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
  ...

2 files changed, 17 insertions, 10 deletions

diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c
index 38f78d9345de..69f81cb555ca 100644
--- a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c
+++ b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c
@@ -30,22 +30,27 @@ int BPF_PROG(test_percpu2, struct bpf_testmod_btf_type_tag_2 *arg)
 
 /* trace_cgroup_mkdir(struct cgroup *cgrp, const char *path)
  *
- * struct cgroup_rstat_cpu {
+ * struct css_rstat_cpu {
  *   ...
- *   struct cgroup *updated_children;
+ *   struct cgroup_subsys_state *updated_children;
  *   ...
  * };
  *
- * struct cgroup {
+ * struct cgroup_subsys_state {
+ *   ...
+ *   struct css_rstat_cpu __percpu *rstat_cpu;
  *   ...
- *   struct cgroup_rstat_cpu __percpu *rstat_cpu;
+ * };
+ *
+ * struct cgroup {
+ *   struct cgroup_subsys_state self;
  *   ...
  * };
  */
 SEC("tp_btf/cgroup_mkdir")
 int BPF_PROG(test_percpu_load, struct cgroup *cgrp, const char *path)
 {
-	g = (__u64)cgrp->rstat_cpu->updated_children;
+	g = (__u64)cgrp->self.rstat_cpu->updated_children;
 	return 0;
 }
 
@@ -56,7 +61,8 @@ int BPF_PROG(test_percpu_helper, struct cgroup *cgrp, const char *path)
 	__u32 cpu;
 
 	cpu = bpf_get_smp_processor_id();
-	rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr(cgrp->rstat_cpu, cpu);
+	rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr(
+			cgrp->self.rstat_cpu, cpu);
 	if (rstat) {
 		/* READ_ONCE */
 		*(volatile int *)rstat;
diff --git a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
index c74362854948..ff189a736ad8 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
@@ -37,8 +37,9 @@ struct {
 	__type(value, struct attach_counter);
 } attach_counters SEC(".maps");
 
-extern void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) __ksym;
-extern void cgroup_rstat_flush(struct cgroup *cgrp) __ksym;
+extern void css_rstat_updated(
+		struct cgroup_subsys_state *css, int cpu) __ksym;
+extern void css_rstat_flush(struct cgroup_subsys_state *css) __ksym;
 
 static uint64_t cgroup_id(struct cgroup *cgrp)
 {
@@ -75,7 +76,7 @@ int BPF_PROG(counter, struct cgroup *dst_cgrp, struct task_struct *leader,
 	else if (create_percpu_attach_counter(cg_id, 1))
 		return 0;
 
-	cgroup_rstat_updated(dst_cgrp, bpf_get_smp_processor_id());
+	css_rstat_updated(&dst_cgrp->self, bpf_get_smp_processor_id());
 	return 0;
 }
 
@@ -141,7 +142,7 @@ int BPF_PROG(dumper, struct bpf_iter_meta *meta, struct cgroup *cgrp)
 		return 1;
 
 	/* Flush the stats to make sure we get the most updated numbers */
-	cgroup_rstat_flush(cgrp);
+	css_rstat_flush(&cgrp->self);
 
 	total_counter = bpf_map_lookup_elem(&attach_counters, &cg_id);
 	if (!total_counter) {