4 files changed, 121 insertions, 43 deletions

diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 08c66969d52a..5e73d6626e50 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -111,11 +111,6 @@ static int sysfs_link_sibling(struct sysfs_dirent *sd)
 	/* add new node and rebalance the tree */
 	rb_link_node(&sd->s_rb, parent, node);
 	rb_insert_color(&sd->s_rb, &sd->s_parent->s_dir.children);
-
-	/* if @sd has ns tag, mark the parent to enable ns filtering */
-	if (sd->s_ns)
-		sd->s_parent->s_flags |= SYSFS_FLAG_HAS_NS;
-
 	return 0;
 }
 
@@ -135,13 +130,6 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
 		sd->s_parent->s_dir.subdirs--;
 
 	rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children);
-
-	/*
-	 * Either all or none of the children have tags.  Clearing HAS_NS
-	 * when there's no child left is enough to keep the flag synced.
-	 */
-	if (RB_EMPTY_ROOT(&sd->s_parent->s_dir.children))
-		sd->s_parent->s_flags &= ~SYSFS_FLAG_HAS_NS;
 }
 
 /**
@@ -291,6 +279,7 @@ static int sysfs_dentry_delete(const struct dentry *dentry)
 static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct sysfs_dirent *sd;
+	int type;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
@@ -311,8 +300,13 @@ static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out_bad;
 
 	/* The sysfs dirent has been moved to a different namespace */
-	if (sd->s_ns && sd->s_ns != sysfs_info(dentry->d_sb)->ns)
-		goto out_bad;
+	type = KOBJ_NS_TYPE_NONE;
+	if (sd->s_parent) {
+		type = sysfs_ns_type(sd->s_parent);
+		if (type != KOBJ_NS_TYPE_NONE &&
+				sysfs_info(dentry->d_sb)->ns[type] != sd->s_ns)
+			goto out_bad;
+	}
 
 	mutex_unlock(&sysfs_mutex);
 out_valid:
@@ -432,6 +426,13 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd,
 	struct sysfs_inode_attrs *ps_iattr;
 	int ret;
 
+	if (!!sysfs_ns_type(parent_sd) != !!sd->s_ns) {
+		WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
+			sysfs_ns_type(parent_sd) ? "required" : "invalid",
+			parent_sd->s_name, sd->s_name);
+		return -EINVAL;
+	}
+
 	sd->s_hash = sysfs_name_hash(sd->s_name, sd->s_ns);
 	sd->s_parent = sysfs_get(parent_sd);
 
@@ -611,6 +612,13 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
 	struct rb_node *node = parent_sd->s_dir.children.rb_node;
 	unsigned int hash;
 
+	if (!!sysfs_ns_type(parent_sd) != !!ns) {
+		WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
+			sysfs_ns_type(parent_sd) ? "required" : "invalid",
+			parent_sd->s_name, name);
+		return NULL;
+	}
+
 	hash = sysfs_name_hash(name, ns);
 	while (node) {
 		struct sysfs_dirent *sd;
@@ -659,6 +667,7 @@ struct sysfs_dirent *sysfs_get_dirent_ns(struct sysfs_dirent *parent_sd,
 EXPORT_SYMBOL_GPL(sysfs_get_dirent_ns);
 
 static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
+		      enum kobj_ns_type type,
 		      const char *name, const void *ns,
 		      struct sysfs_dirent **p_sd)
 {
@@ -672,6 +681,7 @@ static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
 	if (!sd)
 		return -ENOMEM;
 
+	sd->s_flags |= (type << SYSFS_NS_TYPE_SHIFT);
 	sd->s_ns = ns;
 	sd->s_dir.kobj = kobj;
 
@@ -691,7 +701,33 @@ static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
 int sysfs_create_subdir(struct kobject *kobj, const char *name,
 			struct sysfs_dirent **p_sd)
 {
-	return create_dir(kobj, kobj->sd, name, NULL, p_sd);
+	return create_dir(kobj, kobj->sd,
+			  KOBJ_NS_TYPE_NONE, name, NULL, p_sd);
+}
+
+/**
+ *	sysfs_read_ns_type: return associated ns_type
+ *	@kobj: the kobject being queried
+ *
+ *	Each kobject can be tagged with exactly one namespace type
+ *	(i.e. network or user).  Return the ns_type associated with
+ *	this object if any
+ */
+static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj)
+{
+	const struct kobj_ns_type_operations *ops;
+	enum kobj_ns_type type;
+
+	ops = kobj_child_ns_ops(kobj);
+	if (!ops)
+		return KOBJ_NS_TYPE_NONE;
+
+	type = ops->type;
+	BUG_ON(type <= KOBJ_NS_TYPE_NONE);
+	BUG_ON(type >= KOBJ_NS_TYPES);
+	BUG_ON(!kobj_ns_type_registered(type));
+
+	return type;
 }
 
 /**
@@ -701,6 +737,7 @@ int sysfs_create_subdir(struct kobject *kobj, const char *name,
  */
 int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 {
+	enum kobj_ns_type type;
 	struct sysfs_dirent *parent_sd, *sd;
 	int error = 0;
 
@@ -714,7 +751,9 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 	if (!parent_sd)
 		return -ENOENT;
 
-	error = create_dir(kobj, parent_sd, kobject_name(kobj), ns, &sd);
+	type = sysfs_read_ns_type(kobj);
+
+	error = create_dir(kobj, parent_sd, type, kobject_name(kobj), ns, &sd);
 	if (!error)
 		kobj->sd = sd;
 	return error;
@@ -728,12 +767,13 @@ static struct dentry *sysfs_lookup(struct inode *dir, struct dentry *dentry,
 	struct sysfs_dirent *parent_sd = parent->d_fsdata;
 	struct sysfs_dirent *sd;
 	struct inode *inode;
-	const void *ns = NULL;
+	enum kobj_ns_type type;
+	const void *ns;
 
 	mutex_lock(&sysfs_mutex);
 
-	if (parent_sd->s_flags & SYSFS_FLAG_HAS_NS)
-		ns = sysfs_info(dir->i_sb)->ns;
+	type = sysfs_ns_type(parent_sd);
+	ns = sysfs_info(dir->i_sb)->ns[type];
 
 	sd = sysfs_find_dirent(parent_sd, dentry->d_name.name, ns);
 
@@ -1056,15 +1096,15 @@ static int sysfs_readdir(struct file *file, struct dir_context *ctx)
 	struct dentry *dentry = file->f_path.dentry;
 	struct sysfs_dirent *parent_sd = dentry->d_fsdata;
 	struct sysfs_dirent *pos = file->private_data;
-	const void *ns = NULL;
+	enum kobj_ns_type type;
+	const void *ns;
+
+	type = sysfs_ns_type(parent_sd);
+	ns = sysfs_info(dentry->d_sb)->ns[type];
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 	mutex_lock(&sysfs_mutex);
-
-	if (parent_sd->s_flags & SYSFS_FLAG_HAS_NS)
-		ns = sysfs_info(dentry->d_sb)->ns;
-
 	for (pos = sysfs_dir_pos(ns, parent_sd, ctx->pos, pos);
 	     pos;
 	     pos = sysfs_dir_next_pos(ns, parent_sd, ctx->pos, pos)) {
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 8c24bce2f4ae..834ec2cdb7a3 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -36,7 +36,7 @@ static const struct super_operations sysfs_ops = {
 struct sysfs_dirent sysfs_root = {
 	.s_name		= "",
 	.s_count	= ATOMIC_INIT(1),
-	.s_flags	= SYSFS_DIR,
+	.s_flags	= SYSFS_DIR | (KOBJ_NS_TYPE_NONE << SYSFS_NS_TYPE_SHIFT),
 	.s_mode		= S_IFDIR | S_IRUGO | S_IXUGO,
 	.s_ino		= 1,
 };
@@ -77,8 +77,14 @@ static int sysfs_test_super(struct super_block *sb, void *data)
 {
 	struct sysfs_super_info *sb_info = sysfs_info(sb);
 	struct sysfs_super_info *info = data;
+	enum kobj_ns_type type;
+	int found = 1;
 
-	return sb_info->ns == info->ns;
+	for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) {
+		if (sb_info->ns[type] != info->ns[type])
+			found = 0;
+	}
+	return found;
 }
 
 static int sysfs_set_super(struct super_block *sb, void *data)
@@ -92,7 +98,9 @@ static int sysfs_set_super(struct super_block *sb, void *data)
 
 static void free_sysfs_super_info(struct sysfs_super_info *info)
 {
-	kobj_ns_drop(KOBJ_NS_TYPE_NET, info->ns);
+	int type;
+	for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++)
+		kobj_ns_drop(type, info->ns[type]);
 	kfree(info);
 }
 
@@ -100,6 +108,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
 	struct sysfs_super_info *info;
+	enum kobj_ns_type type;
 	struct super_block *sb;
 	int error;
 
@@ -107,15 +116,18 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
 			return ERR_PTR(-EPERM);
 
-		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
-			return ERR_PTR(-EPERM);
+		for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) {
+			if (!kobj_ns_current_may_mount(type))
+				return ERR_PTR(-EPERM);
+		}
 	}
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
-	info->ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
+	for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++)
+		info->ns[type] = kobj_ns_grab_current(type);
 
 	sb = sget(fs_type, sysfs_test_super, sysfs_set_super, flags, info);
 	if (IS_ERR(sb) || sb->s_fs_info != info)
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 1a23681b8179..3ae3f1bf1a09 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -28,6 +28,7 @@ static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
 	struct sysfs_dirent *target_sd = NULL;
 	struct sysfs_dirent *sd = NULL;
 	struct sysfs_addrm_cxt acxt;
+	enum kobj_ns_type ns_type;
 	int error;
 
 	BUG_ON(!name || !parent_sd);
@@ -51,15 +52,29 @@ static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
 	if (!sd)
 		goto out_put;
 
-	sd->s_ns = target_sd->s_ns;
+	ns_type = sysfs_ns_type(parent_sd);
+	if (ns_type)
+		sd->s_ns = target_sd->s_ns;
 	sd->s_symlink.target_sd = target_sd;
 	target_sd = NULL;	/* reference is now owned by the symlink */
 
 	sysfs_addrm_start(&acxt);
-	if (warn)
-		error = sysfs_add_one(&acxt, sd, parent_sd);
-	else
-		error = __sysfs_add_one(&acxt, sd, parent_sd);
+	/* Symlinks must be between directories with the same ns_type */
+	if (!ns_type ||
+	    (ns_type == sysfs_ns_type(sd->s_symlink.target_sd->s_parent))) {
+		if (warn)
+			error = sysfs_add_one(&acxt, sd, parent_sd);
+		else
+			error = __sysfs_add_one(&acxt, sd, parent_sd);
+	} else {
+		error = -EINVAL;
+		WARN(1, KERN_WARNING
+			"sysfs: symlink across ns_types %s/%s -> %s/%s\n",
+			parent_sd->s_name,
+			sd->s_name,
+			sd->s_symlink.target_sd->s_parent->s_name,
+			sd->s_symlink.target_sd->s_name);
+	}
 	sysfs_addrm_finish(&acxt);
 
 	if (error)
@@ -149,7 +164,7 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ,
 	 * sysfs_remove_dir() for details.
 	 */
 	spin_lock(&sysfs_symlink_target_lock);
-	if (targ->sd)
+	if (targ->sd && sysfs_ns_type(kobj->sd))
 		ns = targ->sd->s_ns;
 	spin_unlock(&sysfs_symlink_target_lock);
 	sysfs_hash_and_remove(kobj->sd, name, ns);
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index e3aea92ebfa3..0af09fbfb3f6 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -90,8 +90,11 @@ struct sysfs_dirent {
 #define SYSFS_COPY_NAME			(SYSFS_DIR | SYSFS_KOBJ_LINK)
 #define SYSFS_ACTIVE_REF		(SYSFS_KOBJ_ATTR | SYSFS_KOBJ_BIN_ATTR)
 
-#define SYSFS_FLAG_MASK			~SYSFS_TYPE_MASK
-#define SYSFS_FLAG_HAS_NS		0x01000
+/* identify any namespace tag on sysfs_dirents */
+#define SYSFS_NS_TYPE_MASK		0xf00
+#define SYSFS_NS_TYPE_SHIFT		8
+
+#define SYSFS_FLAG_MASK			~(SYSFS_NS_TYPE_MASK|SYSFS_TYPE_MASK)
 #define SYSFS_FLAG_REMOVED		0x02000
 
 static inline unsigned int sysfs_type(struct sysfs_dirent *sd)
@@ -99,6 +102,15 @@ static inline unsigned int sysfs_type(struct sysfs_dirent *sd)
 	return sd->s_flags & SYSFS_TYPE_MASK;
 }
 
+/*
+ * Return any namespace tags on this dirent.
+ * enum kobj_ns_type is defined in linux/kobject.h
+ */
+static inline enum kobj_ns_type sysfs_ns_type(struct sysfs_dirent *sd)
+{
+	return (sd->s_flags & SYSFS_NS_TYPE_MASK) >> SYSFS_NS_TYPE_SHIFT;
+}
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 #define sysfs_dirent_init_lockdep(sd)				\
@@ -143,13 +155,12 @@ struct sysfs_addrm_cxt {
  */
 
 /*
- * Each sb is associated with one namespace tag, currently the network
- * namespace of the task which mounted this sysfs instance.  If multiple
- * tags become necessary, make the following an array and compare
- * sysfs_dirent tag against every entry.
+ * Each sb is associated with a set of namespace tags (i.e.
+ * the network namespace of the task which mounted this sysfs
+ * instance).
  */
 struct sysfs_super_info {
-	void *ns;
+	void *ns[KOBJ_NS_TYPES];
 };
 #define sysfs_info(SB) ((struct sysfs_super_info *)(SB->s_fs_info))
 extern struct sysfs_dirent sysfs_root;