Merge tag 'cgroup-for-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - cgroup rstat shared the tracking tree across all controllers with the
   rationale being that a cgroup which is using one resource is likely
   to be using other resources at the same time (ie. if something is
   allocating memory, it's probably consuming CPU cycles).

   However, this turned out to not scale very well especially with memcg
   using rstat for internal operations which made memcg stat read and
   flush patterns substantially different from other controllers. JP
   Kobryn split the rstat tree per controller.

 - cgroup BPF support was hooking into cgroup init/exit paths directly.

   Convert them to use a notifier chain instead so that other usages can
   be added easily. The two of the patches which implement this are
   mislabeled as belonging to sched_ext instead of cgroup. Sorry.

 - Relatively minor cpuset updates

 - Documentation updates

* tag 'cgroup-for-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (23 commits)
  sched_ext: Convert cgroup BPF support to use cgroup_lifetime_notifier
  sched_ext: Introduce cgroup_lifetime_notifier
  cgroup: Minor reorganization of cgroup_create()
  cgroup, docs: cpu controller's interaction with various scheduling policies
  cgroup, docs: convert space indentation to tab indentation
  cgroup: avoid per-cpu allocation of size zero rstat cpu locks
  cgroup, docs: be specific about bandwidth control of rt processes
  cgroup: document the rstat per-cpu initialization
  cgroup: helper for checking rstat participation of css
  cgroup: use subsystem-specific rstat locks to avoid contention
  cgroup: use separate rstat trees for each subsystem
  cgroup: compare css to cgroup::self in helper for distingushing css
  cgroup: warn on rstat usage by early init subsystems
  cgroup/cpuset: drop useless cpumask_empty() in compute_effective_exclusive_cpumask()
  cgroup/rstat: Improve cgroup_rstat_push_children() documentation
  cgroup: fix goto ordering in cgroup_init()
  cgroup: fix pointer check in css_rstat_init()
  cgroup/cpuset: Add warnings to catch inconsistency in exclusive CPUs
  cgroup/cpuset: Fix obsolete comment in cpuset_css_offline()
  cgroup/cpuset: Always use cpu_active_mask
  ...

1 files changed, 36 insertions, 2 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 84f58f3d028a..cad0194552fb 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -41,6 +41,19 @@ static int __init cgroup_bpf_wq_init(void)
 }
 core_initcall(cgroup_bpf_wq_init);
 
+static int cgroup_bpf_lifetime_notify(struct notifier_block *nb,
+				      unsigned long action, void *data);
+
+static struct notifier_block cgroup_bpf_lifetime_nb = {
+	.notifier_call = cgroup_bpf_lifetime_notify,
+};
+
+void __init cgroup_bpf_lifetime_notifier_init(void)
+{
+	BUG_ON(blocking_notifier_chain_register(&cgroup_lifetime_notifier,
+						&cgroup_bpf_lifetime_nb));
+}
+
 /* __always_inline is necessary to prevent indirect call through run_prog
  * function pointer.
  */
@@ -206,7 +219,7 @@ bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id)
 }
 #endif /* CONFIG_BPF_LSM */
 
-void cgroup_bpf_offline(struct cgroup *cgrp)
+static void cgroup_bpf_offline(struct cgroup *cgrp)
 {
 	cgroup_get(cgrp);
 	percpu_ref_kill(&cgrp->bpf.refcnt);
@@ -491,7 +504,7 @@ static void activate_effective_progs(struct cgroup *cgrp,
  * cgroup_bpf_inherit() - inherit effective programs from parent
  * @cgrp: the cgroup to modify
  */
-int cgroup_bpf_inherit(struct cgroup *cgrp)
+static int cgroup_bpf_inherit(struct cgroup *cgrp)
 {
 /* has to use marco instead of const int, since compiler thinks
  * that array below is variable length
@@ -534,6 +547,27 @@ cleanup:
 	return -ENOMEM;
 }
 
+static int cgroup_bpf_lifetime_notify(struct notifier_block *nb,
+				      unsigned long action, void *data)
+{
+	struct cgroup *cgrp = data;
+	int ret = 0;
+
+	if (cgrp->root != &cgrp_dfl_root)
+		return NOTIFY_OK;
+
+	switch (action) {
+	case CGROUP_LIFETIME_ONLINE:
+		ret = cgroup_bpf_inherit(cgrp);
+		break;
+	case CGROUP_LIFETIME_OFFLINE:
+		cgroup_bpf_offline(cgrp);
+		break;
+	}
+
+	return notifier_from_errno(ret);
+}
+
 static int update_effective_progs(struct cgroup *cgrp,
 				  enum cgroup_bpf_attach_type atype)
 {