/*
   *  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/sched/mm.h>

  #include <linux/sched/task.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 <linux/swap_slots.h>

  #include <linux/sort.h>

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

  #include <linux/swap_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;

  /*
   * Some modules use swappable objects and may try to swap them out under
   * memory pressure (via the shrinker). Before doing so, they may wish to
   * check to see if any swap space is available.
   */
  EXPORT_SYMBOL_GPL(nr_swap_pages);

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

  long total_swap_pages;

  static int least_priority = -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 ";

  /*
   * all active swap_info_structs
   * protected with swap_lock, and ordered by priority.
   */

  PLIST_HEAD(swap_active_head);
  
  /*
   * all available (active, not full) swap_info_structs
   * protected with swap_avail_lock, ordered by priority.
   * This is used by get_swap_page() instead of swap_active_head
   * because swap_active_head includes all swap_info_structs,
   * but get_swap_page() doesn't need to look at full ones.
   * This uses its own lock instead of swap_lock because when a
   * swap_info_struct changes between not-full/full, it needs to
   * add/remove itself to/from this list, but the swap_info_struct->lock
   * is held and the locking order requires swap_lock to be taken
   * before any swap_info_struct->lock.
   */

  struct plist_head *swap_avail_heads;

  static DEFINE_SPINLOCK(swap_avail_lock);

  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);

  atomic_t nr_rotate_swap = 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), swp_offset(entry));

  	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);
  	}

  	put_page(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) {

  		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;
  		}

  		se = list_next_entry(se, list);

  	}
  }

  #ifdef CONFIG_THP_SWAP
  #define SWAPFILE_CLUSTER	HPAGE_PMD_NR
  #else

  #define SWAPFILE_CLUSTER	256

  #endif

  #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;
  }

  static inline bool cluster_is_huge(struct swap_cluster_info *info)
  {
  	return info->flags & CLUSTER_FLAG_HUGE;
  }
  
  static inline void cluster_clear_huge(struct swap_cluster_info *info)
  {
  	info->flags &= ~CLUSTER_FLAG_HUGE;
  }

  static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
  						     unsigned long offset)
  {
  	struct swap_cluster_info *ci;
  
  	ci = si->cluster_info;
  	if (ci) {
  		ci += offset / SWAPFILE_CLUSTER;
  		spin_lock(&ci->lock);
  	}
  	return ci;
  }
  
  static inline void unlock_cluster(struct swap_cluster_info *ci)
  {
  	if (ci)
  		spin_unlock(&ci->lock);
  }
  
  static inline struct swap_cluster_info *lock_cluster_or_swap_info(
  	struct swap_info_struct *si,
  	unsigned long offset)
  {
  	struct swap_cluster_info *ci;
  
  	ci = lock_cluster(si, offset);
  	if (!ci)
  		spin_lock(&si->lock);
  
  	return ci;
  }
  
  static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
  					       struct swap_cluster_info *ci)
  {
  	if (ci)
  		unlock_cluster(ci);
  	else
  		spin_unlock(&si->lock);
  }

  static inline bool cluster_list_empty(struct swap_cluster_list *list)
  {
  	return cluster_is_null(&list->head);
  }
  
  static inline unsigned int cluster_list_first(struct swap_cluster_list *list)
  {
  	return cluster_next(&list->head);
  }
  
  static void cluster_list_init(struct swap_cluster_list *list)
  {
  	cluster_set_null(&list->head);
  	cluster_set_null(&list->tail);
  }
  
  static void cluster_list_add_tail(struct swap_cluster_list *list,
  				  struct swap_cluster_info *ci,
  				  unsigned int idx)
  {
  	if (cluster_list_empty(list)) {
  		cluster_set_next_flag(&list->head, idx, 0);
  		cluster_set_next_flag(&list->tail, idx, 0);
  	} else {

  		struct swap_cluster_info *ci_tail;

  		unsigned int tail = cluster_next(&list->tail);

  		/*
  		 * Nested cluster lock, but both cluster locks are
  		 * only acquired when we held swap_info_struct->lock
  		 */
  		ci_tail = ci + tail;
  		spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING);
  		cluster_set_next(ci_tail, idx);

  		spin_unlock(&ci_tail->lock);

  		cluster_set_next_flag(&list->tail, idx, 0);
  	}
  }
  
  static unsigned int cluster_list_del_first(struct swap_cluster_list *list,
  					   struct swap_cluster_info *ci)
  {
  	unsigned int idx;
  
  	idx = cluster_next(&list->head);
  	if (cluster_next(&list->tail) == idx) {
  		cluster_set_null(&list->head);
  		cluster_set_null(&list->tail);
  	} else
  		cluster_set_next_flag(&list->head,
  				      cluster_next(&ci[idx]), 0);
  
  	return idx;
  }

  /* 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);

  	cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx);

  
  	schedule_work(&si->discard_work);
  }

  static void __free_cluster(struct swap_info_struct *si, unsigned long idx)
  {
  	struct swap_cluster_info *ci = si->cluster_info;
  
  	cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE);
  	cluster_list_add_tail(&si->free_clusters, ci, idx);
  }

  /*
   * 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, *ci;

  	unsigned int idx;
  
  	info = si->cluster_info;

  	while (!cluster_list_empty(&si->discard_clusters)) {
  		idx = cluster_list_del_first(&si->discard_clusters, info);

  		spin_unlock(&si->lock);
  
  		discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
  				SWAPFILE_CLUSTER);
  
  		spin_lock(&si->lock);

  		ci = lock_cluster(si, idx * SWAPFILE_CLUSTER);

  		__free_cluster(si, idx);

  		memset(si->swap_map + idx * SWAPFILE_CLUSTER,
  				0, SWAPFILE_CLUSTER);

  		unlock_cluster(ci);

  	}
  }
  
  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);
  }

  static void alloc_cluster(struct swap_info_struct *si, unsigned long idx)
  {
  	struct swap_cluster_info *ci = si->cluster_info;
  
  	VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx);
  	cluster_list_del_first(&si->free_clusters, ci);
  	cluster_set_count_flag(ci + idx, 0, 0);
  }
  
  static void free_cluster(struct swap_info_struct *si, unsigned long idx)
  {
  	struct swap_cluster_info *ci = si->cluster_info + idx;
  
  	VM_BUG_ON(cluster_count(ci) != 0);
  	/*
  	 * If the swap is discardable, prepare discard the cluster
  	 * instead of free it immediately. The cluster will be freed
  	 * after discard.
  	 */
  	if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
  	    (SWP_WRITEOK | SWP_PAGE_DISCARD)) {
  		swap_cluster_schedule_discard(si, idx);
  		return;
  	}
  
  	__free_cluster(si, idx);
  }

  /*
   * 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]))
  		alloc_cluster(p, idx);

  
  	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)
  		free_cluster(p, idx);

  }
  
  /*
   * 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_list_empty(&si->free_clusters) &&
  		offset != cluster_list_first(&si->free_clusters) &&

  		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 bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,

  	unsigned long *offset, unsigned long *scan_base)
  {
  	struct percpu_cluster *cluster;

  	struct swap_cluster_info *ci;

  	bool found_free;

  	unsigned long tmp, max;

  
  new_cluster:
  	cluster = this_cpu_ptr(si->percpu_cluster);
  	if (cluster_is_null(&cluster->index)) {

  		if (!cluster_list_empty(&si->free_clusters)) {
  			cluster->index = si->free_clusters.head;

  			cluster->next = cluster_next(&cluster->index) *
  					SWAPFILE_CLUSTER;

  		} else if (!cluster_list_empty(&si->discard_clusters)) {

  			/*
  			 * 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 false;

  	}
  
  	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;

  	max = min_t(unsigned long, si->max,
  		    (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER);
  	if (tmp >= max) {
  		cluster_set_null(&cluster->index);
  		goto new_cluster;
  	}
  	ci = lock_cluster(si, tmp);
  	while (tmp < max) {

  		if (!si->swap_map[tmp]) {
  			found_free = true;
  			break;
  		}
  		tmp++;
  	}

  	unlock_cluster(ci);

  	if (!found_free) {
  		cluster_set_null(&cluster->index);
  		goto new_cluster;
  	}
  	cluster->next = tmp + 1;
  	*offset = tmp;
  	*scan_base = tmp;

  	return found_free;

  }

  static void __del_from_avail_list(struct swap_info_struct *p)
  {
  	int nid;
  
  	for_each_node(nid)
  		plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]);
  }
  
  static void del_from_avail_list(struct swap_info_struct *p)
  {
  	spin_lock(&swap_avail_lock);
  	__del_from_avail_list(p);
  	spin_unlock(&swap_avail_lock);
  }

  static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
  			     unsigned int nr_entries)
  {
  	unsigned int end = offset + nr_entries - 1;
  
  	if (offset == si->lowest_bit)
  		si->lowest_bit += nr_entries;
  	if (end == si->highest_bit)
  		si->highest_bit -= nr_entries;
  	si->inuse_pages += nr_entries;
  	if (si->inuse_pages == si->pages) {
  		si->lowest_bit = si->max;
  		si->highest_bit = 0;

  		del_from_avail_list(si);

  	}
  }

  static void add_to_avail_list(struct swap_info_struct *p)
  {
  	int nid;
  
  	spin_lock(&swap_avail_lock);
  	for_each_node(nid) {
  		WARN_ON(!plist_node_empty(&p->avail_lists[nid]));
  		plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]);
  	}
  	spin_unlock(&swap_avail_lock);
  }

  static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
  			    unsigned int nr_entries)
  {
  	unsigned long end = offset + nr_entries - 1;
  	void (*swap_slot_free_notify)(struct block_device *, unsigned long);
  
  	if (offset < si->lowest_bit)
  		si->lowest_bit = offset;
  	if (end > si->highest_bit) {
  		bool was_full = !si->highest_bit;
  
  		si->highest_bit = end;

  		if (was_full && (si->flags & SWP_WRITEOK))
  			add_to_avail_list(si);

  	}
  	atomic_long_add(nr_entries, &nr_swap_pages);
  	si->inuse_pages -= nr_entries;
  	if (si->flags & SWP_BLKDEV)
  		swap_slot_free_notify =
  			si->bdev->bd_disk->fops->swap_slot_free_notify;
  	else
  		swap_slot_free_notify = NULL;
  	while (offset <= end) {
  		frontswap_invalidate_page(si->type, offset);
  		if (swap_slot_free_notify)
  			swap_slot_free_notify(si->bdev, offset);
  		offset++;
  	}
  }

  static int scan_swap_map_slots(struct swap_info_struct *si,
  			       unsigned char usage, int nr,
  			       swp_entry_t slots[])

  {

  	struct swap_cluster_info *ci;

  	unsigned long offset;

  	unsigned long scan_base;

  	unsigned long last_in_cluster = 0;

  	int latency_ration = LATENCY_LIMIT;

  	int n_ret = 0;
  
  	if (nr > SWAP_BATCH)
  		nr = SWAP_BATCH;

  	/*

  	 * 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) {

  		if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
  			goto checks;
  		else
  			goto scan;

  	}

  	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.

  		 * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info
  		 * case, just handled by scan_swap_map_try_ssd_cluster() above.

  		 */

  		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 = 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)) {
  		/* take a break if we already got some slots */
  			if (n_ret)
  				goto done;
  			if (!scan_swap_map_try_ssd_cluster(si, &offset,
  							&scan_base))
  				goto scan;
  		}

  	}

  	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;

  	ci = lock_cluster(si, offset);

  	/* 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;

  		unlock_cluster(ci);

  		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]) {
  		unlock_cluster(ci);

  		if (!n_ret)
  			goto scan;
  		else
  			goto done;

  	}

  	si->swap_map[offset] = usage;
  	inc_cluster_info_page(si, si->cluster_info, offset);
  	unlock_cluster(ci);

  	swap_range_alloc(si, offset, 1);

  	si->cluster_next = offset + 1;

  	slots[n_ret++] = swp_entry(si->type, offset);
  
  	/* got enough slots or reach max slots? */
  	if ((n_ret == nr) || (offset >= si->highest_bit))
  		goto done;
  
  	/* search for next available slot */
  
  	/* time to take a break? */
  	if (unlikely(--latency_ration < 0)) {
  		if (n_ret)
  			goto done;
  		spin_unlock(&si->lock);
  		cond_resched();
  		spin_lock(&si->lock);
  		latency_ration = LATENCY_LIMIT;
  	}
  
  	/* try to get more slots in cluster */
  	if (si->cluster_info) {
  		if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
  			goto checks;
  		else
  			goto done;
  	}
  	/* non-ssd case */
  	++offset;
  
  	/* non-ssd case, still more slots in cluster? */
  	if (si->cluster_nr && !si->swap_map[offset]) {
  		--si->cluster_nr;
  		goto checks;
  	}

  done:
  	si->flags -= SWP_SCANNING;
  	return n_ret;

  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 n_ret;

  }

  #ifdef CONFIG_THP_SWAP
  static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
  {
  	unsigned long idx;
  	struct swap_cluster_info *ci;
  	unsigned long offset, i;
  	unsigned char *map;
  
  	if (cluster_list_empty(&si->free_clusters))
  		return 0;
  
  	idx = cluster_list_first(&si->free_clusters);
  	offset = idx * SWAPFILE_CLUSTER;
  	ci = lock_cluster(si, offset);
  	alloc_cluster(si, idx);

  	cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE);

  
  	map = si->swap_map + offset;
  	for (i = 0; i < SWAPFILE_CLUSTER; i++)
  		map[i] = SWAP_HAS_CACHE;
  	unlock_cluster(ci);
  	swap_range_alloc(si, offset, SWAPFILE_CLUSTER);
  	*slot = swp_entry(si->type, offset);
  
  	return 1;
  }
  
  static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
  {
  	unsigned long offset = idx * SWAPFILE_CLUSTER;
  	struct swap_cluster_info *ci;
  
  	ci = lock_cluster(si, offset);
  	cluster_set_count_flag(ci, 0, 0);
  	free_cluster(si, idx);
  	unlock_cluster(ci);
  	swap_range_free(si, offset, SWAPFILE_CLUSTER);
  }
  #else
  static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
  {
  	VM_WARN_ON_ONCE(1);
  	return 0;
  }
  #endif /* CONFIG_THP_SWAP */

  static unsigned long scan_swap_map(struct swap_info_struct *si,
  				   unsigned char usage)
  {
  	swp_entry_t entry;
  	int n_ret;
  
  	n_ret = scan_swap_map_slots(si, usage, 1, &entry);
  
  	if (n_ret)
  		return swp_offset(entry);
  	else
  		return 0;
  
  }

  int get_swap_pages(int n_goal, bool cluster, swp_entry_t swp_entries[])

  {

  	unsigned long nr_pages = cluster ? SWAPFILE_CLUSTER : 1;

  	struct swap_info_struct *si, *next;

  	long avail_pgs;
  	int n_ret = 0;

  	int node;

  	/* Only single cluster request supported */
  	WARN_ON_ONCE(n_goal > 1 && cluster);
  
  	avail_pgs = atomic_long_read(&nr_swap_pages) / nr_pages;

  	if (avail_pgs <= 0)

  		goto noswap;

  
  	if (n_goal > SWAP_BATCH)
  		n_goal = SWAP_BATCH;
  
  	if (n_goal > avail_pgs)
  		n_goal = avail_pgs;

  	atomic_long_sub(n_goal * nr_pages, &nr_swap_pages);

  	spin_lock(&swap_avail_lock);
  
  start_over:

  	node = numa_node_id();
  	plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) {

  		/* requeue si to after same-priority siblings */

  		plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]);

  		spin_unlock(&swap_avail_lock);

  		spin_lock(&si->lock);

  		if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) {

  			spin_lock(&swap_avail_lock);

  			if (plist_node_empty(&si->avail_lists[node])) {

  				spin_unlock(&si->lock);
  				goto nextsi;
  			}
  			WARN(!si->highest_bit,
  			     "swap_info %d in list but !highest_bit
  ",
  			     si->type);
  			WARN(!(si->flags & SWP_WRITEOK),
  			     "swap_info %d in list but !SWP_WRITEOK
  ",
  			     si->type);

  			__del_from_avail_list(si);

  			spin_unlock(&si->lock);

  			goto nextsi;

  		}

  		if (cluster) {
  			if (!(si->flags & SWP_FILE))
  				n_ret = swap_alloc_cluster(si, swp_entries);
  		} else

  			n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
  						    n_goal, swp_entries);

  		spin_unlock(&si->lock);

  		if (n_ret || cluster)

  			goto check_out;

  		pr_debug("scan_swap_map of si %d failed to find offset
  ",

  			si->type);

  		spin_lock(&swap_avail_lock);
  nextsi:

  		/*
  		 * if we got here, it's likely that si was almost full before,
  		 * and since scan_swap_map() can drop the si->lock, multiple
  		 * callers probably all tried to get a page from the same si

  		 * and it filled up before we could get one; or, the si filled
  		 * up between us dropping swap_avail_lock and taking si->lock.
  		 * Since we dropped the swap_avail_lock, the swap_avail_head
  		 * list may have been modified; so if next is still in the

  		 * swap_avail_head list then try it, otherwise start over
  		 * if we have not gotten any slots.

  		 */

  		if (plist_node_empty(&next->avail_lists[node]))

  			goto start_over;

  	}

  	spin_unlock(&swap_avail_lock);

  check_out:
  	if (n_ret < n_goal)

  		atomic_long_add((long)(n_goal - n_ret) * nr_pages,
  				&nr_swap_pages);

  noswap:

  	return n_ret;
  }

  /* 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;

  	return p;

  bad_offset:

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

  	goto out;
  bad_device:

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

  	goto out;
  bad_nofile:

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

  out:
  	return NULL;

  }

  static struct swap_info_struct *_swap_info_get(swp_entry_t entry)
  {
  	struct swap_info_struct *p;
  
  	p = __swap_info_get(entry);
  	if (!p)
  		goto out;
  	if (!p->swap_map[swp_offset(entry)])
  		goto bad_free;
  	return p;
  
  bad_free:
  	pr_err("swap_info_get: %s%08lx
  ", Unused_offset, entry.val);
  	goto out;
  out:
  	return NULL;
  }

  static struct swap_info_struct *swap_info_get(swp_entry_t entry)
  {
  	struct swap_info_struct *p;
  
  	p = _swap_info_get(entry);
  	if (p)
  		spin_lock(&p->lock);
  	return p;
  }

  static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry,
  					struct swap_info_struct *q)
  {
  	struct swap_info_struct *p;
  
  	p = _swap_info_get(entry);
  
  	if (p != q) {
  		if (q != NULL)
  			spin_unlock(&q->lock);
  		if (p != NULL)
  			spin_lock(&p->lock);
  	}
  	return p;
  }
  
  static unsigned char __swap_entry_free(struct swap_info_struct *p,
  				       swp_entry_t entry, unsigned char usage)

  {

  	struct swap_cluster_info *ci;

  	unsigned long offset = swp_offset(entry);

  	unsigned char count;
  	unsigned char has_cache;

  	ci = lock_cluster_or_swap_info(p, offset);

  	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--;
  	}

  	usage = count | has_cache;

  	p->swap_map[offset] = usage ? : SWAP_HAS_CACHE;
  
  	unlock_cluster_or_swap_info(p, ci);
  
  	return usage;
  }

  static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry)
  {
  	struct swap_cluster_info *ci;
  	unsigned long offset = swp_offset(entry);
  	unsigned char count;
  
  	ci = lock_cluster(p, offset);
  	count = p->swap_map[offset];
  	VM_BUG_ON(count != SWAP_HAS_CACHE);
  	p->swap_map[offset] = 0;
  	dec_cluster_info_page(p, p->cluster_info, offset);

  	unlock_cluster(ci);

  	mem_cgroup_uncharge_swap(entry, 1);
  	swap_range_free(p, offset, 1);

  }
  
  /*

   * 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) {
  		if (!__swap_entry_free(p, entry, 1))

  			free_swap_slot(entry);

  	}

  }
  
  /*

   * Called after dropping swapcache to decrease refcnt to swap entries.
   */

  static void swapcache_free(swp_entry_t entry)

  {

  	struct swap_info_struct *p;

  	p = _swap_info_get(entry);

  	if (p) {
  		if (!__swap_entry_free(p, entry, SWAP_HAS_CACHE))

  			free_swap_slot(entry);

  	}
  }

  #ifdef CONFIG_THP_SWAP

  static void swapcache_free_cluster(swp_entry_t entry)

  {
  	unsigned long offset = swp_offset(entry);
  	unsigned long idx = offset / SWAPFILE_CLUSTER;
  	struct swap_cluster_info *ci;
  	struct swap_info_struct *si;
  	unsigned char *map;

  	unsigned int i, free_entries = 0;
  	unsigned char val;

  	si = _swap_info_get(entry);

  	if (!si)
  		return;
  
  	ci = lock_cluster(si, offset);

  	VM_BUG_ON(!cluster_is_huge(ci));

  	map = si->swap_map + offset;
  	for (i = 0; i < SWAPFILE_CLUSTER; i++) {

  		val = map[i];
  		VM_BUG_ON(!(val & SWAP_HAS_CACHE));
  		if (val == SWAP_HAS_CACHE)
  			free_entries++;
  	}
  	if (!free_entries) {
  		for (i = 0; i < SWAPFILE_CLUSTER; i++)
  			map[i] &= ~SWAP_HAS_CACHE;

  	}

  	cluster_clear_huge(ci);

  	unlock_cluster(ci);

  	if (free_entries == SWAPFILE_CLUSTER) {
  		spin_lock(&si->lock);
  		ci = lock_cluster(si, offset);
  		memset(map, 0, SWAPFILE_CLUSTER);
  		unlock_cluster(ci);
  		mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER);
  		swap_free_cluster(si, idx);
  		spin_unlock(&si->lock);
  	} else if (free_entries) {
  		for (i = 0; i < SWAPFILE_CLUSTER; i++, entry.val++) {
  			if (!__swap_entry_free(si, entry, SWAP_HAS_CACHE))
  				free_swap_slot(entry);
  		}
  	}

  }

  
  int split_swap_cluster(swp_entry_t entry)
  {
  	struct swap_info_struct *si;
  	struct swap_cluster_info *ci;
  	unsigned long offset = swp_offset(entry);
  
  	si = _swap_info_get(entry);
  	if (!si)
  		return -EBUSY;
  	ci = lock_cluster(si, offset);
  	cluster_clear_huge(ci);
  	unlock_cluster(ci);
  	return 0;
  }

  #else
  static inline void swapcache_free_cluster(swp_entry_t entry)
  {
  }

  #endif /* CONFIG_THP_SWAP */

  void put_swap_page(struct page *page, swp_entry_t entry)
  {
  	if (!PageTransHuge(page))
  		swapcache_free(entry);
  	else
  		swapcache_free_cluster(entry);
  }

  static int swp_entry_cmp(const void *ent1, const void *ent2)
  {
  	const swp_entry_t *e1 = ent1, *e2 = ent2;
  
  	return (int)swp_type(*e1) - (int)swp_type(*e2);
  }

  void swapcache_free_entries(swp_entry_t *entries, int n)
  {
  	struct swap_info_struct *p, *prev;
  	int i;
  
  	if (n <= 0)
  		return;
  
  	prev = NULL;
  	p = NULL;

  
  	/*
  	 * Sort swap entries by swap device, so each lock is only taken once.
  	 * nr_swapfiles isn't absolutely correct, but the overhead of sort() is
  	 * so low that it isn't necessary to optimize further.
  	 */
  	if (nr_swapfiles > 1)
  		sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL);

  	for (i = 0; i < n; ++i) {
  		p = swap_info_get_cont(entries[i], prev);
  		if (p)
  			swap_entry_free(p, entries[i]);

  		prev = p;
  	}

  	if (p)

  		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;

  	struct swap_cluster_info *ci;

  	swp_entry_t entry;

  	unsigned long offset;

  	entry.val = page_private(page);

  	p = _swap_info_get(entry);

  	if (p) {

  		offset = swp_offset(entry);
  		ci = lock_cluster_or_swap_info(p, offset);
  		count = swap_count(p->swap_map[offset]);
  		unlock_cluster_or_swap_info(p, ci);

  	}

  	return count;

  }

  static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry)
  {
  	int count = 0;
  	pgoff_t offset = swp_offset(entry);
  	struct swap_cluster_info *ci;
  
  	ci = lock_cluster_or_swap_info(si, offset);
  	count = swap_count(si->swap_map[offset]);
  	unlock_cluster_or_swap_info(si, ci);
  	return count;
  }

  /*

   * How many references to @entry 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 __swp_swapcount(swp_entry_t entry)
  {
  	int count = 0;

  	struct swap_info_struct *si;

  
  	si = __swap_info_get(entry);

  	if (si)
  		count = swap_swapcount(si, entry);

  	return count;
  }
  
  /*
   * How many references to @entry are currently swapped out?

   * This considers COUNT_CONTINUED so it returns exact answer.
   */
  int swp_swapcount(swp_entry_t entry)
  {
  	int count, tmp_count, n;
  	struct swap_info_struct *p;

  	struct swap_cluster_info *ci;

  	struct page *page;
  	pgoff_t offset;
  	unsigned char *map;

  	p = _swap_info_get(entry);

  	if (!p)
  		return 0;

  	offset = swp_offset(entry);
  
  	ci = lock_cluster_or_swap_info(p, offset);
  
  	count = swap_count(p->swap_map[offset]);

  	if (!(count & COUNT_CONTINUED))
  		goto out;
  
  	count &= ~COUNT_CONTINUED;
  	n = SWAP_MAP_MAX + 1;

  	page = vmalloc_to_page(p->swap_map + offset);
  	offset &= ~PAGE_MASK;
  	VM_BUG_ON(page_private(page) != SWP_CONTINUED);
  
  	do {

  		page = list_next_entry(page, lru);

  		map = kmap_atomic(page);
  		tmp_count = map[offset];
  		kunmap_atomic(map);
  
  		count += (tmp_count & ~COUNT_CONTINUED) * n;
  		n *= (SWAP_CONT_MAX + 1);
  	} while (tmp_count & COUNT_CONTINUED);
  out:

  	unlock_cluster_or_swap_info(p, ci);

  	return count;
  }

  #ifdef CONFIG_THP_SWAP
  static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
  					 swp_entry_t entry)
  {
  	struct swap_cluster_info *ci;
  	unsigned char *map = si->swap_map;
  	unsigned long roffset = swp_offset(entry);
  	unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER);
  	int i;
  	bool ret = false;
  
  	ci = lock_cluster_or_swap_info(si, offset);
  	if (!ci || !cluster_is_huge(ci)) {
  		if (map[roffset] != SWAP_HAS_CACHE)
  			ret = true;
  		goto unlock_out;
  	}
  	for (i = 0; i < SWAPFILE_CLUSTER; i++) {
  		if (map[offset + i] != SWAP_HAS_CACHE) {
  			ret = true;
  			break;
  		}
  	}
  unlock_out:
  	unlock_cluster_or_swap_info(si, ci);
  	return ret;
  }
  
  static bool page_swapped(struct page *page)
  {
  	swp_entry_t entry;
  	struct swap_info_struct *si;
  
  	if (likely(!PageTransCompound(page)))
  		return page_swapcount(page) != 0;
  
  	page = compound_head(page);
  	entry.val = page_private(page);
  	si = _swap_info_get(entry);
  	if (si)
  		return swap_page_trans_huge_swapped(si, entry);
  	return false;
  }

  
  static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount,
  					 int *total_swapcount)
  {
  	int i, map_swapcount, _total_mapcount, _total_swapcount;
  	unsigned long offset = 0;
  	struct swap_info_struct *si;
  	struct swap_cluster_info *ci = NULL;
  	unsigned char *map = NULL;
  	int mapcount, swapcount = 0;
  
  	/* hugetlbfs shouldn't call it */
  	VM_BUG_ON_PAGE(PageHuge(page), page);
  
  	if (likely(!PageTransCompound(page))) {
  		mapcount = atomic_read(&page->_mapcount) + 1;
  		if (total_mapcount)
  			*total_mapcount = mapcount;
  		if (PageSwapCache(page))
  			swapcount = page_swapcount(page);
  		if (total_swapcount)
  			*total_swapcount = swapcount;
  		return mapcount + swapcount;
  	}
  
  	page = compound_head(page);
  
  	_total_mapcount = _total_swapcount = map_swapcount = 0;
  	if (PageSwapCache(page)) {
  		swp_entry_t entry;
  
  		entry.val = page_private(page);
  		si = _swap_info_get(entry);
  		if (si) {
  			map = si->swap_map;
  			offset = swp_offset(entry);
  		}
  	}
  	if (map)
  		ci = lock_cluster(si, offset);
  	for (i = 0; i < HPAGE_PMD_NR; i++) {
  		mapcount = atomic_read(&page[i]._mapcount) + 1;
  		_total_mapcount += mapcount;
  		if (map) {
  			swapcount = swap_count(map[offset + i]);
  			_total_swapcount += swapcount;
  		}
  		map_swapcount = max(map_swapcount, mapcount + swapcount);
  	}
  	unlock_cluster(ci);
  	if (PageDoubleMap(page)) {
  		map_swapcount -= 1;
  		_total_mapcount -= HPAGE_PMD_NR;
  	}
  	mapcount = compound_mapcount(page);
  	map_swapcount += mapcount;
  	_total_mapcount += mapcount;
  	if (total_mapcount)
  		*total_mapcount = _total_mapcount;
  	if (total_swapcount)
  		*total_swapcount = _total_swapcount;
  
  	return map_swapcount;
  }

  #else
  #define swap_page_trans_huge_swapped(si, entry)	swap_swapcount(si, entry)
  #define page_swapped(page)			(page_swapcount(page) != 0)

  
  static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount,
  					 int *total_swapcount)
  {
  	int mapcount, swapcount = 0;
  
  	/* hugetlbfs shouldn't call it */
  	VM_BUG_ON_PAGE(PageHuge(page), page);
  
  	mapcount = page_trans_huge_mapcount(page, total_mapcount);
  	if (PageSwapCache(page))
  		swapcount = page_swapcount(page);
  	if (total_swapcount)
  		*total_swapcount = swapcount;
  	return mapcount + swapcount;
  }

  #endif

  /*

   * 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.

   *

   * NOTE: total_map_swapcount should not be relied upon by the caller if

   * reuse_swap_page() returns false, but it may be always overwritten
   * (see the other implementation for CONFIG_SWAP=n).

   */

  bool reuse_swap_page(struct page *page, int *total_map_swapcount)

  {

  	int count, total_mapcount, total_swapcount;

  	VM_BUG_ON_PAGE(!PageLocked(page), page);

  	if (unlikely(PageKsm(page)))

  		return false;

  	count = page_trans_huge_map_swapcount(page, &total_mapcount,
  					      &total_swapcount);
  	if (total_map_swapcount)
  		*total_map_swapcount = total_mapcount + total_swapcount;
  	if (count == 1 && PageSwapCache(page) &&
  	    (likely(!PageTransCompound(page)) ||
  	     /* The remaining swap count will be freed soon */
  	     total_swapcount == page_swapcount(page))) {

  		if (!PageWriteback(page)) {

  			page = compound_head(page);

  			delete_from_swap_cache(page);
  			SetPageDirty(page);

  		} else {
  			swp_entry_t entry;
  			struct swap_info_struct *p;
  
  			entry.val = page_private(page);
  			p = swap_info_get(entry);
  			if (p->flags & SWP_STABLE_WRITES) {
  				spin_unlock(&p->lock);
  				return false;
  			}
  			spin_unlock(&p->lock);

  		}
  	}

  	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_swapped(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;

  	page = compound_head(page);

  	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;

  	unsigned char count;

  	if (non_swap_entry(entry))

  		return 1;

  	p = _swap_info_get(entry);

  	if (p) {

  		count = __swap_entry_free(p, entry, 1);

  		if (count == SWAP_HAS_CACHE &&
  		    !swap_page_trans_huge_swapped(p, entry)) {

  			page = find_get_page(swap_address_space(entry),

  					     swp_offset(entry));

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

  				put_page(page);

  				page = NULL;
  			}

  		} else if (!count)

  			free_swap_slot(entry);

  	}
  	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) || mem_cgroup_swap_full(page)) &&

  		    !swap_page_trans_huge_swapped(p, entry)) {
  			page = compound_head(page);

  			delete_from_swap_cache(page);
  			SetPageDirty(page);
  		}
  		unlock_page(page);

  		put_page(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 pte_same_as_swp(pte_t pte, pte_t swp_pte)

  {

  	return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte);

  }

  /*

   * 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(page, vma->vm_mm, GFP_KERNEL,
  				&memcg, false)) {

  		ret = -ENOMEM;

  		goto out_nolock;
  	}

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

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

  		mem_cgroup_cancel_charge(page, memcg, false);

  		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, false);

  		mem_cgroup_commit_charge(page, memcg, true, false);

  	} else { /* ksm created a completely new copy */

  		page_add_new_anon_rmap(page, vma, addr, false);

  		mem_cgroup_commit_charge(page, memcg, false, false);

  		lru_cache_add_active_or_unevictable(page, vma);
  	}

  	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(pte_same_as_swp(*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 {

  		cond_resched();

  		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, p4d_t *p4d,

  				unsigned long addr, unsigned long end,
  				swp_entry_t entry, struct page *page)
  {
  	pud_t *pud;
  	unsigned long next;

  	int ret;

  	pud = pud_offset(p4d, 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 inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd,
  				unsigned long addr, unsigned long end,
  				swp_entry_t entry, struct page *page)
  {
  	p4d_t *p4d;
  	unsigned long next;
  	int ret;
  
  	p4d = p4d_offset(pgd, addr);
  	do {
  		next = p4d_addr_end(addr, end);
  		if (p4d_none_or_clear_bad(p4d))
  			continue;
  		ret = unuse_pud_range(vma, p4d, addr, next, entry, page);
  		if (ret)
  			return ret;
  	} while (p4d++, 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_p4d_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;

  		cond_resched();

  	}

  	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;
  		}

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

  		if (count && swap_count(count) != SWAP_MAP_BAD)

  			if (!frontswap || frontswap_test(si, i))
  				break;
  		if ((i % LATENCY_LIMIT) == 0)
  			cond_resched();

  	}
  	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.