Merge branch 'akpm-current/current'

[karo-tx-linux.git] / mm / ksm.c

/*
 * Memory merging support.
 *
 * This code enables dynamic sharing of identical pages found in different
 * memory areas, even if they are not shared by fork()
 *
 * Copyright (C) 2008-2009 Red Hat, Inc.
 * Authors:
 *      Izik Eidus
 *      Andrea Arcangeli
 *      Chris Wright
 *      Hugh Dickins
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 */

#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/mman.h>
#include <linux/sched.h>
#include <linux/rwsem.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/spinlock.h>
#include <linux/jhash.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/memory.h>
#include <linux/mmu_notifier.h>
#include <linux/swap.h>
#include <linux/ksm.h>
#include <linux/hashtable.h>
#include <linux/freezer.h>
#include <linux/oom.h>
#include <linux/numa.h>

#include <asm/tlbflush.h>
#include "internal.h"

#ifdef CONFIG_NUMA
#define NUMA(x)         (x)
#define DO_NUMA(x)      do { (x); } while (0)
#else
#define NUMA(x)         (0)
#define DO_NUMA(x)      do { } while (0)
#endif

/*
 * A few notes about the KSM scanning process,
 * to make it easier to understand the data structures below:
 *
 * In order to reduce excessive scanning, KSM sorts the memory pages by their
 * contents into a data structure that holds pointers to the pages' locations.
 *
 * Since the contents of the pages may change at any moment, KSM cannot just
 * insert the pages into a normal sorted tree and expect it to find anything.
 * Therefore KSM uses two data structures - the stable and the unstable tree.
 *
 * The stable tree holds pointers to all the merged pages (ksm pages), sorted
 * by their contents.  Because each such page is write-protected, searching on
 * this tree is fully assured to be working (except when pages are unmapped),
 * and therefore this tree is called the stable tree.
 *
 * In addition to the stable tree, KSM uses a second data structure called the
 * unstable tree: this tree holds pointers to pages which have been found to
 * be "unchanged for a period of time".  The unstable tree sorts these pages
 * by their contents, but since they are not write-protected, KSM cannot rely
 * upon the unstable tree to work correctly - the unstable tree is liable to
 * be corrupted as its contents are modified, and so it is called unstable.
 *
 * KSM solves this problem by several techniques:
 *
 * 1) The unstable tree is flushed every time KSM completes scanning all
 *    memory areas, and then the tree is rebuilt again from the beginning.
 * 2) KSM will only insert into the unstable tree, pages whose hash value
 *    has not changed since the previous scan of all memory areas.
 * 3) The unstable tree is a RedBlack Tree - so its balancing is based on the
 *    colors of the nodes and not on their contents, assuring that even when
 *    the tree gets "corrupted" it won't get out of balance, so scanning time
 *    remains the same (also, searching and inserting nodes in an rbtree uses
 *    the same algorithm, so we have no overhead when we flush and rebuild).
 * 4) KSM never flushes the stable tree, which means that even if it were to
 *    take 10 attempts to find a page in the unstable tree, once it is found,
 *    it is secured in the stable tree.  (When we scan a new page, we first
 *    compare it against the stable tree, and then against the unstable tree.)
 *
 * If the merge_across_nodes tunable is unset, then KSM maintains multiple
 * stable trees and multiple unstable trees: one of each for each NUMA node.
 */

/**
 * struct mm_slot - ksm information per mm that is being scanned
 * @link: link to the mm_slots hash list
 * @mm_list: link into the mm_slots list, rooted in ksm_mm_head
 * @rmap_list: head for this mm_slot's singly-linked list of rmap_items
 * @mm: the mm that this information is valid for
 */
struct mm_slot {
        struct hlist_node link;
        struct list_head mm_list;
        struct rmap_item *rmap_list;
        struct mm_struct *mm;
};

/**
 * struct ksm_scan - cursor for scanning
 * @mm_slot: the current mm_slot we are scanning
 * @address: the next address inside that to be scanned
 * @rmap_list: link to the next rmap to be scanned in the rmap_list
 * @seqnr: count of completed full scans (needed when removing unstable node)
 *
 * There is only the one ksm_scan instance of this cursor structure.
 */
struct ksm_scan {
        struct mm_slot *mm_slot;
        unsigned long address;
        struct rmap_item **rmap_list;
        unsigned long seqnr;
};

/**
 * struct stable_node - node of the stable rbtree
 * @node: rb node of this ksm page in the stable tree
 * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list
 * @hlist_dup: linked into the stable_node->hlist with a stable_node chain
 * @list: linked into migrate_nodes, pending placement in the proper node tree
 * @hlist: hlist head of rmap_items using this ksm page
 * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid)
 * @chain_prune_time: time of the last full garbage collection
 * @rmap_hlist_len: number of rmap_item entries in hlist or STABLE_NODE_CHAIN
 * @nid: NUMA node id of stable tree in which linked (may not match kpfn)
 */
struct stable_node {
        union {
                struct rb_node node;    /* when node of stable tree */
                struct {                /* when listed for migration */
                        struct list_head *head;
                        struct {
                                struct hlist_node hlist_dup;
                                struct list_head list;
                        };
                };
        };
        struct hlist_head hlist;
        union {
                unsigned long kpfn;
                unsigned long chain_prune_time;
        };
        /*
         * STABLE_NODE_CHAIN can be any negative number in
         * rmap_hlist_len negative range, but better not -1 to be able
         * to reliably detect underflows.
         */
#define STABLE_NODE_CHAIN -1024
        int rmap_hlist_len;
#ifdef CONFIG_NUMA
        int nid;
#endif
};

/**
 * struct rmap_item - reverse mapping item for virtual addresses
 * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list
 * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree
 * @nid: NUMA node id of unstable tree in which linked (may not match page)
 * @mm: the memory structure this rmap_item is pointing into
 * @address: the virtual address this rmap_item tracks (+ flags in low bits)
 * @oldchecksum: previous checksum of the page at that virtual address
 * @node: rb node of this rmap_item in the unstable tree
 * @head: pointer to stable_node heading this list in the stable tree
 * @hlist: link into hlist of rmap_items hanging off that stable_node
 */
struct rmap_item {
        struct rmap_item *rmap_list;
        union {
                struct anon_vma *anon_vma;      /* when stable */
#ifdef CONFIG_NUMA
                int nid;                /* when node of unstable tree */
#endif
        };
        struct mm_struct *mm;
        unsigned long address;          /* + low bits used for flags below */
        unsigned int oldchecksum;       /* when unstable */
        union {
                struct rb_node node;    /* when node of unstable tree */
                struct {                /* when listed from stable tree */
                        struct stable_node *head;
                        struct hlist_node hlist;
                };
        };
};

#define SEQNR_MASK      0x0ff   /* low bits of unstable tree seqnr */
#define UNSTABLE_FLAG   0x100   /* is a node of the unstable tree */
#define STABLE_FLAG     0x200   /* is listed from the stable tree */

/* The stable and unstable tree heads */
static struct rb_root one_stable_tree[1] = { RB_ROOT };
static struct rb_root one_unstable_tree[1] = { RB_ROOT };
static struct rb_root *root_stable_tree = one_stable_tree;
static struct rb_root *root_unstable_tree = one_unstable_tree;

/* Recently migrated nodes of stable tree, pending proper placement */
static LIST_HEAD(migrate_nodes);
#define STABLE_NODE_DUP_HEAD ((struct list_head *)&migrate_nodes.prev)

#define MM_SLOTS_HASH_BITS 10
static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);

static struct mm_slot ksm_mm_head = {
        .mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list),
};
static struct ksm_scan ksm_scan = {
        .mm_slot = &ksm_mm_head,
};

static struct kmem_cache *rmap_item_cache;
static struct kmem_cache *stable_node_cache;
static struct kmem_cache *mm_slot_cache;

/* The number of nodes in the stable tree */
static unsigned long ksm_pages_shared;

/* The number of page slots additionally sharing those nodes */
static unsigned long ksm_pages_sharing;

/* The number of nodes in the unstable tree */
static unsigned long ksm_pages_unshared;

/* The number of rmap_items in use: to calculate pages_volatile */
static unsigned long ksm_rmap_items;

/* The number of stable_node chains */
static unsigned long ksm_stable_node_chains;

/* The number of stable_node dups linked to the stable_node chains */
static unsigned long ksm_stable_node_dups;

/* Delay in pruning stale stable_node_dups in the stable_node_chains */
static int ksm_stable_node_chains_prune_millisecs = 2000;

/* Maximum number of page slots sharing a stable node */
static int ksm_max_page_sharing = 256;

/* Number of pages ksmd should scan in one batch */
static unsigned int ksm_thread_pages_to_scan = 100;

/* Milliseconds ksmd should sleep between batches */
static unsigned int ksm_thread_sleep_millisecs = 20;

#ifdef CONFIG_NUMA
/* Zeroed when merging across nodes is not allowed */
static unsigned int ksm_merge_across_nodes = 1;
static int ksm_nr_node_ids = 1;
#else
#define ksm_merge_across_nodes  1U
#define ksm_nr_node_ids         1
#endif

#define KSM_RUN_STOP    0
#define KSM_RUN_MERGE   1
#define KSM_RUN_UNMERGE 2
#define KSM_RUN_OFFLINE 4
static unsigned long ksm_run = KSM_RUN_STOP;
static void wait_while_offlining(void);

static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait);
static DEFINE_MUTEX(ksm_thread_mutex);
static DEFINE_SPINLOCK(ksm_mmlist_lock);

#define KSM_KMEM_CACHE(__struct, __flags) kmem_cache_create("ksm_"#__struct,\
                sizeof(struct __struct), __alignof__(struct __struct),\
                (__flags), NULL)

static int __init ksm_slab_init(void)
{
        rmap_item_cache = KSM_KMEM_CACHE(rmap_item, 0);
        if (!rmap_item_cache)
                goto out;

        stable_node_cache = KSM_KMEM_CACHE(stable_node, 0);
        if (!stable_node_cache)
                goto out_free1;

        mm_slot_cache = KSM_KMEM_CACHE(mm_slot, 0);
        if (!mm_slot_cache)
                goto out_free2;

        return 0;

out_free2:
        kmem_cache_destroy(stable_node_cache);
out_free1:
        kmem_cache_destroy(rmap_item_cache);
out:
        return -ENOMEM;
}

static void __init ksm_slab_free(void)
{
        kmem_cache_destroy(mm_slot_cache);
        kmem_cache_destroy(stable_node_cache);
        kmem_cache_destroy(rmap_item_cache);
        mm_slot_cache = NULL;
}

static __always_inline bool is_stable_node_chain(struct stable_node *chain)
{
        return chain->rmap_hlist_len == STABLE_NODE_CHAIN;
}

static __always_inline bool is_stable_node_dup(struct stable_node *dup)
{
        return dup->head == STABLE_NODE_DUP_HEAD;
}

static inline void stable_node_chain_add_dup(struct stable_node *dup,
                                             struct stable_node *chain)
{
        VM_BUG_ON(is_stable_node_dup(dup));
        dup->head = STABLE_NODE_DUP_HEAD;
        VM_BUG_ON(!is_stable_node_chain(chain));
        hlist_add_head(&dup->hlist_dup, &chain->hlist);
        ksm_stable_node_dups++;
}

static inline void __stable_node_dup_del(struct stable_node *dup)
{
        hlist_del(&dup->hlist_dup);
        ksm_stable_node_dups--;
}

static inline void stable_node_dup_del(struct stable_node *dup)
{
        VM_BUG_ON(is_stable_node_chain(dup));
        if (is_stable_node_dup(dup))
                __stable_node_dup_del(dup);
        else
                rb_erase(&dup->node, root_stable_tree + NUMA(dup->nid));
#ifdef CONFIG_DEBUG_VM
        dup->head = NULL;
#endif
}

static inline struct rmap_item *alloc_rmap_item(void)
{
        struct rmap_item *rmap_item;

        rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL);
        if (rmap_item)
                ksm_rmap_items++;
        return rmap_item;
}

static inline void free_rmap_item(struct rmap_item *rmap_item)
{
        ksm_rmap_items--;
        rmap_item->mm = NULL;   /* debug safety */
        kmem_cache_free(rmap_item_cache, rmap_item);
}

static inline struct stable_node *alloc_stable_node(void)
{
        return kmem_cache_alloc(stable_node_cache, GFP_KERNEL);
}

static inline void free_stable_node(struct stable_node *stable_node)
{
        VM_BUG_ON(stable_node->rmap_hlist_len &&
                  !is_stable_node_chain(stable_node));
        kmem_cache_free(stable_node_cache, stable_node);
}

static inline struct mm_slot *alloc_mm_slot(void)
{
        if (!mm_slot_cache)     /* initialization failed */
                return NULL;
        return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL);
}

static inline void free_mm_slot(struct mm_slot *mm_slot)
{
        kmem_cache_free(mm_slot_cache, mm_slot);
}

static struct mm_slot *get_mm_slot(struct mm_struct *mm)
{
        struct mm_slot *slot;

        hash_for_each_possible(mm_slots_hash, slot, link, (unsigned long)mm)
                if (slot->mm == mm)
                        return slot;

        return NULL;
}

static void insert_to_mm_slots_hash(struct mm_struct *mm,
                                    struct mm_slot *mm_slot)
{
        mm_slot->mm = mm;
        hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm);
}

/*
 * ksmd, and unmerge_and_remove_all_rmap_items(), must not touch an mm's
 * page tables after it has passed through ksm_exit() - which, if necessary,
 * takes mmap_sem briefly to serialize against them.  ksm_exit() does not set
 * a special flag: they can just back out as soon as mm_users goes to zero.
 * ksm_test_exit() is used throughout to make this test for exit: in some
 * places for correctness, in some places just to avoid unnecessary work.
 */
static inline bool ksm_test_exit(struct mm_struct *mm)
{
        return atomic_read(&mm->mm_users) == 0;
}

/*
 * We use break_ksm to break COW on a ksm page: it's a stripped down
 *
 *      if (get_user_pages(addr, 1, 1, 1, &page, NULL) == 1)
 *              put_page(page);
 *
 * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma,
 * in case the application has unmapped and remapped mm,addr meanwhile.
 * Could a ksm page appear anywhere else?  Actually yes, in a VM_PFNMAP
 * mmap of /dev/mem or /dev/kmem, where we would not want to touch it.
 *
 * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context
 * of the process that owns 'vma'.  We also do not want to enforce
 * protection keys here anyway.
 */
static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
{
        struct page *page;
        int ret = 0;

        do {
                cond_resched();
                page = follow_page(vma, addr,
                                FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE);
                if (IS_ERR_OR_NULL(page))
                        break;
                if (PageKsm(page))
                        ret = handle_mm_fault(vma->vm_mm, vma, addr,
                                                        FAULT_FLAG_WRITE |
                                                        FAULT_FLAG_REMOTE);
                else
                        ret = VM_FAULT_WRITE;
                put_page(page);
        } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
        /*
         * We must loop because handle_mm_fault() may back out if there's
         * any difficulty e.g. if pte accessed bit gets updated concurrently.
         *
         * VM_FAULT_WRITE is what we have been hoping for: it indicates that
         * COW has been broken, even if the vma does not permit VM_WRITE;
         * but note that a concurrent fault might break PageKsm for us.
         *
         * VM_FAULT_SIGBUS could occur if we race with truncation of the
         * backing file, which also invalidates anonymous pages: that's
         * okay, that truncation will have unmapped the PageKsm for us.
         *
         * VM_FAULT_OOM: at the time of writing (late July 2009), setting
         * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the
         * current task has TIF_MEMDIE set, and will be OOM killed on return
         * to user; and ksmd, having no mm, would never be chosen for that.
         *
         * But if the mm is in a limited mem_cgroup, then the fault may fail
         * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and
         * even ksmd can fail in this way - though it's usually breaking ksm
         * just to undo a merge it made a moment before, so unlikely to oom.
         *
         * That's a pity: we might therefore have more kernel pages allocated
         * than we're counting as nodes in the stable tree; but ksm_do_scan
         * will retry to break_cow on each pass, so should recover the page
         * in due course.  The important thing is to not let VM_MERGEABLE
         * be cleared while any such pages might remain in the area.
         */
        return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
}

static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm,
                unsigned long addr)
{
        struct vm_area_struct *vma;
        if (ksm_test_exit(mm))
                return NULL;
        vma = find_vma(mm, addr);
        if (!vma || vma->vm_start > addr)
                return NULL;
        if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
                return NULL;
        return vma;
}

static void break_cow(struct rmap_item *rmap_item)
{
        struct mm_struct *mm = rmap_item->mm;
        unsigned long addr = rmap_item->address;
        struct vm_area_struct *vma;

        /*
         * It is not an accident that whenever we want to break COW
         * to undo, we also need to drop a reference to the anon_vma.
         */
        put_anon_vma(rmap_item->anon_vma);

        down_read(&mm->mmap_sem);
        vma = find_mergeable_vma(mm, addr);
        if (vma)
                break_ksm(vma, addr);
        up_read(&mm->mmap_sem);
}

static struct page *get_mergeable_page(struct rmap_item *rmap_item)
{
        struct mm_struct *mm = rmap_item->mm;
        unsigned long addr = rmap_item->address;
        struct vm_area_struct *vma;
        struct page *page;

        down_read(&mm->mmap_sem);
        vma = find_mergeable_vma(mm, addr);
        if (!vma)
                goto out;

        page = follow_page(vma, addr, FOLL_GET);
        if (IS_ERR_OR_NULL(page))
                goto out;
        if (PageAnon(page)) {
                flush_anon_page(vma, page, addr);
                flush_dcache_page(page);
        } else {
                put_page(page);
out:
                page = NULL;
        }
        up_read(&mm->mmap_sem);
        return page;
}

/*
 * This helper is used for getting right index into array of tree roots.
 * When merge_across_nodes knob is set to 1, there are only two rb-trees for
 * stable and unstable pages from all nodes with roots in index 0. Otherwise,
 * every node has its own stable and unstable tree.
 */
static inline int get_kpfn_nid(unsigned long kpfn)
{
        return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn));
}

static struct stable_node *alloc_stable_node_chain(struct stable_node *dup,
                                                   struct rb_root *root)
{
        struct stable_node *chain = alloc_stable_node();
        VM_BUG_ON(is_stable_node_chain(dup));
        if (likely(chain)) {
                INIT_HLIST_HEAD(&chain->hlist);
                chain->chain_prune_time = jiffies;
                chain->rmap_hlist_len = STABLE_NODE_CHAIN;
#if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA)
                chain->nid = -1; /* debug */
#endif
                ksm_stable_node_chains++;

                /*
                 * Put the stable node chain in the first dimension of
                 * the stable tree and at the same time remove the old
                 * stable node.
                 */
                rb_replace_node(&dup->node, &chain->node, root);

                /*
                 * Move the old stable node to the second dimension
                 * queued in the hlist_dup. The invariant is that all
                 * dup stable_nodes in the chain->hlist point to pages
                 * that are wrprotected and have the exact same
                 * content.
                 */
                stable_node_chain_add_dup(dup, chain);
        }
        return chain;
}

static inline void free_stable_node_chain(struct stable_node *chain,
                                          struct rb_root *root)
{
        rb_erase(&chain->node, root);
        free_stable_node(chain);
        ksm_stable_node_chains--;
}

static void remove_node_from_stable_tree(struct stable_node *stable_node)
{
        struct rmap_item *rmap_item;

        /* check it's not STABLE_NODE_CHAIN or negative */
        BUG_ON(stable_node->rmap_hlist_len < 0);

        hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
                if (rmap_item->hlist.next)
                        ksm_pages_sharing--;
                else
                        ksm_pages_shared--;
                VM_BUG_ON(stable_node->rmap_hlist_len <= 0);
                stable_node->rmap_hlist_len--;
                put_anon_vma(rmap_item->anon_vma);
                rmap_item->address &= PAGE_MASK;
                cond_resched();
        }

        /*
         * We need the second aligned pointer of the migrate_nodes
         * list_head to stay clear from the rb_parent_color union
         * (aligned and different than any node) and also different
         * from &migrate_nodes. This will verify that future list.h changes
         * don't break STABLE_NODE_DUP_HEAD.
         */
#if GCC_VERSION >= 40903 /* only recent gcc can handle it */
        BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes);
        BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1);
#endif

        if (stable_node->head == &migrate_nodes)
                list_del(&stable_node->list);
        else
                stable_node_dup_del(stable_node);
        free_stable_node(stable_node);
}

/*
 * get_ksm_page: checks if the page indicated by the stable node
 * is still its ksm page, despite having held no reference to it.
 * In which case we can trust the content of the page, and it
 * returns the gotten page; but if the page has now been zapped,
 * remove the stale node from the stable tree and return NULL.
 * But beware, the stable node's page might be being migrated.
 *
 * You would expect the stable_node to hold a reference to the ksm page.
 * But if it increments the page's count, swapping out has to wait for
 * ksmd to come around again before it can free the page, which may take
 * seconds or even minutes: much too unresponsive.  So instead we use a
 * "keyhole reference": access to the ksm page from the stable node peeps
 * out through its keyhole to see if that page still holds the right key,
 * pointing back to this stable node.  This relies on freeing a PageAnon
 * page to reset its page->mapping to NULL, and relies on no other use of
 * a page to put something that might look like our key in page->mapping.
 * is on its way to being freed; but it is an anomaly to bear in mind.
 */
static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it)
{
        struct page *page;
        void *expected_mapping;
        unsigned long kpfn;

        expected_mapping = (void *)stable_node +
                                (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
again:
        kpfn = READ_ONCE(stable_node->kpfn);
        page = pfn_to_page(kpfn);

        /*
         * page is computed from kpfn, so on most architectures reading
         * page->mapping is naturally ordered after reading node->kpfn,
         * but on Alpha we need to be more careful.
         */
        smp_read_barrier_depends();
        if (READ_ONCE(page->mapping) != expected_mapping)
                goto stale;

        /*
         * We cannot do anything with the page while its refcount is 0.
         * Usually 0 means free, or tail of a higher-order page: in which
         * case this node is no longer referenced, and should be freed;
         * however, it might mean that the page is under page_freeze_refs().
         * The __remove_mapping() case is easy, again the node is now stale;
         * but if page is swapcache in migrate_page_move_mapping(), it might
         * still be our page, in which case it's essential to keep the node.
         */
        while (!get_page_unless_zero(page)) {
                /*
                 * Another check for page->mapping != expected_mapping would
                 * work here too.  We have chosen the !PageSwapCache test to
                 * optimize the common case, when the page is or is about to
                 * be freed: PageSwapCache is cleared (under spin_lock_irq)
                 * in the freeze_refs section of __remove_mapping(); but Anon
                 * page->mapping reset to NULL later, in free_pages_prepare().
                 */
                if (!PageSwapCache(page))
                        goto stale;
                cpu_relax();
        }

        if (READ_ONCE(page->mapping) != expected_mapping) {
                put_page(page);
                goto stale;
        }

        if (lock_it) {
                lock_page(page);
                if (READ_ONCE(page->mapping) != expected_mapping) {
                        unlock_page(page);
                        put_page(page);
                        goto stale;
                }
        }
        return page;

stale:
        /*
         * We come here from above when page->mapping or !PageSwapCache
         * suggests that the node is stale; but it might be under migration.
         * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(),
         * before checking whether node->kpfn has been changed.
         */
        smp_rmb();
        if (READ_ONCE(stable_node->kpfn) != kpfn)
                goto again;
        remove_node_from_stable_tree(stable_node);
        return NULL;
}

/*
 * Removing rmap_item from stable or unstable tree.
 * This function will clean the information from the stable/unstable tree.
 */
static void remove_rmap_item_from_tree(struct rmap_item *rmap_item)
{
        if (rmap_item->address & STABLE_FLAG) {
                struct stable_node *stable_node;
                struct page *page;

                stable_node = rmap_item->head;
                page = get_ksm_page(stable_node, true);
                if (!page)
                        goto out;

                hlist_del(&rmap_item->hlist);
                unlock_page(page);
                put_page(page);

                if (!hlist_empty(&stable_node->hlist))
                        ksm_pages_sharing--;
                else
                        ksm_pages_shared--;
                VM_BUG_ON(stable_node->rmap_hlist_len <= 0);
                stable_node->rmap_hlist_len--;

                put_anon_vma(rmap_item->anon_vma);
                rmap_item->address &= PAGE_MASK;

        } else if (rmap_item->address & UNSTABLE_FLAG) {
                unsigned char age;
                /*
                 * Usually ksmd can and must skip the rb_erase, because
                 * root_unstable_tree was already reset to RB_ROOT.
                 * But be careful when an mm is exiting: do the rb_erase
                 * if this rmap_item was inserted by this scan, rather
                 * than left over from before.
                 */
                age = (unsigned char)(ksm_scan.seqnr - rmap_item->address);
                BUG_ON(age > 1);
                if (!age)
                        rb_erase(&rmap_item->node,
                                 root_unstable_tree + NUMA(rmap_item->nid));
                ksm_pages_unshared--;
                rmap_item->address &= PAGE_MASK;
        }
out:
        cond_resched();         /* we're called from many long loops */
}

static void remove_trailing_rmap_items(struct mm_slot *mm_slot,
                                       struct rmap_item **rmap_list)
{
        while (*rmap_list) {
                struct rmap_item *rmap_item = *rmap_list;
                *rmap_list = rmap_item->rmap_list;
                remove_rmap_item_from_tree(rmap_item);
                free_rmap_item(rmap_item);
        }
}

/*
 * Though it's very tempting to unmerge rmap_items from stable tree rather
 * than check every pte of a given vma, the locking doesn't quite work for
 * that - an rmap_item is assigned to the stable tree after inserting ksm
 * page and upping mmap_sem.  Nor does it fit with the way we skip dup'ing
 * rmap_items from parent to child at fork time (so as not to waste time
 * if exit comes before the next scan reaches it).
 *
 * Similarly, although we'd like to remove rmap_items (so updating counts
 * and freeing memory) when unmerging an area, it's easier to leave that
 * to the next pass of ksmd - consider, for example, how ksmd might be
 * in cmp_and_merge_page on one of the rmap_items we would be removing.
 */
static int unmerge_ksm_pages(struct vm_area_struct *vma,
                             unsigned long start, unsigned long end)
{
        unsigned long addr;
        int err = 0;

        for (addr = start; addr < end && !err; addr += PAGE_SIZE) {
                if (ksm_test_exit(vma->vm_mm))
                        break;
                if (signal_pending(current))
                        err = -ERESTARTSYS;
                else
                        err = break_ksm(vma, addr);
        }
        return err;
}

#ifdef CONFIG_SYSFS
/*
 * Only called through the sysfs control interface:
 */
static int remove_stable_node(struct stable_node *stable_node)
{
        struct page *page;
        int err;

        page = get_ksm_page(stable_node, true);
        if (!page) {
                /*
                 * get_ksm_page did remove_node_from_stable_tree itself.
                 */
                return 0;
        }

        if (WARN_ON_ONCE(page_mapped(page))) {
                /*
                 * This should not happen: but if it does, just refuse to let
                 * merge_across_nodes be switched - there is no need to panic.
                 */
                err = -EBUSY;
        } else {
                /*
                 * The stable node did not yet appear stale to get_ksm_page(),
                 * since that allows for an unmapped ksm page to be recognized
                 * right up until it is freed; but the node is safe to remove.
                 * This page might be in a pagevec waiting to be freed,
                 * or it might be PageSwapCache (perhaps under writeback),
                 * or it might have been removed from swapcache a moment ago.
                 */
                set_page_stable_node(page, NULL);
                remove_node_from_stable_tree(stable_node);
                err = 0;
        }

        unlock_page(page);
        put_page(page);
        return err;
}

static int remove_stable_node_chain(struct stable_node *stable_node,
                                    struct rb_root *root)
{
        struct stable_node *dup;
        struct hlist_node *hlist_safe;

        if (!is_stable_node_chain(stable_node)) {
                VM_BUG_ON(is_stable_node_dup(stable_node));
                if (remove_stable_node(stable_node))
                        return true;
                else
                        return false;
        }

        hlist_for_each_entry_safe(dup, hlist_safe,
                                  &stable_node->hlist, hlist_dup) {
                VM_BUG_ON(!is_stable_node_dup(dup));
                if (remove_stable_node(dup))
                        return true;
        }
        BUG_ON(!hlist_empty(&stable_node->hlist));
        free_stable_node_chain(stable_node, root);
        return false;
}

static int remove_all_stable_nodes(void)
{
        struct stable_node *stable_node, *next;
        int nid;
        int err = 0;

        for (nid = 0; nid < ksm_nr_node_ids; nid++) {
                while (root_stable_tree[nid].rb_node) {
                        stable_node = rb_entry(root_stable_tree[nid].rb_node,
                                                struct stable_node, node);
                        if (remove_stable_node_chain(stable_node,
                                                     root_stable_tree + nid)) {
                                err = -EBUSY;
                                break;  /* proceed to next nid */
                        }
                        cond_resched();
                }
        }
        list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) {
                if (remove_stable_node(stable_node))
                        err = -EBUSY;
                cond_resched();
        }
        return err;
}

static int unmerge_and_remove_all_rmap_items(void)
{
        struct mm_slot *mm_slot;
        struct mm_struct *mm;
        struct vm_area_struct *vma;
        int err = 0;

        spin_lock(&ksm_mmlist_lock);
        ksm_scan.mm_slot = list_entry(ksm_mm_head.mm_list.next,
                                                struct mm_slot, mm_list);
        spin_unlock(&ksm_mmlist_lock);

        for (mm_slot = ksm_scan.mm_slot;
                        mm_slot != &ksm_mm_head; mm_slot = ksm_scan.mm_slot) {
                mm = mm_slot->mm;
                down_read(&mm->mmap_sem);
                for (vma = mm->mmap; vma; vma = vma->vm_next) {
                        if (ksm_test_exit(mm))
                                break;
                        if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
                                continue;
                        err = unmerge_ksm_pages(vma,
                                                vma->vm_start, vma->vm_end);
                        if (err)
                                goto error;
                }

                remove_trailing_rmap_items(mm_slot, &mm_slot->rmap_list);

                spin_lock(&ksm_mmlist_lock);
                ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next,
                                                struct mm_slot, mm_list);
                if (ksm_test_exit(mm)) {
                        hash_del(&mm_slot->link);
                        list_del(&mm_slot->mm_list);
                        spin_unlock(&ksm_mmlist_lock);

                        free_mm_slot(mm_slot);
                        clear_bit(MMF_VM_MERGEABLE, &mm->flags);
                        up_read(&mm->mmap_sem);
                        mmdrop(mm);
                } else {
                        spin_unlock(&ksm_mmlist_lock);
                        up_read(&mm->mmap_sem);
                }
        }

        /* Clean up stable nodes, but don't worry if some are still busy */
        remove_all_stable_nodes();
        ksm_scan.seqnr = 0;
        return 0;

error:
        up_read(&mm->mmap_sem);
        spin_lock(&ksm_mmlist_lock);
        ksm_scan.mm_slot = &ksm_mm_head;
        spin_unlock(&ksm_mmlist_lock);
        return err;
}
#endif /* CONFIG_SYSFS */

static u32 calc_checksum(struct page *page)
{
        u32 checksum;
        void *addr = kmap_atomic(page);
        checksum = jhash2(addr, PAGE_SIZE / 4, 17);
        kunmap_atomic(addr);
        return checksum;
}

static int memcmp_pages(struct page *page1, struct page *page2)
{
        char *addr1, *addr2;
        int ret;

        addr1 = kmap_atomic(page1);
        addr2 = kmap_atomic(page2);
        ret = memcmp(addr1, addr2, PAGE_SIZE);
        kunmap_atomic(addr2);
        kunmap_atomic(addr1);
        return ret;
}

static inline int pages_identical(struct page *page1, struct page *page2)
{
        return !memcmp_pages(page1, page2);
}

static int write_protect_page(struct vm_area_struct *vma, struct page *page,
                              pte_t *orig_pte)
{
        struct mm_struct *mm = vma->vm_mm;
        unsigned long addr;
        pte_t *ptep;
        spinlock_t *ptl;
        int swapped;
        int err = -EFAULT;
        unsigned long mmun_start;       /* For mmu_notifiers */
        unsigned long mmun_end;         /* For mmu_notifiers */

        addr = page_address_in_vma(page, vma);
        if (addr == -EFAULT)
                goto out;

        BUG_ON(PageTransCompound(page));

        mmun_start = addr;
        mmun_end   = addr + PAGE_SIZE;
        mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

        ptep = page_check_address(page, mm, addr, &ptl, 0);
        if (!ptep)
                goto out_mn;

        if (pte_write(*ptep) || pte_dirty(*ptep)) {
                pte_t entry;

                swapped = PageSwapCache(page);
                flush_cache_page(vma, addr, page_to_pfn(page));
                /*
                 * Ok this is tricky, when get_user_pages_fast() run it doesn't
                 * take any lock, therefore the check that we are going to make
                 * with the pagecount against the mapcount is racey and
                 * O_DIRECT can happen right after the check.
                 * So we clear the pte and flush the tlb before the check
                 * this assure us that no O_DIRECT can happen after the check
                 * or in the middle of the check.
                 */
                entry = ptep_clear_flush_notify(vma, addr, ptep);
                /*
                 * Check that no O_DIRECT or similar I/O is in progress on the
                 * page
                 */
                if (page_mapcount(page) + 1 + swapped != page_count(page)) {
                        set_pte_at(mm, addr, ptep, entry);
                        goto out_unlock;
                }
                if (pte_dirty(entry))
                        set_page_dirty(page);
                entry = pte_mkclean(pte_wrprotect(entry));
                set_pte_at_notify(mm, addr, ptep, entry);
        }
        *orig_pte = *ptep;
        err = 0;

out_unlock:
        pte_unmap_unlock(ptep, ptl);
out_mn:
        mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out:
        return err;
}

/**
 * replace_page - replace page in vma by new ksm page
 * @vma:      vma that holds the pte pointing to page
 * @page:     the page we are replacing by kpage
 * @kpage:    the ksm page we replace page by
 * @orig_pte: the original value of the pte
 *
 * Returns 0 on success, -EFAULT on failure.
 */
static int replace_page(struct vm_area_struct *vma, struct page *page,
                        struct page *kpage, pte_t orig_pte)
{
        struct mm_struct *mm = vma->vm_mm;
        pmd_t *pmd;
        pte_t *ptep;
        spinlock_t *ptl;
        unsigned long addr;
        int err = -EFAULT;
        unsigned long mmun_start;       /* For mmu_notifiers */
        unsigned long mmun_end;         /* For mmu_notifiers */

        addr = page_address_in_vma(page, vma);
        if (addr == -EFAULT)
                goto out;

        pmd = mm_find_pmd(mm, addr);
        if (!pmd)
                goto out;

        mmun_start = addr;
        mmun_end   = addr + PAGE_SIZE;
        mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

        ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
        if (!pte_same(*ptep, orig_pte)) {
                pte_unmap_unlock(ptep, ptl);
                goto out_mn;
        }

        get_page(kpage);
        page_add_anon_rmap(kpage, vma, addr, false);

        flush_cache_page(vma, addr, pte_pfn(*ptep));
        ptep_clear_flush_notify(vma, addr, ptep);
        set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));

        page_remove_rmap(page, false);
        if (!page_mapped(page))
                try_to_free_swap(page);
        put_page(page);

        pte_unmap_unlock(ptep, ptl);
        err = 0;
out_mn:
        mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out:
        return err;
}

/*
 * try_to_merge_one_page - take two pages and merge them into one
 * @vma: the vma that holds the pte pointing to page
 * @page: the PageAnon page that we want to replace with kpage
 * @kpage: the PageKsm page that we want to map instead of page,
 *         or NULL the first time when we want to use page as kpage.
 *
 * This function returns 0 if the pages were merged, -EFAULT otherwise.
 */
static int try_to_merge_one_page(struct vm_area_struct *vma,
                                 struct page *page, struct page *kpage)
{
        pte_t orig_pte = __pte(0);
        int err = -EFAULT;

        if (page == kpage)                      /* ksm page forked */
                return 0;

        if (!PageAnon(page))
                goto out;

        /*
         * We need the page lock to read a stable PageSwapCache in
         * write_protect_page().  We use trylock_page() instead of
         * lock_page() because we don't want to wait here - we
         * prefer to continue scanning and merging different pages,
         * then come back to this page when it is unlocked.
         */
        if (!trylock_page(page))
                goto out;

        if (PageTransCompound(page)) {
                err = split_huge_page(page);
                if (err)
                        goto out_unlock;
        }

        /*
         * If this anonymous page is mapped only here, its pte may need
         * to be write-protected.  If it's mapped elsewhere, all of its
         * ptes are necessarily already write-protected.  But in either
         * case, we need to lock and check page_count is not raised.
         */
        if (write_protect_page(vma, page, &orig_pte) == 0) {
                if (!kpage) {
                        /*
                         * While we hold page lock, upgrade page from
                         * PageAnon+anon_vma to PageKsm+NULL stable_node:
                         * stable_tree_insert() will update stable_node.
                         */
                        set_page_stable_node(page, NULL);
                        mark_page_accessed(page);
                        /*
                         * Page reclaim just frees a clean page with no dirty
                         * ptes: make sure that the ksm page would be swapped.
                         */
                        if (!PageDirty(page))
                                SetPageDirty(page);
                        err = 0;
                } else if (pages_identical(page, kpage))
                        err = replace_page(vma, page, kpage, orig_pte);
        }

        if ((vma->vm_flags & VM_LOCKED) && kpage && !err) {
                munlock_vma_page(page);
                if (!PageMlocked(kpage)) {
                        unlock_page(page);
                        lock_page(kpage);
                        mlock_vma_page(kpage);
                        page = kpage;           /* for final unlock */
                }
        }

out_unlock:
        unlock_page(page);
out:
        return err;
}

/*
 * try_to_merge_with_ksm_page - like try_to_merge_two_pages,
 * but no new kernel page is allocated: kpage must already be a ksm page.
 *
 * This function returns 0 if the pages were merged, -EFAULT otherwise.
 */
static int try_to_merge_with_ksm_page(struct rmap_item *rmap_item,
                                      struct page *page, struct page *kpage)
{
        struct mm_struct *mm = rmap_item->mm;
        struct vm_area_struct *vma;
        int err = -EFAULT;

        down_read(&mm->mmap_sem);
        vma = find_mergeable_vma(mm, rmap_item->address);
        if (!vma)
                goto out;

        err = try_to_merge_one_page(vma, page, kpage);
        if (err)
                goto out;

        /* Unstable nid is in union with stable anon_vma: remove first */
        remove_rmap_item_from_tree(rmap_item);

        /* Must get reference to anon_vma while still holding mmap_sem */
        rmap_item->anon_vma = vma->anon_vma;
        get_anon_vma(vma->anon_vma);
out:
        up_read(&mm->mmap_sem);
        return err;
}

/*
 * try_to_merge_two_pages - take two identical pages and prepare them
 * to be merged into one page.
 *
 * This function returns the kpage if we successfully merged two identical
 * pages into one ksm page, NULL otherwise.
 *
 * Note that this function upgrades page to ksm page: if one of the pages
 * is already a ksm page, try_to_merge_with_ksm_page should be used.
 */
static struct page *try_to_merge_two_pages(struct rmap_item *rmap_item,
                                           struct page *page,
                                           struct rmap_item *tree_rmap_item,
                                           struct page *tree_page)
{
        int err;

        err = try_to_merge_with_ksm_page(rmap_item, page, NULL);
        if (!err) {
                err = try_to_merge_with_ksm_page(tree_rmap_item,
                                                        tree_page, page);
                /*
                 * If that fails, we have a ksm page with only one pte
                 * pointing to it: so break it.
                 */
                if (err)
                        break_cow(rmap_item);
        }
        return err ? NULL : page;
}

static __always_inline
bool __is_page_sharing_candidate(struct stable_node *stable_node, int offset)
{
        VM_BUG_ON(stable_node->rmap_hlist_len < 0);
        /*
         * Check that at least one mapping still exists, otherwise
         * there's no much point to merge and share with this
         * stable_node, as the underlying tree_page of the other
         * sharer is going to be freed soon.
         */
        return stable_node->rmap_hlist_len &&
                stable_node->rmap_hlist_len + offset < ksm_max_page_sharing;
}

static __always_inline
bool is_page_sharing_candidate(struct stable_node *stable_node)
{
        return __is_page_sharing_candidate(stable_node, 0);
}

static struct stable_node *stable_node_dup(struct stable_node *stable_node,
                                           struct page **tree_page,
                                           struct rb_root *root,
                                           bool prune_stale_stable_nodes)
{
        struct stable_node *dup, *found = NULL;
        struct hlist_node *hlist_safe;
        struct page *_tree_page;
        int nr = 0;
        int found_rmap_hlist_len;

        if (!prune_stale_stable_nodes ||
            time_before(jiffies, stable_node->chain_prune_time +
                        msecs_to_jiffies(
                                ksm_stable_node_chains_prune_millisecs)))
                prune_stale_stable_nodes = false;
        else
                stable_node->chain_prune_time = jiffies;

        hlist_for_each_entry_safe(dup, hlist_safe,
                                  &stable_node->hlist, hlist_dup) {
                cond_resched();
                /*
                 * We must walk all stable_node_dup to prune the stale
                 * stable nodes during lookup.
                 *
                 * get_ksm_page can drop the nodes from the
                 * stable_node->hlist if they point to freed pages
                 * (that's why we do a _safe walk). The "dup"
                 * stable_node parameter itself will be freed from
                 * under us if it returns NULL.
                 */
                _tree_page = get_ksm_page(dup, false);
                if (!_tree_page)
                        continue;
                nr += 1;
                if (is_page_sharing_candidate(dup)) {
                        if (!found ||
                            dup->rmap_hlist_len > found_rmap_hlist_len) {
                                if (found)
                                        put_page(*tree_page);
                                found = dup;
                                found_rmap_hlist_len = found->rmap_hlist_len;
                                *tree_page = _tree_page;

                                if (!prune_stale_stable_nodes)
                                        break;
                                /* skip put_page */
                                continue;
                        }
                }
                put_page(_tree_page);
        }

        /*
         * nr is relevant only if prune_stale_stable_nodes is true,
         * otherwise we may break the loop at nr == 1 even if there
         * are multiple entries.
         */
        if (prune_stale_stable_nodes && found) {
                if (nr == 1) {
                        /*
                         * If there's not just one entry it would
                         * corrupt memory, better BUG_ON. In KSM
                         * context with no lock held it's not even
                         * fatal.
                         */
                        BUG_ON(stable_node->hlist.first->next);

                        /*
                         * There's just one entry and it is below the
                         * deduplication limit so drop the chain.
                         */
                        rb_replace_node(&stable_node->node, &found->node,
                                        root);
                        free_stable_node(stable_node);
                        ksm_stable_node_chains--;
                        ksm_stable_node_dups--;
                } else if (__is_page_sharing_candidate(found, 1)) {
                        /*
                         * Refile our candidate at the head
                         * after the prune if our candidate
                         * can accept one more future sharing
                         * in addition to the one underway.
                         */
                        hlist_del(&found->hlist_dup);
                        hlist_add_head(&found->hlist_dup,
                                       &stable_node->hlist);
                }
        }

        return found;
}

static struct stable_node *stable_node_dup_any(struct stable_node *stable_node,
                                               struct rb_root *root)
{
        if (!is_stable_node_chain(stable_node))
                return stable_node;
        if (hlist_empty(&stable_node->hlist)) {
                free_stable_node_chain(stable_node, root);
                return NULL;
        }
        return hlist_entry(stable_node->hlist.first,
                           typeof(*stable_node), hlist_dup);
}

static struct stable_node *__stable_node_chain(struct stable_node *stable_node,
                                               struct page **tree_page,
                                               struct rb_root *root,
                                               bool prune_stale_stable_nodes)
{
        if (!is_stable_node_chain(stable_node)) {
                if (is_page_sharing_candidate(stable_node)) {
                        *tree_page = get_ksm_page(stable_node, false);
                        return stable_node;
                }
                return NULL;
        }
        return stable_node_dup(stable_node, tree_page, root,
                               prune_stale_stable_nodes);
}

static __always_inline struct stable_node *chain_prune(struct stable_node *s_n,
                                                       struct page **t_p,
                                                       struct rb_root *root)
{
        return __stable_node_chain(s_n, t_p, root, true);
}

static __always_inline struct stable_node *chain(struct stable_node *s_n,
                                                 struct page **t_p,
                                                 struct rb_root *root)
{
        return __stable_node_chain(s_n, t_p, root, false);
}

/*
 * stable_tree_search - search for page inside the stable tree
 *
 * This function checks if there is a page inside the stable tree
 * with identical content to the page that we are scanning right now.
 *
 * This function returns the stable tree node of identical content if found,
 * NULL otherwise.
 */
static struct page *stable_tree_search(struct page *page)
{
        int nid;
        struct rb_root *root;
        struct rb_node **new;
        struct rb_node *parent;
        struct stable_node *stable_node, *stable_node_dup, *stable_node_any;
        struct stable_node *page_node;

        page_node = page_stable_node(page);
        if (page_node && page_node->head != &migrate_nodes) {
                /* ksm page forked */
                get_page(page);
                return page;
        }

        nid = get_kpfn_nid(page_to_pfn(page));
        root = root_stable_tree + nid;
again:
        new = &root->rb_node;
        parent = NULL;

        while (*new) {
                struct page *tree_page;
                int ret;

                cond_resched();
                stable_node = rb_entry(*new, struct stable_node, node);
                stable_node_any = NULL;
                stable_node_dup = chain_prune(stable_node, &tree_page, root);
                if (!stable_node_dup) {
                        /*
                         * Either all stable_node dups were full in
                         * this stable_node chain, or this chain was
                         * empty and should be rb_erased.
                         */
                        stable_node_any = stable_node_dup_any(stable_node,
                                                              root);
                        if (!stable_node_any) {
                                /* rb_erase just run */
                                goto again;
                        }
                        /*
                         * Take any of the stable_node dups page of
                         * this stable_node chain to let the tree walk
                         * continue. All KSM pages belonging to the
                         * stable_node dups in a stable_node chain
                         * have the same content and they're
                         * wrprotected at all times. Any will work
                         * fine to continue the walk.
                         */
                        tree_page = get_ksm_page(stable_node_any, false);
                }
                VM_BUG_ON(!stable_node_dup ^ !!stable_node_any);
                if (!tree_page) {
                        /*
                         * If we walked over a stale stable_node,
                         * get_ksm_page() will call rb_erase() and it
                         * may rebalance the tree from under us. So
                         * restart the search from scratch. Returning
                         * NULL would be safe too, but we'd generate
                         * false negative insertions just because some
                         * stable_node was stale.
                         */
                        goto again;
                }

                ret = memcmp_pages(page, tree_page);
                put_page(tree_page);

                parent = *new;
                if (ret < 0)
                        new = &parent->rb_left;
                else if (ret > 0)
                        new = &parent->rb_right;
                else {
                        if (page_node) {
                                VM_BUG_ON(page_node->head != &migrate_nodes);
                                /*
                                 * Test if the migrated page should be merged
                                 * into a stable node dup. If the mapcount is
                                 * 1 we can migrate it with another KSM page
                                 * without adding it to the chain.
                                 */
                                if (page_mapcount(page) > 1)
                                        goto chain_append;
                        }

                        if (!stable_node_dup) {
                                /*
                                 * If the stable_node is a chain and
                                 * we got a payload match in memcmp
                                 * but we cannot merge the scanned
                                 * page in any of the existing
                                 * stable_node dups because they're
                                 * all full, we need to wait the
                                 * scanned page to find itself a match
                                 * in the unstable tree to create a
                                 * brand new KSM page to add later to
                                 * the dups of this stable_node.
                                 */
                                return NULL;
                        }

                        /*
                         * Lock and unlock the stable_node's page (which
                         * might already have been migrated) so that page
                         * migration is sure to notice its raised count.
                         * It would be more elegant to return stable_node
                         * than kpage, but that involves more changes.
                         */
                        tree_page = get_ksm_page(stable_node_dup, true);
                        if (unlikely(!tree_page))
                                /*
                                 * The tree may have been rebalanced,
                                 * so re-evaluate parent and new.
                                 */
                                goto again;
                        unlock_page(tree_page);

                        if (get_kpfn_nid(stable_node_dup->kpfn) !=
                            NUMA(stable_node_dup->nid)) {
                                put_page(tree_page);
                                goto replace;
                        }
                        return tree_page;
                }
        }

        if (!page_node)
                return NULL;

        list_del(&page_node->list);
        DO_NUMA(page_node->nid = nid);
        rb_link_node(&page_node->node, parent, new);
        rb_insert_color(&page_node->node, root);
out:
        if (is_page_sharing_candidate(page_node)) {
                get_page(page);
                return page;
        } else
                return NULL;

replace:
        if (stable_node_dup == stable_node) {
                /* there is no chain */
                if (page_node) {
                        VM_BUG_ON(page_node->head != &migrate_nodes);
                        list_del(&page_node->list);
                        DO_NUMA(page_node->nid = nid);
                        rb_replace_node(&stable_node->node, &page_node->node,
                                        root);
                        if (is_page_sharing_candidate(page_node))
                                get_page(page);
                        else
                                page = NULL;
                } else {
                        rb_erase(&stable_node->node, root);
                        page = NULL;
                }
        } else {
                VM_BUG_ON(!is_stable_node_chain(stable_node));
                __stable_node_dup_del(stable_node_dup);
                if (page_node) {
                        VM_BUG_ON(page_node->head != &migrate_nodes);
                        list_del(&page_node->list);
                        DO_NUMA(page_node->nid = nid);
                        stable_node_chain_add_dup(page_node, stable_node);
                        if (is_page_sharing_candidate(page_node))
                                get_page(page);
                        else
                                page = NULL;
                } else {
                        page = NULL;
                }
        }
        stable_node_dup->head = &migrate_nodes;
        list_add(&stable_node_dup->list, stable_node_dup->head);
        return page;

chain_append:
        /* stable_node_dup could be null if it reached the limit */
        if (!stable_node_dup)
                stable_node_dup = stable_node_any;
        if (stable_node_dup == stable_node) {
                /* chain is missing so create it */
                stable_node = alloc_stable_node_chain(stable_node_dup,
                                                      root);
                if (!stable_node)
                        return NULL;
        }
        /*
         * Add this stable_node dup that was
         * migrated to the stable_node chain
         * of the current nid for this page
         * content.
         */
        VM_BUG_ON(page_node->head != &migrate_nodes);
        list_del(&page_node->list);
        DO_NUMA(page_node->nid = nid);
        stable_node_chain_add_dup(page_node, stable_node);
        goto out;
}

/*
 * stable_tree_insert - insert stable tree node pointing to new ksm page
 * into the stable tree.
 *
 * This function returns the stable tree node just allocated on success,
 * NULL otherwise.
 */
static struct stable_node *stable_tree_insert(struct page *kpage)
{
        int nid;
        unsigned long kpfn;
        struct rb_root *root;
        struct rb_node **new;
        struct rb_node *parent;
        struct stable_node *stable_node, *stable_node_dup, *stable_node_any;
        bool need_chain = false;

        kpfn = page_to_pfn(kpage);
        nid = get_kpfn_nid(kpfn);
        root = root_stable_tree + nid;
again:
        parent = NULL;
        new = &root->rb_node;

        while (*new) {
                struct page *tree_page;
                int ret;

                cond_resched();
                stable_node = rb_entry(*new, struct stable_node, node);
                stable_node_any = NULL;
                stable_node_dup = chain(stable_node, &tree_page, root);
                if (!stable_node_dup) {
                        /*
                         * Either all stable_node dups were full in
                         * this stable_node chain, or this chain was
                         * empty and should be rb_erased.
                         */
                        stable_node_any = stable_node_dup_any(stable_node,
                                                              root);
                        if (!stable_node_any) {
                                /* rb_erase just run */
                                goto again;
                        }
                        /*
                         * Take any of the stable_node dups page of
                         * this stable_node chain to let the tree walk
                         * continue. All KSM pages belonging to the
                         * stable_node dups in a stable_node chain
                         * have the same content and they're
                         * wrprotected at all times. Any will work
                         * fine to continue the walk.
                         */
                        tree_page = get_ksm_page(stable_node_any, false);
                }
                VM_BUG_ON(!stable_node_dup ^ !!stable_node_any);
                if (!tree_page) {
                        /*
                         * If we walked over a stale stable_node,
                         * get_ksm_page() will call rb_erase() and it
                         * may rebalance the tree from under us. So
                         * restart the search from scratch. Returning
                         * NULL would be safe too, but we'd generate
                         * false negative insertions just because some
                         * stable_node was stale.
                         */
                        goto again;
                }

                ret = memcmp_pages(kpage, tree_page);
                put_page(tree_page);

                parent = *new;
                if (ret < 0)
                        new = &parent->rb_left;
                else if (ret > 0)
                        new = &parent->rb_right;
                else {
                        need_chain = true;
                        break;
                }
        }

        stable_node_dup = alloc_stable_node();
        if (!stable_node_dup)
                return NULL;

        INIT_HLIST_HEAD(&stable_node_dup->hlist);
        stable_node_dup->kpfn = kpfn;
        set_page_stable_node(kpage, stable_node_dup);
        stable_node_dup->rmap_hlist_len = 0;
        DO_NUMA(stable_node_dup->nid = nid);
        if (!need_chain) {
                rb_link_node(&stable_node_dup->node, parent, new);
                rb_insert_color(&stable_node_dup->node, root);
        } else {
                if (!is_stable_node_chain(stable_node)) {
                        struct stable_node *orig = stable_node;
                        /* chain is missing so create it */
                        stable_node = alloc_stable_node_chain(orig, root);
                        if (!stable_node) {
                                free_stable_node(stable_node_dup);
                                return NULL;
                        }
                }
                stable_node_chain_add_dup(stable_node_dup, stable_node);
        }

        return stable_node_dup;
}

/*
 * unstable_tree_search_insert - search for identical page,
 * else insert rmap_item into the unstable tree.
 *
 * This function searches for a page in the unstable tree identical to the
 * page currently being scanned; and if no identical page is found in the
 * tree, we insert rmap_item as a new object into the unstable tree.
 *
 * This function returns pointer to rmap_item found to be identical
 * to the currently scanned page, NULL otherwise.
 *
 * This function does both searching and inserting, because they share
 * the same walking algorithm in an rbtree.
 */
static
struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item,
                                              struct page *page,
                                              struct page **tree_pagep)
{
        struct rb_node **new;
        struct rb_root *root;
        struct rb_node *parent = NULL;
        int nid;

        nid = get_kpfn_nid(page_to_pfn(page));
        root = root_unstable_tree + nid;
        new = &root->rb_node;

        while (*new) {
                struct rmap_item *tree_rmap_item;
                struct page *tree_page;
                int ret;

                cond_resched();
                tree_rmap_item = rb_entry(*new, struct rmap_item, node);
                tree_page = get_mergeable_page(tree_rmap_item);
                if (!tree_page)
                        return NULL;

                /*
                 * Don't substitute a ksm page for a forked page.
                 */
                if (page == tree_page) {
                        put_page(tree_page);
                        return NULL;
                }

                ret = memcmp_pages(page, tree_page);

                parent = *new;
                if (ret < 0) {
                        put_page(tree_page);
                        new = &parent->rb_left;
                } else if (ret > 0) {
                        put_page(tree_page);
                        new = &parent->rb_right;
                } else if (!ksm_merge_across_nodes &&
                           page_to_nid(tree_page) != nid) {
                        /*
                         * If tree_page has been migrated to another NUMA node,
                         * it will be flushed out and put in the right unstable
                         * tree next time: only merge with it when across_nodes.
                         */
                        put_page(tree_page);
                        return NULL;
                } else {
                        *tree_pagep = tree_page;
                        return tree_rmap_item;
                }
        }

        rmap_item->address |= UNSTABLE_FLAG;
        rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK);
        DO_NUMA(rmap_item->nid = nid);
        rb_link_node(&rmap_item->node, parent, new);
        rb_insert_color(&rmap_item->node, root);

        ksm_pages_unshared++;
        return NULL;
}

/*
 * stable_tree_append - add another rmap_item to the linked list of
 * rmap_items hanging off a given node of the stable tree, all sharing
 * the same ksm page.
 */
static void stable_tree_append(struct rmap_item *rmap_item,
                               struct stable_node *stable_node,
                               bool max_page_sharing_bypass)
{
        /*
         * rmap won't find this mapping if we don't insert the
         * rmap_item in the right stable_node
         * duplicate. page_migration could break later if rmap breaks,
         * so we can as well crash here. We really need to check for
         * rmap_hlist_len == STABLE_NODE_CHAIN, but we can as well check
         * for other negative values as an undeflow if detected here
         * for the first time (and not when decreasing rmap_hlist_len)
         * would be sign of memory corruption in the stable_node.
         */
        BUG_ON(stable_node->rmap_hlist_len < 0);

        stable_node->rmap_hlist_len++;
        if (!max_page_sharing_bypass)
                /* possibly non fatal but unexpected overflow, only warn */
                WARN_ON_ONCE(stable_node->rmap_hlist_len >
                             ksm_max_page_sharing);

        rmap_item->head = stable_node;
        rmap_item->address |= STABLE_FLAG;
        hlist_add_head(&rmap_item->hlist, &stable_node->hlist);

        if (rmap_item->hlist.next)
                ksm_pages_sharing++;
        else
                ksm_pages_shared++;
}

/*
 * cmp_and_merge_page - first see if page can be merged into the stable tree;
 * if not, compare checksum to previous and if it's the same, see if page can
 * be inserted into the unstable tree, or merged with a page already there and
 * both transferred to the stable tree.
 *
 * @page: the page that we are searching identical page to.
 * @rmap_item: the reverse mapping into the virtual address of this page
 */
static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
{
        struct rmap_item *tree_rmap_item;
        struct page *tree_page = NULL;
        struct stable_node *stable_node;
        struct page *kpage;
        unsigned int checksum;
        int err;
        bool max_page_sharing_bypass = false;

        stable_node = page_stable_node(page);
        if (stable_node) {
                if (stable_node->head != &migrate_nodes &&
                    get_kpfn_nid(READ_ONCE(stable_node->kpfn)) !=
                    NUMA(stable_node->nid)) {
                        stable_node_dup_del(stable_node);
                        stable_node->head = &migrate_nodes;
                        list_add(&stable_node->list, stable_node->head);
                }
                if (stable_node->head != &migrate_nodes &&
                    rmap_item->head == stable_node)
                        return;
                /*
                 * If it's a KSM fork, allow it to go over the sharing limit
                 * without warnings.
                 */
                if (!is_page_sharing_candidate(stable_node))
                        max_page_sharing_bypass = true;
        }

        /* We first start with searching the page inside the stable tree */
        kpage = stable_tree_search(page);
        if (kpage == page && rmap_item->head == stable_node) {
                put_page(kpage);
                return;
        }

        remove_rmap_item_from_tree(rmap_item);

        if (kpage) {
                err = try_to_merge_with_ksm_page(rmap_item, page, kpage);
                if (!err) {
                        /*
                         * The page was successfully merged:
                         * add its rmap_item to the stable tree.
                         */
                        lock_page(kpage);
                        stable_tree_append(rmap_item, page_stable_node(kpage),
                                           max_page_sharing_bypass);
                        unlock_page(kpage);
                }
                put_page(kpage);
                return;
        }

        /*
         * If the hash value of the page has changed from the last time
         * we calculated it, this page is changing frequently: therefore we
         * don't want to insert it in the unstable tree, and we don't want
         * to waste our time searching for something identical to it there.
         */
        checksum = calc_checksum(page);
        if (rmap_item->oldchecksum != checksum) {
                rmap_item->oldchecksum = checksum;
                return;
        }

        tree_rmap_item =
                unstable_tree_search_insert(rmap_item, page, &tree_page);
        if (tree_rmap_item) {
                kpage = try_to_merge_two_pages(rmap_item, page,
                                                tree_rmap_item, tree_page);
                put_page(tree_page);
                if (kpage) {
                        /*
                         * The pages were successfully merged: insert new
                         * node in the stable tree and add both rmap_items.
                         */
                        lock_page(kpage);
                        stable_node = stable_tree_insert(kpage);
                        if (stable_node) {
                                stable_tree_append(tree_rmap_item, stable_node,
                                                   false);
                                stable_tree_append(rmap_item, stable_node,
                                                   false);
                        }
                        unlock_page(kpage);

                        /*
                         * If we fail to insert the page into the stable tree,
                         * we will have 2 virtual addresses that are pointing
                         * to a ksm page left outside the stable tree,
                         * in which case we need to break_cow on both.
                         */
                        if (!stable_node) {
                                break_cow(tree_rmap_item);
                                break_cow(rmap_item);
                        }
                }
        }
}

static struct rmap_item *get_next_rmap_item(struct mm_slot *mm_slot,
                                            struct rmap_item **rmap_list,
                                            unsigned long addr)
{
        struct rmap_item *rmap_item;

        while (*rmap_list) {
                rmap_item = *rmap_list;
                if ((rmap_item->address & PAGE_MASK) == addr)
                        return rmap_item;
                if (rmap_item->address > addr)
                        break;
                *rmap_list = rmap_item->rmap_list;
                remove_rmap_item_from_tree(rmap_item);
                free_rmap_item(rmap_item);
        }

        rmap_item = alloc_rmap_item();
        if (rmap_item) {
                /* It has already been zeroed */
                rmap_item->mm = mm_slot->mm;
                rmap_item->address = addr;
                rmap_item->rmap_list = *rmap_list;
                *rmap_list = rmap_item;
        }
        return rmap_item;
}

static struct rmap_item *scan_get_next_rmap_item(struct page **page)
{
        struct mm_struct *mm;
        struct mm_slot *slot;
        struct vm_area_struct *vma;
        struct rmap_item *rmap_item;
        int nid;

        if (list_empty(&ksm_mm_head.mm_list))
                return NULL;

        slot = ksm_scan.mm_slot;
        if (slot == &ksm_mm_head) {
                /*
                 * A number of pages can hang around indefinitely on per-cpu
                 * pagevecs, raised page count preventing write_protect_page
                 * from merging them.  Though it doesn't really matter much,
                 * it is puzzling to see some stuck in pages_volatile until
                 * other activity jostles them out, and they also prevented
                 * LTP's KSM test from succeeding deterministically; so drain
                 * them here (here rather than on entry to ksm_do_scan(),
                 * so we don't IPI too often when pages_to_scan is set low).
                 */
                lru_add_drain_all();

                /*
                 * Whereas stale stable_nodes on the stable_tree itself
                 * get pruned in the regular course of stable_tree_search(),
                 * those moved out to the migrate_nodes list can accumulate:
                 * so prune them once before each full scan.
                 */
                if (!ksm_merge_across_nodes) {
                        struct stable_node *stable_node, *next;
                        struct page *page;

                        list_for_each_entry_safe(stable_node, next,
                                                 &migrate_nodes, list) {
                                page = get_ksm_page(stable_node, false);
                                if (page)
                                        put_page(page);
                                cond_resched();
                        }
                }

                for (nid = 0; nid < ksm_nr_node_ids; nid++)
                        root_unstable_tree[nid] = RB_ROOT;

                spin_lock(&ksm_mmlist_lock);
                slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list);
                ksm_scan.mm_slot = slot;
                spin_unlock(&ksm_mmlist_lock);
                /*
                 * Although we tested list_empty() above, a racing __ksm_exit
                 * of the last mm on the list may have removed it since then.
                 */
                if (slot == &ksm_mm_head)
                        return NULL;
next_mm:
                ksm_scan.address = 0;
                ksm_scan.rmap_list = &slot->rmap_list;
        }

        mm = slot->mm;
        down_read(&mm->mmap_sem);
        if (ksm_test_exit(mm))
                vma = NULL;
        else
                vma = find_vma(mm, ksm_scan.address);

        for (; vma; vma = vma->vm_next) {
                if (!(vma->vm_flags & VM_MERGEABLE))
                        continue;
                if (ksm_scan.address < vma->vm_start)
                        ksm_scan.address = vma->vm_start;
                if (!vma->anon_vma)
                        ksm_scan.address = vma->vm_end;

                while (ksm_scan.address < vma->vm_end) {
                        if (ksm_test_exit(mm))
                                break;
                        *page = follow_page(vma, ksm_scan.address, FOLL_GET);
                        if (IS_ERR_OR_NULL(*page)) {
                                ksm_scan.address += PAGE_SIZE;
                                cond_resched();
                                continue;
                        }
                        if (PageAnon(*page)) {
                                flush_anon_page(vma, *page, ksm_scan.address);
                                flush_dcache_page(*page);
                                rmap_item = get_next_rmap_item(slot,
                                        ksm_scan.rmap_list, ksm_scan.address);
                                if (rmap_item) {
                                        ksm_scan.rmap_list =
                                                        &rmap_item->rmap_list;
                                        ksm_scan.address += PAGE_SIZE;
                                } else
                                        put_page(*page);
                                up_read(&mm->mmap_sem);
                                return rmap_item;
                        }
                        put_page(*page);
                        ksm_scan.address += PAGE_SIZE;
                        cond_resched();
                }
        }

        if (ksm_test_exit(mm)) {
                ksm_scan.address = 0;
                ksm_scan.rmap_list = &slot->rmap_list;
        }
        /*
         * Nuke all the rmap_items that are above this current rmap:
         * because there were no VM_MERGEABLE vmas with such addresses.
         */
        remove_trailing_rmap_items(slot, ksm_scan.rmap_list);

        spin_lock(&ksm_mmlist_lock);
        ksm_scan.mm_slot = list_entry(slot->mm_list.next,
                                                struct mm_slot, mm_list);
        if (ksm_scan.address == 0) {
                /*
                 * We've completed a full scan of all vmas, holding mmap_sem
                 * throughout, and found no VM_MERGEABLE: so do the same as
                 * __ksm_exit does to remove this mm from all our lists now.
                 * This applies either when cleaning up after __ksm_exit
                 * (but beware: we can reach here even before __ksm_exit),
                 * or when all VM_MERGEABLE areas have been unmapped (and
                 * mmap_sem then protects against race with MADV_MERGEABLE).
                 */
                hash_del(&slot->link);
                list_del(&slot->mm_list);
                spin_unlock(&ksm_mmlist_lock);

                free_mm_slot(slot);
                clear_bit(MMF_VM_MERGEABLE, &mm->flags);
                up_read(&mm->mmap_sem);
                mmdrop(mm);
        } else {
                spin_unlock(&ksm_mmlist_lock);
                up_read(&mm->mmap_sem);
        }

        /* Repeat until we've completed scanning the whole list */
        slot = ksm_scan.mm_slot;
        if (slot != &ksm_mm_head)
                goto next_mm;

        ksm_scan.seqnr++;
        return NULL;
}

/**
 * ksm_do_scan  - the ksm scanner main worker function.
 * @scan_npages - number of pages we want to scan before we return.
 */
static void ksm_do_scan(unsigned int scan_npages)
{
        struct rmap_item *rmap_item;
        struct page *uninitialized_var(page);

        while (scan_npages-- && likely(!freezing(current))) {
                cond_resched();
                rmap_item = scan_get_next_rmap_item(&page);
                if (!rmap_item)
                        return;
                cmp_and_merge_page(page, rmap_item);
                put_page(page);
        }
}

static int ksmd_should_run(void)
{
        return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.mm_list);
}

static int ksm_scan_thread(void *nothing)
{
        set_freezable();
        set_user_nice(current, 5);

        while (!kthread_should_stop()) {
                mutex_lock(&ksm_thread_mutex);
                wait_while_offlining();
                if (ksmd_should_run())
                        ksm_do_scan(ksm_thread_pages_to_scan);
                mutex_unlock(&ksm_thread_mutex);

                try_to_freeze();

                if (ksmd_should_run()) {
                        schedule_timeout_interruptible(
                                msecs_to_jiffies(ksm_thread_sleep_millisecs));
                } else {
                        wait_event_freezable(ksm_thread_wait,
                                ksmd_should_run() || kthread_should_stop());
                }
        }
        return 0;
}

int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
                unsigned long end, int advice, unsigned long *vm_flags)
{
        struct mm_struct *mm = vma->vm_mm;
        int err;

        switch (advice) {
        case MADV_MERGEABLE:
                /*
                 * Be somewhat over-protective for now!
                 */
                if (*vm_flags & (VM_MERGEABLE | VM_SHARED  | VM_MAYSHARE   |
                                 VM_PFNMAP    | VM_IO      | VM_DONTEXPAND |
                                 VM_HUGETLB | VM_MIXEDMAP))
                        return 0;               /* just ignore the advice */

#ifdef VM_SAO
                if (*vm_flags & VM_SAO)
                        return 0;
#endif

                if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
                        err = __ksm_enter(mm);
                        if (err)
                                return err;
                }

                *vm_flags |= VM_MERGEABLE;
                break;

        case MADV_UNMERGEABLE:
                if (!(*vm_flags & VM_MERGEABLE))
                        return 0;               /* just ignore the advice */

                if (vma->anon_vma) {
                        err = unmerge_ksm_pages(vma, start, end);
                        if (err)
                                return err;
                }

                *vm_flags &= ~VM_MERGEABLE;
                break;
        }

        return 0;
}

int __ksm_enter(struct mm_struct *mm)
{
        struct mm_slot *mm_slot;
        int needs_wakeup;

        mm_slot = alloc_mm_slot();
        if (!mm_slot)
                return -ENOMEM;

        /* Check ksm_run too?  Would need tighter locking */
        needs_wakeup = list_empty(&ksm_mm_head.mm_list);

        spin_lock(&ksm_mmlist_lock);
        insert_to_mm_slots_hash(mm, mm_slot);
        /*
         * When KSM_RUN_MERGE (or KSM_RUN_STOP),
         * insert just behind the scanning cursor, to let the area settle
         * down a little; when fork is followed by immediate exec, we don't
         * want ksmd to waste time setting up and tearing down an rmap_list.
         *
         * But when KSM_RUN_UNMERGE, it's important to insert ahead of its
         * scanning cursor, otherwise KSM pages in newly forked mms will be
         * missed: then we might as well insert at the end of the list.
         */
        if (ksm_run & KSM_RUN_UNMERGE)
                list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list);
        else
                list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list);
        spin_unlock(&ksm_mmlist_lock);

        set_bit(MMF_VM_MERGEABLE, &mm->flags);
        atomic_inc(&mm->mm_count);

        if (needs_wakeup)
                wake_up_interruptible(&ksm_thread_wait);

        return 0;
}

void __ksm_exit(struct mm_struct *mm)
{
        struct mm_slot *mm_slot;
        int easy_to_free = 0;

        /*
         * This process is exiting: if it's straightforward (as is the
         * case when ksmd was never running), free mm_slot immediately.
         * But if it's at the cursor or has rmap_items linked to it, use
         * mmap_sem to synchronize with any break_cows before pagetables
         * are freed, and leave the mm_slot on the list for ksmd to free.
         * Beware: ksm may already have noticed it exiting and freed the slot.
         */

        spin_lock(&ksm_mmlist_lock);
        mm_slot = get_mm_slot(mm);
        if (mm_slot && ksm_scan.mm_slot != mm_slot) {
                if (!mm_slot->rmap_list) {
                        hash_del(&mm_slot->link);
                        list_del(&mm_slot->mm_list);
                        easy_to_free = 1;
                } else {
                        list_move(&mm_slot->mm_list,
                                  &ksm_scan.mm_slot->mm_list);
                }
        }
        spin_unlock(&ksm_mmlist_lock);

        if (easy_to_free) {
                free_mm_slot(mm_slot);
                clear_bit(MMF_VM_MERGEABLE, &mm->flags);
                mmdrop(mm);
        } else if (mm_slot) {
                down_write(&mm->mmap_sem);
                up_write(&mm->mmap_sem);
        }
}

struct page *ksm_might_need_to_copy(struct page *page,
                        struct vm_area_struct *vma, unsigned long address)
{
        struct anon_vma *anon_vma = page_anon_vma(page);
        struct page *new_page;

        if (PageKsm(page)) {
                if (page_stable_node(page) &&
                    !(ksm_run & KSM_RUN_UNMERGE))
                        return page;    /* no need to copy it */
        } else if (!anon_vma) {
                return page;            /* no need to copy it */
        } else if (anon_vma->root == vma->anon_vma->root &&
                 page->index == linear_page_index(vma, address)) {
                return page;            /* still no need to copy it */
        }
        if (!PageUptodate(page))
                return page;            /* let do_swap_page report the error */

        new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
        if (new_page) {
                copy_user_highpage(new_page, page, address, vma);

                SetPageDirty(new_page);
                __SetPageUptodate(new_page);
                __SetPageLocked(new_page);
        }

        return new_page;
}

int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc)
{
        struct stable_node *stable_node;
        struct rmap_item *rmap_item;
        int ret = SWAP_AGAIN;
        int search_new_forks = 0;

        VM_BUG_ON_PAGE(!PageKsm(page), page);

        /*
         * Rely on the page lock to protect against concurrent modifications
         * to that page's node of the stable tree.
         */
        VM_BUG_ON_PAGE(!PageLocked(page), page);

        stable_node = page_stable_node(page);
        if (!stable_node)
                return ret;
again:
        hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
                struct anon_vma *anon_vma = rmap_item->anon_vma;
                struct anon_vma_chain *vmac;
                struct vm_area_struct *vma;

                cond_resched();
                anon_vma_lock_read(anon_vma);
                anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
                                               0, ULONG_MAX) {
                        cond_resched();
                        vma = vmac->vma;
                        if (rmap_item->address < vma->vm_start ||
                            rmap_item->address >= vma->vm_end)
                                continue;
                        /*
                         * Initially we examine only the vma which covers this
                         * rmap_item; but later, if there is still work to do,
                         * we examine covering vmas in other mms: in case they
                         * were forked from the original since ksmd passed.
                         */
                        if ((rmap_item->mm == vma->vm_mm) == search_new_forks)
                                continue;

                        if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
                                continue;

                        ret = rwc->rmap_one(page, vma,
                                        rmap_item->address, rwc->arg);
                        if (ret != SWAP_AGAIN) {
                                anon_vma_unlock_read(anon_vma);
                                goto out;
                        }
                        if (rwc->done && rwc->done(page)) {
                                anon_vma_unlock_read(anon_vma);
                                goto out;
                        }
                }
                anon_vma_unlock_read(anon_vma);
        }
        if (!search_new_forks++)
                goto again;
out:
        return ret;
}

#ifdef CONFIG_MIGRATION
void ksm_migrate_page(struct page *newpage, struct page *oldpage)
{
        struct stable_node *stable_node;

        VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
        VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
        VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage);

        stable_node = page_stable_node(newpage);
        if (stable_node) {
                VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage);
                stable_node->kpfn = page_to_pfn(newpage);
                /*
                 * newpage->mapping was set in advance; now we need smp_wmb()
                 * to make sure that the new stable_node->kpfn is visible
                 * to get_ksm_page() before it can see that oldpage->mapping
                 * has gone stale (or that PageSwapCache has been cleared).
                 */
                smp_wmb();
                set_page_stable_node(oldpage, NULL);
        }
}
#endif /* CONFIG_MIGRATION */

#ifdef CONFIG_MEMORY_HOTREMOVE
static void wait_while_offlining(void)
{
        while (ksm_run & KSM_RUN_OFFLINE) {
                mutex_unlock(&ksm_thread_mutex);
                wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE),
                            TASK_UNINTERRUPTIBLE);
                mutex_lock(&ksm_thread_mutex);
        }
}

static bool stable_node_dup_remove_range(struct stable_node *stable_node,
                                         unsigned long start_pfn,
                                         unsigned long end_pfn)
{
        if (stable_node->kpfn >= start_pfn &&
            stable_node->kpfn < end_pfn) {
                /*
                 * Don't get_ksm_page, page has already gone:
                 * which is why we keep kpfn instead of page*
                 */
                remove_node_from_stable_tree(stable_node);
                return true;
        }
        return false;
}

static bool stable_node_chain_remove_range(struct stable_node *stable_node,
                                           unsigned long start_pfn,
                                           unsigned long end_pfn,
                                           struct rb_root *root)
{
        struct stable_node *dup;
        struct hlist_node *hlist_safe;

        if (!is_stable_node_chain(stable_node)) {
                VM_BUG_ON(is_stable_node_dup(stable_node));
                return stable_node_dup_remove_range(stable_node, start_pfn,
                                                    end_pfn);
        }

        hlist_for_each_entry_safe(dup, hlist_safe,
                                  &stable_node->hlist, hlist_dup) {
                VM_BUG_ON(!is_stable_node_dup(dup));
                stable_node_dup_remove_range(dup, start_pfn, end_pfn);
        }
        if (hlist_empty(&stable_node->hlist)) {
                free_stable_node_chain(stable_node, root);
                return true; /* notify caller that tree was rebalanced */
        } else
                return false;
}

static void ksm_check_stable_tree(unsigned long start_pfn,
                                  unsigned long end_pfn)
{
        struct stable_node *stable_node, *next;
        struct rb_node *node;
        int nid;

        for (nid = 0; nid < ksm_nr_node_ids; nid++) {
                node = rb_first(root_stable_tree + nid);
                while (node) {
                        stable_node = rb_entry(node, struct stable_node, node);
                        if (stable_node_chain_remove_range(stable_node,
                                                           start_pfn, end_pfn,
                                                           root_stable_tree +
                                                           nid))
                                node = rb_first(root_stable_tree + nid);
                        else
                                node = rb_next(node);
                        cond_resched();
                }
        }
        list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) {
                if (stable_node->kpfn >= start_pfn &&
                    stable_node->kpfn < end_pfn)
                        remove_node_from_stable_tree(stable_node);
                cond_resched();
        }
}

static int ksm_memory_callback(struct notifier_block *self,
                               unsigned long action, void *arg)
{
        struct memory_notify *mn = arg;

        switch (action) {
        case MEM_GOING_OFFLINE:
                /*
                 * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items()
                 * and remove_all_stable_nodes() while memory is going offline:
                 * it is unsafe for them to touch the stable tree at this time.
                 * But unmerge_ksm_pages(), rmap lookups and other entry points
                 * which do not need the ksm_thread_mutex are all safe.
                 */
                mutex_lock(&ksm_thread_mutex);
                ksm_run |= KSM_RUN_OFFLINE;
                mutex_unlock(&ksm_thread_mutex);
                break;

        case MEM_OFFLINE:
                /*
                 * Most of the work is done by page migration; but there might
                 * be a few stable_nodes left over, still pointing to struct
                 * pages which have been offlined: prune those from the tree,
                 * otherwise get_ksm_page() might later try to access a
                 * non-existent struct page.
                 */
                ksm_check_stable_tree(mn->start_pfn,
                                      mn->start_pfn + mn->nr_pages);
                /* fallthrough */

        case MEM_CANCEL_OFFLINE:
                mutex_lock(&ksm_thread_mutex);
                ksm_run &= ~KSM_RUN_OFFLINE;
                mutex_unlock(&ksm_thread_mutex);

                smp_mb();       /* wake_up_bit advises this */
                wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE));
                break;
        }
        return NOTIFY_OK;
}
#else
static void wait_while_offlining(void)
{
}
#endif /* CONFIG_MEMORY_HOTREMOVE */

#ifdef CONFIG_SYSFS
/*
 * This all compiles without CONFIG_SYSFS, but is a waste of space.
 */

#define KSM_ATTR_RO(_name) \
        static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
#define KSM_ATTR(_name) \
        static struct kobj_attribute _name##_attr = \
                __ATTR(_name, 0644, _name##_show, _name##_store)

static ssize_t sleep_millisecs_show(struct kobject *kobj,
                                    struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%u\n", ksm_thread_sleep_millisecs);
}

static ssize_t sleep_millisecs_store(struct kobject *kobj,
                                     struct kobj_attribute *attr,
                                     const char *buf, size_t count)
{
        unsigned long msecs;
        int err;

        err = kstrtoul(buf, 10, &msecs);
        if (err || msecs > UINT_MAX)
                return -EINVAL;

        ksm_thread_sleep_millisecs = msecs;

        return count;
}
KSM_ATTR(sleep_millisecs);

static ssize_t pages_to_scan_show(struct kobject *kobj,
                                  struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%u\n", ksm_thread_pages_to_scan);
}

static ssize_t pages_to_scan_store(struct kobject *kobj,
                                   struct kobj_attribute *attr,
                                   const char *buf, size_t count)
{
        int err;
        unsigned long nr_pages;

        err = kstrtoul(buf, 10, &nr_pages);
        if (err || nr_pages > UINT_MAX)
                return -EINVAL;

        ksm_thread_pages_to_scan = nr_pages;

        return count;
}
KSM_ATTR(pages_to_scan);

static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr,
                        char *buf)
{
        return sprintf(buf, "%lu\n", ksm_run);
}

static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
                         const char *buf, size_t count)
{
        int err;
        unsigned long flags;

        err = kstrtoul(buf, 10, &flags);
        if (err || flags > UINT_MAX)
                return -EINVAL;
        if (flags > KSM_RUN_UNMERGE)
                return -EINVAL;

        /*
         * KSM_RUN_MERGE sets ksmd running, and 0 stops it running.
         * KSM_RUN_UNMERGE stops it running and unmerges all rmap_items,
         * breaking COW to free the pages_shared (but leaves mm_slots
         * on the list for when ksmd may be set running again).
         */

        mutex_lock(&ksm_thread_mutex);
        wait_while_offlining();
        if (ksm_run != flags) {
                ksm_run = flags;
                if (flags & KSM_RUN_UNMERGE) {
                        set_current_oom_origin();
                        err = unmerge_and_remove_all_rmap_items();
                        clear_current_oom_origin();
                        if (err) {
                                ksm_run = KSM_RUN_STOP;
                                count = err;
                        }
                }
        }
        mutex_unlock(&ksm_thread_mutex);

        if (flags & KSM_RUN_MERGE)
                wake_up_interruptible(&ksm_thread_wait);

        return count;
}
KSM_ATTR(run);

#ifdef CONFIG_NUMA
static ssize_t merge_across_nodes_show(struct kobject *kobj,
                                struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%u\n", ksm_merge_across_nodes);
}

static ssize_t merge_across_nodes_store(struct kobject *kobj,
                                   struct kobj_attribute *attr,
                                   const char *buf, size_t count)
{
        int err;
        unsigned long knob;

        err = kstrtoul(buf, 10, &knob);
        if (err)
                return err;
        if (knob > 1)
                return -EINVAL;

        mutex_lock(&ksm_thread_mutex);
        wait_while_offlining();
        if (ksm_merge_across_nodes != knob) {
                if (ksm_pages_shared || remove_all_stable_nodes())
                        err = -EBUSY;
                else if (root_stable_tree == one_stable_tree) {
                        struct rb_root *buf;
                        /*
                         * This is the first time that we switch away from the
                         * default of merging across nodes: must now allocate
                         * a buffer to hold as many roots as may be needed.
                         * Allocate stable and unstable together:
                         * MAXSMP NODES_SHIFT 10 will use 16kB.
                         */
                        buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf),
                                      GFP_KERNEL);
                        /* Let us assume that RB_ROOT is NULL is zero */
                        if (!buf)
                                err = -ENOMEM;
                        else {
                                root_stable_tree = buf;
                                root_unstable_tree = buf + nr_node_ids;
                                /* Stable tree is empty but not the unstable */
                                root_unstable_tree[0] = one_unstable_tree[0];
                        }
                }
                if (!err) {
                        ksm_merge_across_nodes = knob;
                        ksm_nr_node_ids = knob ? 1 : nr_node_ids;
                }
        }
        mutex_unlock(&ksm_thread_mutex);

        return err ? err : count;
}
KSM_ATTR(merge_across_nodes);
#endif

static ssize_t max_page_sharing_show(struct kobject *kobj,
                                     struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%u\n", ksm_max_page_sharing);
}

static ssize_t max_page_sharing_store(struct kobject *kobj,
                                      struct kobj_attribute *attr,
                                      const char *buf, size_t count)
{
        int err;
        int knob;

        err = kstrtoint(buf, 10, &knob);
        if (err)
                return err;
        /*
         * When a KSM page is created it is shared by 2 mappings. This
         * being a signed comparison, it implicitly verifies it's not
         * negative.
         */
        if (knob < 2)
                return -EINVAL;

        if (READ_ONCE(ksm_max_page_sharing) == knob)
                return count;

        mutex_lock(&ksm_thread_mutex);
        wait_while_offlining();
        if (ksm_max_page_sharing != knob) {
                if (ksm_pages_shared || remove_all_stable_nodes())
                        err = -EBUSY;
                else
                        ksm_max_page_sharing = knob;
        }
        mutex_unlock(&ksm_thread_mutex);

        return err ? err : count;
}
KSM_ATTR(max_page_sharing);

static ssize_t pages_shared_show(struct kobject *kobj,
                                 struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%lu\n", ksm_pages_shared);
}
KSM_ATTR_RO(pages_shared);

static ssize_t pages_sharing_show(struct kobject *kobj,
                                  struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%lu\n", ksm_pages_sharing);
}
KSM_ATTR_RO(pages_sharing);

static ssize_t pages_unshared_show(struct kobject *kobj,
                                   struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%lu\n", ksm_pages_unshared);
}
KSM_ATTR_RO(pages_unshared);

static ssize_t pages_volatile_show(struct kobject *kobj,
                                   struct kobj_attribute *attr, char *buf)
{
        long ksm_pages_volatile;

        ksm_pages_volatile = ksm_rmap_items - ksm_pages_shared
                                - ksm_pages_sharing - ksm_pages_unshared;
        /*
         * It was not worth any locking to calculate that statistic,
         * but it might therefore sometimes be negative: conceal that.
         */
        if (ksm_pages_volatile < 0)
                ksm_pages_volatile = 0;
        return sprintf(buf, "%ld\n", ksm_pages_volatile);
}
KSM_ATTR_RO(pages_volatile);

static ssize_t stable_node_dups_show(struct kobject *kobj,
                                     struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%lu\n", ksm_stable_node_dups);
}
KSM_ATTR_RO(stable_node_dups);

static ssize_t stable_node_chains_show(struct kobject *kobj,
                                       struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%lu\n", ksm_stable_node_chains);
}
KSM_ATTR_RO(stable_node_chains);

static ssize_t
stable_node_chains_prune_millisecs_show(struct kobject *kobj,
                                        struct kobj_attribute *attr,
                                        char *buf)
{
        return sprintf(buf, "%u\n", ksm_stable_node_chains_prune_millisecs);
}

static ssize_t
stable_node_chains_prune_millisecs_store(struct kobject *kobj,
                                         struct kobj_attribute *attr,
                                         const char *buf, size_t count)
{
        unsigned long msecs;
        int err;

        err = kstrtoul(buf, 10, &msecs);
        if (err || msecs > UINT_MAX)
                return -EINVAL;

        ksm_stable_node_chains_prune_millisecs = msecs;

        return count;
}
KSM_ATTR(stable_node_chains_prune_millisecs);

static ssize_t full_scans_show(struct kobject *kobj,
                               struct kobj_attribute *attr, char *buf)
{
        return sprintf(buf, "%lu\n", ksm_scan.seqnr);
}
KSM_ATTR_RO(full_scans);

static struct attribute *ksm_attrs[] = {
        &sleep_millisecs_attr.attr,
        &pages_to_scan_attr.attr,
        &run_attr.attr,
        &pages_shared_attr.attr,
        &pages_sharing_attr.attr,
        &pages_unshared_attr.attr,
        &pages_volatile_attr.attr,
        &full_scans_attr.attr,
#ifdef CONFIG_NUMA
        &merge_across_nodes_attr.attr,
#endif
        &max_page_sharing_attr.attr,
        &stable_node_chains_attr.attr,
        &stable_node_dups_attr.attr,
        &stable_node_chains_prune_millisecs_attr.attr,
        NULL,
};

static struct attribute_group ksm_attr_group = {
        .attrs = ksm_attrs,
        .name = "ksm",
};
#endif /* CONFIG_SYSFS */

static int __init ksm_init(void)
{
        struct task_struct *ksm_thread;
        int err;

        err = ksm_slab_init();
        if (err)
                goto out;

        ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd");
        if (IS_ERR(ksm_thread)) {
                pr_err("ksm: creating kthread failed\n");
                err = PTR_ERR(ksm_thread);
                goto out_free;
        }

#ifdef CONFIG_SYSFS
        err = sysfs_create_group(mm_kobj, &ksm_attr_group);
        if (err) {
                pr_err("ksm: register sysfs failed\n");
                kthread_stop(ksm_thread);
                goto out_free;
        }
#else
        ksm_run = KSM_RUN_MERGE;        /* no way for user to start it */

#endif /* CONFIG_SYSFS */

#ifdef CONFIG_MEMORY_HOTREMOVE
        /* There is no significance to this priority 100 */
        hotplug_memory_notifier(ksm_memory_callback, 100);
#endif
        return 0;

out_free:
        ksm_slab_free();
out:
        return err;
}
subsys_initcall(ksm_init);