/* the list of cgroups eligible for automatic release. Protected by
* release_list_lock */
static LIST_HEAD(release_list);
-static DEFINE_SPINLOCK(release_list_lock);
+static DEFINE_RAW_SPINLOCK(release_list_lock);
static void cgroup_release_agent(struct work_struct *work);
static DECLARE_WORK(release_agent_work, cgroup_release_agent);
static void check_for_release(struct cgroup *cgrp);
struct cgroup *cgrp = link->cgrp;
list_del(&link->cg_link_list);
list_del(&link->cgrp_link_list);
+
+ /*
+ * We may not be holding cgroup_mutex, and if cgrp->count is
+ * dropped to 0 the cgroup can be destroyed at any time, hence
+ * rcu_read_lock is used to keep it alive.
+ */
+ rcu_read_lock();
if (atomic_dec_and_test(&cgrp->count) &&
notify_on_release(cgrp)) {
if (taskexit)
set_bit(CGRP_RELEASABLE, &cgrp->flags);
check_for_release(cgrp);
}
+ rcu_read_unlock();
kfree(link);
}
/*
* If the 'all' option was specified select all the subsystems,
- * otherwise 'all, 'none' and a subsystem name options were not
- * specified, let's default to 'all'
+ * otherwise if 'none', 'name=' and a subsystem name options
+ * were not specified, let's default to 'all'
*/
- if (all_ss || (!all_ss && !one_ss && !opts->none)) {
+ if (all_ss || (!one_ss && !opts->none && !opts->name)) {
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
if (ss == NULL)
* trading it for newcg is protected by cgroup_mutex, we're safe to drop
* it here; it will be freed under RCU.
*/
- put_css_set(oldcg);
-
set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
+ put_css_set(oldcg);
return 0;
}
if (!group)
return -ENOMEM;
/* pre-allocate to guarantee space while iterating in rcu read-side. */
- retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL);
+ retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
if (retval)
goto out_free_group_list;
/* prevent changes to the threadgroup list while we take a snapshot. */
- rcu_read_lock();
+ read_lock(&tasklist_lock);
if (!thread_group_leader(leader)) {
/*
* a race with de_thread from another thread's exec() may strip
* throw this task away and try again (from cgroup_procs_write);
* this is "double-double-toil-and-trouble-check locking".
*/
- rcu_read_unlock();
+ read_unlock(&tasklist_lock);
retval = -EAGAIN;
goto out_free_group_list;
}
} while_each_thread(leader, tsk);
/* remember the number of threads in the array for later. */
group_size = i;
- rcu_read_unlock();
+ read_unlock(&tasklist_lock);
/*
* step 1: check that we can legitimately attach to the cgroup.
continue;
/* get old css_set pointer */
task_lock(tsk);
- if (tsk->flags & PF_EXITING) {
- /* ignore this task if it's going away */
- task_unlock(tsk);
- continue;
- }
oldcg = tsk->cgroups;
get_css_set(oldcg);
task_unlock(tsk);
oldcgrp = task_cgroup_from_root(tsk, root);
if (cgrp == oldcgrp)
continue;
- /* attach each task to each subsystem */
- for_each_subsys(root, ss) {
- if (ss->attach_task)
- ss->attach_task(cgrp, tsk);
- }
/* if the thread is PF_EXITING, it can just get skipped. */
retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, true);
- BUG_ON(retval != 0 && retval != -ESRCH);
+ if (retval == 0) {
+ /* attach each task to each subsystem */
+ for_each_subsys(root, ss) {
+ if (ss->attach_task)
+ ss->attach_task(cgrp, tsk);
+ }
+ } else {
+ BUG_ON(retval != -ESRCH);
+ }
}
/* nothing is sensitive to fork() after this point. */
dentry->d_fsdata = cgrp;
inc_nlink(parent->d_inode);
rcu_assign_pointer(cgrp->dentry, dentry);
- dget(dentry);
}
- dput(dentry);
return error;
}
* We should check if the process is exiting, otherwise
* it will race with cgroup_exit() in that the list
* entry won't be deleted though the process has exited.
+ * Do it while holding siglock so that we don't end up
+ * racing against cgroup_exit().
*/
+ spin_lock_irq(&p->sighand->siglock);
if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
list_add(&p->cg_list, &p->cgroups->tasks);
+ spin_unlock_irq(&p->sighand->siglock);
+
task_unlock(p);
} while_each_thread(g, p);
write_unlock(&css_set_lock);
const char *buffer)
{
struct cgroup_event *event = NULL;
+ struct cgroup *cgrp_cfile;
unsigned int efd, cfd;
struct file *efile = NULL;
struct file *cfile = NULL;
goto fail;
}
+ /*
+ * The file to be monitored must be in the same cgroup as
+ * cgroup.event_control is.
+ */
+ cgrp_cfile = __d_cgrp(cfile->f_dentry->d_parent);
+ if (cgrp_cfile != cgrp) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
if (!event->cft->register_event || !event->cft->unregister_event) {
ret = -EINVAL;
goto fail;
{
struct cgroup *c_parent = dentry->d_parent->d_fsdata;
+ /* Do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable.
+ */
+ if (strchr(dentry->d_name.name, '\n'))
+ return -EINVAL;
+
/* the vfs holds inode->i_mutex already */
return cgroup_create(c_parent, dentry, mode | S_IFDIR);
}
finish_wait(&cgroup_rmdir_waitq, &wait);
clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
- spin_lock(&release_list_lock);
+ raw_spin_lock(&release_list_lock);
set_bit(CGRP_REMOVED, &cgrp->flags);
if (!list_empty(&cgrp->release_list))
list_del_init(&cgrp->release_list);
- spin_unlock(&release_list_lock);
+ raw_spin_unlock(&release_list_lock);
cgroup_lock_hierarchy(cgrp->root);
/* delete this cgroup from parent->children */
INIT_LIST_HEAD(&child->cg_list);
}
-/**
- * cgroup_fork_callbacks - run fork callbacks
- * @child: the new task
- *
- * Called on a new task very soon before adding it to the
- * tasklist. No need to take any locks since no-one can
- * be operating on this task.
- */
-void cgroup_fork_callbacks(struct task_struct *child)
-{
- if (need_forkexit_callback) {
- int i;
- /*
- * forkexit callbacks are only supported for builtin
- * subsystems, and the builtin section of the subsys array is
- * immutable, so we don't need to lock the subsys array here.
- */
- for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
- struct cgroup_subsys *ss = subsys[i];
- if (ss->fork)
- ss->fork(ss, child);
- }
- }
-}
-
/**
* cgroup_post_fork - called on a new task after adding it to the task list
* @child: the task in question
*
- * Adds the task to the list running through its css_set if necessary.
- * Has to be after the task is visible on the task list in case we race
- * with the first call to cgroup_iter_start() - to guarantee that the
- * new task ends up on its list.
+ * Adds the task to the list running through its css_set if necessary and
+ * call the subsystem fork() callbacks. Has to be after the task is
+ * visible on the task list in case we race with the first call to
+ * cgroup_iter_start() - to guarantee that the new task ends up on its
+ * list.
*/
void cgroup_post_fork(struct task_struct *child)
{
+ int i;
+
if (use_task_css_set_links) {
write_lock(&css_set_lock);
task_lock(child);
task_unlock(child);
write_unlock(&css_set_lock);
}
+
+ /*
+ * Call ss->fork(). This must happen after @child is linked on
+ * css_set; otherwise, @child might change state between ->fork()
+ * and addition to css_set.
+ */
+ if (need_forkexit_callback) {
+ for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss->fork)
+ ss->fork(ss, child);
+ }
+ }
}
+
/**
* cgroup_exit - detach cgroup from exiting task
* @tsk: pointer to task_struct of exiting process
* already queued for a userspace notification, queue
* it now */
int need_schedule_work = 0;
- spin_lock(&release_list_lock);
+ raw_spin_lock(&release_list_lock);
if (!cgroup_is_removed(cgrp) &&
list_empty(&cgrp->release_list)) {
list_add(&cgrp->release_list, &release_list);
need_schedule_work = 1;
}
- spin_unlock(&release_list_lock);
+ raw_spin_unlock(&release_list_lock);
if (need_schedule_work)
schedule_work(&release_agent_work);
}
{
BUG_ON(work != &release_agent_work);
mutex_lock(&cgroup_mutex);
- spin_lock(&release_list_lock);
+ raw_spin_lock(&release_list_lock);
while (!list_empty(&release_list)) {
char *argv[3], *envp[3];
int i;
struct cgroup,
release_list);
list_del_init(&cgrp->release_list);
- spin_unlock(&release_list_lock);
+ raw_spin_unlock(&release_list_lock);
pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!pathbuf)
goto continue_free;
continue_free:
kfree(pathbuf);
kfree(agentbuf);
- spin_lock(&release_list_lock);
+ raw_spin_lock(&release_list_lock);
}
- spin_unlock(&release_list_lock);
+ raw_spin_unlock(&release_list_lock);
mutex_unlock(&cgroup_mutex);
}
rcu_assign_pointer(id->css, NULL);
rcu_assign_pointer(css->id, NULL);
- spin_lock(&ss->id_lock);
+ write_lock(&ss->id_lock);
idr_remove(&ss->idr, id->id);
- spin_unlock(&ss->id_lock);
+ write_unlock(&ss->id_lock);
kfree_rcu(id, rcu_head);
}
EXPORT_SYMBOL_GPL(free_css_id);
error = -ENOMEM;
goto err_out;
}
- spin_lock(&ss->id_lock);
+ write_lock(&ss->id_lock);
/* Don't use 0. allocates an ID of 1-65535 */
error = idr_get_new_above(&ss->idr, newid, 1, &myid);
- spin_unlock(&ss->id_lock);
+ write_unlock(&ss->id_lock);
/* Returns error when there are no free spaces for new ID.*/
if (error) {
return newid;
remove_idr:
error = -ENOSPC;
- spin_lock(&ss->id_lock);
+ write_lock(&ss->id_lock);
idr_remove(&ss->idr, myid);
- spin_unlock(&ss->id_lock);
+ write_unlock(&ss->id_lock);
err_out:
kfree(newid);
return ERR_PTR(error);
{
struct css_id *newid;
- spin_lock_init(&ss->id_lock);
+ rwlock_init(&ss->id_lock);
idr_init(&ss->idr);
newid = get_new_cssid(ss, 0);
* scan next entry from bitmap(tree), tmpid is updated after
* idr_get_next().
*/
- spin_lock(&ss->id_lock);
+ read_lock(&ss->id_lock);
tmp = idr_get_next(&ss->idr, &tmpid);
- spin_unlock(&ss->id_lock);
+ read_unlock(&ss->id_lock);
if (!tmp)
break;