[PATCH] fuse: fix handling of moved directory

Fuse considered it an error (EIO) if lookup returned a directory inode, to
which a dentry already refered.  This is because directory aliases are not
allowed.

But in a network filesystem this could happen legitimately, if a directory is
moved on a remote client.  This patch attempts to relax the restriction by
trying to first evict the offending alias from the cache.  If this fails, it
still returns an error (EBUSY).

A rarer situation is if an mkdir races with an indenpendent lookup, which
finds the newly created directory already moved.  In this situation the mkdir
should return success, but that would be incorrect, since the dentry cannot be
instantiated, so return EBUSY.

Previously checking for a directory alias and instantiation of the dentry
weren't done atomically in lookup/mkdir, hence two such calls racing with each
other could create aliased directories.  To prevent this introduce a new
per-connection mutex: fuse_conn->inst_mutex, which is taken for instantiations
with a directory inode.

Signed-off-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 7ecfe95..9d0ef5e1 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -177,22 +177,6 @@
 	return 1;
 }
 
-/*
- * Check if there's already a hashed alias of this directory inode.
- * If yes, then lookup and mkdir must not create a new alias.
- */
-static int dir_alias(struct inode *inode)
-{
-	if (S_ISDIR(inode->i_mode)) {
-		struct dentry *alias = d_find_alias(inode);
-		if (alias) {
-			dput(alias);
-			return 1;
-		}
-	}
-	return 0;
-}
-
 static int invalid_nodeid(u64 nodeid)
 {
 	return !nodeid || nodeid == FUSE_ROOT_ID;
@@ -208,6 +192,24 @@
 		S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m);
 }
 
+/*
+ * Add a directory inode to a dentry, ensuring that no other dentry
+ * refers to this inode.  Called with fc->inst_mutex.
+ */
+static int fuse_d_add_directory(struct dentry *entry, struct inode *inode)
+{
+	struct dentry *alias = d_find_alias(inode);
+	if (alias) {
+		/* This tries to shrink the subtree below alias */
+		fuse_invalidate_entry(alias);
+		dput(alias);
+		if (!list_empty(&inode->i_dentry))
+			return -EBUSY;
+	}
+	d_add(entry, inode);
+	return 0;
+}
+
 static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 				  struct nameidata *nd)
 {
@@ -243,11 +245,17 @@
 	if (err && err != -ENOENT)
 		return ERR_PTR(err);
 
-	if (inode && dir_alias(inode)) {
-		iput(inode);
-		return ERR_PTR(-EIO);
-	}
-	d_add(entry, inode);
+	if (inode && S_ISDIR(inode->i_mode)) {
+		mutex_lock(&fc->inst_mutex);
+		err = fuse_d_add_directory(entry, inode);
+		mutex_unlock(&fc->inst_mutex);
+		if (err) {
+			iput(inode);
+			return ERR_PTR(err);
+		}
+	} else
+		d_add(entry, inode);
+
 	entry->d_op = &fuse_dentry_operations;
 	if (!err)
 		fuse_change_timeout(entry, &outarg);
@@ -403,12 +411,22 @@
 	}
 	fuse_put_request(fc, req);
 
-	if (dir_alias(inode)) {
-		iput(inode);
-		return -EIO;
-	}
+	if (S_ISDIR(inode->i_mode)) {
+		struct dentry *alias;
+		mutex_lock(&fc->inst_mutex);
+		alias = d_find_alias(inode);
+		if (alias) {
+			/* New directory must have moved since mkdir */
+			mutex_unlock(&fc->inst_mutex);
+			dput(alias);
+			iput(inode);
+			return -EBUSY;
+		}
+		d_instantiate(entry, inode);
+		mutex_unlock(&fc->inst_mutex);
+	} else
+		d_instantiate(entry, inode);
 
-	d_instantiate(entry, inode);
 	fuse_change_timeout(entry, &outarg);
 	fuse_invalidate_attr(dir);
 	return 0;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 69c7750..91edb89 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -239,6 +239,9 @@
 	/** Lock protecting accessess to  members of this structure */
 	spinlock_t lock;
 
+	/** Mutex protecting against directory alias creation */
+	struct mutex inst_mutex;
+
 	/** Refcount */
 	atomic_t count;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 4ee8f72..fc42035 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -379,6 +379,7 @@
 	fc = kzalloc(sizeof(*fc), GFP_KERNEL);
 	if (fc) {
 		spin_lock_init(&fc->lock);
+		mutex_init(&fc->inst_mutex);
 		atomic_set(&fc->count, 1);
 		init_waitqueue_head(&fc->waitq);
 		init_waitqueue_head(&fc->blocked_waitq);
@@ -398,8 +399,10 @@
 
 void fuse_conn_put(struct fuse_conn *fc)
 {
-	if (atomic_dec_and_test(&fc->count))
+	if (atomic_dec_and_test(&fc->count)) {
+		mutex_destroy(&fc->inst_mutex);
 		kfree(fc);
+	}
 }
 
 struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)