Use zfs_mknode() to create dataset root

Long, long, long ago when the effort to port ZFS was begun
the zfs_create_fs() function was heavily modified to remove
all of its VFS dependencies.  This allowed Lustre to use
the dataset without us having to spend the time porting all
the required VFS code.

Fast-forward several years and we now have all the VFS code
in place but are still relying on the modified zfs_create_fs().
This isn't required anymore and we can now use zfs_mknode()
to create the root znode for the filesystem.

This commit reverts the contents of zfs_create_fs() to largely
match the upstream OpenSolaris code.  There have been minor
modifications to accomidate the Linux VFS but that is all.

This code fixes issue #116 by bootstraping enough of the VFS
data structures so we can rely on zfs_mknode() to create the
root directory.  This ensures it is created properly with
support for system attributes.  Previously it wasn't which
is why it behaved differently that all other directories
when modified.

Signed-off-by: Brian Behlendorf <[email protected]>
Closes #116

1 files changed, 68 insertions, 31 deletions

diff --git a/module/zfs/zfs_znode.c b/module/zfs/zfs_znode.c
index b56e290cb..ea8b4c505 100644
--- a/module/zfs/zfs_znode.c
+++ b/module/zfs/zfs_znode.c
@@ -1397,13 +1397,18 @@ log:
 void
 zfs_create_fs(objset_t *os, cred_t *cr, nvlist_t *zplprops, dmu_tx_t *tx)
 {
+	struct super_block *sb;
+	zfs_sb_t	*zsb;
 	uint64_t	moid, obj, sa_obj, version;
+	uint64_t	sense = ZFS_CASE_SENSITIVE;
 	uint64_t	norm = 0;
 	nvpair_t	*elem;
 	int		error;
-	timestruc_t	now;
-	dmu_buf_t	*db;
-	znode_phys_t	*pzp;
+	int		i;
+	znode_t		*rootzp = NULL;
+	vattr_t		vattr;
+	znode_t		*zp;
+	zfs_acl_ids_t	acl_ids;
 
 	/*
 	 * First attempt to create master node.
@@ -1439,6 +1444,8 @@ zfs_create_fs(objset_t *os, cred_t *cr, nvlist_t *zplprops, dmu_tx_t *tx)
 		ASSERT(error == 0);
 		if (strcmp(name, zfs_prop_to_name(ZFS_PROP_NORMALIZE)) == 0)
 			norm = val;
+		else if (strcmp(name, zfs_prop_to_name(ZFS_PROP_CASE)) == 0)
+			sense = val;
 	}
 	ASSERT(version != 0);
 	error = zap_update(os, moid, ZPL_VERSION_STR, 8, 1, &version, tx);
@@ -1464,47 +1471,77 @@ zfs_create_fs(objset_t *os, cred_t *cr, nvlist_t *zplprops, dmu_tx_t *tx)
 	ASSERT(error == 0);
 
 	/*
-	 * Create root znode with code free of VFS dependencies.  This
-	 * is important because without a registered filesystem and super
-	 * block all the required VFS hooks will be missing.  The critical
-	 * thing is to just crete the required root znode.
+	 * Create root znode.  Create minimal znode/inode/zsb/sb
+	 * to allow zfs_mknode to work.
 	 */
-	obj = zap_create_norm(os, norm, DMU_OT_DIRECTORY_CONTENTS,
-	                      DMU_OT_ZNODE, sizeof (znode_phys_t), tx);
+	vattr.va_mask = ATTR_MODE|ATTR_UID|ATTR_GID;
+	vattr.va_mode = S_IFDIR|0755;
+	vattr.va_uid = crgetuid(cr);
+	vattr.va_gid = crgetgid(cr);
+
+	rootzp = kmem_cache_alloc(znode_cache, KM_SLEEP);
+	rootzp->z_moved = 0;
+	rootzp->z_unlinked = 0;
+	rootzp->z_atime_dirty = 0;
+	rootzp->z_is_sa = USE_SA(version, os);
+
+	zsb = kmem_zalloc(sizeof (zfs_sb_t), KM_SLEEP);
+	zsb->z_os = os;
+	zsb->z_parent = zsb;
+	zsb->z_version = version;
+	zsb->z_use_fuids = USE_FUIDS(version, os);
+	zsb->z_use_sa = USE_SA(version, os);
+	zsb->z_norm = norm;
+
+	sb = kmem_zalloc(sizeof (struct super_block), KM_SLEEP);
+	sb->s_fs_info = zsb;
+
+	ZTOI(rootzp)->i_sb = sb;
+
+	error = sa_setup(os, sa_obj, zfs_attr_table, ZPL_END,
+	    &zsb->z_attr_table);
 
-	VERIFY(0 == dmu_bonus_hold(os, obj, FTAG, &db));
-	dmu_buf_will_dirty(db, tx);
+	ASSERT(error == 0);
 
 	/*
-	 * Initialize the znode physical data to zero.
+	 * Fold case on file systems that are always or sometimes case
+	 * insensitive.
 	 */
-	ASSERT(db->db_size >= sizeof (znode_phys_t));
-	bzero(db->db_data, db->db_size);
-	pzp = db->db_data;
+	if (sense == ZFS_CASE_INSENSITIVE || sense == ZFS_CASE_MIXED)
+		zsb->z_norm |= U8_TEXTPREP_TOUPPER;
 
-	if (USE_FUIDS(version, os))
-		pzp->zp_flags = ZFS_ARCHIVE | ZFS_AV_MODIFIED;
+	mutex_init(&zsb->z_znodes_lock, NULL, MUTEX_DEFAULT, NULL);
+	list_create(&zsb->z_all_znodes, sizeof (znode_t),
+	    offsetof(znode_t, z_link_node));
 
-	pzp->zp_size = 2; /* "." and ".." */
-	pzp->zp_links = 2;
-	pzp->zp_parent = obj;
-	pzp->zp_gen = dmu_tx_get_txg(tx);
-	pzp->zp_mode = S_IFDIR | 0755;
-	pzp->zp_flags = ZFS_ACL_TRIVIAL;
+	for (i = 0; i != ZFS_OBJ_MTX_SZ; i++)
+		mutex_init(&zsb->z_hold_mtx[i], NULL, MUTEX_DEFAULT, NULL);
 
-	gethrestime(&now);
+	VERIFY(0 == zfs_acl_ids_create(rootzp, IS_ROOT_NODE, &vattr,
+	    cr, NULL, &acl_ids));
+	zfs_mknode(rootzp, &vattr, tx, cr, IS_ROOT_NODE, &zp, &acl_ids);
+	ASSERT3P(zp, ==, rootzp);
+	error = zap_add(os, moid, ZFS_ROOT_OBJ, 8, 1, &rootzp->z_id, tx);
+	ASSERT(error == 0);
+	zfs_acl_ids_free(&acl_ids);
 
-	ZFS_TIME_ENCODE(&now, pzp->zp_crtime);
-	ZFS_TIME_ENCODE(&now, pzp->zp_ctime);
-	ZFS_TIME_ENCODE(&now, pzp->zp_atime);
-	ZFS_TIME_ENCODE(&now, pzp->zp_mtime);
+	atomic_set(&ZTOI(rootzp)->i_count, 0);
+	sa_handle_destroy(rootzp->z_sa_hdl);
+	kmem_free(sb, sizeof (struct super_block));
+	kmem_free(zsb, sizeof (zfs_sb_t));
+	kmem_cache_free(znode_cache, rootzp);
+
+	/*
+	 * Create shares directory
+	 */
+
+	error = zfs_create_share_dir(zsb, tx);
 
-	error = zap_add(os, moid, ZFS_ROOT_OBJ, 8, 1, &obj, tx);
 	ASSERT(error == 0);
 
-	dmu_buf_rele(db, FTAG);
+	for (i = 0; i != ZFS_OBJ_MTX_SZ; i++)
+		mutex_destroy(&zsb->z_hold_mtx[i]);
 }
-
 #endif /* _KERNEL */
 
 static int