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 <linux/kasan.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_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_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_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;

/*
 * 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_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;
	return dentry_hashtable + hash_32(hash, d_hash_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);

#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(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();
	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 = 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)
{
	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);
}

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;
}

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;
}

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

/**
 * dentry_rcuwalk_invalidate - 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_invalidate(struct dentry *dentry)
{
	lockdep_assert_held(&dentry->d_lock);
	/* Go through am invalidation barrier */
	write_seqcount_invalidate(&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) {
		__d_clear_type_and_inode(dentry);
		hlist_del_init(&dentry->d_u.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;

	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.
 *
 * 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 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);
	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;
	list_lru_isolate_move(lru, &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);
}

/**
 * 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;
		/*
		 * Hashed dentries are normally on the dentry hashtable,
		 * with the exception of those newly allocated by
		 * d_obtain_alias, which are always IS_ROOT:
		 */
		if (unlikely(IS_ROOT(dentry)))
			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_invalidate(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);

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);
	__list_del_entry(&dentry->d_child);
	/*
	 * Inform d_walk() 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.
	 */
	BUG_ON(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);

	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);
}

/*
 * 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 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 failed;

	if (!IS_ROOT(dentry)) {
		parent = dentry->d_parent;
		if (unlikely(!spin_trylock(&parent->d_lock))) {
			if (inode)
				spin_unlock(&inode->i_lock);
			goto failed;
		}
	}

	__dentry_kill(dentry);
	return parent;

failed:
	spin_unlock(&dentry->d_lock);
	cpu_relax();
	return dentry; /* try again with same dentry */
}

static inline struct dentry *lock_parent(struct dentry *dentry)
{
	struct dentry *parent = dentry->d_parent;
	if (IS_ROOT(dentry))
		return NULL;
	if (unlikely(dentry->d_lockref.count < 0))
		return NULL;
	if (likely(spin_trylock(&parent->d_lock)))
		return parent;
	rcu_read_lock();
	spin_unlock(&dentry->d_lock);
again:
	parent = ACCESS_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;
}

/*
 * 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 1;
		}
		return 0;
	}

	/*
	 * If we weren't the last ref, we're done.
	 */
	if (ret)
		return 1;

	/*
	 * 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 = ACCESS_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 1;

	/*
	 * 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 1;
	}

	/*
	 * 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 0;
}


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

	/* Slow case: now with the dentry lock held */
	rcu_read_unlock();

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

	if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
		goto kill_it;

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

	if (!(dentry->d_flags & DCACHE_REFERENCED))
		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);
	if (dentry)
		goto repeat;
}
EXPORT_SYMBOL(dput);


/* 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
 *
 * 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, *discon_alias;

again:
	discon_alias = NULL;
	hlist_for_each_entry(alias, &inode->i_dentry, d_u.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 {
				__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)) {
			__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);
		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);

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

	while (!list_empty(list)) {
		struct inode *inode;
		dentry = list_entry(list->prev, struct dentry, d_lru);
		spin_lock(&dentry->d_lock);
		parent = lock_parent(dentry);

		/*
		 * 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 > 0) {
			spin_unlock(&dentry->d_lock);
			if (parent)
				spin_unlock(&parent->d_lock);
			continue;
		}


		if (unlikely(dentry->d_flags & DCACHE_DENTRY_KILLED)) {
			bool can_free = dentry->d_flags & DCACHE_MAY_FREE;
			spin_unlock(&dentry->d_lock);
			if (parent)
				spin_unlock(&parent->d_lock);
			if (can_free)
				dentry_free(dentry);
			continue;
		}

		inode = dentry->d_inode;
		if (inode && unlikely(!spin_trylock(&inode->i_lock))) {
			d_shrink_add(dentry, list);
			spin_unlock(&dentry->d_lock);
			if (parent)
				spin_unlock(&parent->d_lock);
			continue;
		}

		__dentry_kill(dentry);

		/*
		 * 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.
		 */
		dentry = parent;
		while (dentry && !lockref_put_or_lock(&dentry->d_lockref)) {
			parent = lock_parent(dentry);
			if (dentry->d_lockref.count != 1) {
				dentry->d_lockref.count--;
				spin_unlock(&dentry->d_lock);
				if (parent)
					spin_unlock(&parent->d_lock);
				break;
			}
			inode = dentry->d_inode;	/* can't be NULL */
			if (unlikely(!spin_trylock(&inode->i_lock))) {
				spin_unlock(&dentry->d_lock);
				if (parent)