vfs: check unlinked ancestors before mount

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.  Nor do we
prevent mounts to be added to the disconnected subtree using relative paths
after the d_drop().

This patch fixes these issues by checking for unlinked (unhashed, non-root)
ancestors before proceeding with the mount.  This is done with rename
seqlock taken for write and with ->d_lock grabbed on each ancestor in turn,
including our dentry itself.  This ensures that the only one of
check_submounts_and_drop() or has_unlinked_ancestor() can succeed.

Signed-off-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 39 insertions, 6 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index ce5a7e6..761e31b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1184,6 +1184,39 @@ int have_submounts(struct dentry *parent)
 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
diff --git a/fs/internal.h b/fs/internal.h
index 7c5f01c..d208937 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -126,6 +126,7 @@ extern int invalidate_inodes(struct super_block *, bool);
  * dcache.c
  */
 extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
+extern int d_set_mounted(struct dentry *dentry);
 
 /*
  * read_write.c
diff --git a/fs/namespace.c b/fs/namespace.c
index ad8ea9b..5997887 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -611,6 +611,7 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry)
 {
 	struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry);
 	struct mountpoint *mp;
+	int ret;
 
 	list_for_each_entry(mp, chain, m_hash) {
 		if (mp->m_dentry == dentry) {
@@ -626,14 +627,12 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry)
 	if (!mp)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock(&dentry->d_lock);
-	if (d_unlinked(dentry)) {
-		spin_unlock(&dentry->d_lock);
+	ret = d_set_mounted(dentry);
+	if (ret) {
 		kfree(mp);
-		return ERR_PTR(-ENOENT);
+		return ERR_PTR(ret);
 	}
-	dentry->d_flags |= DCACHE_MOUNTED;
-	spin_unlock(&dentry->d_lock);
+
 	mp->m_dentry = dentry;
 	mp->m_count = 1;
 	list_add(&mp->m_hash, chain);