[PATCH v6 1/3] cgroup: track the effective css in each cgroup

[Peng Yu]

Track the effective css in each cgroup and make cgroup_e_css() and
cgroup_get_e_css() use it. When a css is brought online or offline,
update the effective css of its cgroup and of all descendants.

Signed-off-by: Peng Yu <yupeng0921 at gmail.com>
Assisted-by: Claude:claude-fable-5 [Claude Code]
Assisted-by: Claude:claude-opus-5-5 [Claude Code]
---
 include/linux/cgroup-defs.h |  2 ++
 kernel/cgroup/cgroup.c      | 53 ++++++++++++++++++++++---------------
 2 files changed, 34 insertions(+), 21 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 3754d697854b..5bbe6025fc77 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -555,6 +555,8 @@ struct cgroup {
 	/* Private pointers for each registered subsystem */
 	struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
 
+	struct cgroup_subsys_state __rcu *e_css[CGROUP_SUBSYS_COUNT];
+
 	/*
 	 * Keep track of total number of dying CSSes at and below this cgroup.
 	 * Protected by cgroup_mutex.
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 2d532bf2c0c7..69b0f0cf2f3e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -548,20 +548,11 @@ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp,
 struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
 					 struct cgroup_subsys *ss)
 {
-	struct cgroup_subsys_state *css;
-
 	if (!CGROUP_HAS_SUBSYS_CONFIG)
 		return NULL;
 
-	do {
-		css = cgroup_css(cgrp, ss);
-
-		if (css)
-			return css;
-		cgrp = cgroup_parent(cgrp);
-	} while (cgrp);
-
-	return init_css_set.subsys[ss->id];
+	return rcu_dereference_check(cgrp->e_css[ss->id],
+				     lockdep_is_held(&cgroup_mutex));
 }
 
 /**
@@ -585,17 +576,10 @@ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp,
 
 	rcu_read_lock();
 
-	do {
-		css = cgroup_css(cgrp, ss);
-
-		if (css && css_tryget_online(css))
-			goto out_unlock;
-		cgrp = cgroup_parent(cgrp);
-	} while (cgrp);
+	css = cgroup_e_css(cgrp, ss);
+	while (!css_tryget_online(css))
+		css = cgroup_e_css(cgroup_parent(css->cgroup), ss);
 
-	css = init_css_set.subsys[ss->id];
-	css_get(css);
-out_unlock:
 	rcu_read_unlock();
 	return css;
 }
@@ -2131,12 +2115,17 @@ void init_cgroup_root(struct cgroup_fs_context *ctx)
 {
 	struct cgroup_root *root = ctx->root;
 	struct cgroup *cgrp = &root->cgrp;
+	struct cgroup_subsys *ss;
+	int ssid;
 
 	INIT_LIST_HEAD_RCU(&root->root_list);
 	atomic_set(&root->nr_cgrps, 1);
 	cgrp->root = root;
 	init_cgroup_housekeeping(cgrp);
 
+	for_each_subsys(ss, ssid)
+		RCU_INIT_POINTER(cgrp->e_css[ssid], init_css_set.subsys[ssid]);
+
 	/* DYNMODS must be modified through cgroup_favor_dynmods() */
 	root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS;
 	if (ctx->release_agent)
@@ -5856,6 +5845,22 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	BUG_ON(cgroup_css(cgrp, ss));
 }
 
+static void cgroup_update_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	struct cgroup_subsys_state *d_css;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	css_for_each_descendant_pre(d_css, &cgrp->self) {
+		struct cgroup *dsct = d_css->cgroup;
+		struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
+
+		if (!css)
+			css = cgroup_e_css(cgroup_parent(dsct), ss);
+		rcu_assign_pointer(dsct->e_css[ss->id], css);
+	}
+}
+
 /* invoke ->css_online() on a new CSS and mark it online if successful */
 static int online_css(struct cgroup_subsys_state *css)
 {
@@ -5869,6 +5874,7 @@ static int online_css(struct cgroup_subsys_state *css)
 	if (!ret) {
 		css->flags |= CSS_ONLINE;
 		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
+		cgroup_update_e_css(css->cgroup, ss);
 
 		atomic_inc(&css->online_cnt);
 		if (css->parent) {
@@ -5895,6 +5901,7 @@ static void offline_css(struct cgroup_subsys_state *css)
 
 	css->flags &= ~CSS_ONLINE;
 	RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);
+	cgroup_update_e_css(css->cgroup, ss);
 
 	wake_up_all(&css->cgroup->offline_waitq);
 }
@@ -5966,6 +5973,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 {
 	struct cgroup_root *root = parent->root;
 	struct cgroup *cgrp, *tcgrp;
+	struct cgroup_subsys *ss;
 	struct kernfs_node *kn;
 	int i, level = parent->level + 1;
 	int ret;
@@ -6010,6 +6018,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp))
 		cgrp->ancestors[tcgrp->level] = tcgrp;
 
+	for_each_subsys(ss, i)
+		RCU_INIT_POINTER(cgrp->e_css[i], cgroup_e_css(parent, ss));
+
 	/*
 	 * New cgroup inherits effective freeze counter, and
 	 * if the parent has to be frozen, the child has too.
-- 
2.53.0