Allow mounting datasets more than once

Currently mounting an already mounted zfs dataset results in an
error, whereas it is typically allowed with other filesystems.
This causes some bad interactions with mount namespaces. Take
this sequence for example:

- Create a dataset
- Create a snapshot of the dataset
- Create a clone of the snapshot
- Create a new mount namespace
- Rename the original dataset

The rename results in unmounting and remounting the clone in the
original mount namespace, however the remount fails because the
dataset is still mounted in the new mount namespace. (Note that
this means the mount in the new mount namespace is never being
unmounted, so perhaps the unmount/remount of the clone isn't
actually necessary.)

The problem here is a result of the way mounting is implemented
in the kernel module. Since it is not mounting block devices it
uses mount_nodev() instead of the usual mount_bdev(). However,
mount_nodev() is written for filesystems for which each mount is
a new instance (i.e. a new super block), and zfs should be able
to detect when a mount request can be satisfied using an existing
super block.

Change zpl_mount() to call sget() directly with it's own test
callback. Passing the objset_t object as the fs data allows
checking if a superblock already exists for the dataset, and in
that case we just need to return a new reference for the sb's
root dentry.

Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by: Tom Caputi <[email protected]>
Signed-off-by: Alek Pinchuk <[email protected]>
Signed-off-by: Seth Forshee <[email protected]>
Closes #5796
Closes #7207

1 files changed, 59 insertions, 6 deletions

diff --git a/module/zfs/zpl_super.c b/module/zfs/zpl_super.c
index 25e75a897..fc10271b7 100644
--- a/module/zfs/zpl_super.c
+++ b/module/zfs/zpl_super.c
@@ -248,14 +248,61 @@ zpl_fill_super(struct super_block *sb, void *data, int silent)
 	return (error);
 }
 
-#ifdef HAVE_MOUNT_NODEV
+static int
+zpl_test_super(struct super_block *s, void *data)
+{
+	zfsvfs_t *zfsvfs = s->s_fs_info;
+	objset_t *os = data;
+
+	if (zfsvfs == NULL)
+		return (0);
+
+	return (os == zfsvfs->z_os);
+}
+
+static struct super_block *
+zpl_mount_impl(struct file_system_type *fs_type, int flags, zfs_mnt_t *zm)
+{
+	struct super_block *s;
+	objset_t *os;
+	int err;
+
+	err = dmu_objset_hold(zm->mnt_osname, FTAG, &os);
+	if (err)
+		return (ERR_PTR(-err));
+
+	s = zpl_sget(fs_type, zpl_test_super, set_anon_super, flags, os);
+	dmu_objset_rele(os, FTAG);
+	if (IS_ERR(s))
+		return (ERR_CAST(s));
+
+	if (s->s_root == NULL) {
+		err = zpl_fill_super(s, zm, flags & SB_SILENT ? 1 : 0);
+		if (err) {
+			deactivate_locked_super(s);
+			return (ERR_PTR(err));
+		}
+		s->s_flags |= SB_ACTIVE;
+	} else if ((flags ^ s->s_flags) & SB_RDONLY) {
+		deactivate_locked_super(s);
+		return (ERR_PTR(-EBUSY));
+	}
+
+	return (s);
+}
+
+#ifdef HAVE_FST_MOUNT
 static struct dentry *
 zpl_mount(struct file_system_type *fs_type, int flags,
     const char *osname, void *data)
 {
 	zfs_mnt_t zm = { .mnt_osname = osname, .mnt_data = data };
 
-	return (mount_nodev(fs_type, flags, &zm, zpl_fill_super));
+	struct super_block *sb = zpl_mount_impl(fs_type, flags, &zm);
+	if (IS_ERR(sb))
+		return (ERR_CAST(sb));
+
+	return (dget(sb->s_root));
 }
 #else
 static int
@@ -264,9 +311,15 @@ zpl_get_sb(struct file_system_type *fs_type, int flags,
 {
 	zfs_mnt_t zm = { .mnt_osname = osname, .mnt_data = data };
 
-	return (get_sb_nodev(fs_type, flags, &zm, zpl_fill_super, mnt));
+	struct super_block *sb = zpl_mount_impl(fs_type, flags, &zm);
+	if (IS_ERR(sb))
+		return (PTR_ERR(sb));
+
+	(void) simple_set_mnt(mnt, sb);
+
+	return (0);
 }
-#endif /* HAVE_MOUNT_NODEV */
+#endif /* HAVE_FST_MOUNT */
 
 static void
 zpl_kill_sb(struct super_block *sb)
@@ -333,10 +386,10 @@ const struct super_operations zpl_super_operations = {
 struct file_system_type zpl_fs_type = {
 	.owner			= THIS_MODULE,
 	.name			= ZFS_DRIVER,
-#ifdef HAVE_MOUNT_NODEV
+#ifdef HAVE_FST_MOUNT
 	.mount			= zpl_mount,
 #else
 	.get_sb			= zpl_get_sb,
-#endif /* HAVE_MOUNT_NODEV */
+#endif /* HAVE_FST_MOUNT */
 	.kill_sb		= zpl_kill_sb,
 };