summaryrefslogtreecommitdiff
path: root/fs/dcache.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/dcache.c')
-rw-r--r--fs/dcache.c1375
1 files changed, 981 insertions, 394 deletions
diff --git a/fs/dcache.c b/fs/dcache.c
index 23702a9d4e6d..5699d4c027cb 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -33,20 +33,58 @@
#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->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_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
+ * dcache_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_SPINLOCK(dcache_lock);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
-EXPORT_SYMBOL(dcache_lock);
+EXPORT_SYMBOL(rename_lock);
static struct kmem_cache *dentry_cache __read_mostly;
-#define DNAME_INLINE_LEN (sizeof(struct dentry)-offsetof(struct dentry,d_iname))
-
/*
* This is the single most critical data structure when it comes
* to the dcache: the hashtable for lookups. Somebody should try
@@ -60,22 +98,51 @@ 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 = {
.age_limit = 45,
};
-static struct percpu_counter nr_dentry __cacheline_aligned_in_smp;
-static struct percpu_counter nr_dentry_unused __cacheline_aligned_in_smp;
+static DEFINE_PER_CPU(unsigned int, nr_dentry);
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+static int get_nr_dentry(void)
+{
+ int i;
+ int sum = 0;
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_dentry, 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 = percpu_counter_sum_positive(&nr_dentry);
- dentry_stat.nr_unused = percpu_counter_sum_positive(&nr_dentry_unused);
+ dentry_stat.nr_dentry = get_nr_dentry();
return proc_dointvec(table, write, buffer, lenp, ppos);
}
#endif
@@ -91,35 +158,50 @@ static void __d_free(struct rcu_head *head)
}
/*
- * no dcache_lock, please.
+ * no locks, please.
*/
static void d_free(struct dentry *dentry)
{
- percpu_counter_dec(&nr_dentry);
+ BUG_ON(dentry->d_count);
+ this_cpu_dec(nr_dentry);
if (dentry->d_op && dentry->d_op->d_release)
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);
}
+/**
+ * dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
+ * 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.
+ * d_iput() operation if defined. Dentry has no refcount
+ * and is unhashed.
*/
static void dentry_iput(struct dentry * dentry)
__releases(dentry->d_lock)
- __releases(dcache_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_lock);
+ spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
fsnotify_inoderemove(inode);
if (dentry->d_op && dentry->d_op->d_iput)
@@ -128,40 +210,72 @@ static void dentry_iput(struct dentry * dentry)
iput(inode);
} else {
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
}
}
/*
- * dentry_lru_(add|del|move_tail) must be called with dcache_lock held.
+ * 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;
+ list_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);
+}
+
+/*
+ * dentry_lru_(add|del|move_tail) must be called with d_lock held.
*/
static void dentry_lru_add(struct dentry *dentry)
{
if (list_empty(&dentry->d_lru)) {
+ spin_lock(&dcache_lru_lock);
list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
dentry->d_sb->s_nr_dentry_unused++;
- percpu_counter_inc(&nr_dentry_unused);
+ dentry_stat.nr_unused++;
+ spin_unlock(&dcache_lru_lock);
}
}
+static void __dentry_lru_del(struct dentry *dentry)
+{
+ list_del_init(&dentry->d_lru);
+ dentry->d_sb->s_nr_dentry_unused--;
+ dentry_stat.nr_unused--;
+}
+
static void dentry_lru_del(struct dentry *dentry)
{
if (!list_empty(&dentry->d_lru)) {
- list_del_init(&dentry->d_lru);
- dentry->d_sb->s_nr_dentry_unused--;
- percpu_counter_dec(&nr_dentry_unused);
+ spin_lock(&dcache_lru_lock);
+ __dentry_lru_del(dentry);
+ spin_unlock(&dcache_lru_lock);
}
}
static void dentry_lru_move_tail(struct dentry *dentry)
{
+ spin_lock(&dcache_lru_lock);
if (list_empty(&dentry->d_lru)) {
list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
dentry->d_sb->s_nr_dentry_unused++;
- percpu_counter_inc(&nr_dentry_unused);
+ dentry_stat.nr_unused++;
} else {
list_move_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
}
+ spin_unlock(&dcache_lru_lock);
}
/**
@@ -171,22 +285,115 @@ static void dentry_lru_move_tail(struct dentry *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)
+static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
__releases(dentry->d_lock)
- __releases(dcache_lock)
+ __releases(parent->d_lock)
+ __releases(dentry->d_inode->i_lock)
{
- struct dentry *parent;
-
+ dentry->d_parent = NULL;
list_del(&dentry->d_u.d_child);
- /*drops the locks, at that point nobody can reach this dentry */
+ 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 (!(dentry->d_flags & DCACHE_UNHASHED)) {
+ 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);
+
+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 ref)
+ __releases(dentry->d_lock)
+{
+ struct inode *inode;
+ struct dentry *parent;
+
+ inode = dentry->d_inode;
+ if (inode && !spin_trylock(&inode->i_lock)) {
+relock:
+ 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;
- d_free(dentry);
- return parent;
+ if (parent && !spin_trylock(&parent->d_lock)) {
+ if (inode)
+ spin_unlock(&inode->i_lock);
+ goto relock;
+ }
+
+ if (ref)
+ dentry->d_count--;
+ /* if dentry was on the d_lru list delete it from there */
+ dentry_lru_del(dentry);
+ /* if it was on the hash then remove it */
+ __d_drop(dentry);
+ return d_kill(dentry, parent);
}
/*
@@ -214,34 +421,26 @@ static struct dentry *d_kill(struct dentry *dentry)
* 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.
- *
- * no dcache lock, please.
*/
-
void dput(struct dentry *dentry)
{
if (!dentry)
return;
repeat:
- if (atomic_read(&dentry->d_count) == 1)
+ if (dentry->d_count == 1)
might_sleep();
- if (!atomic_dec_and_lock(&dentry->d_count, &dcache_lock))
- return;
-
spin_lock(&dentry->d_lock);
- if (atomic_read(&dentry->d_count)) {
+ BUG_ON(!dentry->d_count);
+ if (dentry->d_count > 1) {
+ dentry->d_count--;
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
return;
}
- /*
- * AV: ->d_delete() is _NOT_ allowed to block now.
- */
- if (dentry->d_op && dentry->d_op->d_delete) {
+ if (dentry->d_flags & DCACHE_OP_DELETE) {
if (dentry->d_op->d_delete(dentry))
- goto unhash_it;
+ goto kill_it;
}
/* Unreachable? Get rid of it */
@@ -252,16 +451,12 @@ repeat:
dentry->d_flags |= DCACHE_REFERENCED;
dentry_lru_add(dentry);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
+ dentry->d_count--;
+ spin_unlock(&dentry->d_lock);
return;
-unhash_it:
- __d_drop(dentry);
kill_it:
- /* if dentry was on the d_lru list delete it from there */
- dentry_lru_del(dentry);
- dentry = d_kill(dentry);
+ dentry = dentry_kill(dentry, 1);
if (dentry)
goto repeat;
}
@@ -284,9 +479,9 @@ int d_invalidate(struct dentry * dentry)
/*
* If it's already been dropped, return OK.
*/
- spin_lock(&dcache_lock);
+ spin_lock(&dentry->d_lock);
if (d_unhashed(dentry)) {
- spin_unlock(&dcache_lock);
+ spin_unlock(&dentry->d_lock);
return 0;
}
/*
@@ -294,9 +489,9 @@ int d_invalidate(struct dentry * dentry)
* to get rid of unused child entries.
*/
if (!list_empty(&dentry->d_subdirs)) {
- spin_unlock(&dcache_lock);
+ spin_unlock(&dentry->d_lock);
shrink_dcache_parent(dentry);
- spin_lock(&dcache_lock);
+ spin_lock(&dentry->d_lock);
}
/*
@@ -309,35 +504,61 @@ int d_invalidate(struct dentry * dentry)
* we might still populate it if it was a
* working directory or similar).
*/
- spin_lock(&dentry->d_lock);
- if (atomic_read(&dentry->d_count) > 1) {
+ if (dentry->d_count > 1) {
if (dentry->d_inode && S_ISDIR(dentry->d_inode->i_mode)) {
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
return -EBUSY;
}
}
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
return 0;
}
EXPORT_SYMBOL(d_invalidate);
-/* This should be called _only_ with dcache_lock held */
-static inline struct dentry * __dget_locked(struct dentry *dentry)
+/* This must be called with d_lock held */
+static inline void __dget_dlock(struct dentry *dentry)
{
- atomic_inc(&dentry->d_count);
- dentry_lru_del(dentry);
- return dentry;
+ dentry->d_count++;
}
-struct dentry * dget_locked(struct dentry *dentry)
+static inline void __dget(struct dentry *dentry)
{
- return __dget_locked(dentry);
+ spin_lock(&dentry->d_lock);
+ __dget_dlock(dentry);
+ spin_unlock(&dentry->d_lock);
+}
+
+struct dentry *dget_parent(struct dentry *dentry)
+{
+ struct dentry *ret;
+
+repeat:
+ /*
+ * Don't need rcu_dereference because we re-check it was correct under
+ * the lock.
+ */
+ rcu_read_lock();
+ ret = dentry->d_parent;
+ if (!ret) {
+ rcu_read_unlock();
+ goto out;
+ }
+ 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_count);
+ ret->d_count++;
+ spin_unlock(&ret->d_lock);
+out:
+ return ret;
}
-EXPORT_SYMBOL(dget_locked);
+EXPORT_SYMBOL(dget_parent);
/**
* d_find_alias - grab a hashed alias of inode
@@ -355,42 +576,51 @@ EXPORT_SYMBOL(dget_locked);
* 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)
+static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
{
- struct list_head *head, *next, *tmp;
- struct dentry *alias, *discon_alias=NULL;
+ struct dentry *alias, *discon_alias;
- head = &inode->i_dentry;
- next = inode->i_dentry.next;
- while (next != head) {
- tmp = next;
- next = tmp->next;
- prefetch(next);
- alias = list_entry(tmp, struct dentry, d_alias);
+again:
+ discon_alias = NULL;
+ list_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))
+ (alias->d_flags & DCACHE_DISCONNECTED)) {
discon_alias = alias;
- else if (!want_discon) {
- __dget_locked(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;
}
- if (discon_alias)
- __dget_locked(discon_alias);
- return discon_alias;
+ return NULL;
}
-struct dentry * d_find_alias(struct inode *inode)
+struct dentry *d_find_alias(struct inode *inode)
{
struct dentry *de = NULL;
if (!list_empty(&inode->i_dentry)) {
- spin_lock(&dcache_lock);
+ spin_lock(&inode->i_lock);
de = __d_find_alias(inode, 0);
- spin_unlock(&dcache_lock);
+ spin_unlock(&inode->i_lock);
}
return de;
}
@@ -404,54 +634,61 @@ void d_prune_aliases(struct inode *inode)
{
struct dentry *dentry;
restart:
- spin_lock(&dcache_lock);
+ spin_lock(&inode->i_lock);
list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
- if (!atomic_read(&dentry->d_count)) {
- __dget_locked(dentry);
+ if (!dentry->d_count) {
+ __dget_dlock(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
+ spin_unlock(&inode->i_lock);
dput(dentry);
goto restart;
}
spin_unlock(&dentry->d_lock);
}
- spin_unlock(&dcache_lock);
+ spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(d_prune_aliases);
/*
- * Throw away a dentry - free the inode, dput the parent. This requires that
- * the LRU list has already been removed.
+ * 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.
*
- * Try to prune ancestors as well. This is necessary to prevent
- * quadratic behavior of shrink_dcache_parent(), but is also expected
- * to be beneficial in reducing dentry cache fragmentation.
+ * This may fail if locks cannot be acquired no problem, just try again.
*/
-static void prune_one_dentry(struct dentry * dentry)
+static void try_prune_one_dentry(struct dentry *dentry)
__releases(dentry->d_lock)
- __releases(dcache_lock)
- __acquires(dcache_lock)
{
- __d_drop(dentry);
- dentry = d_kill(dentry);
+ struct dentry *parent;
+ parent = dentry_kill(dentry, 0);
/*
- * Prune ancestors. Locking is simpler than in dput(),
- * because dcache_lock needs to be taken anyway.
+ * 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.
*/
- spin_lock(&dcache_lock);
+ if (!parent)
+ return;
+ if (parent == dentry)
+ return;
+
+ /* Prune ancestors. */
+ dentry = parent;
while (dentry) {
- if (!atomic_dec_and_lock(&dentry->d_count, &dentry->d_lock))
+ spin_lock(&dentry->d_lock);
+ if (dentry->d_count > 1) {
+ dentry->d_count--;
+ spin_unlock(&dentry->d_lock);
return;
-
- if (dentry->d_op && dentry->d_op->d_delete)
- dentry->d_op->d_delete(dentry);
- dentry_lru_del(dentry);
- __d_drop(dentry);
- dentry = d_kill(dentry);
- spin_lock(&dcache_lock);
+ }
+ dentry = dentry_kill(dentry, 1);
}
}
@@ -459,24 +696,35 @@ static void shrink_dentry_list(struct list_head *list)
{
struct dentry *dentry;
- while (!list_empty(list)) {
- dentry = list_entry(list->prev, struct dentry, d_lru);
- dentry_lru_del(dentry);
+ rcu_read_lock();
+ for (;;) {
+ dentry = list_entry_rcu(list->prev, struct dentry, d_lru);
+ if (&dentry->d_lru == list)
+ break; /* empty */
+ spin_lock(&dentry->d_lock);
+ if (dentry != list_entry(list->prev, struct dentry, d_lru)) {
+ spin_unlock(&dentry->d_lock);
+ continue;
+ }
/*
* We found an inuse dentry which was not removed from
* the LRU because of laziness during lookup. Do not free
* it - just keep it off the LRU list.
*/
- spin_lock(&dentry->d_lock);
- if (atomic_read(&dentry->d_count)) {
+ if (dentry->d_count) {
+ dentry_lru_del(dentry);
spin_unlock(&dentry->d_lock);
continue;
}
- prune_one_dentry(dentry);
- /* dentry->d_lock was dropped in prune_one_dentry() */
- cond_resched_lock(&dcache_lock);
+
+ rcu_read_unlock();
+
+ try_prune_one_dentry(dentry);
+
+ rcu_read_lock();
}
+ rcu_read_unlock();
}
/**
@@ -495,42 +743,44 @@ static void __shrink_dcache_sb(struct super_block *sb, int *count, int flags)
LIST_HEAD(tmp);
int cnt = *count;
- spin_lock(&dcache_lock);
+relock:
+ spin_lock(&dcache_lru_lock);
while (!list_empty(&sb->s_dentry_lru)) {
dentry = list_entry(sb->s_dentry_lru.prev,
struct dentry, d_lru);
BUG_ON(dentry->d_sb != sb);
+ if (!spin_trylock(&dentry->d_lock)) {
+ spin_unlock(&dcache_lru_lock);
+ cpu_relax();
+ goto relock;
+ }
+
/*
* If we are honouring the DCACHE_REFERENCED flag and the
* dentry has this flag set, don't free it. Clear the flag
* and put it back on the LRU.
*/
- if (flags & DCACHE_REFERENCED) {
- spin_lock(&dentry->d_lock);
- if (dentry->d_flags & DCACHE_REFERENCED) {
- dentry->d_flags &= ~DCACHE_REFERENCED;
- list_move(&dentry->d_lru, &referenced);
- spin_unlock(&dentry->d_lock);
- cond_resched_lock(&dcache_lock);
- continue;
- }
+ if (flags & DCACHE_REFERENCED &&
+ dentry->d_flags & DCACHE_REFERENCED) {
+ dentry->d_flags &= ~DCACHE_REFERENCED;
+ list_move(&dentry->d_lru, &referenced);
spin_unlock(&dentry->d_lock);
+ } else {
+ list_move_tail(&dentry->d_lru, &tmp);
+ spin_unlock(&dentry->d_lock);
+ if (!--cnt)
+ break;
}
-
- list_move_tail(&dentry->d_lru, &tmp);
- if (!--cnt)
- break;
- cond_resched_lock(&dcache_lock);
+ cond_resched_lock(&dcache_lru_lock);
}
-
- *count = cnt;
- shrink_dentry_list(&tmp);
-
if (!list_empty(&referenced))
list_splice(&referenced, &sb->s_dentry_lru);
- spin_unlock(&dcache_lock);
+ spin_unlock(&dcache_lru_lock);
+ shrink_dentry_list(&tmp);
+
+ *count = cnt;
}
/**
@@ -546,13 +796,12 @@ static void prune_dcache(int count)
{
struct super_block *sb, *p = NULL;
int w_count;
- int unused = percpu_counter_sum_positive(&nr_dentry_unused);
+ int unused = dentry_stat.nr_unused;
int prune_ratio;
int pruned;
if (unused == 0 || count == 0)
return;
- spin_lock(&dcache_lock);
if (count >= unused)
prune_ratio = 1;
else
@@ -589,11 +838,9 @@ static void prune_dcache(int count)
if (down_read_trylock(&sb->s_umount)) {
if ((sb->s_root != NULL) &&
(!list_empty(&sb->s_dentry_lru))) {
- spin_unlock(&dcache_lock);
__shrink_dcache_sb(sb, &w_count,
DCACHE_REFERENCED);
pruned -= w_count;
- spin_lock(&dcache_lock);
}
up_read(&sb->s_umount);
}
@@ -609,7 +856,6 @@ static void prune_dcache(int count)
if (p)
__put_super(p);
spin_unlock(&sb_lock);
- spin_unlock(&dcache_lock);
}
/**
@@ -623,12 +869,14 @@ void shrink_dcache_sb(struct super_block *sb)
{
LIST_HEAD(tmp);
- spin_lock(&dcache_lock);
+ spin_lock(&dcache_lru_lock);
while (!list_empty(&sb->s_dentry_lru)) {
list_splice_init(&sb->s_dentry_lru, &tmp);
+ spin_unlock(&dcache_lru_lock);
shrink_dentry_list(&tmp);
+ spin_lock(&dcache_lru_lock);
}
- spin_unlock(&dcache_lock);
+ spin_unlock(&dcache_lru_lock);
}
EXPORT_SYMBOL(shrink_dcache_sb);
@@ -645,10 +893,10 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
BUG_ON(!IS_ROOT(dentry));
/* detach this root from the system */
- spin_lock(&dcache_lock);
+ spin_lock(&dentry->d_lock);
dentry_lru_del(dentry);
__d_drop(dentry);
- spin_unlock(&dcache_lock);
+ spin_unlock(&dentry->d_lock);
for (;;) {
/* descend to the first leaf in the current subtree */
@@ -657,14 +905,16 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
/* this is a branch with children - detach all of them
* from the system in one go */
- spin_lock(&dcache_lock);
+ spin_lock(&dentry->d_lock);
list_for_each_entry(loop, &dentry->d_subdirs,
d_u.d_child) {
+ spin_lock_nested(&loop->d_lock,
+ DENTRY_D_LOCK_NESTED);
dentry_lru_del(loop);
__d_drop(loop);
- cond_resched_lock(&dcache_lock);
+ spin_unlock(&loop->d_lock);
}
- spin_unlock(&dcache_lock);
+ spin_unlock(&dentry->d_lock);
/* move to the first child */
dentry = list_entry(dentry->d_subdirs.next,
@@ -676,7 +926,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
do {
struct inode *inode;
- if (atomic_read(&dentry->d_count) != 0) {
+ if (dentry->d_count != 0) {
printk(KERN_ERR
"BUG: Dentry %p{i=%lx,n=%s}"
" still in use (%d)"
@@ -685,20 +935,23 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
dentry->d_inode ?
dentry->d_inode->i_ino : 0UL,
dentry->d_name.name,
- atomic_read(&dentry->d_count),
+ dentry->d_count,
dentry->d_sb->s_type->name,
dentry->d_sb->s_id);
BUG();
}
- if (IS_ROOT(dentry))
+ if (IS_ROOT(dentry)) {
parent = NULL;
- else {
+ list_del(&dentry->d_u.d_child);
+ } else {
parent = dentry->d_parent;
- atomic_dec(&parent->d_count);
+ spin_lock(&parent->d_lock);
+ parent->d_count--;
+ list_del(&dentry->d_u.d_child);
+ spin_unlock(&parent->d_lock);
}
- list_del(&dentry->d_u.d_child);
detached++;
inode = dentry->d_inode;
@@ -728,8 +981,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
/*
* destroy the dentries attached to a superblock on unmounting
- * - we don't need to use dentry->d_lock, and only need dcache_lock when
- * removing the dentry from the system lists and hashes because:
+ * - we don't need to use dentry->d_lock because:
* - the superblock is detached from all mountings and open files, so the
* dentry trees will not be rearranged by the VFS
* - s_umount is write-locked, so the memory pressure shrinker will ignore
@@ -746,11 +998,13 @@ void shrink_dcache_for_umount(struct super_block *sb)
dentry = sb->s_root;
sb->s_root = NULL;
- atomic_dec(&dentry->d_count);
+ spin_lock(&dentry->d_lock);
+ dentry->d_count--;
+ 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);
}
}
@@ -768,15 +1022,20 @@ void shrink_dcache_for_umount(struct super_block *sb)
* Return true if the parent or its subdirectories contain
* a mount point
*/
-
int have_submounts(struct dentry *parent)
{
- struct dentry *this_parent = parent;
+ struct dentry *this_parent;
struct list_head *next;
+ unsigned seq;
+ int locked = 0;
+
+ seq = read_seqbegin(&rename_lock);
+again:
+ this_parent = parent;
- spin_lock(&dcache_lock);
if (d_mountpoint(parent))
goto positive;
+ spin_lock(&this_parent->d_lock);
repeat:
next = this_parent->d_subdirs.next;
resume:
@@ -784,27 +1043,65 @@ resume:
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);
/* Have we found a mount point ? */
- if (d_mountpoint(dentry))
+ if (d_mountpoint(dentry)) {
+ spin_unlock(&dentry->d_lock);
+ spin_unlock(&this_parent->d_lock);
goto positive;
+ }
if (!list_empty(&dentry->d_subdirs)) {
+ spin_unlock(&this_parent->d_lock);
+ spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
this_parent = dentry;
+ spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
goto repeat;
}
+ spin_unlock(&dentry->d_lock);
}
/*
* All done at this level ... ascend and resume the search.
*/
if (this_parent != parent) {
- next = this_parent->d_u.d_child.next;
- this_parent = this_parent->d_parent;
+ struct dentry *tmp;
+ struct dentry *child;
+
+ tmp = this_parent->d_parent;
+ rcu_read_lock();
+ spin_unlock(&this_parent->d_lock);
+ child = this_parent;
+ this_parent = tmp;
+ spin_lock(&this_parent->d_lock);
+ /* might go back up the wrong parent if we have had a rename
+ * or deletion */
+ if (this_parent != child->d_parent ||
+ (!locked && read_seqretry(&rename_lock, seq))) {
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
+ goto rename_retry;
+ }
+ rcu_read_unlock();
+ next = child->d_u.d_child.next;
goto resume;
}
- spin_unlock(&dcache_lock);
+ spin_unlock(&this_parent->d_lock);
+ if (!locked && read_seqretry(&rename_lock, seq))
+ goto rename_retry;
+ if (locked)
+ write_sequnlock(&rename_lock);
return 0; /* No mount points found in tree */
positive:
- spin_unlock(&dcache_lock);
+ if (!locked && read_seqretry(&rename_lock, seq))
+ goto rename_retry;
+ if (locked)
+ write_sequnlock(&rename_lock);
return 1;
+
+rename_retry:
+ locked = 1;
+ write_seqlock(&rename_lock);
+ goto again;
}
EXPORT_SYMBOL(have_submounts);
@@ -824,11 +1121,16 @@ EXPORT_SYMBOL(have_submounts);
*/
static int select_parent(struct dentry * parent)
{
- struct dentry *this_parent = parent;
+ struct dentry *this_parent;
struct list_head *next;
+ unsigned seq;
int found = 0;
+ int locked = 0;
- spin_lock(&dcache_lock);
+ seq = read_seqbegin(&rename_lock);
+again:
+ this_parent = parent;
+ spin_lock(&this_parent->d_lock);
repeat:
next = this_parent->d_subdirs.next;
resume:
@@ -837,11 +1139,13 @@ resume:
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);
+
/*
* move only zero ref count dentries to the end
* of the unused list for prune_dcache
*/
- if (!atomic_read(&dentry->d_count)) {
+ if (!dentry->d_count) {
dentry_lru_move_tail(dentry);
found++;
} else {
@@ -853,28 +1157,63 @@ resume:
* ensures forward progress). We'll be coming back to find
* the rest.
*/
- if (found && need_resched())
+ if (found && need_resched()) {
+ spin_unlock(&dentry->d_lock);
goto out;
+ }
/*
* Descend a level if the d_subdirs list is non-empty.
*/
if (!list_empty(&dentry->d_subdirs)) {
+ spin_unlock(&this_parent->d_lock);
+ spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
this_parent = dentry;
+ spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
goto repeat;
}
+
+ spin_unlock(&dentry->d_lock);
}
/*
* All done at this level ... ascend and resume the search.
*/
if (this_parent != parent) {
- next = this_parent->d_u.d_child.next;
- this_parent = this_parent->d_parent;
+ struct dentry *tmp;
+ struct dentry *child;
+
+ tmp = this_parent->d_parent;
+ rcu_read_lock();
+ spin_unlock(&this_parent->d_lock);
+ child = this_parent;
+ this_parent = tmp;
+ spin_lock(&this_parent->d_lock);
+ /* might go back up the wrong parent if we have had a rename
+ * or deletion */
+ if (this_parent != child->d_parent ||
+ (!locked && read_seqretry(&rename_lock, seq))) {
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
+ goto rename_retry;
+ }
+ rcu_read_unlock();
+ next = child->d_u.d_child.next;
goto resume;
}
out:
- spin_unlock(&dcache_lock);
+ spin_unlock(&this_parent->d_lock);
+ if (!locked && read_seqretry(&rename_lock, seq))
+ goto rename_retry;
+ if (locked)
+ write_sequnlock(&rename_lock);
return found;
+
+rename_retry:
+ if (found)
+ return found;
+ locked = 1;
+ write_seqlock(&rename_lock);
+ goto again;
}
/**
@@ -908,16 +1247,13 @@ EXPORT_SYMBOL(shrink_dcache_parent);
*/
static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
{
- int nr_unused;
-
if (nr) {
if (!(gfp_mask & __GFP_FS))
return -1;
prune_dcache(nr);
}
- nr_unused = percpu_counter_sum_positive(&nr_dentry_unused);
- return (nr_unused / 100) * sysctl_vfs_cache_pressure;
+ return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
}
static struct shrinker dcache_shrinker = {
@@ -960,38 +1296,52 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
memcpy(dname, name->name, name->len);
dname[name->len] = 0;
- atomic_set(&dentry->d_count, 1);
+ dentry->d_count = 1;
dentry->d_flags = DCACHE_UNHASHED;
spin_lock_init(&dentry->d_lock);
+ seqcount_init(&dentry->d_seq);
dentry->d_inode = NULL;
dentry->d_parent = NULL;
dentry->d_sb = NULL;
dentry->d_op = NULL;
dentry->d_fsdata = NULL;
- dentry->d_mounted = 0;
- 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);
+ INIT_LIST_HEAD(&dentry->d_u.d_child);
if (parent) {
- dentry->d_parent = dget(parent);
+ spin_lock(&parent->d_lock);
+ /*
+ * don't need child lock because it is not subject
+ * to concurrency here
+ */
+ __dget_dlock(parent);
+ dentry->d_parent = parent;
dentry->d_sb = parent->d_sb;
- } else {
- INIT_LIST_HEAD(&dentry->d_u.d_child);
- }
-
- spin_lock(&dcache_lock);
- if (parent)
list_add(&dentry->d_u.d_child, &parent->d_subdirs);
- spin_unlock(&dcache_lock);
+ spin_unlock(&parent->d_lock);
+ }
- percpu_counter_inc(&nr_dentry);
+ this_cpu_inc(nr_dentry);
return dentry;
}
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;
+ 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;
@@ -1003,12 +1353,36 @@ struct dentry *d_alloc_name(struct dentry *parent, const char *name)
}
EXPORT_SYMBOL(d_alloc_name);
-/* the caller must hold dcache_lock */
+void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
+{
+ BUG_ON(dentry->d_op);
+ BUG_ON(dentry->d_flags & (DCACHE_OP_HASH |
+ DCACHE_OP_COMPARE |
+ DCACHE_OP_REVALIDATE |
+ DCACHE_OP_DELETE ));
+ dentry->d_op = op;
+ if (!op)
+ return;
+ if (op->d_hash)
+ dentry->d_flags |= DCACHE_OP_HASH;
+ if (op->d_compare)
+ dentry->d_flags |= DCACHE_OP_COMPARE;
+ if (op->d_revalidate)
+ dentry->d_flags |= DCACHE_OP_REVALIDATE;
+ if (op->d_delete)
+ dentry->d_flags |= DCACHE_OP_DELETE;
+
+}
+EXPORT_SYMBOL(d_set_d_op);
+
static void __d_instantiate(struct dentry *dentry, struct inode *inode)
{
+ spin_lock(&dentry->d_lock);
if (inode)
list_add(&dentry->d_alias, &inode->i_dentry);
dentry->d_inode = inode;
+ dentry_rcuwalk_barrier(dentry);
+ spin_unlock(&dentry->d_lock);
fsnotify_d_instantiate(dentry, inode);
}
@@ -1030,9 +1404,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
void d_instantiate(struct dentry *entry, struct inode * inode)
{
BUG_ON(!list_empty(&entry->d_alias));
- spin_lock(&dcache_lock);
+ if (inode)
+ spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
- spin_unlock(&dcache_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
security_d_instantiate(entry, inode);
}
EXPORT_SYMBOL(d_instantiate);
@@ -1069,15 +1445,18 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry,
list_for_each_entry(alias, &inode->i_dentry, d_alias) {
struct qstr *qstr = &alias->d_name;
+ /*
+ * Don't need alias->d_lock here, because aliases with
+ * d_parent == entry->d_parent are not subject to name or
+ * parent changes, because the parent inode i_mutex is held.
+ */
if (qstr->hash != hash)
continue;
if (alias->d_parent != entry->d_parent)
continue;
- if (qstr->len != len)
+ if (dentry_cmp(qstr->name, qstr->len, name, len))
continue;
- if (memcmp(qstr->name, name, len))
- continue;
- dget_locked(alias);
+ __dget(alias);
return alias;
}
@@ -1091,9 +1470,11 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
BUG_ON(!list_empty(&entry->d_alias));
- spin_lock(&dcache_lock);
+ if (inode)
+ spin_lock(&inode->i_lock);
result = __d_instantiate_unique(entry, inode);
- spin_unlock(&dcache_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
if (!result) {
security_d_instantiate(entry, inode);
@@ -1134,14 +1515,6 @@ struct dentry * d_alloc_root(struct inode * 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
@@ -1182,10 +1555,11 @@ struct dentry *d_obtain_alias(struct inode *inode)
}
tmp->d_parent = tmp; /* make sure dput doesn't croak */
- spin_lock(&dcache_lock);
+
+ spin_lock(&inode->i_lock);
res = __d_find_alias(inode, 0);
if (res) {
- spin_unlock(&dcache_lock);
+ spin_unlock(&inode->i_lock);
dput(tmp);
goto out_iput;
}
@@ -1195,12 +1569,14 @@ struct dentry *d_obtain_alias(struct inode *inode)
tmp->d_sb = inode->i_sb;
tmp->d_inode = inode;
tmp->d_flags |= DCACHE_DISCONNECTED;
- tmp->d_flags &= ~DCACHE_UNHASHED;
list_add(&tmp->d_alias, &inode->i_dentry);
- hlist_add_head(&tmp->d_hash, &inode->i_sb->s_anon);
+ 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(&inode->i_lock);
- spin_unlock(&dcache_lock);
return tmp;
out_iput:
@@ -1230,18 +1606,18 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
struct dentry *new = NULL;
if (inode && S_ISDIR(inode->i_mode)) {
- spin_lock(&dcache_lock);
+ spin_lock(&inode->i_lock);
new = __d_find_alias(inode, 1);
if (new) {
BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED));
- spin_unlock(&dcache_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(new, inode);
d_move(new, dentry);
iput(inode);
} else {
- /* already taking dcache_lock, so d_add() by hand */
+ /* already taking inode->i_lock, so d_add() by hand */
__d_instantiate(dentry, inode);
- spin_unlock(&dcache_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(dentry, inode);
d_rehash(dentry);
}
@@ -1314,10 +1690,10 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
* Negative dentry: instantiate it unless the inode is a directory and
* already has a dentry.
*/
- spin_lock(&dcache_lock);
+ spin_lock(&inode->i_lock);
if (!S_ISDIR(inode->i_mode) || list_empty(&inode->i_dentry)) {
__d_instantiate(found, inode);
- spin_unlock(&dcache_lock);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(found, inode);
return found;
}
@@ -1327,8 +1703,8 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
* reference to it, move it in place and use it.
*/
new = list_entry(inode->i_dentry.next, struct dentry, d_alias);
- dget_locked(new);
- spin_unlock(&dcache_lock);
+ __dget(new);
+ spin_unlock(&inode->i_lock);
security_d_instantiate(found, inode);
d_move(new, found);
iput(inode);
@@ -1342,6 +1718,112 @@ err_out:
EXPORT_SYMBOL(d_add_ci);
/**
+ * __d_lookup_rcu - search for a dentry (racy, store-free)
+ * @parent: parent dentry
+ * @name: qstr of name we wish to find
+ * @seq: returns d_seq value at the point where the dentry was found
+ * @inode: returns dentry->d_inode when the inode was found valid.
+ * Returns: dentry, or NULL
+ *
+ * __d_lookup_rcu is the dcache lookup function for rcu-walk name
+ * resolution (store-free path walking) design described in
+ * Documentation/filesystems/path-lookup.txt.
+ *
+ * This is not to be used outside core vfs.
+ *
+ * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock
+ * held, and rcu_read_lock held. The returned dentry must not be stored into
+ * without taking d_lock and checking d_seq sequence count against @seq
+ * returned here.
+ *
+ * A refcount may be taken on the found dentry with the __d_rcu_to_refcount
+ * function.
+ *
+ * Alternatively, __d_lookup_rcu may be called again to look up the child of
+ * the returned dentry, so long as its parent's seqlock is checked after the
+ * child is looked up. Thus, an interlocking stepping of sequence lock checks
+ * is formed, giving integrity down the path walk.
+ */
+struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
+ unsigned *seq, struct inode **inode)
+{
+ unsigned int len = name->len;
+ unsigned int hash = name->hash;
+ const unsigned char *str = name->name;
+ struct dcache_hash_bucket *b = d_hash(parent, hash);
+ struct hlist_bl_node *node;
+ struct dentry *dentry;
+
+ /*
+ * Note: There is significant duplication with __d_lookup_rcu which is
+ * required to prevent single threaded performance regressions
+ * especially on architectures where smp_rmb (in seqcounts) are costly.
+ * Keep the two functions in sync.
+ */
+
+ /*
+ * The hash list is protected using RCU.
+ *
+ * Carefully use d_seq when comparing a candidate dentry, to avoid
+ * races with d_move().
+ *
+ * It is possible that concurrent renames can mess up our list
+ * walk here and result in missing our dentry, resulting in the
+ * false-negative result. d_lookup() protects against concurrent
+ * renames using rename_lock seqlock.
+ *
+ * See Documentation/vfs/dcache-locking.txt for more details.
+ */
+ hlist_bl_for_each_entry_rcu(dentry, node, &b->head, d_hash) {
+ struct inode *i;
+ const char *tname;
+ int tlen;
+
+ if (dentry->d_name.hash != hash)
+ continue;
+
+seqretry:
+ *seq = read_seqcount_begin(&dentry->d_seq);
+ if (dentry->d_parent != parent)
+ continue;
+ if (d_unhashed(dentry))
+ continue;
+ 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
+ * edge of memory when walking. If we could load this
+ * atomically some other way, we could drop this check.
+ */
+ if (read_seqcount_retry(&dentry->d_seq, *seq))
+ goto seqretry;
+ if (parent->d_flags & DCACHE_OP_COMPARE) {
+ if (parent->d_op->d_compare(parent, *inode,
+ dentry, i,
+ tlen, tname, name))
+ continue;
+ } else {
+ if (dentry_cmp(tname, tlen, str, len))
+ continue;
+ }
+ /*
+ * No extra seqcount check is required after the name
+ * compare. The caller must perform a seqcount check in
+ * order to do anything useful with the returned dentry
+ * anyway.
+ */
+ *inode = i;
+ return dentry;
+ }
+ return NULL;
+}
+
+/**
* d_lookup - search for a dentry
* @parent: parent dentry
* @name: qstr of name we wish to find
@@ -1352,10 +1834,10 @@ EXPORT_SYMBOL(d_add_ci);
* dentry is returned. The caller must use dput to free the entry when it has
* finished using it. %NULL is returned if the dentry does not exist.
*/
-struct dentry * d_lookup(struct dentry * parent, struct qstr * name)
+struct dentry *d_lookup(struct dentry *parent, struct qstr *name)
{
- struct dentry * dentry = NULL;
- unsigned long seq;
+ struct dentry *dentry;
+ unsigned seq;
do {
seq = read_seqbegin(&rename_lock);
@@ -1367,7 +1849,7 @@ struct dentry * d_lookup(struct dentry * parent, struct qstr * name)
}
EXPORT_SYMBOL(d_lookup);
-/*
+/**
* __d_lookup - search for a dentry (racy)
* @parent: parent dentry
* @name: qstr of name we wish to find
@@ -1382,17 +1864,24 @@ EXPORT_SYMBOL(d_lookup);
*
* __d_lookup callers must be commented.
*/
-struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
+struct dentry *__d_lookup(struct dentry *parent, struct qstr *name)
{
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 dcache_hash_bucket *b = d_hash(parent, hash);
+ struct hlist_bl_node *node;
struct dentry *found = NULL;
- struct hlist_node *node;
struct dentry *dentry;
/*
+ * Note: There is significant duplication with __d_lookup_rcu which is
+ * required to prevent single threaded performance regressions
+ * especially on architectures where smp_rmb (in seqcounts) are costly.
+ * Keep the two functions in sync.
+ */
+
+ /*
* The hash list is protected using RCU.
*
* Take d_lock when comparing a candidate dentry, to avoid races
@@ -1407,25 +1896,16 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
*/
rcu_read_lock();
- hlist_for_each_entry_rcu(dentry, node, head, d_hash) {
- struct qstr *qstr;
+ hlist_bl_for_each_entry_rcu(dentry, node, &b->head, d_hash) {
+ const char *tname;
+ int tlen;
if (dentry->d_name.hash != hash)
continue;
- if (dentry->d_parent != parent)
- continue;
spin_lock(&dentry->d_lock);
-
- /*
- * Recheck the dentry after taking the lock - d_move may have
- * changed things. Don't bother checking the hash because
- * we're about to compare the whole name anyway.
- */
if (dentry->d_parent != parent)
goto next;
-
- /* non-existing due to RCU? */
if (d_unhashed(dentry))
goto next;
@@ -1433,18 +1913,19 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
* It is safe to compare names since d_move() cannot
* change the qstr (protected by d_lock).
*/
- qstr = &dentry->d_name;
- if (parent->d_op && parent->d_op->d_compare) {
- if (parent->d_op->d_compare(parent, qstr, name))
+ tlen = dentry->d_name.len;
+ tname = dentry->d_name.name;
+ if (parent->d_flags & DCACHE_OP_COMPARE) {
+ if (parent->d_op->d_compare(parent, parent->d_inode,
+ dentry, dentry->d_inode,
+ tlen, tname, name))
goto next;
} else {
- if (qstr->len != len)
- goto next;
- if (memcmp(qstr->name, str, len))
+ if (dentry_cmp(tname, tlen, str, len))
goto next;
}
- atomic_inc(&dentry->d_count);
+ dentry->d_count++;
found = dentry;
spin_unlock(&dentry->d_lock);
break;
@@ -1473,8 +1954,8 @@ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
* routine may choose to leave the hash value unchanged.
*/
name->hash = full_name_hash(name->name, name->len);
- if (dir->d_op && dir->d_op->d_hash) {
- if (dir->d_op->d_hash(dir, name) < 0)
+ if (dir->d_flags & DCACHE_OP_HASH) {
+ if (dir->d_op->d_hash(dir, dir->d_inode, name) < 0)
goto out;
}
dentry = d_lookup(dir, name);
@@ -1483,34 +1964,32 @@ out:
}
/**
- * d_validate - verify dentry provided from insecure source
+ * 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)
*
* An insecure source has sent us a dentry, here we verify it and dget() it.
* This is used by ncpfs in its readdir implementation.
* Zero is returned in the dentry is invalid.
+ *
+ * This function is slow for big directories, and deprecated, do not use it.
*/
-int d_validate(struct dentry *dentry, struct dentry *parent)
+int d_validate(struct dentry *dentry, struct dentry *dparent)
{
- struct hlist_head *head = d_hash(parent, dentry->d_name.hash);
- struct hlist_node *node;
- struct dentry *d;
-
- /* Check whether the ptr might be valid at all.. */
- if (!kmem_ptr_validate(dentry_cache, dentry))
- return 0;
- if (dentry->d_parent != parent)
- return 0;
+ struct dentry *child;
- rcu_read_lock();
- hlist_for_each_entry_rcu(d, node, head, d_hash) {
- if (d == dentry) {
- dget(dentry);
+ spin_lock(&dparent->d_lock);
+ list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) {
+ if (dentry == child) {
+ spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+ __dget_dlock(dentry);
+ spin_unlock(&dentry->d_lock);
+ spin_unlock(&dparent->d_lock);
return 1;
}
}
- rcu_read_unlock();
+ spin_unlock(&dparent->d_lock);
+
return 0;
}
EXPORT_SYMBOL(d_validate);
@@ -1538,16 +2017,23 @@ EXPORT_SYMBOL(d_validate);
void d_delete(struct dentry * dentry)
{
+ struct inode *inode;
int isdir = 0;
/*
* Are we the only user?
*/
- spin_lock(&dcache_lock);
+again:
spin_lock(&dentry->d_lock);
- isdir = S_ISDIR(dentry->d_inode->i_mode);
- if (atomic_read(&dentry->d_count) == 1) {
+ inode = dentry->d_inode;
+ isdir = S_ISDIR(inode->i_mode);
+ if (dentry->d_count == 1) {
+ if (inode && !spin_trylock(&inode->i_lock)) {
+ spin_unlock(&dentry->d_lock);
+ cpu_relax();
+ goto again;
+ }
dentry->d_flags &= ~DCACHE_CANT_MOUNT;
- dentry_iput(dentry);
+ dentry_unlink_inode(dentry);
fsnotify_nameremove(dentry, isdir);
return;
}
@@ -1556,17 +2042,18 @@ void d_delete(struct dentry * dentry)
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
fsnotify_nameremove(dentry, isdir);
}
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)
@@ -1583,25 +2070,39 @@ static void _d_rehash(struct dentry * entry)
void d_rehash(struct dentry * entry)
{
- spin_lock(&dcache_lock);
spin_lock(&entry->d_lock);
_d_rehash(entry);
spin_unlock(&entry->d_lock);
- spin_unlock(&dcache_lock);
}
EXPORT_SYMBOL(d_rehash);
-/*
- * When switching names, the actual string doesn't strictly have to
- * be preserved in the target - because we're dropping the target
- * anyway. As such, we can just do a simple memcpy() to copy over
- * the new name before we switch.
+/**
+ * dentry_update_name_case - update case insensitive dentry with a new name
+ * @dentry: dentry to be updated
+ * @name: new name
*
- * Note that we have to be a lot more careful about getting the hash
- * switched - we have to switch the hash value properly even if it
- * then no longer matches the actual (corrupted) string of the target.
- * The hash value has to match the hash queue that the dentry is on..
+ * Update a case insensitive dentry with new case of name.
+ *
+ * dentry must have been returned by d_lookup with name @name. Old and new
+ * name lengths must match (ie. no d_compare which allows mismatched name
+ * lengths).
+ *
+ * Parent inode i_mutex must be held over d_lookup and into this call (to
+ * keep renames and concurrent inserts, and readdir(2) away).
*/
+void dentry_update_name_case(struct dentry *dentry, struct qstr *name)
+{
+ BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
+ BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */
+
+ spin_lock(&dentry->d_lock);
+ write_seqcount_begin(&dentry->d_seq);
+ memcpy((unsigned char *)dentry->d_name.name, name->name, name->len);
+ write_seqcount_end(&dentry->d_seq);
+ spin_unlock(&dentry->d_lock);
+}
+EXPORT_SYMBOL(dentry_update_name_case);
+
static void switch_names(struct dentry *dentry, struct dentry *target)
{
if (dname_external(target)) {
@@ -1643,54 +2144,84 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
swap(dentry->d_name.len, target->d_name.len);
}
+static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
+{
+ /*
+ * XXXX: do we really need to take target->d_lock?
+ */
+ if (IS_ROOT(dentry) || dentry->d_parent == target->d_parent)
+ spin_lock(&target->d_parent->d_lock);
+ else {
+ if (d_ancestor(dentry->d_parent, target->d_parent)) {
+ spin_lock(&dentry->d_parent->d_lock);
+ spin_lock_nested(&target->d_parent->d_lock,
+ DENTRY_D_LOCK_NESTED);
+ } else {
+ spin_lock(&target->d_parent->d_lock);
+ spin_lock_nested(&dentry->d_parent->d_lock,
+ DENTRY_D_LOCK_NESTED);
+ }
+ }
+ if (target < dentry) {
+ spin_lock_nested(&target->d_lock, 2);
+ spin_lock_nested(&dentry->d_lock, 3);
+ } else {
+ spin_lock_nested(&dentry->d_lock, 2);
+ spin_lock_nested(&target->d_lock, 3);
+ }
+}
+
+static void dentry_unlock_parents_for_move(struct dentry *dentry,
+ struct dentry *target)
+{
+ if (target->d_parent != dentry->d_parent)
+ spin_unlock(&dentry->d_parent->d_lock);
+ if (target->d_parent != target)
+ spin_unlock(&target->d_parent->d_lock);
+}
+
/*
- * We cannibalize "target" when moving dentry on top of it,
- * because it's going to be thrown away anyway. We could be more
- * polite about it, though.
- *
- * This forceful removal will result in ugly /proc output if
- * somebody holds a file open that got deleted due to a rename.
- * We could be nicer about the deleted file, and let it show
- * up under the name it had before it was deleted rather than
- * under the original name of the file that was moved on top of it.
+ * When switching names, the actual string doesn't strictly have to
+ * be preserved in the target - because we're dropping the target
+ * anyway. As such, we can just do a simple memcpy() to copy over
+ * the new name before we switch.
+ *
+ * Note that we have to be a lot more careful about getting the hash
+ * switched - we have to switch the hash value properly even if it
+ * then no longer matches the actual (corrupted) string of the target.
+ * The hash value has to match the hash queue that the dentry is on..
*/
-
/*
- * d_move_locked - move a dentry
+ * d_move - move a dentry
* @dentry: entry to move
* @target: new dentry
*
* Update the dcache to reflect the move of a file name. Negative
* dcache entries should not be moved in this way.
*/
-static void d_move_locked(struct dentry * dentry, struct dentry * target)
+void d_move(struct dentry * dentry, struct dentry * target)
{
- struct hlist_head *list;
-
if (!dentry->d_inode)
printk(KERN_WARNING "VFS: moving negative dcache entry\n");
+ BUG_ON(d_ancestor(dentry, target));
+ BUG_ON(d_ancestor(target, dentry));
+
write_seqlock(&rename_lock);
- /*
- * XXXX: do we really need to take target->d_lock?
- */
- if (target < dentry) {
- spin_lock(&target->d_lock);
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- } else {
- spin_lock(&dentry->d_lock);
- spin_lock_nested(&target->d_lock, DENTRY_D_LOCK_NESTED);
- }
- /* Move the dentry to the target hash queue, if on different bucket */
- if (d_unhashed(dentry))
- goto already_unhashed;
+ dentry_lock_for_move(dentry, target);
- hlist_del_rcu(&dentry->d_hash);
+ write_seqcount_begin(&dentry->d_seq);
+ write_seqcount_begin(&target->d_seq);
-already_unhashed:
- list = d_hash(target->d_parent, target->d_name.hash);
- __d_rehash(dentry, list);
+ /* __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));
/* Unhash the target: dput() will then get rid of it */
__d_drop(target);
@@ -1715,27 +2246,16 @@ already_unhashed:
}
list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+
+ write_seqcount_end(&target->d_seq);
+ write_seqcount_end(&dentry->d_seq);
+
+ dentry_unlock_parents_for_move(dentry, target);
spin_unlock(&target->d_lock);
fsnotify_d_move(dentry);
spin_unlock(&dentry->d_lock);
write_sequnlock(&rename_lock);
}
-
-/**
- * d_move - move a dentry
- * @dentry: entry to move
- * @target: new dentry
- *
- * Update the dcache to reflect the move of a file name. Negative
- * dcache entries should not be moved in this way.
- */
-
-void d_move(struct dentry * dentry, struct dentry * target)
-{
- spin_lock(&dcache_lock);
- d_move_locked(dentry, target);
- spin_unlock(&dcache_lock);
-}
EXPORT_SYMBOL(d_move);
/**
@@ -1761,13 +2281,13 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
* 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_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_lock)
+static struct dentry *__d_unalias(struct inode *inode,
+ struct dentry *dentry, struct dentry *alias)
{
struct mutex *m1 = NULL, *m2 = NULL;
struct dentry *ret;
@@ -1790,10 +2310,10 @@ static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias)
goto out_err;
m2 = &alias->d_parent->d_inode->i_mutex;
out_unalias:
- d_move_locked(alias, dentry);
+ d_move(alias, dentry);
ret = alias;
out_err:
- spin_unlock(&dcache_lock);
+ spin_unlock(&inode->i_lock);
if (m2)
mutex_unlock(m2);
if (m1)
@@ -1804,17 +2324,23 @@ out_err:
/*
* Prepare an anonymous dentry for life in the superblock's dentry tree as a
* named dentry in place of the dentry to be replaced.
+ * returns with anon->d_lock held!
*/
static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
{
struct dentry *dparent, *aparent;
- switch_names(dentry, anon);
- swap(dentry->d_name.hash, anon->d_name.hash);
+ dentry_lock_for_move(anon, dentry);
+
+ write_seqcount_begin(&dentry->d_seq);
+ write_seqcount_begin(&anon->d_seq);
dparent = dentry->d_parent;
aparent = anon->d_parent;
+ switch_names(dentry, anon);
+ swap(dentry->d_name.hash, anon->d_name.hash);
+
dentry->d_parent = (aparent == anon) ? dentry : aparent;
list_del(&dentry->d_u.d_child);
if (!IS_ROOT(dentry))
@@ -1829,6 +2355,13 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
else
INIT_LIST_HEAD(&anon->d_u.d_child);
+ write_seqcount_end(&dentry->d_seq);
+ write_seqcount_end(&anon->d_seq);
+
+ dentry_unlock_parents_for_move(anon, dentry);
+ spin_unlock(&dentry->d_lock);
+
+ /* anon->d_lock still locked, returns locked */
anon->d_flags &= ~DCACHE_DISCONNECTED;
}
@@ -1846,14 +2379,15 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
BUG_ON(!d_unhashed(dentry));
- spin_lock(&dcache_lock);
-
if (!inode) {
actual = dentry;
__d_instantiate(dentry, NULL);
- goto found_lock;
+ d_rehash(actual);
+ goto out_nolock;
}
+ spin_lock(&inode->i_lock);
+
if (S_ISDIR(inode->i_mode)) {
struct dentry *alias;
@@ -1864,13 +2398,12 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
/* Is this an anonymous mountpoint that we could splice
* into our tree? */
if (IS_ROOT(alias)) {
- spin_lock(&alias->d_lock);
__d_materialise_dentry(dentry, alias);
__d_drop(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;
@@ -1881,15 +2414,14 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
actual = __d_instantiate_unique(dentry, inode);
if (!actual)
actual = dentry;
- else if (unlikely(!d_unhashed(actual)))
- goto shouldnt_be_hashed;
+ else
+ BUG_ON(!d_unhashed(actual));
-found_lock:
spin_lock(&actual->d_lock);
found:
_d_rehash(actual);
spin_unlock(&actual->d_lock);
- spin_unlock(&dcache_lock);
+ spin_unlock(&inode->i_lock);
out_nolock:
if (actual == dentry) {
security_d_instantiate(dentry, inode);
@@ -1898,10 +2430,6 @@ out_nolock:
iput(inode);
return actual;
-
-shouldnt_be_hashed:
- spin_unlock(&dcache_lock);
- BUG();
}
EXPORT_SYMBOL_GPL(d_materialise_unique);
@@ -1928,7 +2456,7 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
* @buffer: pointer to the end of the buffer
* @buflen: pointer to buffer length
*
- * Caller holds the dcache_lock.
+ * Caller holds the rename_lock.
*
* If path is not reachable from the supplied root, then the value of
* root is changed (without modifying refcounts).
@@ -1956,7 +2484,9 @@ static int prepend_path(const struct path *path, struct path *root,
}
parent = dentry->d_parent;
prefetch(parent);
+ spin_lock(&dentry->d_lock);
error = prepend_name(buffer, buflen, &dentry->d_name);
+ spin_unlock(&dentry->d_lock);
if (!error)
error = prepend(buffer, buflen, "/", 1);
if (error)
@@ -2012,9 +2542,9 @@ char *__d_path(const struct path *path, struct path *root,
int error;
prepend(&res, &buflen, "\0", 1);
- spin_lock(&dcache_lock);
+ write_seqlock(&rename_lock);
error = prepend_path(path, root, &res, &buflen);
- spin_unlock(&dcache_lock);
+ write_sequnlock(&rename_lock);
if (error)
return ERR_PTR(error);
@@ -2076,12 +2606,12 @@ char *d_path(const struct path *path, char *buf, int buflen)
return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
get_fs_root(current->fs, &root);
- spin_lock(&dcache_lock);
+ write_seqlock(&rename_lock);
tmp = root;
error = path_with_deleted(path, &tmp, &res, &buflen);
if (error)
res = ERR_PTR(error);
- spin_unlock(&dcache_lock);
+ write_sequnlock(&rename_lock);
path_put(&root);
return res;
}
@@ -2107,12 +2637,12 @@ char *d_path_with_unreachable(const struct path *path, char *buf, int buflen)
return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
get_fs_root(current->fs, &root);
- spin_lock(&dcache_lock);
+ write_seqlock(&rename_lock);
tmp = root;
error = path_with_deleted(path, &tmp, &res, &buflen);
if (!error && !path_equal(&tmp, &root))
error = prepend_unreachable(&res, &buflen);
- spin_unlock(&dcache_lock);
+ write_sequnlock(&rename_lock);
path_put(&root);
if (error)
res = ERR_PTR(error);
@@ -2144,7 +2674,7 @@ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
/*
* Write full pathname from the root of the filesystem into the buffer.
*/
-char *__dentry_path(struct dentry *dentry, char *buf, int buflen)
+static char *__dentry_path(struct dentry *dentry, char *buf, int buflen)
{
char *end = buf + buflen;
char *retval;
@@ -2158,10 +2688,13 @@ char *__dentry_path(struct dentry *dentry, char *buf, int buflen)
while (!IS_ROOT(dentry)) {
struct dentry *parent = dentry->d_parent;
+ int error;
prefetch(parent);
- if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) ||
- (prepend(&end, &buflen, "/", 1) != 0))
+ spin_lock(&dentry->d_lock);
+ error = prepend_name(&end, &buflen, &dentry->d_name);
+ spin_unlock(&dentry->d_lock);
+ if (error != 0 || prepend(&end, &buflen, "/", 1) != 0)
goto Elong;
retval = end;
@@ -2171,14 +2704,25 @@ char *__dentry_path(struct dentry *dentry, char *buf, int buflen)
Elong:
return ERR_PTR(-ENAMETOOLONG);
}
-EXPORT_SYMBOL(__dentry_path);
+
+char *dentry_path_raw(struct dentry *dentry, char *buf, int buflen)
+{
+ char *retval;
+
+ write_seqlock(&rename_lock);
+ retval = __dentry_path(dentry, buf, buflen);
+ write_sequnlock(&rename_lock);
+
+ return retval;
+}
+EXPORT_SYMBOL(dentry_path_raw);
char *dentry_path(struct dentry *dentry, char *buf, int buflen)
{
char *p = NULL;
char *retval;
- spin_lock(&dcache_lock);
+ write_seqlock(&rename_lock);
if (d_unlinked(dentry)) {
p = buf + buflen;
if (prepend(&p, &buflen, "//deleted", 10) != 0)
@@ -2186,12 +2730,11 @@ char *dentry_path(struct dentry *dentry, char *buf, int buflen)
buflen++;
}
retval = __dentry_path(dentry, buf, buflen);
- spin_unlock(&dcache_lock);
+ write_sequnlock(&rename_lock);
if (!IS_ERR(retval) && p)
*p = '/'; /* restore '/' overriden with '\0' */
return retval;
Elong:
- spin_unlock(&dcache_lock);
return ERR_PTR(-ENAMETOOLONG);
}
@@ -2225,7 +2768,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
get_fs_root_and_pwd(current->fs, &root, &pwd);
error = -ENOENT;
- spin_lock(&dcache_lock);
+ write_seqlock(&rename_lock);
if (!d_unlinked(pwd.dentry)) {
unsigned long len;
struct path tmp = root;
@@ -2234,7 +2777,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
prepend(&cwd, &buflen, "\0", 1);
error = prepend_path(&pwd, &tmp, &cwd, &buflen);
- spin_unlock(&dcache_lock);
+ write_sequnlock(&rename_lock);
if (error)
goto out;
@@ -2253,8 +2796,9 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
if (copy_to_user(buf, cwd, len))
error = -EFAULT;
}
- } else
- spin_unlock(&dcache_lock);
+ } else {
+ write_sequnlock(&rename_lock);
+ }
out:
path_put(&pwd);
@@ -2282,25 +2826,25 @@ out:
int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
{
int result;
- unsigned long seq;
+ unsigned seq;
if (new_dentry == old_dentry)
return 1;
- /*
- * Need rcu_readlock to protect against the d_parent trashing
- * due to d_move
- */
- rcu_read_lock();
do {
/* for restarting inner loop in case of seq retry */
seq = read_seqbegin(&rename_lock);
+ /*
+ * Need rcu_readlock to protect against the d_parent trashing
+ * due to d_move
+ */
+ rcu_read_lock();
if (d_ancestor(old_dentry, new_dentry))
result = 1;
else
result = 0;
+ rcu_read_unlock();
} while (read_seqretry(&rename_lock, seq));
- rcu_read_unlock();
return result;
}
@@ -2332,10 +2876,15 @@ EXPORT_SYMBOL(path_is_under);
void d_genocide(struct dentry *root)
{
- struct dentry *this_parent = root;
+ struct dentry *this_parent;
struct list_head *next;
+ unsigned seq;
+ int locked = 0;
- spin_lock(&dcache_lock);
+ seq = read_seqbegin(&rename_lock);
+again:
+ this_parent = root;
+ spin_lock(&this_parent->d_lock);
repeat:
next = this_parent->d_subdirs.next;
resume:
@@ -2343,21 +2892,62 @@ resume:
struct list_head *tmp = next;
struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
next = tmp->next;
- if (d_unhashed(dentry)||!dentry->d_inode)
+
+ spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+ if (d_unhashed(dentry) || !dentry->d_inode) {
+ 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;
}
- atomic_dec(&dentry->d_count);
+ if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
+ dentry->d_flags |= DCACHE_GENOCIDE;
+ dentry->d_count--;
+ }
+ spin_unlock(&dentry->d_lock);
}
if (this_parent != root) {
- next = this_parent->d_u.d_child.next;
- atomic_dec(&this_parent->d_count);
- this_parent = this_parent->d_parent;
+ struct dentry *tmp;
+ struct dentry *child;
+
+ tmp = this_parent->d_parent;
+ if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
+ this_parent->d_flags |= DCACHE_GENOCIDE;
+ this_parent->d_count--;
+ }
+ rcu_read_lock();
+ spin_unlock(&this_parent->d_lock);
+ child = this_parent;
+ this_parent = tmp;
+ spin_lock(&this_parent->d_lock);
+ /* might go back up the wrong parent if we have had a rename
+ * or deletion */
+ if (this_parent != child->d_parent ||
+ (!locked && read_seqretry(&rename_lock, seq))) {
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
+ goto rename_retry;
+ }
+ rcu_read_unlock();
+ next = child->d_u.d_child.next;
goto resume;
}
- spin_unlock(&dcache_lock);
+ spin_unlock(&this_parent->d_lock);
+ if (!locked && read_seqretry(&rename_lock, seq))
+ goto rename_retry;
+ if (locked)
+ write_sequnlock(&rename_lock);
+ return;
+
+rename_retry:
+ locked = 1;
+ write_seqlock(&rename_lock);
+ goto again;
}
/**
@@ -2411,7 +3001,7 @@ static void __init dcache_init_early(void)
dentry_hashtable =
alloc_large_system_hash("Dentry cache",
- sizeof(struct hlist_head),
+ sizeof(struct dcache_hash_bucket),
dhash_entries,
13,
HASH_EARLY,
@@ -2420,16 +3010,13 @@ static void __init dcache_init_early(void)
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)
{
int loop;
- percpu_counter_init(&nr_dentry, 0);
- percpu_counter_init(&nr_dentry_unused, 0);
-
/*
* A constructor could be added for stable state like the lists,
* but it is probably not worth it because of the cache nature
@@ -2446,7 +3033,7 @@ 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,
@@ -2455,7 +3042,7 @@ static void __init dcache_init(void)
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 */