static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount)
{
- const unsigned char *cs;
/*
* Be careful about RCU walk racing with rename:
- * use ACCESS_ONCE to fetch the name pointer.
+ * use 'lockless_dereference' to fetch the name pointer.
*
* NOTE! Even if a rename will mean that the length
* was not loaded atomically, we don't care. The
* early because the data cannot match (there can
* be no NUL in the ct/tcount data)
*/
- cs = ACCESS_ONCE(dentry->d_name.name);
- smp_read_barrier_depends();
+ const unsigned char *cs = lockless_dereference(dentry->d_name.name);
+
return dentry_string_cmp(cs, ct, tcount);
}
}
EXPORT_SYMBOL(d_drop);
+static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent)
+{
+ struct dentry *next;
+ /*
+ * Inform d_walk() and shrink_dentry_list() that we are no longer
+ * attached to the dentry tree
+ */
+ dentry->d_flags |= DCACHE_DENTRY_KILLED;
+ if (unlikely(list_empty(&dentry->d_child)))
+ return;
+ __list_del_entry(&dentry->d_child);
+ /*
+ * Cursors can move around the list of children. While we'd been
+ * a normal list member, it didn't matter - ->d_child.next would've
+ * been updated. However, from now on it won't be and for the
+ * things like d_walk() it might end up with a nasty surprise.
+ * Normally d_walk() doesn't care about cursors moving around -
+ * ->d_lock on parent prevents that and since a cursor has no children
+ * of its own, we get through it without ever unlocking the parent.
+ * There is one exception, though - if we ascend from a child that
+ * gets killed as soon as we unlock it, the next sibling is found
+ * using the value left in its ->d_child.next. And if _that_
+ * pointed to a cursor, and cursor got moved (e.g. by lseek())
+ * before d_walk() regains parent->d_lock, we'll end up skipping
+ * everything the cursor had been moved past.
+ *
+ * Solution: make sure that the pointer left behind in ->d_child.next
+ * points to something that won't be moving around. I.e. skip the
+ * cursors.
+ */
+ while (dentry->d_child.next != &parent->d_subdirs) {
+ next = list_entry(dentry->d_child.next, struct dentry, d_child);
+ if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR)))
+ break;
+ dentry->d_child.next = next->d_child.next;
+ }
+}
+
static void __dentry_kill(struct dentry *dentry)
{
struct dentry *parent = NULL;
}
/* if it was on the hash then remove it */
__d_drop(dentry);
- __list_del_entry(&dentry->d_child);
- /*
- * Inform d_walk() that we are no longer attached to the
- * dentry tree
- */
- dentry->d_flags |= DCACHE_DENTRY_KILLED;
+ dentry_unlist(dentry, parent);
if (parent)
spin_unlock(&parent->d_lock);
dentry_iput(dentry);
struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
+ if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR))
+ continue;
+
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
ret = enter(data, dentry);
struct dentry *dentry = __d_alloc(parent->d_sb, name);
if (!dentry)
return NULL;
-
+ dentry->d_flags |= DCACHE_RCUACCESS;
spin_lock(&parent->d_lock);
/*
* don't need child lock because it is not subject
}
EXPORT_SYMBOL(d_alloc);
+struct dentry *d_alloc_cursor(struct dentry * parent)
+{
+ struct dentry *dentry = __d_alloc(parent->d_sb, NULL);
+ if (dentry) {
+ dentry->d_flags |= DCACHE_RCUACCESS | DCACHE_DENTRY_CURSOR;
+ dentry->d_parent = dget(parent);
+ }
+ return dentry;
+}
+
/**
* d_alloc_pseudo - allocate a dentry (for lookup-less filesystems)
* @sb: the superblock
raw_write_seqcount_begin(&dentry->d_seq);
__d_set_inode_and_type(dentry, inode, add_flags);
raw_write_seqcount_end(&dentry->d_seq);
- __fsnotify_d_instantiate(dentry);
+ fsnotify_update_flags(dentry);
spin_unlock(&dentry->d_lock);
}
{
BUG_ON(!d_unhashed(entry));
hlist_bl_lock(b);
- entry->d_flags |= DCACHE_RCUACCESS;
hlist_bl_add_head_rcu(&entry->d_hash, b);
hlist_bl_unlock(b);
}
rcu_read_unlock();
goto retry;
}
- rcu_read_unlock();
/*
* No changes for the parent since the beginning of d_lookup().
* Since all removals from the chain happen with hlist_bl_lock(),
continue;
if (dentry->d_parent != parent)
continue;
- if (d_unhashed(dentry))
- continue;
if (parent->d_flags & DCACHE_OP_COMPARE) {
int tlen = dentry->d_name.len;
const char *tname = dentry->d_name.name;
if (dentry_cmp(dentry, str, len))
continue;
}
- dget(dentry);
hlist_bl_unlock(b);
- /* somebody is doing lookup for it right now; wait for it */
+ /* now we can try to grab a reference */
+ if (!lockref_get_not_dead(&dentry->d_lockref)) {
+ rcu_read_unlock();
+ goto retry;
+ }
+
+ rcu_read_unlock();
+ /*
+ * somebody is likely to be still doing lookup for it;
+ * wait for them to finish
+ */
spin_lock(&dentry->d_lock);
d_wait_lookup(dentry);
/*
dput(new);
return dentry;
}
+ rcu_read_unlock();
/* we can't take ->d_lock here; it's OK, though. */
new->d_flags |= DCACHE_PAR_LOOKUP;
new->d_wait = wq;
raw_write_seqcount_begin(&dentry->d_seq);
__d_set_inode_and_type(dentry, inode, add_flags);
raw_write_seqcount_end(&dentry->d_seq);
- __fsnotify_d_instantiate(dentry);
+ fsnotify_update_flags(dentry);
}
_d_rehash(dentry);
if (dir)
/* ... and switch them in the tree */
if (IS_ROOT(dentry)) {
/* splicing a tree */
+ dentry->d_flags |= DCACHE_RCUACCESS;
dentry->d_parent = target->d_parent;
target->d_parent = target;
list_del_init(&target->d_child);
list_move(&target->d_child, &target->d_parent->d_subdirs);
list_move(&dentry->d_child, &dentry->d_parent->d_subdirs);
if (exchange)
- fsnotify_d_move(target);
- fsnotify_d_move(dentry);
+ fsnotify_update_flags(target);
+ fsnotify_update_flags(dentry);
}
write_seqcount_end(&target->d_seq);