// SPDX-License-Identifier: GPL-2.0-only
/*
 *  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.
 */
static 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 struct swap_info_struct *swap_type_to_swap_info(int type)
{
        if (type >= READ_ONCE(nr_swapfiles))
                return NULL;

        smp_rmb();      /* Pairs with smp_wmb in alloc_swap_info. */
        return READ_ONCE(swap_info[type]);
}

static inline unsigned char swap_count(unsigned char ent)
{
        return ent & ~SWAP_HAS_CACHE;   /* may include COUNT_CONTINUED flag */
}

/* Reclaim the swap entry anyway if possible */
#define TTRS_ANYWAY             0x1
/*
 * Reclaim the swap entry if there are no more mappings of the
 * corresponding page
 */
#define TTRS_UNMAPPED           0x2
/* Reclaim the swap entry if swap is getting full*/
#define TTRS_FULL               0x4

/* returns 1 if swap entry is freed */
static int __try_to_reclaim_swap(struct swap_info_struct *si,
                                 unsigned long offset, unsigned long flags)
{
        swp_entry_t entry = swp_entry(si->type, offset);
        struct page *page;
        int ret = 0;

        page = find_get_page(swap_address_space(entry), offset);
        if (!page)
                return 0;
        /*
         * When this function is called from scan_swap_map_slots() 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)) {
                if ((flags & TTRS_ANYWAY) ||
                    ((flags & TTRS_UNMAPPED) && !page_mapped(page)) ||
                    ((flags & TTRS_FULL) && mem_cgroup_swap_full(page)))
                        ret = try_to_free_swap(page);
                unlock_page(page);
        }
        put_page(page);
        return ret;
}

static inline struct swap_extent *first_se(struct swap_info_struct *sis)
{
        struct rb_node *rb = rb_first(&sis->swap_extent_root);
        return rb_entry(rb, struct swap_extent, rb_node);
}

static inline struct swap_extent *next_se(struct swap_extent *se)
{
        struct rb_node *rb = rb_next(&se->rb_node);
        return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL;
}

/*
 * 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 = first_se(si);
        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();
        }

        for (se = next_se(se); se; se = next_se(se)) {
                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 */
}

static struct swap_extent *
offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset)
{
        struct swap_extent *se;
        struct rb_node *rb;

        rb = sis->swap_extent_root.rb_node;
        while (rb) {
                se = rb_entry(rb, struct swap_extent, rb_node);
                if (offset < se->start_page)
                        rb = rb->rb_left;
                else if (offset >= se->start_page + se->nr_pages)
                        rb = rb->rb_right;
                else
                        return se;
        }
        /* It *must* be present */
        BUG();
}

/*
 * 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 = offset_to_swap_extent(si, start_page);

        while (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;

                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 = next_se(se);
        }
}

#ifdef CONFIG_THP_SWAP
#define SWAPFILE_CLUSTER        HPAGE_PMD_NR

#define swap_entry_size(size)   (size)
#else
#define SWAPFILE_CLUSTER        256

/*
 * Define swap_entry_size() as constant to let compiler to optimize
 * out some code if !CONFIG_THP_SWAP
 */
#define swap_entry_size(size)   1
#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)
{
        if (IS_ENABLED(CONFIG_THP_SWAP))
                return info->flags & CLUSTER_FLAG_HUGE;
        return false;
}

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);
}

/*
 * Determine the locking method in use for this device.  Return
 * swap_cluster_info if SSD-style cluster-based locking is in place.
 */
static inline struct swap_cluster_info *lock_cluster_or_swap_info(
                struct swap_info_struct *si, unsigned long offset)
{
        struct swap_cluster_info *ci;

        /* Try to use fine-grained SSD-style locking if available: */
        ci = lock_cluster(si, offset);
        /* Otherwise, fall back to traditional, coarse locking: */
        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, TTRS_ANYWAY);
                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;
}

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;

        /*
         * Should not even be attempting cluster allocations when huge
         * page swap is disabled.  Warn and fail the allocation.
         */
        if (!IS_ENABLED(CONFIG_THP_SWAP)) {
                VM_WARN_ON_ONCE(1);
                return 0;
        }

        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);
        memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER);
        cluster_set_count_flag(ci, 0, 0);
        free_cluster(si, idx);
        unlock_cluster(ci);
        swap_range_free(si, offset, SWAPFILE_CLUSTER);
}

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, swp_entry_t swp_entries[], int entry_size)
{
        unsigned long size = swap_entry_size(entry_size);
        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 && size == SWAPFILE_CLUSTER);

        avail_pgs = atomic_long_read(&nr_swap_pages) / size;
        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 * size, &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\n",
                             si->type);
                        WARN(!(si->flags & SWP_WRITEOK),
                             "swap_info %d in list but !SWP_WRITEOK\n",
                             si->type);
                        __del_from_avail_list(si);
                        spin_unlock(&si->lock);
                        goto nextsi;
                }
                if (size == SWAPFILE_CLUSTER) {
                        if (!(si->flags & SWP_FS))
                                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 || size == SWAPFILE_CLUSTER)
                        goto check_out;
                pr_debug("scan_swap_map of si %d failed to find offset\n",
                        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) * size,
                                &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 = swap_type_to_swap_info(type);
        pgoff_t offset;

        if (!si)
                goto fail;

        spin_lock(&si->lock);
        if (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);
fail:
        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;

        if (!entry.val)
                goto out;
        p = swp_swap_info(entry);
        if (!p)
                goto bad_nofile;
        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\n", Bad_offset, entry.val);
        goto out;
bad_device:
        pr_err("swap_info_get: %s%08lx\n", Unused_file, entry.val);
        goto out;
bad_nofile:
        pr_err("swap_info_get: %s%08lx\n", 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\n", 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_locked(struct swap_info_struct *p,
                                              unsigned long offset,
                                              unsigned char usage)
{
        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--;
        }

        usage = count | has_cache;
        p->swap_map[offset] = usage ? : SWAP_HAS_CACHE;

        return usage;
}

/*
 * Check whether swap entry is valid in the swap device.  If so,
 * return pointer to swap_info_struct, and keep the swap entry valid
 * via preventing the swap device from being swapoff, until
 * put_swap_device() is called.  Otherwise return NULL.
 *
 * The entirety of the RCU read critical section must come before the
 * return from or after the call to synchronize_rcu() in
 * enable_swap_info() or swapoff().  So if "si->flags & SWP_VALID" is
 * true, the si->map, si->cluster_info, etc. must be valid in the
 * critical section.
 *
 * Notice that swapoff or swapoff+swapon can still happen before the
 * rcu_read_lock() in get_swap_device() or after the rcu_read_unlock()
 * in put_swap_device() if there isn't any other way to prevent
 * swapoff, such as page lock, page table lock, etc.  The caller must
 * be prepared for that.  For example, the following situation is
 * possible.
 *
 *   CPU1                               CPU2
 *   do_swap_page()
 *     ...                              swapoff+swapon
 *     __read_swap_cache_async()
 *       swapcache_prepare()
 *         __swap_duplicate()
 *           // check swap_map
 *     // verify PTE not changed
 *
 * In __swap_duplicate(), the swap_map need to be checked before
 * changing partly because the specified swap entry may be for another
 * swap device which has been swapoff.  And in do_swap_page(), after
 * the page is read from the swap device, the PTE is verified not
 * changed with the page table locked to check whether the swap device
 * has been swapoff or swapoff+swapon.
 */
struct swap_info_struct *get_swap_device(swp_entry_t entry)
{
        struct swap_info_struct *si;
        unsigned long offset;

        if (!entry.val)
                goto out;
        si = swp_swap_info(entry);
        if (!si)
                goto bad_nofile;

        rcu_read_lock();
        if (!(si->flags & SWP_VALID))
                goto unlock_out;
        offset = swp_offset(entry);
        if (offset >= si->max)
                goto unlock_out;

        return si;
bad_nofile:
        pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val);
out:
        return NULL;
unlock_out:
        rcu_read_unlock();
        return NULL;
}

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);

        ci = lock_cluster_or_swap_info(p, offset);
        usage = __swap_entry_free_locked(p, offset, usage);
        unlock_cluster_or_swap_info(p, ci);
        if (!usage)
                free_swap_slot(entry);

        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)
                __swap_entry_free(p, entry, 1);
}

/*
 * Called after dropping swapcache to decrease refcnt to swap entries.
 */
void put_swap_page(struct page *page, 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;
        int size = swap_entry_size(hpage_nr_pages(page));

        si = _swap_info_get(entry);
        if (!si)
                return;

        ci = lock_cluster_or_swap_info(si, offset);
        if (size == SWAPFILE_CLUSTER) {
                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++;
                }
                cluster_clear_huge(ci);
                if (free_entries == SWAPFILE_CLUSTER) {
                        unlock_cluster_or_swap_info(si, ci);
                        spin_lock(&si->lock);
                        mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER);
                        swap_free_cluster(si, idx);
                        spin_unlock(&si->lock);
                        return;
                }
        }
        for (i = 0; i < size; i++, entry.val++) {
                if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) {
                        unlock_cluster_or_swap_info(si, ci);
                        free_swap_slot(entry);
                        if (i == size - 1)
                                return;
                        lock_cluster_or_swap_info(si, offset);
                }
        }
        unlock_cluster_or_swap_info(si, ci);
}

#ifdef CONFIG_THP_SWAP
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;
}
#endif

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;
}

int __swap_count(swp_entry_t entry)
{
        struct swap_info_struct *si;
        pgoff_t offset = swp_offset(entry);
        int count = 0;

        si = get_swap_device(entry);
        if (si) {
                count = swap_count(si->swap_map[offset]);
                put_swap_device(si);
        }
        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 = get_swap_device(entry);
        if (si) {
                count = swap_swapcount(si, entry);
                put_swap_device(si);
        }
        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;
}

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 (swap_count(map[roffset]))
                        ret = true;
                goto unlock_out;
        }
        for (i = 0; i < SWAPFILE_CLUSTER; i++) {
                if (swap_count(map[offset + i])) {
                        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 (!IS_ENABLED(CONFIG_THP_SWAP) || 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 (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(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;
        }

        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;
}

/*
 * 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;
        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))
                        __try_to_reclaim_swap(p, swp_offset(entry),
                                              TTRS_UNMAPPED | TTRS_FULL);
        }
        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 = first_se(sis);

                        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;
        struct swap_info_struct *si = swap_type_to_swap_info(type);

        if (!si || !(si->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,
                        unsigned int type, bool frontswap,
                        unsigned long *fs_pages_to_unuse)
{
        struct page *page;
        swp_entry_t entry;
        pte_t *pte;
        struct swap_info_struct *si;
        unsigned long offset;
        int ret = 0;
        volatile unsigned char *swap_map;

        si = swap_info[type];
        pte = pte_offset_map(pmd, addr);
        do {
                struct vm_fault vmf;

                if (!is_swap_pte(*pte))
                        continue;

                entry = pte_to_swp_entry(*pte);
                if (swp_type(entry) != type)
                        continue;

                offset = swp_offset(entry);
                if (frontswap && !frontswap_test(si, offset))
                        continue;

                pte_unmap(pte);
                swap_map = &si->swap_map[offset];
                vmf.vma = vma;
                vmf.address = addr;
                vmf.pmd = pmd;
                page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf);
                if (!page) {
                        if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD)
                                goto try_next;
                        return -ENOMEM;
                }

                lock_page(page);
                wait_on_page_writeback(page);
                ret = unuse_pte(vma, pmd, addr, entry, page);
                if (ret < 0) {
                        unlock_page(page);
                        put_page(page);
                        goto out;
                }

                try_to_free_swap(page);
                unlock_page(page);
                put_page(page);

                if (*fs_pages_to_unuse && !--(*fs_pages_to_unuse)) {
                        ret = FRONTSWAP_PAGES_UNUSED;
                        goto out;
                }
try_next:
                pte = pte_offset_map(pmd, addr);
        } while (pte++, addr += PAGE_SIZE, addr != end);
        pte_unmap(pte - 1);

        ret = 0;
out:
        return ret;
}

static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
                                unsigned long addr, unsigned long end,
                                unsigned int type, bool frontswap,
                                unsigned long *fs_pages_to_unuse)
{
        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, type,
                                      frontswap, fs_pages_to_unuse);
                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,
                                unsigned int type, bool frontswap,
                                unsigned long *fs_pages_to_unuse)
{
        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, type,
                                      frontswap, fs_pages_to_unuse);
                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,
                                unsigned int type, bool frontswap,
                                unsigned long *fs_pages_to_unuse)
{
        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, type,
                                      frontswap, fs_pages_to_unuse);
                if (ret)
                        return ret;
        } while (p4d++, addr = next, addr != end);
        return 0;
}

static int unuse_vma(struct vm_area_struct *vma, unsigned int type,
                     bool frontswap, unsigned long *fs_pages_to_unuse)
{
        pgd_t *pgd;
        unsigned long addr, end, next;
        int ret;

        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, type,
                                      frontswap, fs_pages_to_unuse);
                if (ret)
                        return ret;
        } while (pgd++, addr = next, addr != end);
        return 0;
}

static int unuse_mm(struct mm_struct *mm, unsigned int type,
                    bool frontswap, unsigned long *fs_pages_to_unuse)
{
        struct vm_area_struct *vma;
        int ret = 0;

        down_read(&mm->mmap_sem);
        for (vma = mm->mmap; vma; vma = vma->vm_next) {
                if (vma->anon_vma) {
                        ret = unuse_vma(vma, type, frontswap,
                                        fs_pages_to_unuse);
                        if (ret)
                                break;
                }
                cond_resched();
        }
        up_read(&mm->mmap_sem);
        return ret;
}

/*
 * Scan swap_map (or frontswap_map if frontswap parameter is true)
 * from current position to next entry still in use. Return 0
 * if there are no inuse entries after prev till end of the map.
 */
static unsigned int find_next_to_unuse(struct swap_info_struct *si,
                                        unsigned int prev, bool frontswap)
{
        unsigned int i;
        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 (i = prev + 1; i < si->max; i++) {
                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();
        }

        if (i == si->max)
                i = 0;

        return i;
}

/*
 * 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 mm_struct *prev_mm;
        struct mm_struct *mm;
        struct list_head *p;
        int retval = 0;
        struct swap_info_struct *si = swap_info[type];
        struct page *page;
        swp_entry_t entry;
        unsigned int i;

        if (!si->inuse_pages)
                return 0;

        if (!frontswap)
                pages_to_unuse = 0;

retry:
        retval = shmem_unuse(type, frontswap, &pages_to_unuse);
        if (retval)
                goto out;

        prev_mm = &init_mm;
        mmget(prev_mm);

        spin_lock(&mmlist_lock);
        p = &init_mm.mmlist;
        while (si->inuse_pages &&
               !signal_pending(current) &&
               (p = p->next) != &init_mm.mmlist) {

                mm = list_entry(p, struct mm_struct, mmlist);
                if (!mmget_not_zero(mm))
                        continue;
                spin_unlock(&mmlist_lock);
                mmput(prev_mm);
                prev_mm = mm;
                retval = unuse_mm(mm, type, frontswap, &pages_to_unuse);

                if (retval) {
                        mmput(prev_mm);
                        goto out;
                }

                /*
                 * Make sure that we aren't completely killing
                 * interactive performance.
                 */
                cond_resched();
                spin_lock(&mmlist_lock);
        }
        spin_unlock(&mmlist_lock);

        mmput(prev_mm);

        i = 0;
        while (si->inuse_pages &&
               !signal_pending(current) &&
               (i = find_next_to_unuse(si, i, frontswap)) != 0) {

                entry = swp_entry(type, i);
                page = find_get_page(swap_address_space(entry), i);
                if (!page)
                        continue;

                /*
                 * It is conceivable that a racing task removed this page from
                 * swap cache just before we acquired the page lock. The page
                 * might even be back in swap cache on another swap area. But
                 * that is okay, try_to_free_swap() only removes stale pages.
                 */
                lock_page(page);
                wait_on_page_writeback(page);
                try_to_free_swap(page);
                unlock_page(page);
                put_page(page);

                /*
                 * For frontswap, we just need to unuse pages_to_unuse, if
                 * it was specified. Need not check frontswap again here as
                 * we already zeroed out pages_to_unuse if not frontswap.
                 */
                if (pages_to_unuse && --pages_to_unuse == 0)
                        goto out;
        }

        /*
         * Lets check again to see if there are still swap entries in the map.
         * If yes, we would need to do retry the unuse logic again.
         * Under global memory pressure, swap entries can be reinserted back
         * into process space after the mmlist loop above passes over them.
         *
         * Limit the number of retries? No: when mmget_not_zero() above fails,
         * that mm is likely to be freeing swap from exit_mmap(), which proceeds
         * at its own independent pace; and even shmem_writepage() could have
         * been preempted after get_swap_page(), temporarily hiding that swap.
         * It's easy and robust (though cpu-intensive) just to keep retrying.
         */
        if (si->inuse_pages) {
                if (!signal_pending(current))
                        goto retry;
                retval = -EINTR;
        }
out:
        return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : 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 *se;
        pgoff_t offset;

        sis = swp_swap_info(entry);
        *bdev = sis->bdev;

        offset = swp_offset(entry);
        se = offset_to_swap_extent(sis, offset);
        return se->start_block + (offset - se->start_page);
}

/*
 * 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 (!RB_EMPTY_ROOT(&sis->swap_extent_root)) {
                struct rb_node *rb = sis->swap_extent_root.rb_node;
                struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node);

                rb_erase(rb, &sis->swap_extent_root);
                kfree(se);
        }

        if (sis->flags & SWP_ACTIVATED) {
                struct file *swap_file = sis->swap_file;
                struct address_space *mapping = swap_file->f_mapping;

                sis->flags &= ~SWP_ACTIVATED;
                if (mapping->a_ops->swap_deactivate)
                        mapping->a_ops->swap_deactivate(swap_file);
        }
}

/*
 * Add a block range (and the corresponding page range) into this swapdev's
 * extent tree.
 *
 * 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 rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL;
        struct swap_extent *se;
        struct swap_extent *new_se;

        /*
         * place the new node at the right most since the
         * function is called in ascending page order.
         */
        while (*link) {
                parent = *link;
                link = &parent->rb_right;
        }

        if (parent) {
                se = rb_entry(parent, struct swap_extent, rb_node);
                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. */
        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;

        rb_link_node(&new_se->rb_node, parent, link);
        rb_insert_color(&new_se->rb_node, &sis->swap_extent_root);
        return 1;
}
EXPORT_SYMBOL_GPL(add_swap_extent);

/*
 * 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 all swap devices we set S_SWAPFILE across the life of the swapon.  This
 * prevents users from writing to the swap device, which will corrupt memory.
 *
 * 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 >= 0)
                        sis->flags |= SWP_ACTIVATED;
                if (!ret) {
                        sis->flags |= SWP_FS;
                        ret = add_swap_extent(sis, 0, sis->max, 0);
                        *span = sis->pages;
                }
                return ret;
        }

        return generic_swapfile_activate(sis, swap_file, span);
}

static int swap_node(struct swap_info_struct *p)
{
        struct block_device *bdev;

        if (p->bdev)
                bdev = p->bdev;
        else
                bdev = p->swap_file->f_inode->i_sb->s_bdev;

        return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE;
}

static void setup_swap_info(struct swap_info_struct *p, int prio,
                            unsigned char *swap_map,
                            struct swap_cluster_info *cluster_info)
{
        int i;

        if (prio >= 0)
                p->prio = prio;
        else
                p->prio = --least_priority;
        /*
         * the plist prio is negated because plist ordering is
         * low-to-high, while swap ordering is high-to-low
         */
        p->list.prio = -p->prio;
        for_each_node(i) {
                if (p->prio >= 0)
                        p->avail_lists[i].prio = -p->prio;
                else {
                        if (swap_node(p) == i)
                                p->avail_lists[i].prio = 1;
                        else
                                p->avail_lists[i].prio = -p->prio;
                }
        }
        p->swap_map = swap_map;
        p->cluster_info = cluster_info;
}

static void _enable_swap_info(struct swap_info_struct *p)
{
        p->flags |= SWP_WRITEOK | SWP_VALID;
        atomic_long_add(p->pages, &nr_swap_pages);
        total_swap_pages += p->pages;

        assert_spin_locked(&swap_lock);
        /*
         * both lists are plists, and thus priority ordered.
         * swap_active_head needs to be priority ordered for swapoff(),
         * which on removal of any swap_info_struct with an auto-assigned
         * (i.e. negative) priority increments the auto-assigned priority
         * of any lower-priority swap_info_structs.
         * swap_avail_head needs to be priority ordered for get_swap_page(),
         * which allocates swap pages from the highest available priority
         * swap_info_struct.
         */
        plist_add(&p->list, &swap_active_head);
        add_to_avail_list(p);
}

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);
        setup_swap_info(p, prio, swap_map, cluster_info);
        spin_unlock(&p->lock);
        spin_unlock(&swap_lock);
        /*
         * Guarantee swap_map, cluster_info, etc. fields are valid
         * between get/put_swap_device() if SWP_VALID bit is set
         */
        synchronize_rcu();
        spin_lock(&swap_lock);
        spin_lock(&p->lock);
        _enable_swap_info(p);
        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);
        setup_swap_info(p, p->prio, p->swap_map, p->cluster_info);
        _enable_swap_info(p);
        spin_unlock(&p->lock);
        spin_unlock(&swap_lock);
}

bool has_usable_swap(void)
{
        bool ret = true;

        spin_lock(&swap_lock);
        if (plist_head_empty(&swap_active_head))
                ret = false;
        spin_unlock(&swap_lock);
        return ret;
}

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 err, found = 0;
        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;
        spin_lock(&swap_lock);
        plist_for_each_entry(p, &swap_active_head, list) {
                if (p->flags & SWP_WRITEOK) {
                        if (p->swap_file->f_mapping == mapping) {
                                found = 1;
                                break;
                        }
                }
        }
        if (!found) {
                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;
        }
        del_from_avail_list(p);
        spin_lock(&p->lock);
        if (p->prio < 0) {
                struct swap_info_struct *si = p;
                int nid;

                plist_for_each_entry_continue(si, &swap_active_head, list) {
                        si->prio++;
                        si->list.prio--;
                        for_each_node(nid) {
                                if (si->avail_lists[nid].prio != 1)
                                        si->avail_lists[nid].prio--;
                        }
                }
                least_priority++;
        }
        plist_del(&p->list, &swap_active_head);
        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);

        disable_swap_slots_cache_lock();

        set_current_oom_origin();
        err = try_to_unuse(p->type, false, 0); /* force unuse all pages */
        clear_current_oom_origin();

        if (err) {
                /* re-insert swap space back into swap_list */
                reinsert_swap_info(p);
                reenable_swap_slots_cache_unlock();
                goto out_dput;
        }

        reenable_swap_slots_cache_unlock();

        spin_lock(&swap_lock);
        spin_lock(&p->lock);
        p->flags &= ~SWP_VALID;         /* mark swap device as invalid */
        spin_unlock(&p->lock);
        spin_unlock(&swap_lock);
        /*
         * wait for swap operations protected by get/put_swap_device()
         * to complete
         */
        synchronize_rcu();

        flush_work(&p->discard_work);

        destroy_swap_extents(p);
        if (p->flags & SWP_CONTINUED)
                free_swap_count_continuations(p);

        if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev)))
                atomic_dec(&nr_rotate_swap);

        mutex_lock(&swapon_mutex);
        spin_lock(&swap_lock);
        spin_lock(&p->lock);
        drain_mmlist();

        /* wait for anyone still in scan_swap_map */
        p->highest_bit = 0;             /* cuts scans short */
        while (p->flags >= SWP_SCANNING) {
                spin_unlock(&p->lock);
                spin_unlock(&swap_lock);
                schedule_timeout_uninterruptible(1);
                spin_lock(&swap_lock);
                spin_lock(&p->lock);
        }

        swap_file = p->swap_file;
        old_block_size = p->old_block_size;
        p->swap_file = NULL;
        p->max = 0;
        swap_map = p->swap_map;
        p->swap_map = NULL;
        cluster_info = p->cluster_info;
        p->cluster_info = NULL;
        frontswap_map = frontswap_map_get(p);
        spin_unlock(&p->lock);
        spin_unlock(&swap_lock);
        frontswap_invalidate_area(p->type);
        frontswap_map_set(p, NULL);
        mutex_unlock(&swapon_mutex);
        free_percpu(p->percpu_cluster);
        p->percpu_cluster = NULL;
        vfree(swap_map);
        kvfree(cluster_info);
        kvfree(frontswap_map);
        /* Destroy swap account information */
        swap_cgroup_swapoff(p->type);
        exit_swap_address_space(p->type);

        inode = mapping->host;
        if (S_ISBLK(inode->i_mode)) {
                struct block_device *bdev = I_BDEV(inode);

                set_blocksize(bdev, old_block_size);
                blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
        }

        inode_lock(inode);
        inode->i_flags &= ~S_SWAPFILE;
        inode_unlock(inode);
        filp_close(swap_file, NULL);

        /*
         * Clear the SWP_USED flag after all resources are freed so that swapon
         * can reuse this swap_info in alloc_swap_info() safely.  It is ok to
         * not hold p->lock after we cleared its SWP_WRITEOK.
         */
        spin_lock(&swap_lock);
        p->flags = 0;
        spin_unlock(&swap_lock);

        err = 0;
        atomic_inc(&proc_poll_event);
        wake_up_interruptible(&proc_poll_wait);

out_dput:
        filp_close(victim, NULL);
out:
        putname(pathname);
        return err;
}

#ifdef CONFIG_PROC_FS
static __poll_t swaps_poll(struct file *file, poll_table *wait)
{
        struct seq_file *seq = file->private_data;

        poll_wait(file, &proc_poll_wait, wait);

        if (seq->poll_event != atomic_read(&proc_poll_event)) {
                seq->poll_event = atomic_read(&proc_poll_event);
                return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI;
        }

        return EPOLLIN | EPOLLRDNORM;
}

/* iterator */
static void *swap_start(struct seq_file *swap, loff_t *pos)
{
        struct swap_info_struct *si;
        int type;
        loff_t l = *pos;

        mutex_lock(&swapon_mutex);

        if (!l)
                return SEQ_START_TOKEN;

        for (type = 0; (si = swap_type_to_swap_info(type)); type++) {
                if (!(si->flags & SWP_USED) || !si->swap_map)
                        continue;
                if (!--l)
                        return si;
        }

        return NULL;
}

static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
{
        struct swap_info_struct *si = v;
        int type;

        if (v == SEQ_START_TOKEN)
                type = 0;
        else
                type = si->type + 1;

        for (; (si = swap_type_to_swap_info(type)); type++) {
                if (!(si->flags & SWP_USED) || !si->swap_map)
                        continue;
                ++*pos;
                return si;
        }

        return NULL;
}

static void swap_stop(struct seq_file *swap, void *v)
{
        mutex_unlock(&swapon_mutex);
}

static int swap_show(struct seq_file *swap, void *v)
{
        struct swap_info_struct *si = v;
        struct file *file;
        int len;

        if (si == SEQ_START_TOKEN) {
                seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n");
                return 0;
        }

        file = si->swap_file;
        len = seq_file_path(swap, file, " \t\n\\");
        seq_printf(swap, "%*s%s\t%u\t%u\t%d\n",
                        len < 40 ? 40 - len : 1, " ",
                        S_ISBLK(file_inode(file)->i_mode) ?
                                "partition" : "file\t",
                        si->pages << (PAGE_SHIFT - 10),
                        si->inuse_pages << (PAGE_SHIFT - 10),
                        si->prio);
        return 0;
}

static const struct seq_operations swaps_op = {
        .start =        swap_start,
        .next =         swap_next,
        .stop =         swap_stop,
        .show =         swap_show
};

static int swaps_open(struct inode *inode, struct file *file)
{
        struct seq_file *seq;
        int ret;

        ret = seq_open(file, &swaps_op);
        if (ret)
                return ret;

        seq = file->private_data;
        seq->poll_event = atomic_read(&proc_poll_event);
        return 0;
}

static const struct file_operations proc_swaps_operations = {
        .open           = swaps_open,
        .read           = seq_read,
        .llseek         = seq_lseek,
        .release        = seq_release,
        .poll           = swaps_poll,
};

static int __init procswaps_init(void)
{
        proc_create("swaps", 0, NULL, &proc_swaps_operations);
        return 0;
}
__initcall(procswaps_init);
#endif /* CONFIG_PROC_FS */

#ifdef MAX_SWAPFILES_CHECK
static int __init max_swapfiles_check(void)
{
        MAX_SWAPFILES_CHECK();
        return 0;
}
late_initcall(max_swapfiles_check);
#endif

static struct swap_info_struct *alloc_swap_info(void)
{
        struct swap_info_struct *p;
        unsigned int type;
        int i;

        p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL);
        if (!p)
                return ERR_PTR(-ENOMEM);

        spin_lock(&swap_lock);
        for (type = 0; type < nr_swapfiles; type++) {
                if (!(swap_info[type]->flags & SWP_USED))
                        break;
        }
        if (type >= MAX_SWAPFILES) {
                spin_unlock(&swap_lock);
                kvfree(p);
                return ERR_PTR(-EPERM);
        }
        if (type >= nr_swapfiles) {
                p->type = type;
                WRITE_ONCE(swap_info[type], p);
                /*
                 * Write swap_info[type] before nr_swapfiles, in case a
                 * racing procfs swap_start() or swap_next() is reading them.
                 * (We never shrink nr_swapfiles, we never free this entry.)
                 */
                smp_wmb();
                WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1);
        } else {
                kvfree(p);
                p = swap_info[type];
                /*
                 * Do not memset this entry: a racing procfs swap_next()
                 * would be relying on p->type to remain valid.
                 */
        }
        p->swap_extent_root = RB_ROOT;
        plist_node_init(&p->list, 0);
        for_each_node(i)
                plist_node_init(&p->avail_lists[i], 0);
        p->flags = SWP_USED;
        spin_unlock(&swap_lock);
        spin_lock_init(&p->lock);
        spin_lock_init(&p->cont_lock);

        return p;
}

static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
{
        int error;

        if (S_ISBLK(inode->i_mode)) {
                p->bdev = bdgrab(I_BDEV(inode));
                error = blkdev_get(p->bdev,
                                   FMODE_READ | FMODE_WRITE | FMODE_EXCL, p);
                if (error < 0) {
                        p->bdev = NULL;
                        return error;
                }
                p->old_block_size = block_size(p->bdev);
                error = set_blocksize(p->bdev, PAGE_SIZE);
                if (error < 0)
                        return error;
                p->flags |= SWP_BLKDEV;
        } else if (S_ISREG(inode->i_mode)) {
                p->bdev = inode->i_sb->s_bdev;
        }

        inode_lock(inode);
        if (IS_SWAPFILE(inode))
                return -EBUSY;

        return 0;
}


/*
 * Find out how many pages are allowed for a single swap device. There
 * are two limiting factors:
 * 1) the number of bits for the swap offset in the swp_entry_t type, and
 * 2) the number of bits in the swap pte, as defined by the different
 * architectures.
 *
 * In order to find the largest possible bit mask, a swap entry with
 * swap type 0 and swap offset ~0UL is created, encoded to a swap pte,
 * decoded to a swp_entry_t again, and finally the swap offset is
 * extracted.
 *
 * This will mask all the bits from the initial ~0UL mask that can't
 * be encoded in either the swp_entry_t or the architecture definition
 * of a swap pte.
 */
unsigned long generic_max_swapfile_size(void)
{
        return swp_offset(pte_to_swp_entry(
                        swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
}

/* Can be overridden by an architecture for additional checks. */
__weak unsigned long max_swapfile_size(void)
{
        return generic_max_swapfile_size();
}

static unsigned long read_swap_header(struct swap_info_struct *p,
                                        union swap_header *swap_header,
                                        struct inode *inode)
{
        int i;
        unsigned long maxpages;
        unsigned long swapfilepages;
        unsigned long last_page;

        if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) {
                pr_err("Unable to find swap-space signature\n");
                return 0;
        }

        /* swap partition endianess hack... */
        if (swab32(swap_header->info.version) == 1) {
                swab32s(&swap_header->info.version);
                swab32s(&swap_header->info.last_page);
                swab32s(&swap_header->info.nr_badpages);
                if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
                        return 0;
                for (i = 0; i < swap_header->info.nr_badpages; i++)
                        swab32s(&swap_header->info.badpages[i]);
        }
        /* Check the swap header's sub-version */
        if (swap_header->info.version != 1) {
                pr_warn("Unable to handle swap header version %d\n",
                        swap_header->info.version);
                return 0;
        }

        p->lowest_bit  = 1;
        p->cluster_next = 1;
        p->cluster_nr = 0;

        maxpages = max_swapfile_size();
        last_page = swap_header->info.last_page;
        if (!last_page) {
                pr_warn("Empty swap-file\n");
                return 0;
        }
        if (last_page > maxpages) {
                pr_warn("Truncating oversized swap area, only using %luk out of %luk\n",
                        maxpages << (PAGE_SHIFT - 10),
                        last_page << (PAGE_SHIFT - 10));
        }
        if (maxpages > last_page) {
                maxpages = last_page + 1;
                /* p->max is an unsigned int: don't overflow it */
                if ((unsigned int)maxpages == 0)
                        maxpages = UINT_MAX;
        }
        p->highest_bit = maxpages - 1;

        if (!maxpages)
                return 0;
        swapfilepages = i_size_read(inode) >> PAGE_SHIFT;
        if (swapfilepages && maxpages > swapfilepages) {
                pr_warn("Swap area shorter than signature indicates\n");
                return 0;
        }
        if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
                return 0;
        if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
                return 0;

        return maxpages;
}

#define SWAP_CLUSTER_INFO_COLS                                          \