// SPDX-License-Identifier: GPL-2.0-only

  /*
   * fs/dcache.c
   *
   * Complete reimplementation
   * (C) 1997 Thomas Schoebel-Theuer,
   * with heavy changes by Linus Torvalds
   */
  
  /*
   * Notes on the allocation strategy:
   *
   * The dcache is a master of the icache - whenever a dcache entry
   * exists, the inode will always exist. "iput()" is done either when
   * the dcache entry is deleted or garbage collected.
   */

  #include <linux/ratelimit.h>

  #include <linux/string.h>
  #include <linux/mm.h>
  #include <linux/fs.h>

  #include <linux/fscrypt.h>

  #include <linux/fsnotify.h>

  #include <linux/slab.h>
  #include <linux/init.h>

  #include <linux/hash.h>
  #include <linux/cache.h>

  #include <linux/export.h>

  #include <linux/security.h>
  #include <linux/seqlock.h>

  #include <linux/memblock.h>

  #include <linux/bit_spinlock.h>
  #include <linux/rculist_bl.h>

  #include <linux/list_lru.h>

  #include "internal.h"

  #include "mount.h"

  /*
   * Usage:

   * dcache->d_inode->i_lock protects:

   *   - i_dentry, d_u.d_alias, d_inode of aliases

   * dcache_hash_bucket lock protects:
   *   - the dcache hash table

   * s_roots bl list spinlock protects:
   *   - the s_roots list (see __d_drop)

   * dentry->d_sb->s_dentry_lru_lock protects:

   *   - the dcache lru lists and counters
   * d_lock protects:
   *   - d_flags
   *   - d_name
   *   - d_lru

   *   - d_count

   *   - d_unhashed()

   *   - d_parent and d_subdirs
   *   - childrens' d_child and d_parent

   *   - d_u.d_alias, d_inode

   *
   * Ordering:

   * dentry->d_inode->i_lock

   *   dentry->d_lock

   *     dentry->d_sb->s_dentry_lru_lock

   *     dcache_hash_bucket lock

   *     s_roots lock

   *

   * If there is an ancestor relationship:
   * dentry->d_parent->...->d_parent->d_lock
   *   ...
   *     dentry->d_parent->d_lock
   *       dentry->d_lock
   *
   * If no ancestor relationship:

   * arbitrary, since it's serialized on rename_lock

   */

  int sysctl_vfs_cache_pressure __read_mostly = 100;

  EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);

  __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);

  EXPORT_SYMBOL(rename_lock);

  static struct kmem_cache *dentry_cache __read_mostly;

  const struct qstr empty_name = QSTR_INIT("", 0);
  EXPORT_SYMBOL(empty_name);
  const struct qstr slash_name = QSTR_INIT("/", 1);
  EXPORT_SYMBOL(slash_name);

  /*
   * This is the single most critical data structure when it comes
   * to the dcache: the hashtable for lookups. Somebody should try
   * to make this good - I've just made it work.
   *
   * This hash-function tries to avoid losing too many bits of hash
   * information, yet avoid using a prime hash-size or similar.
   */

  static unsigned int d_hash_shift __read_mostly;

  static struct hlist_bl_head *dentry_hashtable __read_mostly;

  static inline struct hlist_bl_head *d_hash(unsigned int hash)

  {

  	return dentry_hashtable + (hash >> d_hash_shift);

  }

  #define IN_LOOKUP_SHIFT 10
  static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT];
  
  static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent,
  					unsigned int hash)
  {
  	hash += (unsigned long) parent / L1_CACHE_BYTES;
  	return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT);
  }

  /* Statistics gathering. */
  struct dentry_stat_t dentry_stat = {
  	.age_limit = 45,
  };

  static DEFINE_PER_CPU(long, nr_dentry);

  static DEFINE_PER_CPU(long, nr_dentry_unused);

  static DEFINE_PER_CPU(long, nr_dentry_negative);

  
  #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)

  
  /*
   * Here we resort to our own counters instead of using generic per-cpu counters
   * for consistency with what the vfs inode code does. We are expected to harvest
   * better code and performance by having our own specialized counters.
   *
   * Please note that the loop is done over all possible CPUs, not over all online
   * CPUs. The reason for this is that we don't want to play games with CPUs going
   * on and off. If one of them goes off, we will just keep their counters.
   *
   * glommer: See cffbc8a for details, and if you ever intend to change this,
   * please update all vfs counters to match.
   */

  static long get_nr_dentry(void)

  {
  	int i;

  	long sum = 0;

  	for_each_possible_cpu(i)
  		sum += per_cpu(nr_dentry, i);
  	return sum < 0 ? 0 : sum;
  }

  static long get_nr_dentry_unused(void)
  {
  	int i;
  	long sum = 0;
  	for_each_possible_cpu(i)
  		sum += per_cpu(nr_dentry_unused, i);
  	return sum < 0 ? 0 : sum;
  }

  static long get_nr_dentry_negative(void)
  {
  	int i;
  	long sum = 0;
  
  	for_each_possible_cpu(i)
  		sum += per_cpu(nr_dentry_negative, i);
  	return sum < 0 ? 0 : sum;
  }

  int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer,

  		   size_t *lenp, loff_t *ppos)
  {

  	dentry_stat.nr_dentry = get_nr_dentry();

  	dentry_stat.nr_unused = get_nr_dentry_unused();

  	dentry_stat.nr_negative = get_nr_dentry_negative();

  	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);

  }
  #endif

  /*
   * Compare 2 name strings, return 0 if they match, otherwise non-zero.
   * The strings are both count bytes long, and count is non-zero.
   */

  #ifdef CONFIG_DCACHE_WORD_ACCESS
  
  #include <asm/word-at-a-time.h>
  /*
   * NOTE! 'cs' and 'scount' come from a dentry, so it has a
   * aligned allocation for this particular component. We don't
   * strictly need the load_unaligned_zeropad() safety, but it
   * doesn't hurt either.
   *
   * In contrast, 'ct' and 'tcount' can be from a pathname, and do
   * need the careful unaligned handling.
   */

  static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)

  {

  	unsigned long a,b,mask;

  
  	for (;;) {

  		a = read_word_at_a_time(cs);

  		b = load_unaligned_zeropad(ct);

  		if (tcount < sizeof(unsigned long))
  			break;
  		if (unlikely(a != b))
  			return 1;
  		cs += sizeof(unsigned long);
  		ct += sizeof(unsigned long);
  		tcount -= sizeof(unsigned long);
  		if (!tcount)
  			return 0;
  	}

  	mask = bytemask_from_count(tcount);

  	return unlikely(!!((a ^ b) & mask));

  }

  #else

  static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)

  {

  	do {
  		if (*cs != *ct)
  			return 1;
  		cs++;
  		ct++;
  		tcount--;
  	} while (tcount);
  	return 0;
  }

  #endif

  static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount)
  {

  	/*
  	 * Be careful about RCU walk racing with rename:

  	 * use 'READ_ONCE' to fetch the name pointer.

  	 *
  	 * NOTE! Even if a rename will mean that the length
  	 * was not loaded atomically, we don't care. The
  	 * RCU walk will check the sequence count eventually,
  	 * and catch it. And we won't overrun the buffer,
  	 * because we're reading the name pointer atomically,
  	 * and a dentry name is guaranteed to be properly
  	 * terminated with a NUL byte.
  	 *
  	 * End result: even if 'len' is wrong, we'll exit
  	 * early because the data cannot match (there can
  	 * be no NUL in the ct/tcount data)
  	 */

  	const unsigned char *cs = READ_ONCE(dentry->d_name.name);

  	return dentry_string_cmp(cs, ct, tcount);

  }

  struct external_name {
  	union {
  		atomic_t count;
  		struct rcu_head head;
  	} u;
  	unsigned char name[];
  };
  
  static inline struct external_name *external_name(struct dentry *dentry)
  {
  	return container_of(dentry->d_name.name, struct external_name, name[0]);
  }

  static void __d_free(struct rcu_head *head)

  {

  	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);

  	kmem_cache_free(dentry_cache, dentry); 
  }
  
  static void __d_free_external(struct rcu_head *head)
  {
  	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);

  	kfree(external_name(dentry));

  	kmem_cache_free(dentry_cache, dentry);

  }

  static inline int dname_external(const struct dentry *dentry)
  {
  	return dentry->d_name.name != dentry->d_iname;
  }

  void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry)
  {
  	spin_lock(&dentry->d_lock);

  	name->name = dentry->d_name;

  	if (unlikely(dname_external(dentry))) {

  		atomic_inc(&external_name(dentry)->u.count);

  	} else {

  		memcpy(name->inline_name, dentry->d_iname,
  		       dentry->d_name.len + 1);

  		name->name.name = name->inline_name;

  	}

  	spin_unlock(&dentry->d_lock);

  }
  EXPORT_SYMBOL(take_dentry_name_snapshot);
  
  void release_dentry_name_snapshot(struct name_snapshot *name)
  {

  	if (unlikely(name->name.name != name->inline_name)) {

  		struct external_name *p;

  		p = container_of(name->name.name, struct external_name, name[0]);

  		if (unlikely(atomic_dec_and_test(&p->u.count)))

  			kfree_rcu(p, u.head);

  	}
  }
  EXPORT_SYMBOL(release_dentry_name_snapshot);

  static inline void __d_set_inode_and_type(struct dentry *dentry,
  					  struct inode *inode,
  					  unsigned type_flags)
  {
  	unsigned flags;
  
  	dentry->d_inode = inode;

  	flags = READ_ONCE(dentry->d_flags);
  	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
  	flags |= type_flags;
  	WRITE_ONCE(dentry->d_flags, flags);
  }

  static inline void __d_clear_type_and_inode(struct dentry *dentry)
  {
  	unsigned flags = READ_ONCE(dentry->d_flags);
  
  	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
  	WRITE_ONCE(dentry->d_flags, flags);

  	dentry->d_inode = NULL;

  	if (dentry->d_flags & DCACHE_LRU_LIST)
  		this_cpu_inc(nr_dentry_negative);

  }

  static void dentry_free(struct dentry *dentry)
  {

  	WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));

  	if (unlikely(dname_external(dentry))) {
  		struct external_name *p = external_name(dentry);
  		if (likely(atomic_dec_and_test(&p->u.count))) {
  			call_rcu(&dentry->d_u.d_rcu, __d_free_external);
  			return;
  		}
  	}

  	/* if dentry was never visible to RCU, immediate free is OK */

  	if (dentry->d_flags & DCACHE_NORCU)

  		__d_free(&dentry->d_u.d_rcu);
  	else
  		call_rcu(&dentry->d_u.d_rcu, __d_free);
  }

  /*
   * Release the dentry's inode, using the filesystem

   * d_iput() operation if defined.

   */
  static void dentry_unlink_inode(struct dentry * dentry)
  	__releases(dentry->d_lock)

  	__releases(dentry->d_inode->i_lock)

  {
  	struct inode *inode = dentry->d_inode;

  	raw_write_seqcount_begin(&dentry->d_seq);

  	__d_clear_type_and_inode(dentry);

  	hlist_del_init(&dentry->d_u.d_alias);

  	raw_write_seqcount_end(&dentry->d_seq);

  	spin_unlock(&dentry->d_lock);

  	spin_unlock(&inode->i_lock);

  	if (!inode->i_nlink)
  		fsnotify_inoderemove(inode);
  	if (dentry->d_op && dentry->d_op->d_iput)
  		dentry->d_op->d_iput(dentry, inode);
  	else
  		iput(inode);
  }
  
  /*

   * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry
   * is in use - which includes both the "real" per-superblock
   * LRU list _and_ the DCACHE_SHRINK_LIST use.
   *
   * The DCACHE_SHRINK_LIST bit is set whenever the dentry is
   * on the shrink list (ie not on the superblock LRU list).
   *
   * The per-cpu "nr_dentry_unused" counters are updated with
   * the DCACHE_LRU_LIST bit.
   *

   * The per-cpu "nr_dentry_negative" counters are only updated
   * when deleted from or added to the per-superblock LRU list, not
   * from/to the shrink list. That is to avoid an unneeded dec/inc
   * pair when moving from LRU to shrink list in select_collect().
   *

   * These helper functions make sure we always follow the
   * rules. d_lock must be held by the caller.
   */
  #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x))
  static void d_lru_add(struct dentry *dentry)
  {
  	D_FLAG_VERIFY(dentry, 0);
  	dentry->d_flags |= DCACHE_LRU_LIST;
  	this_cpu_inc(nr_dentry_unused);

  	if (d_is_negative(dentry))
  		this_cpu_inc(nr_dentry_negative);

  	WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
  }
  
  static void d_lru_del(struct dentry *dentry)
  {
  	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
  	dentry->d_flags &= ~DCACHE_LRU_LIST;
  	this_cpu_dec(nr_dentry_unused);

  	if (d_is_negative(dentry))
  		this_cpu_dec(nr_dentry_negative);

  	WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
  }
  
  static void d_shrink_del(struct dentry *dentry)
  {
  	D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
  	list_del_init(&dentry->d_lru);
  	dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
  	this_cpu_dec(nr_dentry_unused);
  }
  
  static void d_shrink_add(struct dentry *dentry, struct list_head *list)
  {
  	D_FLAG_VERIFY(dentry, 0);
  	list_add(&dentry->d_lru, list);
  	dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST;
  	this_cpu_inc(nr_dentry_unused);
  }
  
  /*
   * These can only be called under the global LRU lock, ie during the
   * callback for freeing the LRU list. "isolate" removes it from the
   * LRU lists entirely, while shrink_move moves it to the indicated
   * private list.
   */

  static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry)

  {
  	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
  	dentry->d_flags &= ~DCACHE_LRU_LIST;
  	this_cpu_dec(nr_dentry_unused);

  	if (d_is_negative(dentry))
  		this_cpu_dec(nr_dentry_negative);

  	list_lru_isolate(lru, &dentry->d_lru);

  }

  static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry,
  			      struct list_head *list)

  {
  	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
  	dentry->d_flags |= DCACHE_SHRINK_LIST;

  	if (d_is_negative(dentry))
  		this_cpu_dec(nr_dentry_negative);

  	list_lru_isolate_move(lru, &dentry->d_lru, list);

  }

  /**

   * d_drop - drop a dentry
   * @dentry: dentry to drop
   *
   * d_drop() unhashes the entry from the parent dentry hashes, so that it won't
   * be found through a VFS lookup any more. Note that this is different from
   * deleting the dentry - d_delete will try to mark the dentry negative if
   * possible, giving a successful _negative_ lookup, while d_drop will
   * just make the cache lookup fail.
   *
   * d_drop() is used mainly for stuff that wants to invalidate a dentry for some
   * reason (NFS timeouts or autofs deletes).
   *

   * __d_drop requires dentry->d_lock
   * ___d_drop doesn't mark dentry as "unhashed"
   *   (dentry->d_hash.pprev will be LIST_POISON2, not NULL).

   */

  static void ___d_drop(struct dentry *dentry)

  {

  	struct hlist_bl_head *b;
  	/*
  	 * Hashed dentries are normally on the dentry hashtable,
  	 * with the exception of those newly allocated by
  	 * d_obtain_root, which are always IS_ROOT:
  	 */
  	if (unlikely(IS_ROOT(dentry)))
  		b = &dentry->d_sb->s_roots;
  	else
  		b = d_hash(dentry->d_name.hash);

  	hlist_bl_lock(b);
  	__hlist_bl_del(&dentry->d_hash);
  	hlist_bl_unlock(b);

  }

  
  void __d_drop(struct dentry *dentry)
  {

  	if (!d_unhashed(dentry)) {
  		___d_drop(dentry);
  		dentry->d_hash.pprev = NULL;
  		write_seqcount_invalidate(&dentry->d_seq);
  	}

  }

  EXPORT_SYMBOL(__d_drop);
  
  void d_drop(struct dentry *dentry)
  {

  	spin_lock(&dentry->d_lock);
  	__d_drop(dentry);
  	spin_unlock(&dentry->d_lock);

  }
  EXPORT_SYMBOL(d_drop);

  static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent)
  {
  	struct dentry *next;
  	/*
  	 * Inform d_walk() and shrink_dentry_list() that we are no longer
  	 * attached to the dentry tree
  	 */
  	dentry->d_flags |= DCACHE_DENTRY_KILLED;
  	if (unlikely(list_empty(&dentry->d_child)))
  		return;
  	__list_del_entry(&dentry->d_child);
  	/*
  	 * Cursors can move around the list of children.  While we'd been
  	 * a normal list member, it didn't matter - ->d_child.next would've
  	 * been updated.  However, from now on it won't be and for the
  	 * things like d_walk() it might end up with a nasty surprise.
  	 * Normally d_walk() doesn't care about cursors moving around -
  	 * ->d_lock on parent prevents that and since a cursor has no children
  	 * of its own, we get through it without ever unlocking the parent.
  	 * There is one exception, though - if we ascend from a child that
  	 * gets killed as soon as we unlock it, the next sibling is found
  	 * using the value left in its ->d_child.next.  And if _that_
  	 * pointed to a cursor, and cursor got moved (e.g. by lseek())
  	 * before d_walk() regains parent->d_lock, we'll end up skipping
  	 * everything the cursor had been moved past.
  	 *
  	 * Solution: make sure that the pointer left behind in ->d_child.next
  	 * points to something that won't be moving around.  I.e. skip the
  	 * cursors.
  	 */
  	while (dentry->d_child.next != &parent->d_subdirs) {
  		next = list_entry(dentry->d_child.next, struct dentry, d_child);
  		if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR)))
  			break;
  		dentry->d_child.next = next->d_child.next;
  	}
  }

  static void __dentry_kill(struct dentry *dentry)

  {

  	struct dentry *parent = NULL;
  	bool can_free = true;

  	if (!IS_ROOT(dentry))

  		parent = dentry->d_parent;

  	/*
  	 * The dentry is now unrecoverably dead to the world.
  	 */
  	lockref_mark_dead(&dentry->d_lockref);

  	/*

  	 * inform the fs via d_prune that this dentry is about to be
  	 * unhashed and destroyed.
  	 */

  	if (dentry->d_flags & DCACHE_OP_PRUNE)

  		dentry->d_op->d_prune(dentry);

  	if (dentry->d_flags & DCACHE_LRU_LIST) {
  		if (!(dentry->d_flags & DCACHE_SHRINK_LIST))
  			d_lru_del(dentry);

  	}

  	/* if it was on the hash then remove it */
  	__d_drop(dentry);

  	dentry_unlist(dentry, parent);

  	if (parent)
  		spin_unlock(&parent->d_lock);

  	if (dentry->d_inode)
  		dentry_unlink_inode(dentry);
  	else
  		spin_unlock(&dentry->d_lock);

  	this_cpu_dec(nr_dentry);
  	if (dentry->d_op && dentry->d_op->d_release)
  		dentry->d_op->d_release(dentry);

  	spin_lock(&dentry->d_lock);
  	if (dentry->d_flags & DCACHE_SHRINK_LIST) {
  		dentry->d_flags |= DCACHE_MAY_FREE;
  		can_free = false;
  	}
  	spin_unlock(&dentry->d_lock);

  	if (likely(can_free))
  		dentry_free(dentry);

  	cond_resched();

  }

  static struct dentry *__lock_parent(struct dentry *dentry)

  {

  	struct dentry *parent;

  	rcu_read_lock();

  	spin_unlock(&dentry->d_lock);

  again:

  	parent = READ_ONCE(dentry->d_parent);

  	spin_lock(&parent->d_lock);
  	/*
  	 * We can't blindly lock dentry until we are sure
  	 * that we won't violate the locking order.
  	 * Any changes of dentry->d_parent must have
  	 * been done with parent->d_lock held, so
  	 * spin_lock() above is enough of a barrier
  	 * for checking if it's still our child.
  	 */
  	if (unlikely(parent != dentry->d_parent)) {
  		spin_unlock(&parent->d_lock);
  		goto again;
  	}

  	rcu_read_unlock();
  	if (parent != dentry)

  		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);

  	else

  		parent = NULL;
  	return parent;
  }

  static inline struct dentry *lock_parent(struct dentry *dentry)
  {
  	struct dentry *parent = dentry->d_parent;
  	if (IS_ROOT(dentry))
  		return NULL;
  	if (likely(spin_trylock(&parent->d_lock)))
  		return parent;
  	return __lock_parent(dentry);
  }

  static inline bool retain_dentry(struct dentry *dentry)
  {
  	WARN_ON(d_in_lookup(dentry));
  
  	/* Unreachable? Get rid of it */
  	if (unlikely(d_unhashed(dentry)))
  		return false;
  
  	if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
  		return false;
  
  	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) {
  		if (dentry->d_op->d_delete(dentry))
  			return false;
  	}

  	/* retain; LRU fodder */
  	dentry->d_lockref.count--;
  	if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST)))
  		d_lru_add(dentry);
  	else if (unlikely(!(dentry->d_flags & DCACHE_REFERENCED)))
  		dentry->d_flags |= DCACHE_REFERENCED;

  	return true;
  }

  /*

   * Finish off a dentry we've decided to kill.
   * dentry->d_lock must be held, returns with it unlocked.
   * Returns dentry requiring refcount drop, or NULL if we're done.
   */
  static struct dentry *dentry_kill(struct dentry *dentry)
  	__releases(dentry->d_lock)
  {
  	struct inode *inode = dentry->d_inode;
  	struct dentry *parent = NULL;
  
  	if (inode && unlikely(!spin_trylock(&inode->i_lock)))

  		goto slow_positive;

  
  	if (!IS_ROOT(dentry)) {
  		parent = dentry->d_parent;
  		if (unlikely(!spin_trylock(&parent->d_lock))) {

  			parent = __lock_parent(dentry);
  			if (likely(inode || !dentry->d_inode))
  				goto got_locks;
  			/* negative that became positive */
  			if (parent)
  				spin_unlock(&parent->d_lock);
  			inode = dentry->d_inode;
  			goto slow_positive;

  		}
  	}

  	__dentry_kill(dentry);
  	return parent;

  slow_positive:
  	spin_unlock(&dentry->d_lock);
  	spin_lock(&inode->i_lock);
  	spin_lock(&dentry->d_lock);
  	parent = lock_parent(dentry);
  got_locks:
  	if (unlikely(dentry->d_lockref.count != 1)) {
  		dentry->d_lockref.count--;
  	} else if (likely(!retain_dentry(dentry))) {
  		__dentry_kill(dentry);
  		return parent;
  	}
  	/* we are keeping it, after all */
  	if (inode)
  		spin_unlock(&inode->i_lock);
  	if (parent)
  		spin_unlock(&parent->d_lock);

  	spin_unlock(&dentry->d_lock);

  	return NULL;

  }
  
  /*

   * Try to do a lockless dput(), and return whether that was successful.
   *
   * If unsuccessful, we return false, having already taken the dentry lock.
   *
   * The caller needs to hold the RCU read lock, so that the dentry is
   * guaranteed to stay around even if the refcount goes down to zero!
   */
  static inline bool fast_dput(struct dentry *dentry)
  {
  	int ret;
  	unsigned int d_flags;
  
  	/*
  	 * If we have a d_op->d_delete() operation, we sould not

  	 * let the dentry count go to zero, so use "put_or_lock".

  	 */
  	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE))
  		return lockref_put_or_lock(&dentry->d_lockref);
  
  	/*
  	 * .. otherwise, we can try to just decrement the
  	 * lockref optimistically.
  	 */
  	ret = lockref_put_return(&dentry->d_lockref);
  
  	/*
  	 * If the lockref_put_return() failed due to the lock being held
  	 * by somebody else, the fast path has failed. We will need to
  	 * get the lock, and then check the count again.
  	 */
  	if (unlikely(ret < 0)) {
  		spin_lock(&dentry->d_lock);
  		if (dentry->d_lockref.count > 1) {
  			dentry->d_lockref.count--;
  			spin_unlock(&dentry->d_lock);

  			return true;

  		}

  		return false;

  	}
  
  	/*
  	 * If we weren't the last ref, we're done.
  	 */
  	if (ret)

  		return true;

  
  	/*
  	 * Careful, careful. The reference count went down
  	 * to zero, but we don't hold the dentry lock, so
  	 * somebody else could get it again, and do another
  	 * dput(), and we need to not race with that.
  	 *
  	 * However, there is a very special and common case
  	 * where we don't care, because there is nothing to
  	 * do: the dentry is still hashed, it does not have
  	 * a 'delete' op, and it's referenced and already on
  	 * the LRU list.
  	 *
  	 * NOTE! Since we aren't locked, these values are
  	 * not "stable". However, it is sufficient that at
  	 * some point after we dropped the reference the
  	 * dentry was hashed and the flags had the proper
  	 * value. Other dentry users may have re-gotten
  	 * a reference to the dentry and change that, but
  	 * our work is done - we can leave the dentry
  	 * around with a zero refcount.
  	 */
  	smp_rmb();

  	d_flags = READ_ONCE(dentry->d_flags);

  	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED;

  
  	/* Nothing to do? Dropping the reference was all we needed? */
  	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))

  		return true;

  
  	/*
  	 * Not the fast normal case? Get the lock. We've already decremented
  	 * the refcount, but we'll need to re-check the situation after
  	 * getting the lock.
  	 */
  	spin_lock(&dentry->d_lock);
  
  	/*
  	 * Did somebody else grab a reference to it in the meantime, and
  	 * we're no longer the last user after all? Alternatively, somebody
  	 * else could have killed it and marked it dead. Either way, we
  	 * don't need to do anything else.
  	 */
  	if (dentry->d_lockref.count) {
  		spin_unlock(&dentry->d_lock);

  		return true;

  	}
  
  	/*
  	 * Re-get the reference we optimistically dropped. We hold the
  	 * lock, and we just tested that it was zero, so we can just
  	 * set it to 1.
  	 */
  	dentry->d_lockref.count = 1;

  	return false;

  }

  /* 
   * This is dput
   *
   * This is complicated by the fact that we do not want to put
   * dentries that are no longer on any hash chain on the unused
   * list: we'd much rather just get rid of them immediately.
   *
   * However, that implies that we have to traverse the dentry
   * tree upwards to the parents which might _also_ now be
   * scheduled for deletion (it may have been only waiting for
   * its last child to go away).
   *
   * This tail recursion is done by hand as we don't want to depend
   * on the compiler to always get this right (gcc generally doesn't).
   * Real recursion would eat up our stack space.
   */
  
  /*
   * dput - release a dentry
   * @dentry: dentry to release 
   *
   * Release a dentry. This will drop the usage count and if appropriate
   * call the dentry unlink method as well as removing it from the queues and
   * releasing its resources. If the parent dentries were scheduled for release
   * they too may now get deleted.

   */

  void dput(struct dentry *dentry)
  {

  	while (dentry) {
  		might_sleep();

  		rcu_read_lock();
  		if (likely(fast_dput(dentry))) {
  			rcu_read_unlock();
  			return;
  		}

  		/* Slow case: now with the dentry lock held */

  		rcu_read_unlock();

  		if (likely(retain_dentry(dentry))) {
  			spin_unlock(&dentry->d_lock);
  			return;
  		}

  		dentry = dentry_kill(dentry);

  	}

  }

  EXPORT_SYMBOL(dput);

  static void __dput_to_list(struct dentry *dentry, struct list_head *list)
  __must_hold(&dentry->d_lock)
  {
  	if (dentry->d_flags & DCACHE_SHRINK_LIST) {
  		/* let the owner of the list it's on deal with it */
  		--dentry->d_lockref.count;
  	} else {
  		if (dentry->d_flags & DCACHE_LRU_LIST)
  			d_lru_del(dentry);
  		if (!--dentry->d_lockref.count)
  			d_shrink_add(dentry, list);
  	}
  }
  
  void dput_to_list(struct dentry *dentry, struct list_head *list)
  {
  	rcu_read_lock();
  	if (likely(fast_dput(dentry))) {
  		rcu_read_unlock();
  		return;
  	}
  	rcu_read_unlock();
  	if (!retain_dentry(dentry))
  		__dput_to_list(dentry, list);
  	spin_unlock(&dentry->d_lock);
  }

  /* This must be called with d_lock held */

  static inline void __dget_dlock(struct dentry *dentry)

  {

  	dentry->d_lockref.count++;

  }

  static inline void __dget(struct dentry *dentry)

  {

  	lockref_get(&dentry->d_lockref);

  }

  struct dentry *dget_parent(struct dentry *dentry)
  {

  	int gotref;

  	struct dentry *ret;

  	unsigned seq;

  	/*
  	 * Do optimistic parent lookup without any
  	 * locking.
  	 */
  	rcu_read_lock();

  	seq = raw_seqcount_begin(&dentry->d_seq);

  	ret = READ_ONCE(dentry->d_parent);

  	gotref = lockref_get_not_zero(&ret->d_lockref);
  	rcu_read_unlock();
  	if (likely(gotref)) {

  		if (!read_seqcount_retry(&dentry->d_seq, seq))

  			return ret;
  		dput(ret);
  	}

  repeat:

  	/*
  	 * Don't need rcu_dereference because we re-check it was correct under
  	 * the lock.
  	 */
  	rcu_read_lock();

  	ret = dentry->d_parent;

  	spin_lock(&ret->d_lock);
  	if (unlikely(ret != dentry->d_parent)) {
  		spin_unlock(&ret->d_lock);
  		rcu_read_unlock();

  		goto repeat;
  	}

  	rcu_read_unlock();

  	BUG_ON(!ret->d_lockref.count);
  	ret->d_lockref.count++;

  	spin_unlock(&ret->d_lock);

  	return ret;
  }
  EXPORT_SYMBOL(dget_parent);

  static struct dentry * __d_find_any_alias(struct inode *inode)
  {
  	struct dentry *alias;
  
  	if (hlist_empty(&inode->i_dentry))
  		return NULL;
  	alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
  	__dget(alias);
  	return alias;
  }
  
  /**
   * d_find_any_alias - find any alias for a given inode
   * @inode: inode to find an alias for
   *
   * If any aliases exist for the given inode, take and return a
   * reference for one of them.  If no aliases exist, return %NULL.
   */
  struct dentry *d_find_any_alias(struct inode *inode)
  {
  	struct dentry *de;
  
  	spin_lock(&inode->i_lock);
  	de = __d_find_any_alias(inode);
  	spin_unlock(&inode->i_lock);
  	return de;
  }
  EXPORT_SYMBOL(d_find_any_alias);

  /**
   * d_find_alias - grab a hashed alias of inode
   * @inode: inode in question

   *
   * If inode has a hashed alias, or is a directory and has any alias,
   * acquire the reference to alias and return it. Otherwise return NULL.
   * Notice that if inode is a directory there can be only one alias and
   * it can be unhashed only if it has no children, or if it is the root

   * of a filesystem, or if the directory was renamed and d_revalidate
   * was the first vfs operation to notice.

   *

   * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer

   * any other hashed alias over that one.

   */

  static struct dentry *__d_find_alias(struct inode *inode)

  {

  	struct dentry *alias;
  
  	if (S_ISDIR(inode->i_mode))
  		return __d_find_any_alias(inode);

  	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {

  		spin_lock(&alias->d_lock);

   		if (!d_unhashed(alias)) {

  			__dget_dlock(alias);
  			spin_unlock(&alias->d_lock);
  			return alias;

  		}

  		spin_unlock(&alias->d_lock);

  	}

  	return NULL;

  }

  struct dentry *d_find_alias(struct inode *inode)

  {

  	struct dentry *de = NULL;

  	if (!hlist_empty(&inode->i_dentry)) {

  		spin_lock(&inode->i_lock);

  		de = __d_find_alias(inode);

  		spin_unlock(&inode->i_lock);

  	}

  	return de;
  }

  EXPORT_SYMBOL(d_find_alias);

  
  /*
   *	Try to kill dentries associated with this inode.
   * WARNING: you must own a reference to inode.
   */
  void d_prune_aliases(struct inode *inode)
  {

  	struct dentry *dentry;

  restart:

  	spin_lock(&inode->i_lock);

  	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {

  		spin_lock(&dentry->d_lock);

  		if (!dentry->d_lockref.count) {

  			struct dentry *parent = lock_parent(dentry);
  			if (likely(!dentry->d_lockref.count)) {
  				__dentry_kill(dentry);

  				dput(parent);

  				goto restart;
  			}
  			if (parent)
  				spin_unlock(&parent->d_lock);

  		}
  		spin_unlock(&dentry->d_lock);
  	}

  	spin_unlock(&inode->i_lock);

  }

  EXPORT_SYMBOL(d_prune_aliases);

  /*
   * Lock a dentry from shrink list.

   * Called under rcu_read_lock() and dentry->d_lock; the former
   * guarantees that nothing we access will be freed under us.

   * Note that dentry is *not* protected from concurrent dentry_kill(),

   * d_delete(), etc.
   *

   * Return false if dentry has been disrupted or grabbed, leaving
   * the caller to kick it off-list.  Otherwise, return true and have
   * that dentry's inode and parent both locked.
   */
  static bool shrink_lock_dentry(struct dentry *dentry)

  {

  	struct inode *inode;
  	struct dentry *parent;

  	if (dentry->d_lockref.count)
  		return false;
  
  	inode = dentry->d_inode;
  	if (inode && unlikely(!spin_trylock(&inode->i_lock))) {

  		spin_unlock(&dentry->d_lock);
  		spin_lock(&inode->i_lock);

  		spin_lock(&dentry->d_lock);

  		if (unlikely(dentry->d_lockref.count))
  			goto out;
  		/* changed inode means that somebody had grabbed it */
  		if (unlikely(inode != dentry->d_inode))
  			goto out;

  	}

  	parent = dentry->d_parent;
  	if (IS_ROOT(dentry) || likely(spin_trylock(&parent->d_lock)))
  		return true;

  	spin_unlock(&dentry->d_lock);

  	spin_lock(&parent->d_lock);
  	if (unlikely(parent != dentry->d_parent)) {
  		spin_unlock(&parent->d_lock);
  		spin_lock(&dentry->d_lock);
  		goto out;
  	}
  	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);

  	if (likely(!dentry->d_lockref.count))

  		return true;

  	spin_unlock(&parent->d_lock);
  out:
  	if (inode)
  		spin_unlock(&inode->i_lock);

  	return false;
  }

  void shrink_dentry_list(struct list_head *list)

  {
  	while (!list_empty(list)) {
  		struct dentry *dentry, *parent;

  		dentry = list_entry(list->prev, struct dentry, d_lru);
  		spin_lock(&dentry->d_lock);

  		rcu_read_lock();

  		if (!shrink_lock_dentry(dentry)) {
  			bool can_free = false;

  			rcu_read_unlock();

  			d_shrink_del(dentry);
  			if (dentry->d_lockref.count < 0)
  				can_free = dentry->d_flags & DCACHE_MAY_FREE;

  			spin_unlock(&dentry->d_lock);
  			if (can_free)
  				dentry_free(dentry);
  			continue;
  		}

  		rcu_read_unlock();

  		d_shrink_del(dentry);
  		parent = dentry->d_parent;

  		if (parent != dentry)
  			__dput_to_list(parent, list);

  		__dentry_kill(dentry);

  	}

  }

  static enum lru_status dentry_lru_isolate(struct list_head *item,
  		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)

  {
  	struct list_head *freeable = arg;
  	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
  
  
  	/*
  	 * we are inverting the lru lock/dentry->d_lock here,
  	 * so use a trylock. If we fail to get the lock, just skip
  	 * it
  	 */
  	if (!spin_trylock(&dentry->d_lock))
  		return LRU_SKIP;
  
  	/*
  	 * Referenced dentries are still in use. If they have active
  	 * counts, just remove them from the LRU. Otherwise give them
  	 * another pass through the LRU.
  	 */
  	if (dentry->d_lockref.count) {

  		d_lru_isolate(lru, dentry);

  		spin_unlock(&dentry->d_lock);
  		return LRU_REMOVED;
  	}
  
  	if (dentry->d_flags & DCACHE_REFERENCED) {
  		dentry->d_flags &= ~DCACHE_REFERENCED;
  		spin_unlock(&dentry->d_lock);
  
  		/*
  		 * The list move itself will be made by the common LRU code. At
  		 * this point, we've dropped the dentry->d_lock but keep the
  		 * lru lock. This is safe to do, since every list movement is
  		 * protected by the lru lock even if both locks are held.
  		 *
  		 * This is guaranteed by the fact that all LRU management
  		 * functions are intermediated by the LRU API calls like
  		 * list_lru_add and list_lru_del. List movement in this file
  		 * only ever occur through this functions or through callbacks
  		 * like this one, that are called from the LRU API.
  		 *
  		 * The only exceptions to this are functions like
  		 * shrink_dentry_list, and code that first checks for the
  		 * DCACHE_SHRINK_LIST flag.  Those are guaranteed to be
  		 * operating only with stack provided lists after they are
  		 * properly isolated from the main list.  It is thus, always a
  		 * local access.
  		 */
  		return LRU_ROTATE;
  	}

  	d_lru_shrink_move(lru, dentry, freeable);

  	spin_unlock(&dentry->d_lock);
  
  	return LRU_REMOVED;
  }

  /**

   * prune_dcache_sb - shrink the dcache
   * @sb: superblock

   * @sc: shrink control, passed to list_lru_shrink_walk()

   *

   * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This
   * is done when we need more memory and called from the superblock shrinker

   * function.

   *

   * This function may fail to free any resources if all the dentries are in
   * use.

   */

  long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc)

  {

  	LIST_HEAD(dispose);
  	long freed;

  	freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc,
  				     dentry_lru_isolate, &dispose);

  	shrink_dentry_list(&dispose);

  	return freed;

  }

  static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,

  		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)

  {

  	struct list_head *freeable = arg;
  	struct dentry	*dentry = container_of(item, struct dentry, d_lru);

  	/*
  	 * we are inverting the lru lock/dentry->d_lock here,
  	 * so use a trylock. If we fail to get the lock, just skip
  	 * it
  	 */
  	if (!spin_trylock(&dentry->d_lock))
  		return LRU_SKIP;

  	d_lru_shrink_move(lru, dentry, freeable);

  	spin_unlock(&dentry->d_lock);

  	return LRU_REMOVED;

  }

  /**

   * shrink_dcache_sb - shrink dcache for a superblock
   * @sb: superblock
   *

   * Shrink the dcache for the specified super block. This is used to free
   * the dcache before unmounting a file system.

   */

  void shrink_dcache_sb(struct super_block *sb)

  {

  	do {
  		LIST_HEAD(dispose);

  		list_lru_walk(&sb->s_dentry_lru,

  			dentry_lru_isolate_shrink, &dispose, 1024);

  		shrink_dentry_list(&dispose);

  	} while (list_lru_count(&sb->s_dentry_lru) > 0);

  }

  EXPORT_SYMBOL(shrink_dcache_sb);

  /**
   * enum d_walk_ret - action to talke during tree walk
   * @D_WALK_CONTINUE:	contrinue walk
   * @D_WALK_QUIT:	quit walk
   * @D_WALK_NORETRY:	quit when retry is needed
   * @D_WALK_SKIP:	skip this dentry and its children
   */
  enum d_walk_ret {
  	D_WALK_CONTINUE,
  	D_WALK_QUIT,
  	D_WALK_NORETRY,
  	D_WALK_SKIP,
  };

  /**

   * d_walk - walk the dentry tree
   * @parent:	start of walk
   * @data:	data passed to @enter() and @finish()
   * @enter:	callback when first entering the dentry

   *

   * The @enter() callbacks are called with d_lock held.

   */

  static void d_walk(struct dentry *parent, void *data,

  		   enum d_walk_ret (*enter)(void *, struct dentry *))

  {

  	struct dentry *this_parent;

  	struct list_head *next;

  	unsigned seq = 0;

  	enum d_walk_ret ret;
  	bool retry = true;

  again:

  	read_seqbegin_or_lock(&rename_lock, &seq);

  	this_parent = parent;

  	spin_lock(&this_parent->d_lock);

  
  	ret = enter(data, this_parent);
  	switch (ret) {
  	case D_WALK_CONTINUE:
  		break;
  	case D_WALK_QUIT:
  	case D_WALK_SKIP:
  		goto out_unlock;
  	case D_WALK_NORETRY:
  		retry = false;
  		break;
  	}

  repeat:
  	next = this_parent->d_subdirs.next;
  resume:
  	while (next != &this_parent->d_subdirs) {
  		struct list_head *tmp = next;

  		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);

  		next = tmp->next;

  		if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR))
  			continue;

  		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);

  
  		ret = enter(data, dentry);
  		switch (ret) {
  		case D_WALK_CONTINUE:
  			break;
  		case D_WALK_QUIT:

  			spin_unlock(&dentry->d_lock);

  			goto out_unlock;
  		case D_WALK_NORETRY:
  			retry = false;
  			break;
  		case D_WALK_SKIP:
  			spin_unlock(&dentry->d_lock);
  			continue;

  		}

  		if (!list_empty(&dentry->d_subdirs)) {

  			spin_unlock(&this_parent->d_lock);
  			spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);

  			this_parent = dentry;

  			spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);

  			goto repeat;
  		}

  		spin_unlock(&dentry->d_lock);

  	}
  	/*
  	 * All done at this level ... ascend and resume the search.
  	 */

  	rcu_read_lock();
  ascend:

  	if (this_parent != parent) {

  		struct dentry *child = this_parent;

  		this_parent = child->d_parent;

  		spin_unlock(&child->d_lock);
  		spin_lock(&this_parent->d_lock);

  		/* might go back up the wrong parent if we have had a rename. */
  		if (need_seqretry(&rename_lock, seq))

  			goto rename_retry;

  		/* go into the first sibling still alive */
  		do {
  			next = child->d_child.next;

  			if (next == &this_parent->d_subdirs)
  				goto ascend;
  			child = list_entry(next, struct dentry, d_child);

  		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));

  		rcu_read_unlock();

  		goto resume;
  	}

  	if (need_seqretry(&rename_lock, seq))

  		goto rename_retry;

  	rcu_read_unlock();

  
  out_unlock:
  	spin_unlock(&this_parent->d_lock);

  	done_seqretry(&rename_lock, seq);

  	return;

  
  rename_retry:

  	spin_unlock(&this_parent->d_lock);
  	rcu_read_unlock();
  	BUG_ON(seq & 1);

  	if (!retry)
  		return;

  	seq = 1;

  	goto again;

  }

  struct check_mount {
  	struct vfsmount *mnt;
  	unsigned int mounted;
  };
  
  static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry)
  {
  	struct check_mount *info = data;
  	struct path path = { .mnt = info->mnt, .dentry = dentry };
  
  	if (likely(!d_mountpoint(dentry)))
  		return D_WALK_CONTINUE;
  	if (__path_is_mountpoint(&path)) {
  		info->mounted = 1;
  		return D_WALK_QUIT;
  	}
  	return D_WALK_CONTINUE;
  }
  
  /**
   * path_has_submounts - check for mounts over a dentry in the
   *                      current namespace.
   * @parent: path to check.
   *
   * Return true if the parent or its subdirectories contain
   * a mount point in the current namespace.
   */
  int path_has_submounts(const struct path *parent)
  {
  	struct check_mount data = { .mnt = parent->mnt, .mounted = 0 };
  
  	read_seqlock_excl(&mount_lock);

  	d_walk(parent->dentry, &data, path_check_mount);

  	read_sequnlock_excl(&mount_lock);
  
  	return data.mounted;
  }
  EXPORT_SYMBOL(path_has_submounts);

  /*

   * Called by mount code to set a mountpoint and check if the mountpoint is
   * reachable (e.g. NFS can unhash a directory dentry and then the complete
   * subtree can become unreachable).
   *

   * Only one of d_invalidate() and d_set_mounted() must succeed.  For

   * this reason take rename_lock and d_lock on dentry and ancestors.
   */
  int d_set_mounted(struct dentry *dentry)
  {
  	struct dentry *p;
  	int ret = -ENOENT;
  	write_seqlock(&rename_lock);
  	for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) {

  		/* Need exclusion wrt. d_invalidate() */

  		spin_lock(&p->d_lock);
  		if (unlikely(d_unhashed(p))) {
  			spin_unlock(&p->d_lock);
  			goto out;
  		}
  		spin_unlock(&p->d_lock);
  	}
  	spin_lock(&dentry->d_lock);
  	if (!d_unlinked(dentry)) {

  		ret = -EBUSY;
  		if (!d_mountpoint(dentry)) {
  			dentry->d_flags |= DCACHE_MOUNTED;
  			ret = 0;
  		}

  	}
   	spin_unlock(&dentry->d_lock);
  out:
  	write_sequnlock(&rename_lock);
  	return ret;
  }
  
  /*

   * Search the dentry child list of the specified parent,

   * and move any unused dentries to the end of the unused
   * list for prune_dcache(). We descend to the next level
   * whenever the d_subdirs list is non-empty and continue
   * searching.
   *
   * It returns zero iff there are no unused children,
   * otherwise  it returns the number of children moved to
   * the end of the unused list. This may not be the total
   * number of unused children, because select_parent can
   * drop the lock and return early due to latency
   * constraints.
   */

  struct select_data {
  	struct dentry *start;

  	union {
  		long found;
  		struct dentry *victim;
  	};

  	struct list_head dispose;

  };

  static enum d_walk_ret select_collect(void *_data, struct dentry *dentry)
  {
  	struct select_data *data = _data;
  	enum d_walk_ret ret = D_WALK_CONTINUE;

  	if (data->start == dentry)
  		goto out;

  	if (dentry->d_flags & DCACHE_SHRINK_LIST) {

  		data->found++;

  	} else {
  		if (dentry->d_flags & DCACHE_LRU_LIST)
  			d_lru_del(dentry);
  		if (!dentry->d_lockref.count) {
  			d_shrink_add(dentry, &data->dispose);
  			data->found++;
  		}

  	}

  	/*
  	 * We can return to the caller if we have found some (this
  	 * ensures forward progress). We'll be coming back to find
  	 * the rest.
  	 */

  	if (!list_empty(&data->dispose))
  		ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY;

  out:

  	return ret;

  }

  static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry)
  {
  	struct select_data *data = _data;
  	enum d_walk_ret ret = D_WALK_CONTINUE;
  
  	if (data->start == dentry)
  		goto out;
  
  	if (dentry->d_flags & DCACHE_SHRINK_LIST) {
  		if (!dentry->d_lockref.count) {
  			rcu_read_lock();
  			data->victim = dentry;
  			return D_WALK_QUIT;
  		}
  	} else {
  		if (dentry->d_flags & DCACHE_LRU_LIST)
  			d_lru_del(dentry);
  		if (!dentry->d_lockref.count)
  			d_shrink_add(dentry, &data->dispose);
  	}
  	/*
  	 * We can return to the caller if we have found some (this
  	 * ensures forward progress). We'll be coming back to find
  	 * the rest.
  	 */
  	if (!list_empty(&data->dispose))
  		ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY;
  out:
  	return ret;
  }

  /**
   * shrink_dcache_parent - prune dcache
   * @parent: parent of entries to prune
   *
   * Prune the dcache to remove unused children of the parent dentry.
   */

  void shrink_dcache_parent(struct dentry *parent)

  {

  	for (;;) {

  		struct select_data data = {.start = parent};

  		INIT_LIST_HEAD(&data.dispose);

  		d_walk(parent, &data, select_collect);

  
  		if (!list_empty(&data.dispose)) {
  			shrink_dentry_list(&data.dispose);
  			continue;
  		}
  
  		cond_resched();

  		if (!data.found)
  			break;

  		data.victim = NULL;
  		d_walk(parent, &data, select_collect2);
  		if (data.victim) {
  			struct dentry *parent;
  			spin_lock(&data.victim->d_lock);
  			if (!shrink_lock_dentry(data.victim)) {
  				spin_unlock(&data.victim->d_lock);
  				rcu_read_unlock();
  			} else {
  				rcu_read_unlock();
  				parent = data.victim->d_parent;
  				if (parent != data.victim)
  					__dput_to_list(parent, &data.dispose);
  				__dentry_kill(data.victim);
  			}
  		}
  		if (!list_empty(&data.dispose))
  			shrink_dentry_list(&data.dispose);

  	}

  }

  EXPORT_SYMBOL(shrink_dcache_parent);

  static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)

  {

  	/* it has busy descendents; complain about those instead */
  	if (!list_empty(&dentry->d_subdirs))
  		return D_WALK_CONTINUE;

  	/* root with refcount 1 is fine */
  	if (dentry == _data && dentry->d_lockref.count == 1)
  		return D_WALK_CONTINUE;
  
  	printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%pd} "
  			" still in use (%d) [unmount of %s %s]
  ",

  		       dentry,
  		       dentry->d_inode ?
  		       dentry->d_inode->i_ino : 0UL,

  		       dentry,

  		       dentry->d_lockref.count,
  		       dentry->d_sb->s_type->name,
  		       dentry->d_sb->s_id);

  	WARN_ON(1);
  	return D_WALK_CONTINUE;
  }
  
  static void do_one_tree(struct dentry *dentry)
  {
  	shrink_dcache_parent(dentry);

  	d_walk(dentry, dentry, umount_check);

  	d_drop(dentry);
  	dput(dentry);

  }
  
  /*
   * destroy the dentries attached to a superblock on unmounting
   */
  void shrink_dcache_for_umount(struct super_block *sb)
  {
  	struct dentry *dentry;

  	WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked");

  
  	dentry = sb->s_root;
  	sb->s_root = NULL;

  	do_one_tree(dentry);

  	while (!hlist_bl_empty(&sb->s_roots)) {
  		dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash));

  		do_one_tree(dentry);

  	}
  }

  static enum d_walk_ret find_submount(void *_data, struct dentry *dentry)

  {

  	struct dentry **victim = _data;

  	if (d_mountpoint(dentry)) {

  		__dget_dlock(dentry);

  		*victim = dentry;

  		return D_WALK_QUIT;
  	}

  	return D_WALK_CONTINUE;

  }
  
  /**

   * d_invalidate - detach submounts, prune dcache, and drop
   * @dentry: dentry to invalidate (aka detach, prune and drop)

   */

  void d_invalidate(struct dentry *dentry)

  {

  	bool had_submounts = false;

  	spin_lock(&dentry->d_lock);
  	if (d_unhashed(dentry)) {
  		spin_unlock(&dentry->d_lock);

  		return;

  	}

  	__d_drop(dentry);

  	spin_unlock(&dentry->d_lock);

  	/* Negative dentries can be dropped without further checks */

  	if (!dentry->d_inode)

  		return;

  	shrink_dcache_parent(dentry);

  	for (;;) {

  		struct dentry *victim = NULL;

  		d_walk(dentry, &victim, find_submount);

  		if (!victim) {
  			if (had_submounts)
  				shrink_dcache_parent(dentry);

  			return;

  		}

  		had_submounts = true;
  		detach_mounts(victim);
  		dput(victim);

  	}

  }

  EXPORT_SYMBOL(d_invalidate);

  /**

   * __d_alloc	-	allocate a dcache entry
   * @sb: filesystem it will belong to

   * @name: qstr of the name
   *
   * Allocates a dentry. It returns %NULL if there is insufficient memory
   * available. On a success the dentry is returned. The name passed in is
   * copied and the copy passed in may be reused after this call.
   */
   

  struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)

  {
  	struct dentry *dentry;
  	char *dname;

  	int err;

  	dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL);

  	if (!dentry)
  		return NULL;

  	/*
  	 * We guarantee that the inline name is always NUL-terminated.
  	 * This way the memcpy() done by the name switching in rename
  	 * will still always have a NUL at the end, even if we might
  	 * be overwriting an internal NUL character
  	 */
  	dentry->d_iname[DNAME_INLINE_LEN-1] = 0;

  	if (unlikely(!name)) {

  		name = &slash_name;

  		dname = dentry->d_iname;
  	} else if (name->len > DNAME_INLINE_LEN-1) {

  		size_t size = offsetof(struct external_name, name[1]);

  		struct external_name *p = kmalloc(size + name->len,
  						  GFP_KERNEL_ACCOUNT |
  						  __GFP_RECLAIMABLE);
  		if (!p) {

  			kmem_cache_free(dentry_cache, dentry); 
  			return NULL;
  		}

  		atomic_set(&p->u.count, 1);
  		dname = p->name;

  	} else  {
  		dname = dentry->d_iname;
  	}	

  
  	dentry->d_name.len = name->len;
  	dentry->d_name.hash = name->hash;
  	memcpy(dname, name->name, name->len);
  	dname[name->len] = 0;

  	/* Make sure we always see the terminating NUL character */

  	smp_store_release(&dentry->d_name.name, dname); /* ^^^ */

  	dentry->d_lockref.count = 1;

  	dentry->d_flags = 0;

  	spin_lock_init(&dentry->d_lock);

  	seqcount_init(&dentry->d_seq);

  	dentry->d_inode = NULL;

  	dentry->d_parent = dentry;
  	dentry->d_sb = sb;

  	dentry->d_op = NULL;
  	dentry->d_fsdata = NULL;

  	INIT_HLIST_BL_NODE(&dentry->d_hash);

  	INIT_LIST_HEAD(&dentry->d_lru);
  	INIT_LIST_HEAD(&dentry->d_subdirs);

  	INIT_HLIST_NODE(&dentry->d_u.d_alias);
  	INIT_LIST_HEAD(&dentry->d_child);

  	d_set_d_op(dentry, dentry->d_sb->s_d_op);

  	if (dentry->d_op && dentry->d_op->d_init) {
  		err = dentry->d_op->d_init(dentry);
  		if (err) {
  			if (dname_external(dentry))
  				kfree(external_name(dentry));
  			kmem_cache_free(dentry_cache, dentry);
  			return NULL;
  		}
  	}

  	this_cpu_inc(nr_dentry);

  	return dentry;
  }

  
  /**
   * d_alloc	-	allocate a dcache entry
   * @parent: parent of entry to allocate
   * @name: qstr of the name
   *
   * Allocates a dentry. It returns %NULL if there is insufficient memory
   * available. On a success the dentry is returned. The name passed in is
   * copied and the copy passed in may be reused after this call.
   */
  struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
  {
  	struct dentry *dentry = __d_alloc(parent->d_sb, name);
  	if (!dentry)
  		return NULL;

  	spin_lock(&parent->d_lock);
  	/*
  	 * don't need child lock because it is not subject
  	 * to concurrency here
  	 */
  	__dget_dlock(parent);
  	dentry->d_parent = parent;

  	list_add(&dentry->d_child, &parent->d_subdirs);

  	spin_unlock(&parent->d_lock);
  
  	return dentry;
  }

  EXPORT_SYMBOL(d_alloc);

  struct dentry *d_alloc_anon(struct super_block *sb)
  {
  	return __d_alloc(sb, NULL);
  }
  EXPORT_SYMBOL(d_alloc_anon);

  struct dentry *d_alloc_cursor(struct dentry * parent)
  {

  	struct dentry *dentry = d_alloc_anon(parent->d_sb);

  	if (dentry) {

  		dentry->d_flags |= DCACHE_DENTRY_CURSOR;

  		dentry->d_parent = dget(parent);
  	}
  	return dentry;
  }

  /**
   * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems)
   * @sb: the superblock
   * @name: qstr of the name
   *
   * For a filesystem that just pins its dentries in memory and never
   * performs lookups at all, return an unhashed IS_ROOT dentry.

   * This is used for pipes, sockets et.al. - the stuff that should
   * never be anyone's children or parents.  Unlike all other
   * dentries, these will not have RCU delay between dropping the
   * last reference and freeing them.

   *
   * The only user is alloc_file_pseudo() and that's what should
   * be considered a public interface.  Don't use directly.

   */

  struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
  {

  	struct dentry *dentry = __d_alloc(sb, name);
  	if (likely(dentry))
  		dentry->d_flags |= DCACHE_NORCU;
  	return dentry;

  }

  struct dentry *d_alloc_name(struct dentry *parent, const char *name)
  {
  	struct qstr q;
  
  	q.name = name;

  	q.hash_len = hashlen_string(parent, name);

  	return d_alloc(parent, &q);
  }

  EXPORT_SYMBOL(d_alloc_name);