locks: break delegations on any attribute modification

NFSv4 uses leases to guarantee that clients can cache metadata as well
as data.

Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>
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>

drivers/base/devtmpfs.c

@@ -216,7 +216,7 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid,
 		newattrs.ia_gid = gid;
 		newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID;
 		mutex_lock(&dentry->d_inode->i_mutex);
-		notify_change(dentry, &newattrs);
+		notify_change(dentry, &newattrs, NULL);
 		mutex_unlock(&dentry->d_inode->i_mutex);
 
 		/* mark as kernel-created inode */
@@ -322,7 +322,7 @@ static int handle_remove(const char *nodename, struct device *dev)
 			newattrs.ia_valid =
 				ATTR_UID|ATTR_GID|ATTR_MODE;
 			mutex_lock(&dentry->d_inode->i_mutex);
-			notify_change(dentry, &newattrs);
+			notify_change(dentry, &newattrs, NULL);
 			mutex_unlock(&dentry->d_inode->i_mutex);
 			err = vfs_unlink(parent.dentry->d_inode, dentry, NULL);
 			if (!err || err == -ENOENT)

fs/attr.c

@@ -167,7 +167,27 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 }
 EXPORT_SYMBOL(setattr_copy);
 
-int notify_change(struct dentry * dentry, struct iattr * attr)
+/**
+ * notify_change - modify attributes of a filesytem object
+ * @dentry:	object affected
+ * @iattr:	new attributes
+ * @delegated_inode: returns inode, if the inode is delegated
+ *
+ * The caller must hold the i_mutex on the affected object.
+ *
+ * If notify_change discovers a delegation in need of breaking,
+ * it will return -EWOULDBLOCK and return a reference to the inode in
+ * delegated_inode.  The caller should then break the delegation and
+ * retry.  Because breaking a delegation may take a long time, the
+ * caller should drop the 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.  Also, passing NULL is fine for callers holding
+ * the file open for write, as there can be no conflicting delegation in
+ * that case.
+ */
+int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	umode_t mode = inode->i_mode;
@@ -241,6 +261,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
 		return 0;
 
 	error = security_inode_setattr(dentry, attr);
+	if (error)
+		return error;
+	error = try_break_deleg(inode, delegated_inode);
 	if (error)
 		return error;
 

fs/cachefiles/interface.c

@@ -449,14 +449,14 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
 		_debug("discard tail %llx", oi_size);
 		newattrs.ia_valid = ATTR_SIZE;
 		newattrs.ia_size = oi_size & PAGE_MASK;
-		ret = notify_change(object->backer, &newattrs);
+		ret = notify_change(object->backer, &newattrs, NULL);
 		if (ret < 0)
 			goto truncate_failed;
 	}
 
 	newattrs.ia_valid = ATTR_SIZE;
 	newattrs.ia_size = ni_size;
-	ret = notify_change(object->backer, &newattrs);
+	ret = notify_change(object->backer, &newattrs, NULL);
 
 truncate_failed:
 	mutex_unlock(&object->backer->d_inode->i_mutex);

fs/ecryptfs/inode.c

@@ -882,7 +882,7 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 		struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
 
 		mutex_lock(&lower_dentry->d_inode->i_mutex);
-		rc = notify_change(lower_dentry, &lower_ia);
+		rc = notify_change(lower_dentry, &lower_ia, NULL);
 		mutex_unlock(&lower_dentry->d_inode->i_mutex);
 	}
 	return rc;
@@ -983,7 +983,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 		lower_ia.ia_valid &= ~ATTR_MODE;
 
 	mutex_lock(&lower_dentry->d_inode->i_mutex);
-	rc = notify_change(lower_dentry, &lower_ia);
+	rc = notify_change(lower_dentry, &lower_ia, NULL);
 	mutex_unlock(&lower_dentry->d_inode->i_mutex);
 out:
 	fsstack_copy_attr_all(inode, lower_inode);

fs/hpfs/namei.c

@@ -407,7 +407,7 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry)
 			/*printk("HPFS: truncating file before delete.\n");*/
 			newattrs.ia_size = 0;
 			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
-			err = notify_change(dentry, &newattrs);
+			err = notify_change(dentry, &newattrs, NULL);
 			put_write_access(inode);
 			if (!err)
 				goto again;

fs/inode.c

@@ -1603,7 +1603,11 @@ static int __remove_suid(struct dentry *dentry, int kill)
 	struct iattr newattrs;
 
 	newattrs.ia_valid = ATTR_FORCE | kill;
-	return notify_change(dentry, &newattrs);
+	/*
+	 * Note we call this on write, so notify_change will not
+	 * encounter any conflicting delegations:
+	 */
+	return notify_change(dentry, &newattrs, NULL);
 }
 
 int file_remove_suid(struct file *file)

fs/nfsd/vfs.c

@@ -427,7 +427,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 			goto out_nfserr;
 		fh_lock(fhp);
 
-		host_err = notify_change(dentry, iap);
+		host_err = notify_change(dentry, iap, NULL);
 		err = nfserrno(host_err);
 		fh_unlock(fhp);
 	}
@@ -988,7 +988,11 @@ static void kill_suid(struct dentry *dentry)
 	ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
 
 	mutex_lock(&dentry->d_inode->i_mutex);
-	notify_change(dentry, &ia);
+	/*
+	 * Note we call this on write, so notify_change will not
+	 * encounter any conflicting delegations:
+	 */
+	notify_change(dentry, &ia, NULL);
 	mutex_unlock(&dentry->d_inode->i_mutex);
 }
 

fs/open.c

@@ -57,7 +57,8 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 		newattrs.ia_valid |= ret | ATTR_FORCE;
 
 	mutex_lock(&dentry->d_inode->i_mutex);
-	ret = notify_change(dentry, &newattrs);
+	/* Note any delegations or leases have already been broken: */
+	ret = notify_change(dentry, &newattrs, NULL);
 	mutex_unlock(&dentry->d_inode->i_mutex);
 	return ret;
 }
@@ -464,21 +465,28 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename)
 static int chmod_common(struct path *path, umode_t mode)
 {
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 	struct iattr newattrs;
 	int error;
 
 	error = mnt_want_write(path->mnt);
 	if (error)
 		return error;
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
 	error = security_path_chmod(path, mode);
 	if (error)
 		goto out_unlock;
 	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
 	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-	error = notify_change(path->dentry, &newattrs);
+	error = notify_change(path->dentry, &newattrs, &delegated_inode);
 out_unlock:
 	mutex_unlock(&inode->i_mutex);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	mnt_drop_write(path->mnt);
 	return error;
 }
@@ -522,6 +530,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
 static int chown_common(struct path *path, uid_t user, gid_t group)
 {
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 	int error;
 	struct iattr newattrs;
 	kuid_t uid;
@@ -546,12 +555,17 @@ static int chown_common(struct path *path, uid_t user, gid_t group)
 	if (!S_ISDIR(inode->i_mode))
 		newattrs.ia_valid |=
 			ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
 	error = security_path_chown(path, uid, gid);
 	if (!error)
-		error = notify_change(path->dentry, &newattrs);
+		error = notify_change(path->dentry, &newattrs, &delegated_inode);
 	mutex_unlock(&inode->i_mutex);
-
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	return error;
 }
 

fs/utimes.c

@@ -53,6 +53,7 @@ static int utimes_common(struct path *path, struct timespec *times)
 	int error;
 	struct iattr newattrs;
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 
 	error = mnt_want_write(path->mnt);
 	if (error)
@@ -101,9 +102,15 @@ static int utimes_common(struct path *path, struct timespec *times)
 				goto mnt_drop_write_and_out;
 		}
 	}
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
-	error = notify_change(path->dentry, &newattrs);
+	error = notify_change(path->dentry, &newattrs, &delegated_inode);
 	mutex_unlock(&inode->i_mutex);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 
 mnt_drop_write_and_out:
 	mnt_drop_write(path->mnt);

include/linux/fs.h

@@ -2278,7 +2278,7 @@ extern void emergency_remount(void);
 #ifdef CONFIG_BLOCK
 extern sector_t bmap(struct inode *, sector_t);
 #endif
-extern int notify_change(struct dentry *, struct iattr *);
+extern int notify_change(struct dentry *, struct iattr *, struct inode **);
 extern int inode_permission(struct inode *, int);
 extern int generic_permission(struct inode *, int);