summaryrefslogtreecommitdiffstats
path: root/fs/configfs
diff options
context:
space:
mode:
authorJoel Becker <Joel.Becker@oracle.com>2008-12-17 14:23:52 -0800
committerMark Fasheh <mfasheh@suse.com>2009-02-02 14:20:18 -0800
commit0e0333429a6280e6eb3c98845e4eed90d5f8078a (patch)
tree5c04f9892c52faedfaa5b879a23f96bf77d02953 /fs/configfs
parentf8afead7169f0f28a4b421bcbdb510e52a2d094d (diff)
downloadlinux-0e0333429a6280e6eb3c98845e4eed90d5f8078a.tar.bz2
configfs: Silence lockdep on mkdir(), rmdir() and configfs_depend_item()
When attaching default groups (subdirs) of a new group (in mkdir() or in configfs_register()), configfs recursively takes inode's mutexes along the path from the parent of the new group to the default subdirs. This is needed to ensure that the VFS will not race with operations on these sub-dirs. This is safe for the following reasons: - the VFS allows one to lock first an inode and second one of its children (The lock subclasses for this pattern are respectively I_MUTEX_PARENT and I_MUTEX_CHILD); - from this rule any inode path can be recursively locked in descending order as long as it stays under a single mountpoint and does not follow symlinks. Unfortunately lockdep does not know (yet?) how to handle such recursion. I've tried to use Peter Zijlstra's lock_set_subclass() helper to upgrade i_mutexes from I_MUTEX_CHILD to I_MUTEX_PARENT when we know that we might recursively lock some of their descendant, but this usage does not seem to fit the purpose of lock_set_subclass() because it leads to several i_mutex locked with subclass I_MUTEX_PARENT by the same task. >From inside configfs it is not possible to serialize those recursive locking with a top-level one, because mkdir() and rmdir() are already called with inodes locked by the VFS. So using some mutex_lock_nest_lock() is not an option. I am proposing two solutions: 1) one that wraps recursive mutex_lock()s with lockdep_off()/lockdep_on(). 2) (as suggested earlier by Peter Zijlstra) one that puts the i_mutexes recursively locked in different classes based on their depth from the top-level config_group created. This induces an arbitrary limit (MAX_LOCK_DEPTH - 2 == 46) on the nesting of configfs default groups whenever lockdep is activated but this limit looks reasonably high. Unfortunately, this alos isolates VFS operations on configfs default groups from the others and thus lowers the chances to detect locking issues. This patch implements solution 1). Solution 2) looks better from lockdep's point of view, but fails with configfs_depend_item(). This needs to rework the locking scheme of configfs_depend_item() by removing the variable lock recursion depth, and I think that it's doable thanks to the configfs_dirent_lock. For now, let's stick to solution 1). Signed-off-by: Louis Rilling <louis.rilling@kerlabs.com> Acked-by: Joel Becker <joel.becker@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Diffstat (limited to 'fs/configfs')
-rw-r--r--fs/configfs/dir.c59
1 files changed, 59 insertions, 0 deletions
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 8e93341f3e82..9c2358391147 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -553,12 +553,24 @@ static void detach_groups(struct config_group *group)
child = sd->s_dentry;
+ /*
+ * Note: we hide this from lockdep since we have no way
+ * to teach lockdep about recursive
+ * I_MUTEX_PARENT -> I_MUTEX_CHILD patterns along a path
+ * in an inode tree, which are valid as soon as
+ * I_MUTEX_PARENT -> I_MUTEX_CHILD is valid from a
+ * parent inode to one of its children.
+ */
+ lockdep_off();
mutex_lock(&child->d_inode->i_mutex);
+ lockdep_on();
configfs_detach_group(sd->s_element);
child->d_inode->i_flags |= S_DEAD;
+ lockdep_off();
mutex_unlock(&child->d_inode->i_mutex);
+ lockdep_on();
d_delete(child);
dput(child);
@@ -748,11 +760,22 @@ static int configfs_attach_item(struct config_item *parent_item,
* We are going to remove an inode and its dentry but
* the VFS may already have hit and used them. Thus,
* we must lock them as rmdir() would.
+ *
+ * Note: we hide this from lockdep since we have no way
+ * to teach lockdep about recursive
+ * I_MUTEX_PARENT -> I_MUTEX_CHILD patterns along a path
+ * in an inode tree, which are valid as soon as
+ * I_MUTEX_PARENT -> I_MUTEX_CHILD is valid from a
+ * parent inode to one of its children.
*/
+ lockdep_off();
mutex_lock(&dentry->d_inode->i_mutex);
+ lockdep_on();
configfs_remove_dir(item);
dentry->d_inode->i_flags |= S_DEAD;
+ lockdep_off();
mutex_unlock(&dentry->d_inode->i_mutex);
+ lockdep_on();
d_delete(dentry);
}
}
@@ -787,14 +810,25 @@ static int configfs_attach_group(struct config_item *parent_item,
*
* We must also lock the inode to remove it safely in case of
* error, as rmdir() would.
+ *
+ * Note: we hide this from lockdep since we have no way
+ * to teach lockdep about recursive
+ * I_MUTEX_PARENT -> I_MUTEX_CHILD patterns along a path
+ * in an inode tree, which are valid as soon as
+ * I_MUTEX_PARENT -> I_MUTEX_CHILD is valid from a
+ * parent inode to one of its children.
*/
+ lockdep_off();
mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
+ lockdep_on();
ret = populate_groups(to_config_group(item));
if (ret) {
configfs_detach_item(item);
dentry->d_inode->i_flags |= S_DEAD;
}
+ lockdep_off();
mutex_unlock(&dentry->d_inode->i_mutex);
+ lockdep_on();
if (ret)
d_delete(dentry);
}
@@ -956,7 +990,17 @@ static int configfs_depend_prep(struct dentry *origin,
BUG_ON(!origin || !sd);
/* Lock this guy on the way down */
+ /*
+ * Note: we hide this from lockdep since we have no way
+ * to teach lockdep about recursive
+ * I_MUTEX_PARENT -> I_MUTEX_CHILD patterns along a path
+ * in an inode tree, which are valid as soon as
+ * I_MUTEX_PARENT -> I_MUTEX_CHILD is valid from a
+ * parent inode to one of its children.
+ */
+ lockdep_off();
mutex_lock(&sd->s_dentry->d_inode->i_mutex);
+ lockdep_on();
if (sd->s_element == target) /* Boo-yah */
goto out;
@@ -970,7 +1014,9 @@ static int configfs_depend_prep(struct dentry *origin,
}
/* We looped all our children and didn't find target */
+ lockdep_off();
mutex_unlock(&sd->s_dentry->d_inode->i_mutex);
+ lockdep_on();
ret = -ENOENT;
out:
@@ -990,11 +1036,16 @@ static void configfs_depend_rollback(struct dentry *origin,
struct dentry *dentry = item->ci_dentry;
while (dentry != origin) {
+ /* See comments in configfs_depend_prep() */
+ lockdep_off();
mutex_unlock(&dentry->d_inode->i_mutex);
+ lockdep_on();
dentry = dentry->d_parent;
}
+ lockdep_off();
mutex_unlock(&origin->d_inode->i_mutex);
+ lockdep_on();
}
int configfs_depend_item(struct configfs_subsystem *subsys,
@@ -1329,8 +1380,16 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
}
/* Wait until the racing operation terminates */
+ /*
+ * Note: we hide this from lockdep since we are locked
+ * with subclass I_MUTEX_NORMAL from vfs_rmdir() (why
+ * not I_MUTEX_CHILD?), and I_MUTEX_XATTR or
+ * I_MUTEX_QUOTA are not relevant for the locked inode.
+ */
+ lockdep_off();
mutex_lock(wait_mutex);
mutex_unlock(wait_mutex);
+ lockdep_on();
}
} while (ret == -EAGAIN);