/**
* cgroup_trasnsfer_tasks - move tasks from one cgroup to another
* @to: cgroup to which the tasks will be moved
* @from: cgroup in which the tasks currently reside
*
* Locking rules between cgroup_post_fork() and the migration path
* guarantee that, if a task is forking while being migrated, the new child
* is guaranteed to be either visible in the source cgroup after the
* parent's migration is complete or put into the target cgroup. No task
* can slip out of migration through forking.
*/
int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
{
DEFINE_CGROUP_MGCTX(mgctx);
struct cgrp_cset_link *link;
struct css_task_iter it;
struct task_struct *task;
int ret;
if (cgroup_on_dfl(to))
return -EINVAL;
ret = cgroup_migrate_vet_dst(to);
if (ret)
return ret;
mutex_lock(&cgroup_mutex);
percpu_down_write(&cgroup_threadgroup_rwsem);
/* all tasks in @from are being moved, all csets are source */
spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &from->cset_links, cset_link)
cgroup_migrate_add_src(link->cset, to, &mgctx);
spin_unlock_irq(&css_set_lock);
ret = cgroup_migrate_prepare_dst(&mgctx);
if (ret)
goto out_err;
/*
* Migrate tasks one-by-one until @from is empty. This fails iff
* ->can_attach() fails.
*/
do {
css_task_iter_start(&from->self, 0, &it);
do {
task = css_task_iter_next(&it);
} while (task && (task->flags & PF_EXITING));
if (task)
get_task_struct(task);
css_task_iter_end(&it);
if (task) {
ret = cgroup_migrate(task, false, &mgctx);
if (!ret)
TRACE_CGROUP_PATH(transfer_tasks, to, task, false);
put_task_struct(task);
}
} while (task && !ret);
out_err:
cgroup_migrate_finish(&mgctx);
percpu_up_write(&cgroup_threadgroup_rwsem);
mutex_unlock(&cgroup_mutex);
return ret;
}
/*
* Load a cgroup's pidarray with either procs' tgids or tasks' pids
*/
static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
struct cgroup_pidlist **lp)
{
pid_t *array;
int length;
int pid, n = 0; /* used for populating the array */
struct css_task_iter it;
struct task_struct *tsk;
struct cgroup_pidlist *l;
lockdep_assert_held(&cgrp->pidlist_mutex);
/*
* If cgroup gets more users after we read count, we won't have
* enough space - tough. This race is indistinguishable to the
* caller from the case that the additional cgroup users didn't
* show up until sometime later on.
*/
length = cgroup_task_count(cgrp);
array = pidlist_allocate(length);
if (!array)
return -ENOMEM;
/* now, populate the array */
css_task_iter_start(&cgrp->self, 0, &it);
while ((tsk = css_task_iter_next(&it))) {
if (unlikely(n == length))
break;
/* get tgid or pid for procs or tasks file respectively */
if (type == CGROUP_FILE_PROCS)
pid = task_tgid_vnr(tsk);
else
pid = task_pid_vnr(tsk);
if (pid > 0) /* make sure to only use valid results */
array[n++] = pid;
}
css_task_iter_end(&it);
length = n;
/* now sort & (if procs) strip out duplicates */
sort(array, length, sizeof(pid_t), cmppid, NULL);
if (type == CGROUP_FILE_PROCS)
length = pidlist_uniq(array, length);
l = cgroup_pidlist_find_create(cgrp, type);
if (!l) {
pidlist_free(array);
return -ENOMEM;
}
/* store array, freeing old if necessary */
pidlist_free(l->list);
l->list = array;
l->length = length;
*lp = l;
return 0;
}
/**
* cgroupstats_build - build and fill cgroupstats
* @stats: cgroupstats to fill information into
* @dentry: A dentry entry belonging to the cgroup for which stats have
* been requested.
*
* Build and fill cgroupstats so that taskstats can export it to user
* space.
*/
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
struct cgroup *cgrp;
struct css_task_iter it;
struct task_struct *tsk;
/* it should be kernfs_node belonging to cgroupfs and is a directory */
if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
kernfs_type(kn) != KERNFS_DIR)
return -EINVAL;
mutex_lock(&cgroup_mutex);
/*
* We aren't being called from kernfs and there's no guarantee on
* @kn->priv's validity. For this and css_tryget_online_from_dir(),
* @kn->priv is RCU safe. Let's do the RCU dancing.
*/
rcu_read_lock();
cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv);
if (!cgrp || cgroup_is_dead(cgrp)) {
rcu_read_unlock();
mutex_unlock(&cgroup_mutex);
return -ENOENT;
}
rcu_read_unlock();
css_task_iter_start(&cgrp->self, 0, &it);
while ((tsk = css_task_iter_next(&it))) {
switch (tsk->state) {
case TASK_RUNNING:
stats->nr_running++;
break;
case TASK_INTERRUPTIBLE:
stats->nr_sleeping++;
break;
case TASK_UNINTERRUPTIBLE:
stats->nr_uninterruptible++;
break;
case TASK_STOPPED:
stats->nr_stopped++;
break;
default:
if (delayacct_is_task_waiting_on_io(tsk))
stats->nr_io_wait++;
break;
}
}
css_task_iter_end(&it);
mutex_unlock(&cgroup_mutex);
return 0;
}
static void update_classid(struct cgroup_subsys_state *css, void *v)
{
struct css_task_iter it;
struct task_struct *p;
css_task_iter_start(css, &it);
while ((p = css_task_iter_next(&it))) {
task_lock(p);
iterate_fd(p->files, 0, update_classid_sock, v);
task_unlock(p);
}
css_task_iter_end(&it);
}