   * locking. Mark it as volatile
  					   * to prevent compiler doing
  					   * something odd.
  					   */

  	unsigned char swcount;

  	struct page *page;
  	swp_entry_t entry;

  	unsigned int i = 0;

  	int retval = 0;

  
  	/*
  	 * 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.

  	 */
  	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, frontswap)) != 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.
  			 */

  			swcount = *swap_map;
  			/*
  			 * We don't hold lock here, so the swap entry could be
  			 * SWAP_MAP_BAD (when the cluster is discarding).
  			 * Instead of fail out, We can just skip the swap
  			 * entry because swapoff will wait for discarding
  			 * finish anyway.
  			 */
  			if (!swcount || swcount == SWAP_MAP_BAD)

  				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.

  		 */

  		swcount = *swap_map;

  		if (swap_count(swcount) == SWAP_MAP_SHMEM) {
  			retval = shmem_unuse(entry, page);
  			/* page has already been unlocked and released */
  			if (retval < 0)
  				break;
  			continue;

  		}

  		if (swap_count(swcount) && start_mm != &init_mm)
  			retval = unuse_mm(start_mm, entry, page);

  		if (swap_count(*swap_map)) {

  			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;
  			struct mm_struct *mm;
  
  			atomic_inc(&new_start_mm->mm_users);
  			atomic_inc(&prev_mm->mm_users);
  			spin_lock(&mmlist_lock);

  			while (swap_count(*swap_map) && !retval &&

  					(p = p->next) != &start_mm->mmlist) {
  				mm = list_entry(p, struct mm_struct, mmlist);

  				if (!atomic_inc_not_zero(&mm->mm_users))

  					continue;

  				spin_unlock(&mmlist_lock);
  				mmput(prev_mm);
  				prev_mm = mm;
  
  				cond_resched();
  
  				swcount = *swap_map;

  				if (!swap_count(swcount)) /* any usage ? */

  					;

  				else if (mm == &init_mm)

  					set_start_mm = 1;

  				else

  					retval = unuse_mm(mm, entry, page);

  				if (set_start_mm && *swap_map < swcount) {

  					mmput(new_start_mm);
  					atomic_inc(&mm->mm_users);
  					new_start_mm = mm;
  					set_start_mm = 0;
  				}
  				spin_lock(&mmlist_lock);
  			}
  			spin_unlock(&mmlist_lock);
  			mmput(prev_mm);
  			mmput(start_mm);
  			start_mm = new_start_mm;
  		}
  		if (retval) {
  			unlock_page(page);
  			page_cache_release(page);
  			break;
  		}
  
  		/*

  		 * If a reference remains (rare), we would like to leave
  		 * the page in the swap cache; but try_to_unmap could
  		 * then re-duplicate the entry once we drop page lock,
  		 * so we might loop indefinitely; also, that page could
  		 * not be swapped out to other storage meanwhile.  So:
  		 * delete from cache even if there's another reference,
  		 * after ensuring that the data has been saved to disk -
  		 * since if the reference remains (rarer), it will be
  		 * read from disk into another page.  Splitting into two
  		 * pages would be incorrect if swap supported "shared
  		 * private" pages, but they are handled by tmpfs files.

  		 *
  		 * Given how unuse_vma() targets one particular offset
  		 * in an anon_vma, once the anon_vma has been determined,
  		 * this splitting happens to be just what is needed to
  		 * handle where KSM pages have been swapped out: re-reading
  		 * is unnecessarily slow, but we can fix that later on.

  		 */

  		if (swap_count(*swap_map) &&
  		     PageDirty(page) && PageSwapCache(page)) {

  			struct writeback_control wbc = {
  				.sync_mode = WB_SYNC_NONE,
  			};
  
  			swap_writepage(page, &wbc);
  			lock_page(page);
  			wait_on_page_writeback(page);
  		}

  
  		/*
  		 * It is conceivable that a racing task removed this page from
  		 * swap cache just before we acquired the page lock at the top,
  		 * or while we dropped it in unuse_mm().  The page might even
  		 * be back in swap cache on another swap area: that we must not
  		 * delete, since it may not have been written out to swap yet.
  		 */
  		if (PageSwapCache(page) &&
  		    likely(page_private(page) == entry.val))

  			delete_from_swap_cache(page);

  
  		/*
  		 * So we could skip searching mms once swap count went
  		 * to 1, we did not mark any present ptes as dirty: must

  		 * mark page dirty so shrink_page_list will preserve it.

  		 */
  		SetPageDirty(page);
  		unlock_page(page);
  		page_cache_release(page);
  
  		/*
  		 * Make sure that we aren't completely killing
  		 * interactive performance.
  		 */
  		cond_resched();

  		if (frontswap && pages_to_unuse > 0) {
  			if (!--pages_to_unuse)
  				break;
  		}

  	}
  
  	mmput(start_mm);

  	return retval;
  }
  
  /*

   * After a successful try_to_unuse, if no swap is now in use, we know
   * we can empty the mmlist.  swap_lock must be held on entry and exit.
   * Note that mmlist_lock nests inside swap_lock, and an mm must be

   * added to the mmlist just after page_duplicate - before would be racy.
   */
  static void drain_mmlist(void)
  {
  	struct list_head *p, *next;

  	unsigned int type;

  	for (type = 0; type < nr_swapfiles; type++)
  		if (swap_info[type]->inuse_pages)

  			return;
  	spin_lock(&mmlist_lock);
  	list_for_each_safe(p, next, &init_mm.mmlist)
  		list_del_init(p);
  	spin_unlock(&mmlist_lock);
  }
  
  /*
   * Use this swapdev's extent info to locate the (PAGE_SIZE) block which

   * corresponds to page offset for the specified swap entry.
   * Note that the type of this function is sector_t, but it returns page offset
   * into the bdev, not sector offset.

   */

  static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev)

  {

  	struct swap_info_struct *sis;
  	struct swap_extent *start_se;
  	struct swap_extent *se;
  	pgoff_t offset;

  	sis = swap_info[swp_type(entry)];

  	*bdev = sis->bdev;
  
  	offset = swp_offset(entry);
  	start_se = sis->curr_swap_extent;
  	se = start_se;

  
  	for ( ; ; ) {
  		struct list_head *lh;
  
  		if (se->start_page <= offset &&
  				offset < (se->start_page + se->nr_pages)) {
  			return se->start_block + (offset - se->start_page);
  		}

  		lh = se->list.next;

  		se = list_entry(lh, struct swap_extent, list);
  		sis->curr_swap_extent = se;
  		BUG_ON(se == start_se);		/* It *must* be present */
  	}
  }
  
  /*

   * Returns the page offset into bdev for the specified page's swap entry.
   */
  sector_t map_swap_page(struct page *page, struct block_device **bdev)
  {
  	swp_entry_t entry;
  	entry.val = page_private(page);
  	return map_swap_entry(entry, bdev);
  }
  
  /*

   * Free all of a swapdev's extent information
   */
  static void destroy_swap_extents(struct swap_info_struct *sis)
  {

  	while (!list_empty(&sis->first_swap_extent.list)) {

  		struct swap_extent *se;

  		se = list_entry(sis->first_swap_extent.list.next,

  				struct swap_extent, list);
  		list_del(&se->list);
  		kfree(se);
  	}

  
  	if (sis->flags & SWP_FILE) {
  		struct file *swap_file = sis->swap_file;
  		struct address_space *mapping = swap_file->f_mapping;
  
  		sis->flags &= ~SWP_FILE;
  		mapping->a_ops->swap_deactivate(swap_file);
  	}

  }
  
  /*
   * Add a block range (and the corresponding page range) into this swapdev's

   * extent list.  The extent list is kept sorted in page order.

   *

   * This function rather assumes that it is called in ascending page order.

   */

  int

  add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
  		unsigned long nr_pages, sector_t start_block)
  {
  	struct swap_extent *se;
  	struct swap_extent *new_se;
  	struct list_head *lh;

  	if (start_page == 0) {
  		se = &sis->first_swap_extent;
  		sis->curr_swap_extent = se;
  		se->start_page = 0;
  		se->nr_pages = nr_pages;
  		se->start_block = start_block;
  		return 1;
  	} else {
  		lh = sis->first_swap_extent.list.prev;	/* Highest extent */

  		se = list_entry(lh, struct swap_extent, list);

  		BUG_ON(se->start_page + se->nr_pages != start_page);
  		if (se->start_block + se->nr_pages == start_block) {

  			/* Merge it */
  			se->nr_pages += nr_pages;
  			return 0;
  		}

  	}
  
  	/*
  	 * No merge.  Insert a new extent, preserving ordering.
  	 */
  	new_se = kmalloc(sizeof(*se), GFP_KERNEL);
  	if (new_se == NULL)
  		return -ENOMEM;
  	new_se->start_page = start_page;
  	new_se->nr_pages = nr_pages;
  	new_se->start_block = start_block;

  	list_add_tail(&new_se->list, &sis->first_swap_extent.list);

  	return 1;

  }
  
  /*
   * A `swap extent' is a simple thing which maps a contiguous range of pages
   * onto a contiguous range of disk blocks.  An ordered list of swap extents
   * is built at swapon time and is then used at swap_writepage/swap_readpage
   * time for locating where on disk a page belongs.
   *
   * If the swapfile is an S_ISBLK block device, a single extent is installed.
   * This is done so that the main operating code can treat S_ISBLK and S_ISREG
   * swap files identically.
   *
   * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap
   * extent list operates in PAGE_SIZE disk blocks.  Both S_ISREG and S_ISBLK
   * swapfiles are handled *identically* after swapon time.
   *
   * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks
   * and will parse them into an ordered extent list, in PAGE_SIZE chunks.  If
   * some stray blocks are found which do not fall within the PAGE_SIZE alignment
   * requirements, they are simply tossed out - we will never use those blocks
   * for swapping.
   *

   * For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon.  This

   * prevents root from shooting her foot off by ftruncating an in-use swapfile,
   * which will scribble on the fs.
   *
   * The amount of disk space which a single swap extent represents varies.
   * Typically it is in the 1-4 megabyte range.  So we can have hundreds of
   * extents in the list.  To avoid much list walking, we cache the previous
   * search location in `curr_swap_extent', and start new searches from there.
   * This is extremely effective.  The average number of iterations in
   * map_swap_page() has been measured at about 0.3 per page.  - akpm.
   */

  static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)

  {

  	struct file *swap_file = sis->swap_file;
  	struct address_space *mapping = swap_file->f_mapping;
  	struct inode *inode = mapping->host;

  	int ret;

  	if (S_ISBLK(inode->i_mode)) {
  		ret = add_swap_extent(sis, 0, sis->max, 0);

  		*span = sis->pages;

  		return ret;

  	}

  	if (mapping->a_ops->swap_activate) {

  		ret = mapping->a_ops->swap_activate(sis, swap_file, span);

  		if (!ret) {
  			sis->flags |= SWP_FILE;
  			ret = add_swap_extent(sis, 0, sis->max, 0);
  			*span = sis->pages;
  		}

  		return ret;

  	}

  	return generic_swapfile_activate(sis, swap_file, span);

  }

  static void _enable_swap_info(struct swap_info_struct *p, int prio,

  				unsigned char *swap_map,
  				struct swap_cluster_info *cluster_info)

  {
  	int i, prev;

  	if (prio >= 0)
  		p->prio = prio;
  	else
  		p->prio = --least_priority;
  	p->swap_map = swap_map;

  	p->cluster_info = cluster_info;

  	p->flags |= SWP_WRITEOK;

  	atomic_long_add(p->pages, &nr_swap_pages);

  	total_swap_pages += p->pages;
  
  	/* insert swap space into swap_list: */
  	prev = -1;
  	for (i = swap_list.head; i >= 0; i = swap_info[i]->next) {
  		if (p->prio >= swap_info[i]->prio)
  			break;
  		prev = i;
  	}
  	p->next = i;
  	if (prev < 0)
  		swap_list.head = swap_list.next = p->type;
  	else
  		swap_info[prev]->next = p->type;

  }
  
  static void enable_swap_info(struct swap_info_struct *p, int prio,
  				unsigned char *swap_map,

  				struct swap_cluster_info *cluster_info,

  				unsigned long *frontswap_map)
  {

  	frontswap_init(p->type, frontswap_map);

  	spin_lock(&swap_lock);

  	spin_lock(&p->lock);

  	 _enable_swap_info(p, prio, swap_map, cluster_info);

  	spin_unlock(&p->lock);

  	spin_unlock(&swap_lock);
  }
  
  static void reinsert_swap_info(struct swap_info_struct *p)
  {
  	spin_lock(&swap_lock);

  	spin_lock(&p->lock);

  	_enable_swap_info(p, p->prio, p->swap_map, p->cluster_info);

  	spin_unlock(&p->lock);

  	spin_unlock(&swap_lock);
  }

  SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)

  {

  	struct swap_info_struct *p = NULL;

  	unsigned char *swap_map;

  	struct swap_cluster_info *cluster_info;

  	unsigned long *frontswap_map;

  	struct file *swap_file, *victim;
  	struct address_space *mapping;
  	struct inode *inode;

  	struct filename *pathname;

  	int i, type, prev;
  	int err;

  	unsigned int old_block_size;

  	if (!capable(CAP_SYS_ADMIN))
  		return -EPERM;

  	BUG_ON(!current->mm);

  	pathname = getname(specialfile);

  	if (IS_ERR(pathname))

  		return PTR_ERR(pathname);

  	victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0);

  	err = PTR_ERR(victim);
  	if (IS_ERR(victim))
  		goto out;
  
  	mapping = victim->f_mapping;
  	prev = -1;

  	spin_lock(&swap_lock);

  	for (type = swap_list.head; type >= 0; type = swap_info[type]->next) {
  		p = swap_info[type];

  		if (p->flags & SWP_WRITEOK) {

  			if (p->swap_file->f_mapping == mapping)
  				break;
  		}
  		prev = type;
  	}
  	if (type < 0) {
  		err = -EINVAL;

  		spin_unlock(&swap_lock);

  		goto out_dput;
  	}

  	if (!security_vm_enough_memory_mm(current->mm, p->pages))

  		vm_unacct_memory(p->pages);
  	else {
  		err = -ENOMEM;

  		spin_unlock(&swap_lock);

  		goto out_dput;
  	}

  	if (prev < 0)

  		swap_list.head = p->next;

  	else
  		swap_info[prev]->next = p->next;

  	if (type == swap_list.next) {
  		/* just pick something that's safe... */
  		swap_list.next = swap_list.head;
  	}

  	spin_lock(&p->lock);

  	if (p->prio < 0) {

  		for (i = p->next; i >= 0; i = swap_info[i]->next)
  			swap_info[i]->prio = p->prio--;

  		least_priority++;
  	}

  	atomic_long_sub(p->pages, &nr_swap_pages);

  	total_swap_pages -= p->pages;
  	p->flags &= ~SWP_WRITEOK;

  	spin_unlock(&p->lock);

  	spin_unlock(&swap_lock);

  	set_current_oom_origin();

  	err = try_to_unuse(type, false, 0); /* force all pages to be unused */

  	clear_current_oom_origin();

  	if (err) {
  		/* re-insert swap space back into swap_list */

  		reinsert_swap_info(p);

  		goto out_dput;
  	}