summaryrefslogtreecommitdiff
path: root/fs/dcache.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/dcache.c')
-rw-r--r--fs/dcache.c505
1 files changed, 305 insertions, 200 deletions
diff --git a/fs/dcache.c b/fs/dcache.c
index 87bdb5329c3c..761e31bacbc2 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -229,7 +229,7 @@ static void __d_free(struct rcu_head *head)
*/
static void d_free(struct dentry *dentry)
{
- BUG_ON(dentry->d_count);
+ BUG_ON(dentry->d_lockref.count);
this_cpu_dec(nr_dentry);
if (dentry->d_op && dentry->d_op->d_release)
dentry->d_op->d_release(dentry);
@@ -467,12 +467,12 @@ relock:
}
if (ref)
- dentry->d_count--;
+ dentry->d_lockref.count--;
/*
* inform the fs via d_prune that this dentry is about to be
* unhashed and destroyed.
*/
- if (dentry->d_flags & DCACHE_OP_PRUNE)
+ if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry))
dentry->d_op->d_prune(dentry);
dentry_lru_del(dentry);
@@ -513,15 +513,10 @@ void dput(struct dentry *dentry)
return;
repeat:
- if (dentry->d_count == 1)
+ if (dentry->d_lockref.count == 1)
might_sleep();
- spin_lock(&dentry->d_lock);
- BUG_ON(!dentry->d_count);
- if (dentry->d_count > 1) {
- dentry->d_count--;
- spin_unlock(&dentry->d_lock);
+ if (lockref_put_or_lock(&dentry->d_lockref))
return;
- }
if (dentry->d_flags & DCACHE_OP_DELETE) {
if (dentry->d_op->d_delete(dentry))
@@ -535,7 +530,7 @@ repeat:
dentry->d_flags |= DCACHE_REFERENCED;
dentry_lru_add(dentry);
- dentry->d_count--;
+ dentry->d_lockref.count--;
spin_unlock(&dentry->d_lock);
return;
@@ -590,7 +585,7 @@ int d_invalidate(struct dentry * dentry)
* We also need to leave mountpoints alone,
* directory or not.
*/
- if (dentry->d_count > 1 && dentry->d_inode) {
+ if (dentry->d_lockref.count > 1 && dentry->d_inode) {
if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
spin_unlock(&dentry->d_lock);
return -EBUSY;
@@ -606,20 +601,33 @@ EXPORT_SYMBOL(d_invalidate);
/* This must be called with d_lock held */
static inline void __dget_dlock(struct dentry *dentry)
{
- dentry->d_count++;
+ dentry->d_lockref.count++;
}
static inline void __dget(struct dentry *dentry)
{
- spin_lock(&dentry->d_lock);
- __dget_dlock(dentry);
- spin_unlock(&dentry->d_lock);
+ lockref_get(&dentry->d_lockref);
}
struct dentry *dget_parent(struct dentry *dentry)
{
+ int gotref;
struct dentry *ret;
+ /*
+ * Do optimistic parent lookup without any
+ * locking.
+ */
+ rcu_read_lock();
+ ret = ACCESS_ONCE(dentry->d_parent);
+ gotref = lockref_get_not_zero(&ret->d_lockref);
+ rcu_read_unlock();
+ if (likely(gotref)) {
+ if (likely(ret == ACCESS_ONCE(dentry->d_parent)))
+ return ret;
+ dput(ret);
+ }
+
repeat:
/*
* Don't need rcu_dereference because we re-check it was correct under
@@ -634,8 +642,8 @@ repeat:
goto repeat;
}
rcu_read_unlock();
- BUG_ON(!ret->d_count);
- ret->d_count++;
+ BUG_ON(!ret->d_lockref.count);
+ ret->d_lockref.count++;
spin_unlock(&ret->d_lock);
return ret;
}
@@ -718,7 +726,15 @@ restart:
spin_lock(&inode->i_lock);
hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
- if (!dentry->d_count) {
+ if (!dentry->d_lockref.count) {
+ /*
+ * inform the fs via d_prune that this dentry
+ * is about to be unhashed and destroyed.
+ */
+ if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
+ !d_unhashed(dentry))
+ dentry->d_op->d_prune(dentry);
+
__dget_dlock(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
@@ -763,12 +779,8 @@ static void try_prune_one_dentry(struct dentry *dentry)
/* Prune ancestors. */
dentry = parent;
while (dentry) {
- spin_lock(&dentry->d_lock);
- if (dentry->d_count > 1) {
- dentry->d_count--;
- spin_unlock(&dentry->d_lock);
+ if (lockref_put_or_lock(&dentry->d_lockref))
return;
- }
dentry = dentry_kill(dentry, 1);
}
}
@@ -793,7 +805,7 @@ static void shrink_dentry_list(struct list_head *list)
* the LRU because of laziness during lookup. Do not free
* it - just keep it off the LRU list.
*/
- if (dentry->d_count) {
+ if (dentry->d_lockref.count) {
dentry_lru_del(dentry);
spin_unlock(&dentry->d_lock);
continue;
@@ -907,13 +919,14 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
* inform the fs that this dentry is about to be
* unhashed and destroyed.
*/
- if (dentry->d_flags & DCACHE_OP_PRUNE)
+ if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
+ !d_unhashed(dentry))
dentry->d_op->d_prune(dentry);
dentry_lru_del(dentry);
__d_shrink(dentry);
- if (dentry->d_count != 0) {
+ if (dentry->d_lockref.count != 0) {
printk(KERN_ERR
"BUG: Dentry %p{i=%lx,n=%s}"
" still in use (%d)"
@@ -922,7 +935,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
dentry->d_inode ?
dentry->d_inode->i_ino : 0UL,
dentry->d_name.name,
- dentry->d_count,
+ dentry->d_lockref.count,
dentry->d_sb->s_type->name,
dentry->d_sb->s_id);
BUG();
@@ -933,7 +946,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
list_del(&dentry->d_u.d_child);
} else {
parent = dentry->d_parent;
- parent->d_count--;
+ parent->d_lockref.count--;
list_del(&dentry->d_u.d_child);
}
@@ -981,7 +994,7 @@ void shrink_dcache_for_umount(struct super_block *sb)
dentry = sb->s_root;
sb->s_root = NULL;
- dentry->d_count--;
+ dentry->d_lockref.count--;
shrink_dcache_for_umount_subtree(dentry);
while (!hlist_bl_empty(&sb->s_anon)) {
@@ -1018,34 +1031,56 @@ static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq
return new;
}
+/**
+ * enum d_walk_ret - action to talke during tree walk
+ * @D_WALK_CONTINUE: contrinue walk
+ * @D_WALK_QUIT: quit walk
+ * @D_WALK_NORETRY: quit when retry is needed
+ * @D_WALK_SKIP: skip this dentry and its children
+ */
+enum d_walk_ret {
+ D_WALK_CONTINUE,
+ D_WALK_QUIT,
+ D_WALK_NORETRY,
+ D_WALK_SKIP,
+};
-/*
- * Search for at least 1 mount point in the dentry's subdirs.
- * We descend to the next level whenever the d_subdirs
- * list is non-empty and continue searching.
- */
-
/**
- * have_submounts - check for mounts over a dentry
- * @parent: dentry to check.
+ * d_walk - walk the dentry tree
+ * @parent: start of walk
+ * @data: data passed to @enter() and @finish()
+ * @enter: callback when first entering the dentry
+ * @finish: callback when successfully finished the walk
*
- * Return true if the parent or its subdirectories contain
- * a mount point
+ * The @enter() and @finish() callbacks are called with d_lock held.
*/
-int have_submounts(struct dentry *parent)
+static void d_walk(struct dentry *parent, void *data,
+ enum d_walk_ret (*enter)(void *, struct dentry *),
+ void (*finish)(void *))
{
struct dentry *this_parent;
struct list_head *next;
unsigned seq;
int locked = 0;
+ enum d_walk_ret ret;
+ bool retry = true;
seq = read_seqbegin(&rename_lock);
again:
this_parent = parent;
-
- if (d_mountpoint(parent))
- goto positive;
spin_lock(&this_parent->d_lock);
+
+ ret = enter(data, this_parent);
+ switch (ret) {
+ case D_WALK_CONTINUE:
+ break;
+ case D_WALK_QUIT:
+ case D_WALK_SKIP:
+ goto out_unlock;
+ case D_WALK_NORETRY:
+ retry = false;
+ break;
+ }
repeat:
next = this_parent->d_subdirs.next;
resume:
@@ -1055,12 +1090,22 @@ resume:
next = tmp->next;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- /* Have we found a mount point ? */
- if (d_mountpoint(dentry)) {
+
+ ret = enter(data, dentry);
+ switch (ret) {
+ case D_WALK_CONTINUE:
+ break;
+ case D_WALK_QUIT:
spin_unlock(&dentry->d_lock);
- spin_unlock(&this_parent->d_lock);
- goto positive;
+ goto out_unlock;
+ case D_WALK_NORETRY:
+ retry = false;
+ break;
+ case D_WALK_SKIP:
+ spin_unlock(&dentry->d_lock);
+ continue;
}
+
if (!list_empty(&dentry->d_subdirs)) {
spin_unlock(&this_parent->d_lock);
spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
@@ -1081,29 +1126,97 @@ resume:
next = child->d_u.d_child.next;
goto resume;
}
- 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:
- if (!locked && read_seqretry(&rename_lock, seq))
+ if (!locked && read_seqretry(&rename_lock, seq)) {
+ spin_unlock(&this_parent->d_lock);
goto rename_retry;
+ }
+ if (finish)
+ finish(data);
+
+out_unlock:
+ spin_unlock(&this_parent->d_lock);
if (locked)
write_sequnlock(&rename_lock);
- return 1;
+ return;
rename_retry:
+ if (!retry)
+ return;
if (locked)
goto again;
locked = 1;
write_seqlock(&rename_lock);
goto again;
}
+
+/*
+ * Search for at least 1 mount point in the dentry's subdirs.
+ * We descend to the next level whenever the d_subdirs
+ * list is non-empty and continue searching.
+ */
+
+/**
+ * have_submounts - check for mounts over a dentry
+ * @parent: dentry to check.
+ *
+ * Return true if the parent or its subdirectories contain
+ * a mount point
+ */
+
+static enum d_walk_ret check_mount(void *data, struct dentry *dentry)
+{
+ int *ret = data;
+ if (d_mountpoint(dentry)) {
+ *ret = 1;
+ return D_WALK_QUIT;
+ }
+ return D_WALK_CONTINUE;
+}
+
+int have_submounts(struct dentry *parent)
+{
+ int ret = 0;
+
+ d_walk(parent, &ret, check_mount, NULL);
+
+ return ret;
+}
EXPORT_SYMBOL(have_submounts);
/*
+ * Called by mount code to set a mountpoint and check if the mountpoint is
+ * reachable (e.g. NFS can unhash a directory dentry and then the complete
+ * subtree can become unreachable).
+ *
+ * Only one of check_submounts_and_drop() and d_set_mounted() must succeed. For
+ * this reason take rename_lock and d_lock on dentry and ancestors.
+ */
+int d_set_mounted(struct dentry *dentry)
+{
+ struct dentry *p;
+ int ret = -ENOENT;
+ write_seqlock(&rename_lock);
+ for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) {
+ /* Need exclusion wrt. check_submounts_and_drop() */
+ spin_lock(&p->d_lock);
+ if (unlikely(d_unhashed(p))) {
+ spin_unlock(&p->d_lock);
+ goto out;
+ }
+ spin_unlock(&p->d_lock);
+ }
+ spin_lock(&dentry->d_lock);
+ if (!d_unlinked(dentry)) {
+ dentry->d_flags |= DCACHE_MOUNTED;
+ ret = 0;
+ }
+ spin_unlock(&dentry->d_lock);
+out:
+ write_sequnlock(&rename_lock);
+ return ret;
+}
+
+/*
* Search the dentry child list of the specified parent,
* and move any unused dentries to the end of the unused
* list for prune_dcache(). We descend to the next level
@@ -1117,93 +1230,46 @@ EXPORT_SYMBOL(have_submounts);
* drop the lock and return early due to latency
* constraints.
*/
-static int select_parent(struct dentry *parent, struct list_head *dispose)
-{
- struct dentry *this_parent;
- struct list_head *next;
- unsigned seq;
- int found = 0;
- int locked = 0;
- seq = read_seqbegin(&rename_lock);
-again:
- this_parent = parent;
- spin_lock(&this_parent->d_lock);
-repeat:
- next = this_parent->d_subdirs.next;
-resume:
- while (next != &this_parent->d_subdirs) {
- struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
- next = tmp->next;
-
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+struct select_data {
+ struct dentry *start;
+ struct list_head dispose;
+ int found;
+};
- /*
- * move only zero ref count dentries to the dispose list.
- *
- * Those which are presently on the shrink list, being processed
- * by shrink_dentry_list(), shouldn't be moved. Otherwise the
- * loop in shrink_dcache_parent() might not make any progress
- * and loop forever.
- */
- if (dentry->d_count) {
- dentry_lru_del(dentry);
- } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
- dentry_lru_move_list(dentry, dispose);
- dentry->d_flags |= DCACHE_SHRINK_LIST;
- found++;
- }
- /*
- * We can return to the caller if we have found some (this
- * ensures forward progress). We'll be coming back to find
- * the rest.
- */
- if (found && need_resched()) {
- spin_unlock(&dentry->d_lock);
- goto out;
- }
+static enum d_walk_ret select_collect(void *_data, struct dentry *dentry)
+{
+ struct select_data *data = _data;
+ enum d_walk_ret ret = D_WALK_CONTINUE;
- /*
- * 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;
- }
+ if (data->start == dentry)
+ goto out;
- spin_unlock(&dentry->d_lock);
- }
/*
- * All done at this level ... ascend and resume the search.
+ * move only zero ref count dentries to the dispose list.
+ *
+ * Those which are presently on the shrink list, being processed
+ * by shrink_dentry_list(), shouldn't be moved. Otherwise the
+ * loop in shrink_dcache_parent() might not make any progress
+ * and loop forever.
*/
- if (this_parent != parent) {
- struct dentry *child = this_parent;
- this_parent = try_to_ascend(this_parent, locked, seq);
- if (!this_parent)
- goto rename_retry;
- next = child->d_u.d_child.next;
- goto resume;
+ if (dentry->d_lockref.count) {
+ dentry_lru_del(dentry);
+ } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
+ dentry_lru_move_list(dentry, &data->dispose);
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
+ data->found++;
+ ret = D_WALK_NORETRY;
}
+ /*
+ * We can return to the caller if we have found some (this
+ * ensures forward progress). We'll be coming back to find
+ * the rest.
+ */
+ if (data->found && need_resched())
+ ret = D_WALK_QUIT;
out:
- 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;
- if (locked)
- goto again;
- locked = 1;
- write_seqlock(&rename_lock);
- goto again;
+ return ret;
}
/**
@@ -1212,18 +1278,90 @@ rename_retry:
*
* Prune the dcache to remove unused children of the parent dentry.
*/
-void shrink_dcache_parent(struct dentry * parent)
+void shrink_dcache_parent(struct dentry *parent)
{
- LIST_HEAD(dispose);
- int found;
+ for (;;) {
+ struct select_data data;
+
+ INIT_LIST_HEAD(&data.dispose);
+ data.start = parent;
+ data.found = 0;
- while ((found = select_parent(parent, &dispose)) != 0) {
- shrink_dentry_list(&dispose);
+ d_walk(parent, &data, select_collect, NULL);
+ if (!data.found)
+ break;
+
+ shrink_dentry_list(&data.dispose);
cond_resched();
}
}
EXPORT_SYMBOL(shrink_dcache_parent);
+static enum d_walk_ret check_and_collect(void *_data, struct dentry *dentry)
+{
+ struct select_data *data = _data;
+
+ if (d_mountpoint(dentry)) {
+ data->found = -EBUSY;
+ return D_WALK_QUIT;
+ }
+
+ return select_collect(_data, dentry);
+}
+
+static void check_and_drop(void *_data)
+{
+ struct select_data *data = _data;
+
+ if (d_mountpoint(data->start))
+ data->found = -EBUSY;
+ if (!data->found)
+ __d_drop(data->start);
+}
+
+/**
+ * check_submounts_and_drop - prune dcache, check for submounts and drop
+ *
+ * All done as a single atomic operation relative to has_unlinked_ancestor().
+ * Returns 0 if successfully unhashed @parent. If there were submounts then
+ * return -EBUSY.
+ *
+ * @dentry: dentry to prune and drop
+ */
+int check_submounts_and_drop(struct dentry *dentry)
+{
+ int ret = 0;
+
+ /* Negative dentries can be dropped without further checks */
+ if (!dentry->d_inode) {
+ d_drop(dentry);
+ goto out;
+ }
+
+ for (;;) {
+ struct select_data data;
+
+ INIT_LIST_HEAD(&data.dispose);
+ data.start = dentry;
+ data.found = 0;
+
+ d_walk(dentry, &data, check_and_collect, check_and_drop);
+ ret = data.found;
+
+ if (!list_empty(&data.dispose))
+ shrink_dentry_list(&data.dispose);
+
+ if (ret <= 0)
+ break;
+
+ cond_resched();
+ }
+
+out:
+ return ret;
+}
+EXPORT_SYMBOL(check_submounts_and_drop);
+
/**
* __d_alloc - allocate a dcache entry
* @sb: filesystem it will belong to
@@ -1269,7 +1407,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
smp_wmb();
dentry->d_name.name = dname;
- dentry->d_count = 1;
+ dentry->d_lockref.count = 1;
dentry->d_flags = 0;
spin_lock_init(&dentry->d_lock);
seqcount_init(&dentry->d_seq);
@@ -1782,7 +1920,7 @@ static noinline enum slow_d_compare slow_dentry_cmp(
* 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
+ * 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
@@ -1970,7 +2108,7 @@ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name)
goto next;
}
- dentry->d_count++;
+ dentry->d_lockref.count++;
found = dentry;
spin_unlock(&dentry->d_lock);
break;
@@ -2069,7 +2207,7 @@ again:
spin_lock(&dentry->d_lock);
inode = dentry->d_inode;
isdir = S_ISDIR(inode->i_mode);
- if (dentry->d_count == 1) {
+ if (dentry->d_lockref.count == 1) {
if (!spin_trylock(&inode->i_lock)) {
spin_unlock(&dentry->d_lock);
cpu_relax();
@@ -2724,6 +2862,17 @@ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
return memcpy(buffer, temp, sz);
}
+char *simple_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+ char *end = buffer + buflen;
+ /* these dentries are never renamed, so d_lock is not needed */
+ if (prepend(&end, &buflen, " (deleted)", 11) ||
+ prepend_name(&end, &buflen, &dentry->d_name) ||
+ prepend(&end, &buflen, "/", 1))
+ end = ERR_PTR(-ENAMETOOLONG);
+ return end;
+}
+
/*
* Write full pathname from the root of the filesystem into the buffer.
*/
@@ -2904,68 +3053,24 @@ int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
return result;
}
-void d_genocide(struct dentry *root)
+static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
{
- struct dentry *this_parent;
- struct list_head *next;
- unsigned seq;
- int locked = 0;
+ struct dentry *root = data;
+ if (dentry != root) {
+ if (d_unhashed(dentry) || !dentry->d_inode)
+ return D_WALK_SKIP;
- seq = read_seqbegin(&rename_lock);
-again:
- this_parent = root;
- spin_lock(&this_parent->d_lock);
-repeat:
- next = this_parent->d_subdirs.next;
-resume:
- while (next != &this_parent->d_subdirs) {
- struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
- next = tmp->next;
-
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- 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;
- }
if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
dentry->d_flags |= DCACHE_GENOCIDE;
- dentry->d_count--;
+ dentry->d_lockref.count--;
}
- spin_unlock(&dentry->d_lock);
}
- if (this_parent != root) {
- struct dentry *child = this_parent;
- if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
- this_parent->d_flags |= DCACHE_GENOCIDE;
- this_parent->d_count--;
- }
- this_parent = try_to_ascend(this_parent, locked, seq);
- if (!this_parent)
- goto rename_retry;
- next = child->d_u.d_child.next;
- goto resume;
- }
- spin_unlock(&this_parent->d_lock);
- if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry;
- if (locked)
- write_sequnlock(&rename_lock);
- return;
+ return D_WALK_CONTINUE;
+}
-rename_retry:
- if (locked)
- goto again;
- locked = 1;
- write_seqlock(&rename_lock);
- goto again;
+void d_genocide(struct dentry *parent)
+{
+ d_walk(parent, parent, d_genocide_kill, NULL);
}
void d_tmpfile(struct dentry *dentry, struct inode *inode)