summaryrefslogtreecommitdiff
path: root/kernel/cgroup/cgroup.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/cgroup/cgroup.c')
-rw-r--r--kernel/cgroup/cgroup.c195
1 files changed, 186 insertions, 9 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 44857278eb8a..0b1ffe147f24 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -142,12 +142,14 @@ static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
};
#undef SUBSYS
+static DEFINE_PER_CPU(struct cgroup_cpu_stat, cgrp_dfl_root_cpu_stat);
+
/*
* The default hierarchy, reserved for the subsystems that are otherwise
* unattached - it never has more than a single cgroup, and all tasks are
* part of that cgroup.
*/
-struct cgroup_root cgrp_dfl_root;
+struct cgroup_root cgrp_dfl_root = { .cgrp.cpu_stat = &cgrp_dfl_root_cpu_stat };
EXPORT_SYMBOL_GPL(cgrp_dfl_root);
/*
@@ -462,6 +464,28 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
}
/**
+ * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest
+ *
+ * Find and get @cgrp's css assocaited with @ss. If the css doesn't exist
+ * or is offline, %NULL is returned.
+ */
+static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
+ struct cgroup_subsys *ss)
+{
+ struct cgroup_subsys_state *css;
+
+ rcu_read_lock();
+ css = cgroup_css(cgrp, ss);
+ if (!css || !css_tryget_online(css))
+ css = NULL;
+ rcu_read_unlock();
+
+ return css;
+}
+
+/**
* cgroup_e_css - obtain a cgroup's effective css for the specified subsystem
* @cgrp: the cgroup of interest
* @ss: the subsystem of interest (%NULL returns @cgrp->self)
@@ -647,6 +671,14 @@ struct css_set init_css_set = {
.cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
.mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node),
.mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
+
+ /*
+ * The following field is re-initialized when this cset gets linked
+ * in cgroup_init(). However, let's initialize the field
+ * statically too so that the default cgroup can be accessed safely
+ * early during boot.
+ */
+ .dfl_cgrp = &cgrp_dfl_root.cgrp,
};
static int css_set_count = 1; /* 1 for init_css_set */
@@ -1896,6 +1928,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
if (ret)
goto destroy_root;
+ ret = cgroup_bpf_inherit(root_cgrp);
+ WARN_ON_ONCE(ret);
+
trace_cgroup_setup_root(root);
/*
@@ -3312,6 +3347,37 @@ static int cgroup_stat_show(struct seq_file *seq, void *v)
return 0;
}
+static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq,
+ struct cgroup *cgrp, int ssid)
+{
+ struct cgroup_subsys *ss = cgroup_subsys[ssid];
+ struct cgroup_subsys_state *css;
+ int ret;
+
+ if (!ss->css_extra_stat_show)
+ return 0;
+
+ css = cgroup_tryget_css(cgrp, ss);
+ if (!css)
+ return 0;
+
+ ret = ss->css_extra_stat_show(seq, css);
+ css_put(css);
+ return ret;
+}
+
+static int cpu_stat_show(struct seq_file *seq, void *v)
+{
+ struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup;
+ int ret = 0;
+
+ cgroup_stat_show_cputime(seq);
+#ifdef CONFIG_CGROUP_SCHED
+ ret = cgroup_extra_stat_show(seq, cgrp, cpu_cgrp_id);
+#endif
+ return ret;
+}
+
static int cgroup_file_open(struct kernfs_open_file *of)
{
struct cftype *cft = of->kn->priv;
@@ -4419,6 +4485,11 @@ static struct cftype cgroup_base_files[] = {
.name = "cgroup.stat",
.seq_show = cgroup_stat_show,
},
+ {
+ .name = "cpu.stat",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_stat_show,
+ },
{ } /* terminate */
};
@@ -4479,6 +4550,8 @@ static void css_free_work_fn(struct work_struct *work)
*/
cgroup_put(cgroup_parent(cgrp));
kernfs_put(cgrp->kn);
+ if (cgroup_on_dfl(cgrp))
+ cgroup_stat_exit(cgrp);
kfree(cgrp);
} else {
/*
@@ -4523,6 +4596,9 @@ static void css_release_work_fn(struct work_struct *work)
/* cgroup release path */
trace_cgroup_release(cgrp);
+ if (cgroup_on_dfl(cgrp))
+ cgroup_stat_flush(cgrp);
+
for (tcgrp = cgroup_parent(cgrp); tcgrp;
tcgrp = cgroup_parent(tcgrp))
tcgrp->nr_dying_descendants--;
@@ -4706,6 +4782,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
if (ret)
goto out_free_cgrp;
+ if (cgroup_on_dfl(parent)) {
+ ret = cgroup_stat_init(cgrp);
+ if (ret)
+ goto out_cancel_ref;
+ }
+
/*
* Temporarily set the pointer to NULL, so idr_find() won't return
* a half-baked cgroup.
@@ -4713,7 +4795,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL);
if (cgrp->id < 0) {
ret = -ENOMEM;
- goto out_cancel_ref;
+ goto out_stat_exit;
}
init_cgroup_housekeeping(cgrp);
@@ -4721,6 +4803,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
cgrp->self.parent = &parent->self;
cgrp->root = root;
cgrp->level = level;
+ ret = cgroup_bpf_inherit(cgrp);
+ if (ret)
+ goto out_idr_free;
for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
@@ -4755,13 +4840,15 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
if (!cgroup_on_dfl(cgrp))
cgrp->subtree_control = cgroup_control(cgrp);
- if (parent)
- cgroup_bpf_inherit(cgrp, parent);
-
cgroup_propagate_control(cgrp);
return cgrp;
+out_idr_free:
+ cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
+out_stat_exit:
+ if (cgroup_on_dfl(parent))
+ cgroup_stat_exit(cgrp);
out_cancel_ref:
percpu_ref_exit(&cgrp->self.refcnt);
out_free_cgrp:
@@ -5156,6 +5243,8 @@ int __init cgroup_init(void)
BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
+ cgroup_stat_boot();
+
/*
* The latency of the synchronize_sched() is too high for cgroups,
* avoid it at the cost of forcing all readers into the slow path.
@@ -5744,15 +5833,103 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
#endif /* CONFIG_SOCK_CGROUP_DATA */
#ifdef CONFIG_CGROUP_BPF
-int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
- enum bpf_attach_type type, bool overridable)
+int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags)
{
- struct cgroup *parent = cgroup_parent(cgrp);
int ret;
mutex_lock(&cgroup_mutex);
- ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
+ ret = __cgroup_bpf_attach(cgrp, prog, type, flags);
+ mutex_unlock(&cgroup_mutex);
+ return ret;
+}
+int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags)
+{
+ int ret;
+
+ mutex_lock(&cgroup_mutex);
+ ret = __cgroup_bpf_detach(cgrp, prog, type, flags);
+ mutex_unlock(&cgroup_mutex);
+ return ret;
+}
+int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ int ret;
+
+ mutex_lock(&cgroup_mutex);
+ ret = __cgroup_bpf_query(cgrp, attr, uattr);
mutex_unlock(&cgroup_mutex);
return ret;
}
#endif /* CONFIG_CGROUP_BPF */
+
+#ifdef CONFIG_SYSFS
+static ssize_t show_delegatable_files(struct cftype *files, char *buf,
+ ssize_t size, const char *prefix)
+{
+ struct cftype *cft;
+ ssize_t ret = 0;
+
+ for (cft = files; cft && cft->name[0] != '\0'; cft++) {
+ if (!(cft->flags & CFTYPE_NS_DELEGATABLE))
+ continue;
+
+ if (prefix)
+ ret += snprintf(buf + ret, size - ret, "%s.", prefix);
+
+ ret += snprintf(buf + ret, size - ret, "%s\n", cft->name);
+
+ if (unlikely(ret >= size)) {
+ WARN_ON(1);
+ break;
+ }
+ }
+
+ return ret;
+}
+
+static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ struct cgroup_subsys *ss;
+ int ssid;
+ ssize_t ret = 0;
+
+ ret = show_delegatable_files(cgroup_base_files, buf, PAGE_SIZE - ret,
+ NULL);
+
+ for_each_subsys(ss, ssid)
+ ret += show_delegatable_files(ss->dfl_cftypes, buf + ret,
+ PAGE_SIZE - ret,
+ cgroup_subsys_name[ssid]);
+
+ return ret;
+}
+static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate);
+
+static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "nsdelegate\n");
+}
+static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
+
+static struct attribute *cgroup_sysfs_attrs[] = {
+ &cgroup_delegate_attr.attr,
+ &cgroup_features_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group cgroup_sysfs_attr_group = {
+ .attrs = cgroup_sysfs_attrs,
+ .name = "cgroup",
+};
+
+static int __init cgroup_sysfs_init(void)
+{
+ return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group);
+}
+subsys_initcall(cgroup_sysfs_init);
+#endif /* CONFIG_SYSFS */