cgroup: Update comments about task exit path

We no longer take cgroup_mutex in cgroup_exit and the exiting tasks are
not moved to init_css_set, reflect that in several comments to prevent
confusion.

Signed-off-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index f6cba23290a133c09e1d98481609244bb72092a2..01fc24aeac71c28a8ec7c384cedecd029d21b437 100644 (file)
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -899,8 +899,7 @@ static void css_set_move_task(struct task_struct *task,
                /*
                 * We are synchronized through cgroup_threadgroup_rwsem
                 * against PF_EXITING setting such that we can't race
-                * against cgroup_exit() changing the css_set to
-                * init_css_set and dropping the old one.
+                * against cgroup_exit()/cgroup_free() dropping the css_set.
                 */
                WARN_ON_ONCE(task->flags & PF_EXITING);
 
@@ -1432,9 +1431,8 @@ struct cgroup *task_cgroup_from_root(struct task_struct *task,
                                     struct cgroup_root *root)
 {
        /*
-        * No need to lock the task - since we hold cgroup_mutex the
-        * task can't change groups, so the only thing that can happen
-        * is that it exits and its css is set back to init_css_set.
+        * No need to lock the task - since we hold css_set_lock the
+        * task can't change groups.
         */
        return cset_cgroup_from_root(task_css_set(task), root);
 }
@@ -6030,7 +6028,7 @@ void cgroup_post_fork(struct task_struct *child)
                struct css_set *cset;
 
                spin_lock_irq(&css_set_lock);
-               cset = task_css_set(current);
+               cset = task_css_set(current); /* current is @child's parent */
                if (list_empty(&child->cg_list)) {
                        get_css_set(cset);
                        cset->nr_tasks++;
@@ -6073,20 +6071,8 @@ void cgroup_post_fork(struct task_struct *child)
  * cgroup_exit - detach cgroup from exiting task
  * @tsk: pointer to task_struct of exiting process
  *
- * Description: Detach cgroup from @tsk and release it.
- *
- * Note that cgroups marked notify_on_release force every task in
- * them to take the global cgroup_mutex mutex when exiting.
- * This could impact scaling on very large systems.  Be reluctant to
- * use notify_on_release cgroups where very high task exit scaling
- * is required on large systems.
+ * Description: Detach cgroup from @tsk.
  *
- * We set the exiting tasks cgroup to the root cgroup (top_cgroup).  We
- * call cgroup_exit() while the task is still competent to handle
- * notify_on_release(), then leave the task attached to the root cgroup in
- * each hierarchy for the remainder of its exit.  No need to bother with
- * init_css_set refcnting.  init_css_set never goes away and we can't race
- * with migration path - PF_EXITING is visible to migration path.
  */
 void cgroup_exit(struct task_struct *tsk)
 {
@@ -6096,7 +6082,8 @@ void cgroup_exit(struct task_struct *tsk)
 
        /*
         * Unlink from @tsk from its css_set.  As migration path can't race
-        * with us, we can check css_set and cg_list without synchronization.
+        * with us (thanks to cgroup_threadgroup_rwsem), we can check css_set
+        * and cg_list without synchronization.
         */
        cset = task_css_set(tsk);
 
@@ -6112,6 +6099,8 @@ void cgroup_exit(struct task_struct *tsk)
 
                spin_unlock_irq(&css_set_lock);
        } else {
+               /* Take reference to avoid freeing init_css_set in cgroup_free,
+                * see cgroup_fork(). */
                get_css_set(cset);
        }