vfs: check submounts and drop atomically

We check submounts before doing d_drop() on a non-empty directory dentry in
NFS (have_submounts()), but we do not exclude a racing mount.

 Process A: have_submounts() -> returns false
 Process B: mount() -> success
 Process A: d_drop()

This patch prepares the ground for the fix by doing the following
operations all under the same rename lock:

  have_submounts()
  shrink_dcache_parent()
  d_drop()

This is actually an optimization since have_submounts() and
shrink_dcache_parent() both traverse the same dentry tree separately.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
CC: David Howells <dhowells@redhat.com>
CC: Steven Whitehouse <swhiteho@redhat.com>
CC: Trond Myklebust <Trond.Myklebust@netapp.com>
CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

2 files changed, 66 insertions, 0 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index 043c5b4..ce5a7e6 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1264,6 +1264,71 @@ void shrink_dcache_parent(struct dentry *parent)
 }
 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
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 9169b91..c6d3fe5 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -253,6 +253,7 @@ extern void d_prune_aliases(struct inode *);
 
 /* test whether we have any submounts in a subdir tree */
 extern int have_submounts(struct dentry *);
+extern int check_submounts_and_drop(struct dentry *);
 
 /*
  * This adds the entry to the hash queues.