locks: break delegations on unlink

We need to break delegations on any operation that changes the set of
links pointing to an inode.  Start with unlink.

Such operations also hold the i_mutex on a parent directory.  Breaking a
delegation may require waiting for a timeout (by default 90 seconds) in
the case of a unresponsive NFS client.  To avoid blocking all directory
operations, we therefore drop locks before waiting for the delegation.
The logic then looks like:

	acquire locks
	...
	test for delegation; if found:
		take reference on inode
		release locks
		wait for delegation break
		drop reference on inode
		retry

It is possible this could never terminate.  (Even if we take precautions
to prevent another delegation being acquired on the same inode, we could
get a different inode on each retry.)  But this seems very unlikely.

The initial test for a delegation happens after the lock on the target
inode is acquired, but the directory inode may have been acquired
further up the call stack.  We therefore add a "struct inode **"
argument to any intervening functions, which we use to pass the inode
back up to the caller in the case it needs a delegation synchronously
broken.

Cc: David Howells <dhowells@redhat.com>
Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: Dustin Kirkland <dustin.kirkland@gazzang.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

7 files changed, 46 insertions, 10 deletions

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 7413d065906b..1b8490e2fbde 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -324,7 +324,7 @@ static int handle_remove(const char *nodename, struct device *dev)
 			mutex_lock(&dentry->d_inode->i_mutex);
 			notify_change(dentry, &newattrs);
 			mutex_unlock(&dentry->d_inode->i_mutex);
-			err = vfs_unlink(parent.dentry->d_inode, dentry);
+			err = vfs_unlink(parent.dentry->d_inode, dentry, NULL);
 			if (!err || err == -ENOENT)
 				deleted = 1;
 		}
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index f4a08d7fa2f7..31d480c0e046 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -294,7 +294,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
 		if (ret < 0) {
 			cachefiles_io_error(cache, "Unlink security error");
 		} else {
-			ret = vfs_unlink(dir->d_inode, rep);
+			ret = vfs_unlink(dir->d_inode, rep, NULL);
 
 			if (preemptive)
 				cachefiles_mark_object_buried(cache, rep);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 0f9b66eaa767..dc60b8bd09ec 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -153,7 +153,7 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
 
 	dget(lower_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
-	rc = vfs_unlink(lower_dir_inode, lower_dentry);
+	rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
 	if (rc) {
 		printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
 		goto out_unlock;
@@ -208,7 +208,7 @@ ecryptfs_do_create(struct inode *directory_inode,
 	inode = __ecryptfs_get_inode(lower_dentry->d_inode,
 				     directory_inode->i_sb);
 	if (IS_ERR(inode)) {
-		vfs_unlink(lower_dir_dentry->d_inode, lower_dentry);
+		vfs_unlink(lower_dir_dentry->d_inode, lower_dentry, NULL);
 		goto out_lock;
 	}
 	fsstack_copy_attr_times(directory_inode, lower_dir_dentry->d_inode);
diff --git a/fs/namei.c b/fs/namei.c
index e633a58d4222..67ce331a3ed8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3615,7 +3615,25 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
 	return do_rmdir(AT_FDCWD, pathname);
 }
 
-int vfs_unlink(struct inode *dir, struct dentry *dentry)
+/**
+ * vfs_unlink - unlink a filesystem object
+ * @dir:	parent directory
+ * @dentry:	victim
+ * @delegated_inode: returns victim inode, if the inode is delegated.
+ *
+ * The caller must hold dir->i_mutex.
+ *
+ * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and
+ * return a reference to the inode in delegated_inode.  The caller
+ * should then break the delegation on that inode and retry.  Because
+ * breaking a delegation may take a long time, the caller should drop
+ * dir->i_mutex before doing so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ */
+int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
 {
 	struct inode *target = dentry->d_inode;
 	int error = may_delete(dir, dentry, 0);
@@ -3632,11 +3650,20 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
 	else {
 		error = security_inode_unlink(dir, dentry);
 		if (!error) {
+			error = break_deleg(target, O_WRONLY|O_NONBLOCK);
+			if (error) {
+				if (error == -EWOULDBLOCK && delegated_inode) {
+					*delegated_inode = target;
+					ihold(target);
+				}
+				goto out;
+			}
 			error = dir->i_op->unlink(dir, dentry);
 			if (!error)
 				dont_mount(dentry);
 		}
 	}
+out:
 	mutex_unlock(&target->i_mutex);
 
 	/* We don't d_delete() NFS sillyrenamed files--they still exist. */
@@ -3661,6 +3688,7 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 	struct dentry *dentry;
 	struct nameidata nd;
 	struct inode *inode = NULL;
+	struct inode *delegated_inode = NULL;
 	unsigned int lookup_flags = 0;
 retry:
 	name = user_path_parent(dfd, pathname, &nd, lookup_flags);
@@ -3675,7 +3703,7 @@ retry:
 	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto exit1;
-
+retry_deleg:
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
 	dentry = lookup_hash(&nd);
 	error = PTR_ERR(dentry);
@@ -3690,13 +3718,21 @@ retry:
 		error = security_path_unlink(&nd.path, dentry);
 		if (error)
 			goto exit2;
-		error = vfs_unlink(nd.path.dentry->d_inode, dentry);
+		error = vfs_unlink(nd.path.dentry->d_inode, dentry, &delegated_inode);
 exit2:
 		dput(dentry);
 	}
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 	if (inode)
 		iput(inode);	/* truncate the inode here */
+	inode = NULL;
+	if (delegated_inode) {
+		error = break_deleg(delegated_inode, O_WRONLY);
+		iput(delegated_inode);
+		delegated_inode = NULL;
+		if (!error)
+			goto retry_deleg;
+	}
 	mnt_drop_write(nd.path.mnt);
 exit1:
 	path_put(&nd.path);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 13886f7f40d5..7a810235d599 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1910,7 +1910,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (host_err)
 		goto out_put;
 	if (type != S_IFDIR)
-		host_err = vfs_unlink(dirp, rdentry);
+		host_err = vfs_unlink(dirp, rdentry, NULL);
 	else
 		host_err = vfs_rmdir(dirp, rdentry);
 	if (!host_err)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8e4be1be1a62..a5799233142a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1455,7 +1455,7 @@ extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
 extern int vfs_rmdir(struct inode *, struct dentry *);
-extern int vfs_unlink(struct inode *, struct dentry *);
+extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
 
 /*
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index ae1996d3c539..95827ce2f3c7 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -886,7 +886,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
 		err = -ENOENT;
 	} else {
 		ihold(inode);
-		err = vfs_unlink(dentry->d_parent->d_inode, dentry);
+		err = vfs_unlink(dentry->d_parent->d_inode, dentry, NULL);
 	}
 	dput(dentry);