#include <linux/bootmem.h>
#include <linux/fs_struct.h>
#include <linux/hardirq.h>
+#include <linux/bit_spinlock.h>
+#include <linux/rculist_bl.h>
#include "internal.h"
/*
* Usage:
- * dcache_inode_lock protects:
- * - i_dentry, d_alias, d_inode
- * dcache_hash_lock protects:
- * - the dcache hash table, s_anon lists
+ * 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)
* dcache_lru_lock protects:
* - the dcache lru lists and counters
* d_lock protects:
* - d_alias, d_inode
*
* Ordering:
- * dcache_inode_lock
+ * dentry->d_inode->i_lock
* dentry->d_lock
* dcache_lru_lock
- * dcache_hash_lock
+ * dcache_hash_bucket lock
+ * s_anon lock
*
* If there is an ancestor relationship:
* dentry->d_parent->...->d_parent->d_lock
int sysctl_vfs_cache_pressure __read_mostly = 100;
EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_inode_lock);
-static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_hash_lock);
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
EXPORT_SYMBOL(rename_lock);
-EXPORT_SYMBOL(dcache_inode_lock);
static struct kmem_cache *dentry_cache __read_mostly;
static unsigned int d_hash_mask __read_mostly;
static unsigned int d_hash_shift __read_mostly;
-static struct hlist_head *dentry_hashtable __read_mostly;
+
+struct dcache_hash_bucket {
+ struct hlist_bl_head head;
+};
+static struct dcache_hash_bucket *dentry_hashtable __read_mostly;
+
+static inline struct dcache_hash_bucket *d_hash(struct dentry *parent,
+ unsigned long hash)
+{
+ hash += ((unsigned long) parent ^ GOLDEN_RATIO_PRIME) / L1_CACHE_BYTES;
+ hash = hash ^ ((hash ^ GOLDEN_RATIO_PRIME) >> D_HASHBITS);
+ return dentry_hashtable + (hash & D_HASHMASK);
+}
+
+static inline void spin_lock_bucket(struct dcache_hash_bucket *b)
+{
+ bit_spin_lock(0, (unsigned long *)&b->head.first);
+}
+
+static inline void spin_unlock_bucket(struct dcache_hash_bucket *b)
+{
+ __bit_spin_unlock(0, (unsigned long *)&b->head.first);
+}
/* Statistics gathering. */
struct dentry_stat_t dentry_stat = {
dentry->d_op->d_release(dentry);
/* if dentry was never inserted into hash, immediate free is OK */
- if (hlist_unhashed(&dentry->d_hash))
+ if (hlist_bl_unhashed(&dentry->d_hash))
__d_free(&dentry->d_u.d_rcu);
else
call_rcu(&dentry->d_u.d_rcu, __d_free);
*/
static void dentry_iput(struct dentry * dentry)
__releases(dentry->d_lock)
- __releases(dcache_inode_lock)
+ __releases(dentry->d_inode->i_lock)
{
struct inode *inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
list_del_init(&dentry->d_alias);
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
fsnotify_inoderemove(inode);
if (dentry->d_op && dentry->d_op->d_iput)
iput(inode);
} else {
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_inode_lock);
}
}
*/
static void dentry_unlink_inode(struct dentry * dentry)
__releases(dentry->d_lock)
- __releases(dcache_inode_lock)
+ __releases(dentry->d_inode->i_lock)
{
struct inode *inode = dentry->d_inode;
dentry->d_inode = NULL;
list_del_init(&dentry->d_alias);
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
fsnotify_inoderemove(inode);
if (dentry->d_op && dentry->d_op->d_iput)
static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
__releases(dentry->d_lock)
__releases(parent->d_lock)
- __releases(dcache_inode_lock)
+ __releases(dentry->d_inode->i_lock)
{
dentry->d_parent = NULL;
list_del(&dentry->d_u.d_child);
void __d_drop(struct dentry *dentry)
{
if (!(dentry->d_flags & DCACHE_UNHASHED)) {
- dentry->d_flags |= DCACHE_UNHASHED;
- spin_lock(&dcache_hash_lock);
- hlist_del_rcu(&dentry->d_hash);
- spin_unlock(&dcache_hash_lock);
- dentry_rcuwalk_barrier(dentry);
+ if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) {
+ bit_spin_lock(0,
+ (unsigned long *)&dentry->d_sb->s_anon.first);
+ dentry->d_flags |= DCACHE_UNHASHED;
+ hlist_bl_del_init(&dentry->d_hash);
+ __bit_spin_unlock(0,
+ (unsigned long *)&dentry->d_sb->s_anon.first);
+ } else {
+ struct dcache_hash_bucket *b;
+ b = d_hash(dentry->d_parent, dentry->d_name.hash);
+ spin_lock_bucket(b);
+ /*
+ * We may not actually need to put DCACHE_UNHASHED
+ * manipulations under the hash lock, but follow
+ * the principle of least surprise.
+ */
+ dentry->d_flags |= DCACHE_UNHASHED;
+ hlist_bl_del_rcu(&dentry->d_hash);
+ spin_unlock_bucket(b);
+ dentry_rcuwalk_barrier(dentry);
+ }
}
}
EXPORT_SYMBOL(__d_drop);
static inline struct dentry *dentry_kill(struct dentry *dentry, int ref)
__releases(dentry->d_lock)
{
+ struct inode *inode;
struct dentry *parent;
- if (!spin_trylock(&dcache_inode_lock)) {
+ inode = dentry->d_inode;
+ if (inode && !spin_trylock(&inode->i_lock)) {
relock:
spin_unlock(&dentry->d_lock);
cpu_relax();
else
parent = dentry->d_parent;
if (parent && !spin_trylock(&parent->d_lock)) {
- spin_unlock(&dcache_inode_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
goto relock;
}
struct dentry *de = NULL;
if (!list_empty(&inode->i_dentry)) {
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
de = __d_find_alias(inode, 0);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
}
return de;
}
{
struct dentry *dentry;
restart:
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_count) {
__dget_dlock(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
dput(dentry);
goto restart;
}
spin_unlock(&dentry->d_lock);
}
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(d_prune_aliases);
spin_unlock(&dentry->d_lock);
shrink_dcache_for_umount_subtree(dentry);
- while (!hlist_empty(&sb->s_anon)) {
- dentry = hlist_entry(sb->s_anon.first, struct dentry, d_hash);
+ while (!hlist_bl_empty(&sb->s_anon)) {
+ dentry = hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash);
shrink_dcache_for_umount_subtree(dentry);
}
}
dentry->d_sb = NULL;
dentry->d_op = NULL;
dentry->d_fsdata = NULL;
- INIT_HLIST_NODE(&dentry->d_hash);
+ INIT_HLIST_BL_NODE(&dentry->d_hash);
INIT_LIST_HEAD(&dentry->d_lru);
INIT_LIST_HEAD(&dentry->d_subdirs);
INIT_LIST_HEAD(&dentry->d_alias);
__dget_dlock(parent);
dentry->d_parent = parent;
dentry->d_sb = parent->d_sb;
+ d_set_d_op(dentry, dentry->d_sb->s_d_op);
list_add(&dentry->d_u.d_child, &parent->d_subdirs);
spin_unlock(&parent->d_lock);
}
}
EXPORT_SYMBOL(d_alloc);
+struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
+{
+ struct dentry *dentry = d_alloc(NULL, name);
+ if (dentry) {
+ dentry->d_sb = sb;
+ d_set_d_op(dentry, dentry->d_sb->s_d_op);
+ dentry->d_parent = dentry;
+ dentry->d_flags |= DCACHE_DISCONNECTED;
+ }
+ return dentry;
+}
+EXPORT_SYMBOL(d_alloc_pseudo);
+
struct dentry *d_alloc_name(struct dentry *parent, const char *name)
{
struct qstr q;
void d_instantiate(struct dentry *entry, struct inode * inode)
{
BUG_ON(!list_empty(&entry->d_alias));
- spin_lock(&dcache_inode_lock);
+ if (inode)
+ spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
- spin_unlock(&dcache_inode_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
security_d_instantiate(entry, inode);
}
EXPORT_SYMBOL(d_instantiate);
continue;
if (alias->d_parent != entry->d_parent)
continue;
- if (qstr->len != len)
- continue;
- if (memcmp(qstr->name, name, len))
+ if (dentry_cmp(qstr->name, qstr->len, name, len))
continue;
__dget(alias);
return alias;
BUG_ON(!list_empty(&entry->d_alias));
- spin_lock(&dcache_inode_lock);
+ if (inode)
+ spin_lock(&inode->i_lock);
result = __d_instantiate_unique(entry, inode);
- spin_unlock(&dcache_inode_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
if (!result) {
security_d_instantiate(entry, inode);
res = d_alloc(NULL, &name);
if (res) {
res->d_sb = root_inode->i_sb;
+ d_set_d_op(res, res->d_sb->s_d_op);
res->d_parent = res;
d_instantiate(res, root_inode);
}
}
EXPORT_SYMBOL(d_alloc_root);
-static inline struct hlist_head *d_hash(struct dentry *parent,
- unsigned long hash)
-{
- hash += ((unsigned long) parent ^ GOLDEN_RATIO_PRIME) / L1_CACHE_BYTES;
- hash = hash ^ ((hash ^ GOLDEN_RATIO_PRIME) >> D_HASHBITS);
- return dentry_hashtable + (hash & D_HASHMASK);
-}
-
/**
* d_obtain_alias - find or allocate a dentry for a given inode
* @inode: inode to allocate the dentry for
tmp->d_parent = tmp; /* make sure dput doesn't croak */
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
res = __d_find_alias(inode, 0);
if (res) {
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
dput(tmp);
goto out_iput;
}
/* attach a disconnected dentry */
spin_lock(&tmp->d_lock);
tmp->d_sb = inode->i_sb;
+ d_set_d_op(tmp, tmp->d_sb->s_d_op);
tmp->d_inode = inode;
tmp->d_flags |= DCACHE_DISCONNECTED;
- tmp->d_flags &= ~DCACHE_UNHASHED;
list_add(&tmp->d_alias, &inode->i_dentry);
- spin_lock(&dcache_hash_lock);
- hlist_add_head(&tmp->d_hash, &inode->i_sb->s_anon);
- spin_unlock(&dcache_hash_lock);
+ bit_spin_lock(0, (unsigned long *)&tmp->d_sb->s_anon.first);
+ tmp->d_flags &= ~DCACHE_UNHASHED;
+ hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
+ __bit_spin_unlock(0, (unsigned long *)&tmp->d_sb->s_anon.first);
spin_unlock(&tmp->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
return tmp;
struct dentry *new = NULL;
if (inode && S_ISDIR(inode->i_mode)) {
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
new = __d_find_alias(inode, 1);
if (new) {
BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED));
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(new, inode);
d_move(new, dentry);
iput(inode);
} else {
- /* already taking dcache_inode_lock, so d_add() by hand */
+ /* already taking inode->i_lock, so d_add() by hand */
__d_instantiate(dentry, inode);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(dentry, inode);
d_rehash(dentry);
}
* Negative dentry: instantiate it unless the inode is a directory and
* already has a dentry.
*/
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
if (!S_ISDIR(inode->i_mode) || list_empty(&inode->i_dentry)) {
__d_instantiate(found, inode);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(found, inode);
return found;
}
*/
new = list_entry(inode->i_dentry.next, struct dentry, d_alias);
__dget(new);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(found, inode);
d_move(new, found);
iput(inode);
unsigned int len = name->len;
unsigned int hash = name->hash;
const unsigned char *str = name->name;
- struct hlist_head *head = d_hash(parent, hash);
- struct hlist_node *node;
+ struct dcache_hash_bucket *b = d_hash(parent, hash);
+ struct hlist_bl_node *node;
struct dentry *dentry;
/*
*
* See Documentation/vfs/dcache-locking.txt for more details.
*/
- hlist_for_each_entry_rcu(dentry, node, head, d_hash) {
+ hlist_bl_for_each_entry_rcu(dentry, node, &b->head, d_hash) {
struct inode *i;
const char *tname;
int tlen;
tlen = dentry->d_name.len;
tname = dentry->d_name.name;
i = dentry->d_inode;
+ prefetch(tname);
+ if (i)
+ prefetch(i);
/*
* This seqcount check is required to ensure name and
* len are loaded atomically, so as not to walk off the
tlen, tname, name))
continue;
} else {
- if (tlen != len)
- continue;
- if (memcmp(tname, str, tlen))
+ if (dentry_cmp(tname, tlen, str, len))
continue;
}
/*
unsigned int len = name->len;
unsigned int hash = name->hash;
const unsigned char *str = name->name;
- struct hlist_head *head = d_hash(parent,hash);
- struct hlist_node *node;
+ struct dcache_hash_bucket *b = d_hash(parent, hash);
+ struct hlist_bl_node *node;
struct dentry *found = NULL;
struct dentry *dentry;
*/
rcu_read_lock();
- hlist_for_each_entry_rcu(dentry, node, head, d_hash) {
+ hlist_bl_for_each_entry_rcu(dentry, node, &b->head, d_hash) {
const char *tname;
int tlen;
tlen, tname, name))
goto next;
} else {
- if (tlen != len)
- goto next;
- if (memcmp(tname, str, tlen))
+ if (dentry_cmp(tname, tlen, str, len))
goto next;
}
/**
* d_validate - verify dentry provided from insecure source (deprecated)
* @dentry: The dentry alleged to be valid child of @dparent
- * @dparent: The parent dentry (known to be valid)
+ * @parent: The parent dentry (known to be valid)
*
* An insecure source has sent us a dentry, here we verify it and dget() it.
* This is used by ncpfs in its readdir implementation.
void d_delete(struct dentry * dentry)
{
+ struct inode *inode;
int isdir = 0;
/*
* Are we the only user?
*/
again:
spin_lock(&dentry->d_lock);
- isdir = S_ISDIR(dentry->d_inode->i_mode);
+ inode = dentry->d_inode;
+ isdir = S_ISDIR(inode->i_mode);
if (dentry->d_count == 1) {
- if (!spin_trylock(&dcache_inode_lock)) {
+ if (inode && !spin_trylock(&inode->i_lock)) {
spin_unlock(&dentry->d_lock);
cpu_relax();
goto again;
}
EXPORT_SYMBOL(d_delete);
-static void __d_rehash(struct dentry * entry, struct hlist_head *list)
+static void __d_rehash(struct dentry * entry, struct dcache_hash_bucket *b)
{
-
+ BUG_ON(!d_unhashed(entry));
+ spin_lock_bucket(b);
entry->d_flags &= ~DCACHE_UNHASHED;
- hlist_add_head_rcu(&entry->d_hash, list);
+ hlist_bl_add_head_rcu(&entry->d_hash, &b->head);
+ spin_unlock_bucket(b);
}
static void _d_rehash(struct dentry * entry)
void d_rehash(struct dentry * entry)
{
spin_lock(&entry->d_lock);
- spin_lock(&dcache_hash_lock);
_d_rehash(entry);
- spin_unlock(&dcache_hash_lock);
spin_unlock(&entry->d_lock);
}
EXPORT_SYMBOL(d_rehash);
write_seqcount_begin(&dentry->d_seq);
write_seqcount_begin(&target->d_seq);
- /* Move the dentry to the target hash queue, if on different bucket */
- spin_lock(&dcache_hash_lock);
- if (!d_unhashed(dentry))
- hlist_del_rcu(&dentry->d_hash);
+ /* __d_drop does write_seqcount_barrier, but they're OK to nest. */
+
+ /*
+ * Move the dentry to the target hash queue. Don't bother checking
+ * for the same hash queue because of how unlikely it is.
+ */
+ __d_drop(dentry);
__d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
- spin_unlock(&dcache_hash_lock);
/* Unhash the target: dput() will then get rid of it */
- /* __d_drop does write_seqcount_barrier, but they're OK to nest. */
__d_drop(target);
list_del(&dentry->d_u.d_child);
* This helper attempts to cope with remotely renamed directories
*
* It assumes that the caller is already holding
- * dentry->d_parent->d_inode->i_mutex and the dcache_inode_lock
+ * dentry->d_parent->d_inode->i_mutex and the inode->i_lock
*
* Note: If ever the locking in lock_rename() changes, then please
* remember to update this too...
*/
-static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias)
- __releases(dcache_inode_lock)
+static struct dentry *__d_unalias(struct inode *inode,
+ struct dentry *dentry, struct dentry *alias)
{
struct mutex *m1 = NULL, *m2 = NULL;
struct dentry *ret;
d_move(alias, dentry);
ret = alias;
out_err:
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
if (m2)
mutex_unlock(m2);
if (m1)
goto out_nolock;
}
- spin_lock(&dcache_inode_lock);
+ spin_lock(&inode->i_lock);
if (S_ISDIR(inode->i_mode)) {
struct dentry *alias;
goto found;
}
/* Nope, but we must(!) avoid directory aliasing */
- actual = __d_unalias(dentry, alias);
+ actual = __d_unalias(inode, dentry, alias);
if (IS_ERR(actual))
dput(alias);
goto out_nolock;
spin_lock(&actual->d_lock);
found:
- spin_lock(&dcache_hash_lock);
_d_rehash(actual);
- spin_unlock(&dcache_hash_lock);
spin_unlock(&actual->d_lock);
- spin_unlock(&dcache_inode_lock);
+ spin_unlock(&inode->i_lock);
out_nolock:
if (actual == dentry) {
security_d_instantiate(dentry, inode);
}
/**
- * Prepend path string to a buffer
- *
+ * prepend_path - Prepend path string to a buffer
* @path: the dentry/vfsmount to report
* @root: root vfsmnt/dentry (may be modified by this function)
* @buffer: pointer to the end of the buffer
dentry_hashtable =
alloc_large_system_hash("Dentry cache",
- sizeof(struct hlist_head),
+ sizeof(struct dcache_hash_bucket),
dhash_entries,
13,
HASH_EARLY,
0);
for (loop = 0; loop < (1 << d_hash_shift); loop++)
- INIT_HLIST_HEAD(&dentry_hashtable[loop]);
+ INIT_HLIST_BL_HEAD(&dentry_hashtable[loop].head);
}
static void __init dcache_init(void)
dentry_hashtable =
alloc_large_system_hash("Dentry cache",
- sizeof(struct hlist_head),
+ sizeof(struct dcache_hash_bucket),
dhash_entries,
13,
0,
0);
for (loop = 0; loop < (1 << d_hash_shift); loop++)
- INIT_HLIST_HEAD(&dentry_hashtable[loop]);
+ INIT_HLIST_BL_HEAD(&dentry_hashtable[loop].head);
}
/* SLAB cache for __getname() consumers */