dcache.c

// 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"

#include <asm/runtime-const.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_chilren
 *   - childrens' d_sib 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 __ro_after_init;

const struct qstr empty_name = QSTR_INIT("", 0);
EXPORT_SYMBOL(empty_name);
const struct qstr slash_name = QSTR_INIT("/", 1);
EXPORT_SYMBOL(slash_name);
const struct qstr dotdot_name = QSTR_INIT("..", 2);
EXPORT_SYMBOL(dotdot_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 __ro_after_init;

static struct hlist_bl_head *dentry_hashtable __ro_after_init;

static inline struct hlist_bl_head *d_hash(unsigned long hashlen)
{
	return runtime_const_ptr(dentry_hashtable) +
		runtime_const_shift_right_32(hashlen, 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);
}

struct dentry_stat_t {
	long nr_dentry;
	long nr_unused;
	long age_limit;		/* age in seconds */
	long want_pages;	/* pages requested by system */
	long nr_negative;	/* # of unused negative dentries */
	long dummy;		/* Reserved for future use */
};

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

/*
 * 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;
}

static int proc_nr_dentry(struct ctl_table *table, int write, void *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);
}

static struct ctl_table fs_dcache_sysctls[] = {
	{
		.procname	= "dentry-state",
		.data		= &dentry_stat,
		.maxlen		= 6*sizeof(long),
		.mode		= 0444,
		.proc_handler	= proc_nr_dentry,
	},
};

static int __init init_fs_dcache_sysctls(void)
{
	register_sysctl_init("fs", fs_dcache_sysctls);
	return 0;
}
fs_initcall(init_fs_dcache_sysctls);
#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;
	flags |= type_flags;
	smp_store_release(&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;
	WRITE_ONCE(dentry->d_flags, flags);
	dentry->d_inode = NULL;
	/*
	 * The negative counter only tracks dentries on the LRU. Don't inc if
	 * d_lru is on another list.
	 */
	if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == 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_obj(
			&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_obj(
			&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);
}

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);

/**
 * 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).
 */
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 *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(hlist_unhashed(&dentry->d_sib)))
		return;
	__hlist_del(&dentry->d_sib);
	/*
	 * Cursors can move around the list of children.  While we'd been
	 * a normal list member, it didn't matter - ->d_sib.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_sib.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_sib.next
	 * points to something that won't be moving around.  I.e. skip the
	 * cursors.
	 */
	while (dentry->d_sib.next) {
		next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib);
		if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR)))
			break;
		dentry->d_sib.next = next->d_sib.next;
	}
}

static struct dentry *__dentry_kill(struct dentry *dentry)
{
	struct dentry *parent = NULL;
	bool can_free = true;

	/*
	 * 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);
	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);

	cond_resched();
	/* now that it's negative, ->d_parent is stable */
	if (!IS_ROOT(dentry)) {
		parent = dentry->d_parent;
		spin_lock(&parent->d_lock);
	}
	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
	dentry_unlist(dentry);
	if (dentry->d_flags & DCACHE_SHRINK_LIST)
		can_free = false;
	spin_unlock(&dentry->d_lock);
	if (likely(can_free))
		dentry_free(dentry);
	if (parent && --parent->d_lockref.count) {
		spin_unlock(&parent->d_lock);
		return NULL;
	}
	return parent;
}

/*
 * Lock a dentry for feeding it to __dentry_kill().
 * 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 is busy.  Otherwise, return true and have
 * that dentry's inode locked.
 */

static bool lock_for_kill(struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;

	if (unlikely(dentry->d_lockref.count))
		return false;

	if (!inode || likely(spin_trylock(&inode->i_lock)))
		return true;

	do {
		spin_unlock(&dentry->d_lock);
		spin_lock(&inode->i_lock);
		spin_lock(&dentry->d_lock);
		if (likely(inode == dentry->d_inode))
			break;
		spin_unlock(&inode->i_lock);
		inode = dentry->d_inode;
	} while (inode);
	if (likely(!dentry->d_lockref.count))
		return true;
	if (inode)
		spin_unlock(&inode->i_lock);
	return false;
}

/*
 * Decide if dentry is worth retaining.  Usually this is called with dentry
 * locked; if not locked, we are more limited and might not be able to tell
 * without a lock.  False in this case means "punt to locked path and recheck".
 *
 * In case we aren't locked, these predicates 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.
 */
static inline bool retain_dentry(struct dentry *dentry, bool locked)
{
	unsigned int d_flags;

	smp_rmb();
	d_flags = READ_ONCE(dentry->d_flags);

	// Unreachable? Nobody would be able to look it up, no point retaining
	if (unlikely(d_unhashed(dentry)))
		return false;

	// Same if it's disconnected
	if (unlikely(d_flags & DCACHE_DISCONNECTED))
		return false;

	// ->d_delete() might tell us not to bother, but that requires
	// ->d_lock; can't decide without it
	if (unlikely(d_flags & DCACHE_OP_DELETE)) {
		if (!locked || dentry->d_op->d_delete(dentry))
			return false;
	}

	// Explicitly told not to bother
	if (unlikely(d_flags & DCACHE_DONTCACHE))
		return false;

	// At this point it looks like we ought to keep it.  We also might
	// need to do something - put it on LRU if it wasn't there already
	// and mark it referenced if it was on LRU, but not marked yet.
	// Unfortunately, both actions require ->d_lock, so in lockless
	// case we'd have to punt rather than doing those.
	if (unlikely(!(d_flags & DCACHE_LRU_LIST))) {
		if (!locked)
			return false;
		d_lru_add(dentry);
	} else if (unlikely(!(d_flags & DCACHE_REFERENCED))) {
		if (!locked)
			return false;
		dentry->d_flags |= DCACHE_REFERENCED;
	}
	return true;
}

void d_mark_dontcache(struct inode *inode)
{
	struct dentry *de;

	spin_lock(&inode->i_lock);
	hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) {
		spin_lock(&de->d_lock);
		de->d_flags |= DCACHE_DONTCACHE;
		spin_unlock(&de->d_lock);
	}
	inode->i_state |= I_DONTCACHE;
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(d_mark_dontcache);

/*
 * Try to do a lockless dput(), and return whether that was successful.
 *
 * If unsuccessful, we return false, having already taken the dentry lock.
 * In that case refcount is guaranteed to be zero and we have already
 * decided that it's not worth keeping around.
 *
 * 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;

	/*
	 * try to 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 (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) {
			spin_unlock(&dentry->d_lock);
			return true;
		}
		dentry->d_lockref.count--;
		goto locked;
	}

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

	/*
	 * Can we decide that decrement of refcount is all we needed without
	 * taking the lock?  There's a very common case when it's all we need -
	 * dentry looks like it ought to be retained and there's nothing else
	 * to do.
	 */
	if (retain_dentry(dentry, false))
		return true;

	/*
	 * Either not worth retaining or we can't tell without the lock.
	 * Get the lock, then.  We've already decremented the refcount to 0,
	 * 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.
	 */
locked:
	if (dentry->d_lockref.count || retain_dentry(dentry, true)) {
		spin_unlock(&dentry->d_lock);
		return true;
	}
	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)
{
	if (!dentry)
		return;
	might_sleep();
	rcu_read_lock();
	if (likely(fast_dput(dentry))) {
		rcu_read_unlock();
		return;
	}
	while (lock_for_kill(dentry)) {
		rcu_read_unlock();
		dentry = __dentry_kill(dentry);
		if (!dentry)
			return;
		if (retain_dentry(dentry, true)) {
			spin_unlock(&dentry->d_lock);
			return;
		}
		rcu_read_lock();
	}
	rcu_read_unlock();
	spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL(dput);

static void to_shrink_list(struct dentry *dentry, struct list_head *list)
__must_hold(&dentry->d_lock)
{
	if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
		if (dentry->d_flags & DCACHE_LRU_LIST)
			d_lru_del(dentry);
		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();
	to_shrink_list(dentry, list);
	spin_unlock(&dentry->d_lock);
}

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);
	lockref_get(&alias->d_lockref);
	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);

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;
}

/**
 * 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.
 */
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);
	}