/* Ditto for the can_fork callback. */
static unsigned long have_canfork_callback __read_mostly;
+static struct file_system_type cgroup2_fs_type;
static struct cftype cgroup_dfl_base_files[];
static struct cftype cgroup_legacy_base_files[];
*/
static bool cgroup_ssid_enabled(int ssid)
{
+ if (CGROUP_SUBSYS_COUNT == 0)
+ return false;
+
return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
}
all_ss = true;
continue;
}
- if (!strcmp(token, "__DEVEL__sane_behavior")) {
- opts->flags |= CGRP_ROOT_SANE_BEHAVIOR;
- continue;
- }
if (!strcmp(token, "noprefix")) {
opts->flags |= CGRP_ROOT_NOPREFIX;
continue;
return -ENOENT;
}
- if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
- pr_warn("sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
- if (nr_opts != 1) {
- pr_err("sane_behavior: no other mount options allowed\n");
- return -EINVAL;
- }
- return 0;
- }
-
/*
* If the 'all' option was specified select all the subsystems,
* otherwise if 'none', 'name=' and a subsystem name options were
int flags, const char *unused_dev_name,
void *data)
{
+ bool is_v2 = fs_type == &cgroup2_fs_type;
struct super_block *pinned_sb = NULL;
struct cgroup_subsys *ss;
struct cgroup_root *root;
if (!use_task_css_set_links)
cgroup_enable_task_cg_lists();
+ if (is_v2) {
+ if (data) {
+ pr_err("cgroup2: unknown option \"%s\"\n", (char *)data);
+ return ERR_PTR(-EINVAL);
+ }
+ cgrp_dfl_root_visible = true;
+ root = &cgrp_dfl_root;
+ cgroup_get(&root->cgrp);
+ goto out_mount;
+ }
+
mutex_lock(&cgroup_mutex);
/* First find the desired set of subsystems */
if (ret)
goto out_unlock;
- /* look for a matching existing root */
- if (opts.flags & CGRP_ROOT_SANE_BEHAVIOR) {
- cgrp_dfl_root_visible = true;
- root = &cgrp_dfl_root;
- cgroup_get(&root->cgrp);
- ret = 0;
- goto out_unlock;
- }
-
/*
* Destruction of cgroup root is asynchronous, so subsystems may
* still be dying after the previous unmount. Let's drain the
if (ret)
return ERR_PTR(ret);
-
+out_mount:
dentry = kernfs_mount(fs_type, flags, root->kf_root,
- CGROUP_SUPER_MAGIC, &new_sb);
+ is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC,
+ &new_sb);
if (IS_ERR(dentry) || !new_sb)
cgroup_put(&root->cgrp);
.kill_sb = cgroup_kill_sb,
};
+static struct file_system_type cgroup2_fs_type = {
+ .name = "cgroup2",
+ .mount = cgroup_mount,
+ .kill_sb = cgroup_kill_sb,
+};
+
/**
* task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
* @task: target task
return ret;
}
-int subsys_cgroup_allow_attach(struct cgroup_taskset *tset)
-{
- const struct cred *cred = current_cred(), *tcred;
- struct task_struct *task;
- struct cgroup_subsys_state *css;
-
- if (capable(CAP_SYS_NICE))
- return 0;
-
- cgroup_taskset_for_each(task, css, tset) {
- tcred = __task_cred(task);
-
- if (current != task && !uid_eq(cred->euid, tcred->uid) &&
- !uid_eq(cred->euid, tcred->suid))
- return -EACCES;
- }
-
- return 0;
-}
-
-static int cgroup_allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
-{
- struct cgroup_subsys_state *css;
- int i;
- int ret;
-
- for_each_css(css, i, cgrp) {
- if (css->ss->allow_attach) {
- ret = css->ss->allow_attach(tset);
- if (ret)
- return ret;
- } else {
- return -EACCES;
- }
- }
-
- return 0;
-}
-
static int cgroup_procs_write_permission(struct task_struct *task,
struct cgroup *dst_cgrp,
struct kernfs_open_file *of)
*/
if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
!uid_eq(cred->euid, tcred->uid) &&
- !uid_eq(cred->euid, tcred->suid)) {
- /*
- * if the default permission check fails, give each
- * cgroup a chance to extend the permission check
- */
- struct cgroup_taskset tset = {
- .src_csets = LIST_HEAD_INIT(tset.src_csets),
- .dst_csets = LIST_HEAD_INIT(tset.dst_csets),
- .csets = &tset.src_csets,
- };
- struct css_set *cset;
- cset = task_css_set(task);
- list_add(&cset->mg_node, &tset.src_csets);
- ret = cgroup_allow_attach(dst_cgrp, &tset);
- list_del(&tset.src_csets);
- if (ret)
- ret = -EACCES;
- }
+ !uid_eq(cred->euid, tcred->suid) &&
+ !ns_capable(tcred->user_ns, CAP_SYS_RESOURCE))
+ ret = -EACCES;
if (!ret && cgroup_on_dfl(dst_cgrp)) {
struct super_block *sb = of->file->f_path.dentry->d_sb;
memset(css, 0, sizeof(*css));
css->cgroup = cgrp;
css->ss = ss;
+ css->id = -1;
INIT_LIST_HEAD(&css->sibling);
INIT_LIST_HEAD(&css->children);
css->serial_nr = css_serial_nr_next++;
BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
+ /*
+ * The latency of the synchronize_sched() is too high for cgroups,
+ * avoid it at the cost of forcing all readers into the slow path.
+ */
+ rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
+
mutex_lock(&cgroup_mutex);
/* Add init_css_set to the hash table */
WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup"));
WARN_ON(register_filesystem(&cgroup_fs_type));
+ WARN_ON(register_filesystem(&cgroup2_fs_type));
WARN_ON(!proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations));
return 0;