kernfs: Use RCU to access kernfs_node::parent.

kernfs_rename_lock is used to obtain stable kernfs_node::{name|parent}
pointer. This is a preparation to access kernfs_node::parent under RCU
and ensure that the pointer remains stable under the RCU lifetime
guarantees.

For a complete path, as it is done in kernfs_path_from_node(), the
kernfs_rename_lock is still required in order to obtain a stable parent
relationship while computing the relevant node depth. This must not
change while the nodes are inspected in order to build the path.
If the kernfs user never moves the nodes (changes the parent) then the
kernfs_rename_lock is not required and the RCU guarantees are
sufficient. This "restriction" can be set with
KERNFS_ROOT_INVARIANT_PARENT. Otherwise the lock is required.

Rename kernfs_node::parent to kernfs_node::__parent to denote the RCU
access and use RCU accessor while accessing the node.
Make cgroup use KERNFS_ROOT_INVARIANT_PARENT since the parent here can
not change.

Acked-by: Tejun Heo <tj@kernel.org>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250213145023.2820193-6-bigeasy@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 20 insertions, 6 deletions

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index e28d5f0d20ed..c9752eb607ec 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -844,7 +844,7 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent
 
 	if (kernfs_type(kn) != KERNFS_DIR)
 		return -ENOTDIR;
-	if (kn->parent != new_parent)
+	if (rcu_access_pointer(kn->__parent) != new_parent)
 		return -EIO;
 
 	/*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index d9061bd55436..71819e58d70c 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -633,9 +633,22 @@ int cgroup_task_count(const struct cgroup *cgrp)
 	return count;
 }
 
+static struct cgroup *kn_priv(struct kernfs_node *kn)
+{
+	struct kernfs_node *parent;
+	/*
+	 * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT.
+	 * Therefore it is always safe to dereference this pointer outside of a
+	 * RCU section.
+	 */
+	parent = rcu_dereference_check(kn->__parent,
+				       kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT);
+	return parent->priv;
+}
+
 struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 {
-	struct cgroup *cgrp = of->kn->parent->priv;
+	struct cgroup *cgrp = kn_priv(of->kn);
 	struct cftype *cft = of_cft(of);
 
 	/*
@@ -1612,7 +1625,7 @@ void cgroup_kn_unlock(struct kernfs_node *kn)
 	if (kernfs_type(kn) == KERNFS_DIR)
 		cgrp = kn->priv;
 	else
-		cgrp = kn->parent->priv;
+		cgrp = kn_priv(kn);
 
 	cgroup_unlock();
 
@@ -1644,7 +1657,7 @@ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline)
 	if (kernfs_type(kn) == KERNFS_DIR)
 		cgrp = kn->priv;
 	else
-		cgrp = kn->parent->priv;
+		cgrp = kn_priv(kn);
 
 	/*
 	 * We're gonna grab cgroup_mutex which nests outside kernfs
@@ -2118,7 +2131,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	root->kf_root = kernfs_create_root(kf_sops,
 					   KERNFS_ROOT_CREATE_DEACTIVATED |
 					   KERNFS_ROOT_SUPPORT_EXPORTOP |
-					   KERNFS_ROOT_SUPPORT_USER_XATTR,
+					   KERNFS_ROOT_SUPPORT_USER_XATTR |
+					   KERNFS_ROOT_INVARIANT_PARENT,
 					   root_cgrp);
 	if (IS_ERR(root->kf_root)) {
 		ret = PTR_ERR(root->kf_root);
@@ -4119,7 +4133,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 				 size_t nbytes, loff_t off)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
-	struct cgroup *cgrp = of->kn->parent->priv;
+	struct cgroup *cgrp = kn_priv(of->kn);
 	struct cftype *cft = of_cft(of);
 	struct cgroup_subsys_state *css;
 	int ret;