cgroup: rstat: support cgroup1

Rstat currently only supports the default hierarchy in cgroup2.  In
order to replace memcg's private stats infrastructure - used in both
cgroup1 and cgroup2 - with rstat, the latter needs to support cgroup1.

The initialization and destruction callbacks for regular cgroups are
already in place.  Remove the cgroup_on_dfl() guards to handle cgroup1.

The initialization of the root cgroup is currently hardcoded to only
handle cgrp_dfl_root.cgrp.  Move those callbacks to cgroup_setup_root()
and cgroup_destroy_root() to handle the default root as well as the
various cgroup1 roots we may set up during mounting.

The linking of css to cgroups happens in code shared between cgroup1 and
cgroup2 as well.  Simply remove the cgroup_on_dfl() guard.

Linkage of the root css to the root cgroup is a bit trickier: per
default, the root css of a subsystem controller belongs to the default
hierarchy (i.e.  the cgroup2 root).  When a controller is mounted in its
cgroup1 version, the root css is stolen and moved to the cgroup1 root;
on unmount, the css moves back to the default hierarchy.  Annotate
rebind_subsystems() to move the root css linkage along between roots.

Link: https://lkml.kernel.org/r/20210209163304.77088-5-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 21 insertions, 15 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 9153b20e5cc6..e049edd66776 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1339,6 +1339,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 
 	mutex_unlock(&cgroup_mutex);
 
+	cgroup_rstat_exit(cgrp);
 	kernfs_destroy_root(root->kf_root);
 	cgroup_free_root(root);
 }
@@ -1751,6 +1752,12 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 				       &dcgrp->e_csets[ss->id]);
 		spin_unlock_irq(&css_set_lock);
 
+		if (ss->css_rstat_flush) {
+			list_del_rcu(&css->rstat_css_node);
+			list_add_rcu(&css->rstat_css_node,
+				     &dcgrp->rstat_css_list);
+		}
+
 		/* default hierarchy doesn't enable controllers by default */
 		dst_root->subsys_mask |= 1 << ssid;
 		if (dst_root == &cgrp_dfl_root) {
@@ -1971,10 +1978,14 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	if (ret)
 		goto destroy_root;
 
-	ret = rebind_subsystems(root, ss_mask);
+	ret = cgroup_rstat_init(root_cgrp);
 	if (ret)
 		goto destroy_root;
 
+	ret = rebind_subsystems(root, ss_mask);
+	if (ret)
+		goto exit_stats;
+
 	ret = cgroup_bpf_inherit(root_cgrp);
 	WARN_ON_ONCE(ret);
 
@@ -2006,6 +2017,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	ret = 0;
 	goto out;
 
+exit_stats:
+	cgroup_rstat_exit(root_cgrp);
 destroy_root:
 	kernfs_destroy_root(root->kf_root);
 	root->kf_root = NULL;
@@ -4934,8 +4947,7 @@ static void css_free_rwork_fn(struct work_struct *work)
 			cgroup_put(cgroup_parent(cgrp));
 			kernfs_put(cgrp->kn);
 			psi_cgroup_free(cgrp);
-			if (cgroup_on_dfl(cgrp))
-				cgroup_rstat_exit(cgrp);
+			cgroup_rstat_exit(cgrp);
 			kfree(cgrp);
 		} else {
 			/*
@@ -4976,8 +4988,7 @@ static void css_release_work_fn(struct work_struct *work)
 		/* cgroup release path */
 		TRACE_CGROUP_PATH(release, cgrp);
 
-		if (cgroup_on_dfl(cgrp))
-			cgroup_rstat_flush(cgrp);
+		cgroup_rstat_flush(cgrp);
 
 		spin_lock_irq(&css_set_lock);
 		for (tcgrp = cgroup_parent(cgrp); tcgrp;
@@ -5034,7 +5045,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 		css_get(css->parent);
 	}
 
-	if (cgroup_on_dfl(cgrp) && ss->css_rstat_flush)
+	if (ss->css_rstat_flush)
 		list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list);
 
 	BUG_ON(cgroup_css(cgrp, ss));
@@ -5159,11 +5170,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	if (ret)
 		goto out_free_cgrp;
 
-	if (cgroup_on_dfl(parent)) {
-		ret = cgroup_rstat_init(cgrp);
-		if (ret)
-			goto out_cancel_ref;
-	}
+	ret = cgroup_rstat_init(cgrp);
+	if (ret)
+		goto out_cancel_ref;
 
 	/* create the directory */
 	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
@@ -5250,8 +5259,7 @@ out_psi_free:
 out_kernfs_remove:
 	kernfs_remove(cgrp->kn);
 out_stat_exit:
-	if (cgroup_on_dfl(parent))
-		cgroup_rstat_exit(cgrp);
+	cgroup_rstat_exit(cgrp);
 out_cancel_ref:
 	percpu_ref_exit(&cgrp->self.refcnt);
 out_free_cgrp:
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index d51175cedfca..faa767a870ba 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -285,8 +285,6 @@ void __init cgroup_rstat_boot(void)
 
 	for_each_possible_cpu(cpu)
 		raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu));
-
-	BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp));
 }
 
 /*