dcache.c

/*
 * 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/syscalls.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/fs.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/mount.h>
#include <linux/file.h>
#include <asm/uaccess.h>
#include <linux/security.h>
#include <linux/seqlock.h>
#include <linux/swap.h>
#include <linux/bootmem.h>
#include <linux/fs_struct.h>
#include <linux/hardirq.h>
#include <linux/bit_spinlock.h>
#include <linux/rculist_bl.h>
#include <linux/prefetch.h>
#include <linux/ratelimit.h>
#include <linux/list_lru.h>
#include "internal.h"
#include "mount.h"

/*
 * Usage:
 * dcache->d_inode->i_lock protects:
 *   - i_dentry, d_alias, d_inode of aliases
 * dcache_hash_bucket lock protects:
 *   - the dcache hash table
 * s_anon bl list spinlock protects:
 *   - the s_anon 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_alias, d_inode
 *
 * Ordering:
 * dentry->d_inode->i_lock
 *   dentry->d_lock
 *     dentry->d_sb->s_dentry_lru_lock
 *     dcache_hash_bucket lock
 *     s_anon 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:
 * if (dentry1 < dentry2)
 *   dentry1->d_lock
 *     dentry2->d_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;

/**
 * read_seqbegin_or_lock - begin a sequence number check or locking block
 * @lock: sequence lock
 * @seq : sequence number to be checked
 *
 * First try it once optimistically without taking the lock. If that fails,
 * take the lock. The sequence number is also used as a marker for deciding
 * whether to be a reader (even) or writer (odd).
 * N.B. seq must be initialized to an even number to begin with.
 */
static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
{
	if (!(*seq & 1))	/* Even */
		*seq = read_seqbegin(lock);
	else			/* Odd */
		read_seqlock_excl(lock);
}

static inline int need_seqretry(seqlock_t *lock, int seq)
{
	return !(seq & 1) && read_seqretry(lock, seq);
}

static inline void done_seqretry(seqlock_t *lock, int seq)
{
	if (seq & 1)
		read_sequnlock_excl(lock);
}

/*
 * 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.
 */
#define D_HASHBITS     d_hash_shift
#define D_HASHMASK     d_hash_mask

static unsigned int d_hash_mask __read_mostly;
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(const struct dentry *parent,
					unsigned int hash)
{
	hash += (unsigned long) parent / L1_CACHE_BYTES;
	hash = hash + (hash >> D_HASHBITS);
	return dentry_hashtable + (hash & D_HASHMASK);
}

/* 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);

#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;
}

int proc_nr_dentry(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();
	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 = *(unsigned long *)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 = ~(~0ul << tcount*8);
	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)
{
	const unsigned char *cs;
	/*
	 * Be careful about RCU walk racing with rename:
	 * use ACCESS_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)
	 */
	cs = ACCESS_ONCE(dentry->d_name.name);
	smp_read_barrier_depends();
	return dentry_string_cmp(cs, ct, tcount);
}

static void __d_free(struct rcu_head *head)
{
	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);

	WARN_ON(!hlist_unhashed(&dentry->d_alias));
	if (dname_external(dentry))
		kfree(dentry->d_name.name);
	kmem_cache_free(dentry_cache, dentry); 
}

/*
 * no locks, please.
 */
static void d_free(struct dentry *dentry)
{
	BUG_ON((int)dentry->d_lockref.count > 0);
	this_cpu_dec(nr_dentry);
	if (dentry->d_op && dentry->d_op->d_release)
		dentry->d_op->d_release(dentry);

	/* if dentry was never visible to RCU, immediate free is OK */
	if (!(dentry->d_flags & DCACHE_RCUACCESS))
		__d_free(&dentry->d_u.d_rcu);
	else
		call_rcu(&dentry->d_u.d_rcu, __d_free);
}

/**
 * dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
 * @dentry: the target dentry
 * After this call, in-progress rcu-walk path lookup will fail. This
 * should be called after unhashing, and after changing d_inode (if
 * the dentry has not already been unhashed).
 */
static inline void dentry_rcuwalk_barrier(struct dentry *dentry)
{
	assert_spin_locked(&dentry->d_lock);
	/* Go through a barrier */
	write_seqcount_barrier(&dentry->d_seq);
}

/*
 * Release the dentry's inode, using the filesystem
 * d_iput() operation if defined. Dentry has no refcount
 * and is unhashed.
 */
static void dentry_iput(struct dentry * dentry)
	__releases(dentry->d_lock)
	__releases(dentry->d_inode->i_lock)
{
	struct inode *inode = dentry->d_inode;
	if (inode) {
		dentry->d_inode = NULL;
		hlist_del_init(&dentry->d_alias);
		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);
	} else {
		spin_unlock(&dentry->d_lock);
	}
}

/*
 * Release the dentry's inode, using the filesystem
 * d_iput() operation if defined. dentry remains in-use.
 */
static void dentry_unlink_inode(struct dentry * dentry)
	__releases(dentry->d_lock)
	__releases(dentry->d_inode->i_lock)
{
	struct inode *inode = dentry->d_inode;
	dentry->d_inode = NULL;
	hlist_del_init(&dentry->d_alias);
	dentry_rcuwalk_barrier(dentry);
	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.
 *
 * 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);
	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);
	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 dentry *dentry)
{
	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
	dentry->d_flags &= ~DCACHE_LRU_LIST;
	this_cpu_dec(nr_dentry_unused);
	list_del_init(&dentry->d_lru);
}

static void d_lru_shrink_move(struct dentry *dentry, struct list_head *list)
{
	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
	dentry->d_flags |= DCACHE_SHRINK_LIST;
	list_move_tail(&dentry->d_lru, list);
}

/*
 * dentry_lru_(add|del)_list) must be called with d_lock held.
 */
static void dentry_lru_add(struct dentry *dentry)
{
	if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST)))
		d_lru_add(dentry);
}

/*
 * Remove a dentry with references from the LRU.
 *
 * If we are on the shrink list, then we can get to try_prune_one_dentry() and
 * lose our last reference through the parent walk. In this case, we need to
 * remove ourselves from the shrink list, not the LRU.
 */
static void dentry_lru_del(struct dentry *dentry)
{
	if (dentry->d_flags & DCACHE_LRU_LIST) {
		if (dentry->d_flags & DCACHE_SHRINK_LIST)
			return d_shrink_del(dentry);
		d_lru_del(dentry);
	}
}

/**
 * d_kill - kill dentry and return parent
 * @dentry: dentry to kill
 * @parent: parent dentry
 *
 * The dentry must already be unhashed and removed from the LRU.
 *
 * If this is the root of the dentry tree, return NULL.
 *
 * dentry->d_lock and parent->d_lock must be held by caller, and are dropped by
 * d_kill.
 */
static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
	__releases(dentry->d_lock)
	__releases(parent->d_lock)
	__releases(dentry->d_inode->i_lock)
{
	list_del(&dentry->d_u.d_child);
	/*
	 * Inform try_to_ascend() that we are no longer attached to the
	 * dentry tree
	 */
	dentry->d_flags |= DCACHE_DENTRY_KILLED;
	if (parent)
		spin_unlock(&parent->d_lock);
	dentry_iput(dentry);
	/*
	 * dentry_iput drops the locks, at which point nobody (except
	 * transient RCU lookups) can reach this dentry.
	 */
	d_free(dentry);
	return parent;
}

/**
 * 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.
 */
void __d_drop(struct dentry *dentry)
{
	if (!d_unhashed(dentry)) {
		struct hlist_bl_head *b;
		if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
			b = &dentry->d_sb->s_anon;
		else
			b = d_hash(dentry->d_parent, dentry->d_name.hash);

		hlist_bl_lock(b);
		__hlist_bl_del(&dentry->d_hash);
		dentry->d_hash.pprev = NULL;
		hlist_bl_unlock(b);
		dentry_rcuwalk_barrier(dentry);
	}
}
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);

/*
 * Finish off a dentry we've decided to kill.
 * dentry->d_lock must be held, returns with it unlocked.
 * If ref is non-zero, then decrement the refcount too.
 * Returns dentry requiring refcount drop, or NULL if we're done.
 */
static inline struct dentry *
dentry_kill(struct dentry *dentry, int unlock_on_failure)
	__releases(dentry->d_lock)
{
	struct inode *inode;
	struct dentry *parent;

	inode = dentry->d_inode;
	if (inode && !spin_trylock(&inode->i_lock)) {
relock:
		if (unlock_on_failure) {
			spin_unlock(&dentry->d_lock);
			cpu_relax();
		}
		return dentry; /* try again with same dentry */
	}
	if (IS_ROOT(dentry))
		parent = NULL;
	else
		parent = dentry->d_parent;
	if (parent && !spin_trylock(&parent->d_lock)) {
		if (inode)
			spin_unlock(&inode->i_lock);
		goto relock;
	}

	/*
	 * 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) && !d_unhashed(dentry))
		dentry->d_op->d_prune(dentry);

	dentry_lru_del(dentry);
	/* if it was on the hash then remove it */
	__d_drop(dentry);
	return d_kill(dentry, parent);
}

/* 
 * 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)
{
	if (unlikely(!dentry))
		return;

repeat:
	if (lockref_put_or_lock(&dentry->d_lockref))
		return;

	/* Unreachable? Get rid of it */
	if (unlikely(d_unhashed(dentry)))
		goto kill_it;

	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) {
		if (dentry->d_op->d_delete(dentry))
			goto kill_it;
	}

	dentry->d_flags |= DCACHE_REFERENCED;
	dentry_lru_add(dentry);

	dentry->d_lockref.count--;
	spin_unlock(&dentry->d_lock);
	return;

kill_it:
	dentry = dentry_kill(dentry, 1);
	if (dentry)
		goto repeat;
}
EXPORT_SYMBOL(dput);

/**
 * d_invalidate - invalidate a dentry
 * @dentry: dentry to invalidate
 *
 * Try to invalidate the dentry if it turns out to be
 * possible. If there are other dentries that can be
 * reached through this one we can't delete it and we
 * return -EBUSY. On success we return 0.
 *
 * no dcache lock.
 */
 
int d_invalidate(struct dentry * dentry)
{
	/*
	 * If it's already been dropped, return OK.
	 */
	spin_lock(&dentry->d_lock);
	if (d_unhashed(dentry)) {
		spin_unlock(&dentry->d_lock);
		return 0;
	}
	/*
	 * Check whether to do a partial shrink_dcache
	 * to get rid of unused child entries.
	 */
	if (!list_empty(&dentry->d_subdirs)) {
		spin_unlock(&dentry->d_lock);
		shrink_dcache_parent(dentry);
		spin_lock(&dentry->d_lock);
	}

	/*
	 * Somebody else still using it?
	 *
	 * If it's a directory, we can't drop it
	 * for fear of somebody re-populating it
	 * with children (even though dropping it
	 * would make it unreachable from the root,
	 * we might still populate it if it was a
	 * working directory or similar).
	 * We also need to leave mountpoints alone,
	 * directory or not.
	 */
	if (dentry->d_lockref.count > 1 && dentry->d_inode) {
		if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
			spin_unlock(&dentry->d_lock);
			return -EBUSY;
		}
	}

	__d_drop(dentry);
	spin_unlock(&dentry->d_lock);
	return 0;
}
EXPORT_SYMBOL(d_invalidate);

/* 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;

	/*
	 * Do optimistic parent lookup without any
	 * locking.
	 */
	rcu_read_lock();
	ret = ACCESS_ONCE(dentry->d_parent);
	gotref = lockref_get_not_zero(&ret->d_lockref);
	rcu_read_unlock();
	if (likely(gotref)) {
		if (likely(ret == ACCESS_ONCE(dentry->d_parent)))
			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);

/**
 * d_find_alias - grab a hashed alias of inode
 * @inode: inode in question
 * @want_discon:  flag, used by d_splice_alias, to request
 *          that only a DISCONNECTED alias be returned.
 *
 * 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.
 *
 * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
 * any other hashed alias over that one unless @want_discon is set,
 * in which case only return an IS_ROOT, DCACHE_DISCONNECTED alias.
 */
static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
{
	struct dentry *alias, *discon_alias;

again:
	discon_alias = NULL;
	hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
		spin_lock(&alias->d_lock);
 		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
			if (IS_ROOT(alias) &&
			    (alias->d_flags & DCACHE_DISCONNECTED)) {
				discon_alias = alias;
			} else if (!want_discon) {
				__dget_dlock(alias);
				spin_unlock(&alias->d_lock);
				return alias;
			}
		}
		spin_unlock(&alias->d_lock);
	}
	if (discon_alias) {
		alias = discon_alias;
		spin_lock(&alias->d_lock);
		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
			if (IS_ROOT(alias) &&
			    (alias->d_flags & DCACHE_DISCONNECTED)) {
				__dget_dlock(alias);
				spin_unlock(&alias->d_lock);
				return alias;
			}
		}
		spin_unlock(&alias->d_lock);
		goto again;
	}
	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, 0);
		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_alias) {
		spin_lock(&dentry->d_lock);
		if (!dentry->d_lockref.count) {
			/*
			 * inform the fs via d_prune that this dentry
			 * is about to be unhashed and destroyed.
			 */
			if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
			    !d_unhashed(dentry))
				dentry->d_op->d_prune(dentry);

			__dget_dlock(dentry);
			__d_drop(dentry);
			spin_unlock(&dentry->d_lock);
			spin_unlock(&inode->i_lock);
			dput(dentry);
			goto restart;
		}
		spin_unlock(&dentry->d_lock);
	}
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(d_prune_aliases);

/*
 * Try to throw away a dentry - free the inode, dput the parent.
 * Requires dentry->d_lock is held, and dentry->d_count == 0.
 * Releases dentry->d_lock.
 *
 * This may fail if locks cannot be acquired no problem, just try again.
 */
static struct dentry * try_prune_one_dentry(struct dentry *dentry)
	__releases(dentry->d_lock)
{
	struct dentry *parent;

	parent = dentry_kill(dentry, 0);
	/*
	 * If dentry_kill returns NULL, we have nothing more to do.
	 * if it returns the same dentry, trylocks failed. In either
	 * case, just loop again.
	 *
	 * Otherwise, we need to prune ancestors too. This is necessary
	 * to prevent quadratic behavior of shrink_dcache_parent(), but
	 * is also expected to be beneficial in reducing dentry cache
	 * fragmentation.
	 */
	if (!parent)
		return NULL;
	if (parent == dentry)
		return dentry;

	/* Prune ancestors. */
	dentry = parent;
	while (dentry) {
		if (lockref_put_or_lock(&dentry->d_lockref))
			return NULL;
		dentry = dentry_kill(dentry, 1);
	}
	return NULL;
}

static void shrink_dentry_list(struct list_head *list)
{
	struct dentry *dentry;

	rcu_read_lock();
	for (;;) {
		dentry = list_entry_rcu(list->prev, struct dentry, d_lru);
		if (&dentry->d_lru == list)
			break; /* empty */

		/*
		 * Get the dentry lock, and re-verify that the dentry is
		 * this on the shrinking list. If it is, we know that
		 * DCACHE_SHRINK_LIST and DCACHE_LRU_LIST are set.
		 */
		spin_lock(&dentry->d_lock);
		if (dentry != list_entry(list->prev, struct dentry, d_lru)) {
			spin_unlock(&dentry->d_lock);
			continue;
		}

		/*
		 * The dispose list is isolated and dentries are not accounted
		 * to the LRU here, so we can simply remove it from the list
		 * here regardless of whether it is referenced or not.
		 */
		d_shrink_del(dentry);

		/*
		 * We found an inuse dentry which was not removed from
		 * the LRU because of laziness during lookup. Do not free it.
		 */
		if (dentry->d_lockref.count) {
			spin_unlock(&dentry->d_lock);
			continue;
		}
		rcu_read_unlock();

		/*
		 * If 'try_to_prune()' returns a dentry, it will
		 * be the same one we passed in, and d_lock will
		 * have been held the whole time, so it will not
		 * have been added to any other lists. We failed
		 * to get the inode lock.
		 *
		 * We just add it back to the shrink list.
		 */
		dentry = try_prune_one_dentry(dentry);

		rcu_read_lock();
		if (dentry) {
			d_shrink_add(dentry, list);
			spin_unlock(&dentry->d_lock);
		}
	}
	rcu_read_unlock();
}

static enum lru_status
dentry_lru_isolate(struct list_head *item, 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(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(dentry, freeable);
	spin_unlock(&dentry->d_lock);

	return LRU_REMOVED;
}

/**
 * prune_dcache_sb - shrink the dcache
 * @sb: superblock
 * @nr_to_scan : number of entries to try to free
 * @nid: which node to scan for freeable entities
 *
 * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
 * done when we need more memory an 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, unsigned long nr_to_scan,
		     int nid)
{
	LIST_HEAD(dispose);
	long freed;

	freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
				       &dispose, &nr_to_scan);
	shrink_dentry_list(&dispose);
	return freed;
}

static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
						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(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)
{
	long freed;

	do {
		LIST_HEAD(dispose);

		freed = list_lru_walk(&sb->s_dentry_lru,
			dentry_lru_isolate_shrink, &dispose, UINT_MAX);

		this_cpu_sub(nr_dentry_unused, freed);
		shrink_dentry_list(&dispose);
	} while (freed > 0);
}
EXPORT_SYMBOL(shrink_dcache_sb);

/*
 * This tries to ascend one level of parenthood, but
 * we can race with renaming, so we need to re-check
 * the parenthood after dropping the lock and check
 * that the sequence number still matches.
 */
static struct dentry *try_to_ascend(struct dentry *old, unsigned seq)
{
	struct dentry *new = old->d_parent;

	rcu_read_lock();
	spin_unlock(&old->d_lock);
	spin_lock(&new->d_lock);

	/*
	 * might go back up the wrong parent if we have had a rename
	 * or deletion
	 */
	if (new != old->d_parent ||
		 (old->d_flags & DCACHE_DENTRY_KILLED) ||
		 need_seqretry(&rename_lock, seq)) {
		spin_unlock(&new->d_lock);
		new = NULL;
	}
	rcu_read_unlock();
	return new;
}

/**
 * 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
 * @finish:	callback when successfully finished the walk
 *
 * The @enter() and @finish() callbacks are called with d_lock held.
 */
static void d_walk(struct dentry *parent, void *data,
		   enum d_walk_ret (*enter)(void *, struct dentry *),
		   void (*finish)(void *))
{
	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_u.d_child);
		next = tmp->next;

		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);