pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
}
}
- }
-
- kfree(opts.release_agent);
- kfree(opts.name);
- return dget(sb->s_root);
-
- rm_base_files:
- free_cgrp_cset_links(&tmp_links);
- cgroup_addrm_files(&root->top_cgroup, cgroup_base_files, false);
- revert_creds(cred);
- unlock_drop:
- cgroup_exit_root_id(root);
- mutex_unlock(&cgroup_root_mutex);
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
- drop_new_super:
- deactivate_locked_super(sb);
- out_err:
- kfree(opts.release_agent);
- kfree(opts.name);
- return ERR_PTR(ret);
- }
- static void cgroup_kill_sb(struct super_block *sb)
- {
- struct cgroupfs_root *root = sb->s_fs_info;
- struct cgroup *cgrp = &root->top_cgroup;
- struct cgrp_cset_link *link, *tmp_link;
- int ret;
+ /*
+ * A root's lifetime is governed by its root cgroup. Zero
+ * ref indicate that the root is being destroyed. Wait for
+ * destruction to complete so that the subsystems are free.
+ * We can use wait_queue for the wait but this path is
+ * super cold. Let's just sleep for a bit and retry.
+ */
+ if (!atomic_inc_not_zero(&root->cgrp.refcnt)) {
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
+ kfree(opts.release_agent);
+ kfree(opts.name);
+ msleep(10);
+ goto retry;
+ }
- BUG_ON(!root);
-
- BUG_ON(root->number_of_cgroups != 1);
- BUG_ON(!list_empty(&cgrp->children));
-
- mutex_lock(&cgrp->dentry->d_inode->i_mutex);
- mutex_lock(&cgroup_mutex);
- mutex_lock(&cgroup_root_mutex);
-
- /* Rebind all subsystems back to the default hierarchy */
- if (root->flags & CGRP_ROOT_SUBSYS_BOUND) {
- ret = rebind_subsystems(root, 0, root->subsys_mask);
- /* Shouldn't be able to fail ... */
- BUG_ON(ret);
- }
+ ret = 0;
+ goto out_unlock;
+ }
/*
- * Release all the links from cset_links to this hierarchy's
- * root cgroup
+ * No such thing, create a new one. name= matching without subsys
+ * specification is allowed for already existing hierarchies but we
+ * can't create new one without subsys specification.
*/
- write_lock(&css_set_lock);
-
- list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
- list_del(&link->cset_link);
- list_del(&link->cgrp_link);
- kfree(link);
+ if (!opts.subsys_mask && !opts.none) {
+ ret = -EINVAL;
+ goto out_unlock;
}
- write_unlock(&css_set_lock);
- if (!list_empty(&root->root_list)) {
- list_del(&root->root_list);
- cgroup_root_count--;
+ root = kzalloc(sizeof(*root), GFP_KERNEL);
+ if (!root) {
+ ret = -ENOMEM;
+ goto out_unlock;
}
- cgroup_exit_root_id(root);
+ init_cgroup_root(root, &opts);
+
+ ret = cgroup_setup_root(root, opts.subsys_mask);
+ if (ret)
+ cgroup_free_root(root);
- mutex_unlock(&cgroup_root_mutex);
+ out_unlock:
mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
- simple_xattrs_free(&cgrp->xattrs);
+ kfree(opts.release_agent);
+ kfree(opts.name);
- kill_litter_super(sb);
- cgroup_free_root(root);
+ if (ret)
+ return ERR_PTR(ret);
+
- dentry = kernfs_mount(fs_type, flags, root->kf_root);
++ dentry = kernfs_mount(fs_type, flags, root->kf_root, NULL);
+ if (IS_ERR(dentry))
+ cgroup_put(&root->cgrp);
+ return dentry;
+ }
+
+ static void cgroup_kill_sb(struct super_block *sb)
+ {
+ struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
+ struct cgroup_root *root = cgroup_root_from_kf(kf_root);
+
+ cgroup_put(&root->cgrp);
+ kernfs_kill_sb(sb);
}
static struct file_system_type cgroup_fs_type = {
init_css(css, ss, cgrp);
- err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id);
+ err = cgroup_populate_dir(cgrp, 1 << ss->id);
if (err)
- goto err_free;
+ goto err_free_percpu_ref;
err = online_css(css);
if (err)
- goto err_free;
+ goto err_clear_dir;
- dget(cgrp->dentry);
+ cgroup_get(cgrp);
css_get(css->parent);
+ cgrp->subsys_mask |= 1 << ss->id;
+
if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
parent->parent) {
pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
return 0;
-err_free:
+err_clear_dir:
- cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id);
++ cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
+err_free_percpu_ref:
percpu_ref_cancel_init(&css->refcnt);
+err_free_css:
ss->css_free(css);
return err;
}
*/
void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
{
- /*
- * protects memcg_name and makes sure that parallel ooms do not
- * interleave
- */
+ /* oom_info_lock ensures that parallel ooms do not interleave */
- static DEFINE_SPINLOCK(oom_info_lock);
+ static DEFINE_MUTEX(oom_info_lock);
- struct cgroup *task_cgrp;
- struct cgroup *mem_cgrp;
- static char memcg_name[PATH_MAX];
- int ret;
struct mem_cgroup *iter;
unsigned int i;
if (!p)
return;
- spin_lock(&oom_info_lock);
+ mutex_lock(&oom_info_lock);
rcu_read_lock();
- mem_cgrp = memcg->css.cgroup;
- task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);
-
- ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
- if (ret < 0) {
- /*
- * Unfortunately, we are unable to convert to a useful name
- * But we'll still print out the usage information
- */
- rcu_read_unlock();
- goto done;
- }
- rcu_read_unlock();
-
- pr_info("Task in %s killed", memcg_name);
+ pr_info("Task in ");
+ pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
+ pr_info(" killed as a result of limit of ");
+ pr_cont_cgroup_path(memcg->css.cgroup);
+ pr_info("\n");
- rcu_read_lock();
- ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
- if (ret < 0) {
- rcu_read_unlock();
- goto done;
- }
rcu_read_unlock();
- /*
- * Continues from above, so we don't need an KERN_ level
- */
- pr_cont(" as a result of limit of %s\n", memcg_name);
- done:
-
pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n",
res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
projects / linux.git / commitdiff