Linux compat 2.6.39: mount_nodev()

The .get_sb callback has been replaced by a .mount callback
in the file_system_type structure.  When using the new
interface the caller must now use the mount_nodev() helper.

Unfortunately, the new interface no longer passes the vfsmount
down to the zfs layers.  This poses a problem for the existing
implementation because we currently save this pointer in the
super block for latter use.  It provides our only entry point
in to the namespace layer for manipulating certain mount options.

This needed to be done originally to allow commands like
'zfs set atime=off tank' to work properly.  It also allowed me
to keep more of the original Solaris code unmodified.  Under
Solaris there is a 1-to-1 mapping between a mount point and a
file system so this is a fairly natural thing to do.  However,
under Linux they many be multiple entries in the namespace
which reference the same filesystem.  Thus keeping a back
reference from the filesystem to the namespace is complicated.

Rather than introduce some ugly hack to get the vfsmount and
continue as before.  I'm leveraging this API change to update
the ZFS code to do things in a more natural way for Linux.
This has the upside that is resolves the compatibility issue
for the long term and fixes several other minor bugs which
have been reported.

This commit updates the code to remove this vfsmount back
reference entirely.  All modifications to filesystem mount
options are now passed in to the kernel via a '-o remount'.
This is the expected Linux mechanism and allows the namespace
to properly handle any options which apply to it before passing
them on to the file system itself.

Aside from fixing the compatibility issue, removing the
vfsmount has had the benefit of simplifying the code.  This
change which fairly involved has turned out nicely.

Closes #246
Closes #217
Closes #187
Closes #248
Closes #231

1 files changed, 9 insertions, 8 deletions

diff --git a/module/zfs/zfs_ioctl.c b/module/zfs/zfs_ioctl.c
index 39c60915ea50..b50f02383af4 100644
--- a/module/zfs/zfs_ioctl.c
+++ b/module/zfs/zfs_ioctl.c
@@ -1107,8 +1107,9 @@ get_zfs_sb(const char *dsname, zfs_sb_t **zsbp)
 
 	mutex_enter(&os->os_user_ptr_lock);
 	*zsbp = dmu_objset_get_user(os);
-	if (*zsbp) {
-		mntget((*zsbp)->z_vfs);
+	if (*zsbp && (*zsbp)->z_sb) {
+		if (atomic_inc_not_zero(&((*zsbp)->z_sb->s_active)))
+			error = ESRCH;
 	} else {
 		error = ESRCH;
 	}
@@ -1119,7 +1120,7 @@ get_zfs_sb(const char *dsname, zfs_sb_t **zsbp)
 
 /*
  * Find a zfs_sb_t for a mounted filesystem, or create our own, in which
- * case its z_vfs will be NULL, and it will be opened as the owner.
+ * case its z_sb will be NULL, and it will be opened as the owner.
  */
 static int
 zfs_sb_hold(const char *name, void *tag, zfs_sb_t **zsbp, boolean_t writer)
@@ -1149,8 +1150,8 @@ zfs_sb_rele(zfs_sb_t *zsb, void *tag)
 {
 	rrw_exit(&zsb->z_teardown_lock, tag);
 
-	if (zsb->z_vfs) {
-		mntput(zsb->z_vfs);
+	if (zsb->z_sb) {
+		deactivate_super(zsb->z_sb);
 	} else {
 		dmu_objset_disown(zsb->z_os, zsb);
 		zfs_sb_free(zsb);
@@ -3239,7 +3240,7 @@ zfs_ioc_rollback(zfs_cmd_t *zc)
 			resume_err = zfs_resume_fs(zsb, zc->zc_name);
 			error = error ? error : resume_err;
 		}
-		mntput(zsb->z_vfs);
+		deactivate_super(zsb->z_sb);
 	} else {
 		if (dsl_dataset_tryown(ds, B_FALSE, FTAG)) {
 			error = dsl_dataset_clone_swap(clone, ds, B_TRUE);
@@ -3724,7 +3725,7 @@ zfs_ioc_recv(zfs_cmd_t *zc)
 			if (error == 0)
 				error = zfs_resume_fs(zsb, tofs);
 			error = error ? error : end_err;
-			mntput(zsb->z_vfs);
+			deactivate_super(zsb->z_sb);
 		} else {
 			error = dmu_recv_end(&drc);
 		}
@@ -4137,7 +4138,7 @@ zfs_ioc_userspace_upgrade(zfs_cmd_t *zc)
 		}
 		if (error == 0)
 			error = dmu_objset_userspace_upgrade(zsb->z_os);
-		mntput(zsb->z_vfs);
+		deactivate_super(zsb->z_sb);
 	} else {
 		/* XXX kind of reading contents without owning */
 		error = dmu_objset_hold(zc->zc_name, FTAG, &os);