cgroup: Include dying leaders with live threads in PROCS iterations

[mirror_ubuntu-bionic-kernel.git] / kernel / cgroup / cgroup.c

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index b6a6612116df461f99640040480c70418bcb144c..b46fcad6d564c559def4249f840a99f70f558c41 100644 (file)
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -667,6 +667,7 @@ struct css_set init_css_set = {
        .dom_cset               = &init_css_set,
        .tasks                  = LIST_HEAD_INIT(init_css_set.tasks),
        .mg_tasks               = LIST_HEAD_INIT(init_css_set.mg_tasks),
+       .dying_tasks            = LIST_HEAD_INIT(init_css_set.dying_tasks),
        .task_iters             = LIST_HEAD_INIT(init_css_set.task_iters),
        .threaded_csets         = LIST_HEAD_INIT(init_css_set.threaded_csets),
        .cgrp_links             = LIST_HEAD_INIT(init_css_set.cgrp_links),
@@ -1139,6 +1140,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
        cset->dom_cset = cset;
        INIT_LIST_HEAD(&cset->tasks);
        INIT_LIST_HEAD(&cset->mg_tasks);
+       INIT_LIST_HEAD(&cset->dying_tasks);
        INIT_LIST_HEAD(&cset->task_iters);
        INIT_LIST_HEAD(&cset->threaded_csets);
        INIT_HLIST_NODE(&cset->hlist);
@@ -4114,15 +4116,18 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
                        it->task_pos = NULL;
                        return;
                }
-       } while (!css_set_populated(cset));
+       } while (!css_set_populated(cset) && !list_empty(&cset->dying_tasks));
 
        if (!list_empty(&cset->tasks))
                it->task_pos = cset->tasks.next;
-       else
+       else if (!list_empty(&cset->mg_tasks))
                it->task_pos = cset->mg_tasks.next;
+       else
+               it->task_pos = cset->dying_tasks.next;
 
        it->tasks_head = &cset->tasks;
        it->mg_tasks_head = &cset->mg_tasks;
+       it->dying_tasks_head = &cset->dying_tasks;
 
        /*
         * We don't keep css_sets locked across iteration steps and thus
@@ -4161,6 +4166,8 @@ static void css_task_iter_skip(struct css_task_iter *it,
 
 static void css_task_iter_advance(struct css_task_iter *it)
 {
+       struct task_struct *task;
+
        lockdep_assert_held(&css_set_lock);
 repeat:
        if (it->task_pos) {
@@ -4177,17 +4184,32 @@ repeat:
                if (it->task_pos == it->tasks_head)
                        it->task_pos = it->mg_tasks_head->next;
                if (it->task_pos == it->mg_tasks_head)
+                       it->task_pos = it->dying_tasks_head->next;
+               if (it->task_pos == it->dying_tasks_head)
                        css_task_iter_advance_css_set(it);
        } else {
                /* called from start, proceed to the first cset */
                css_task_iter_advance_css_set(it);
        }
 
-       /* if PROCS, skip over tasks which aren't group leaders */
-       if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos &&
-           !thread_group_leader(list_entry(it->task_pos, struct task_struct,
-                                           cg_list)))
-               goto repeat;
+       if (!it->task_pos)
+               return;
+
+       task = list_entry(it->task_pos, struct task_struct, cg_list);
+
+       if (it->flags & CSS_TASK_ITER_PROCS) {
+               /* if PROCS, skip over tasks which aren't group leaders */
+               if (!thread_group_leader(task))
+                       goto repeat;
+
+               /* and dying leaders w/o live member threads */
+               if (!atomic_read(&task->signal->live))
+                       goto repeat;
+       } else {
+               /* skip all dying ones */
+               if (task->flags & PF_EXITING)
+                       goto repeat;
+       }
 }
 
 /**
@@ -5644,6 +5666,7 @@ void cgroup_exit(struct task_struct *tsk)
        if (!list_empty(&tsk->cg_list)) {
                spin_lock_irq(&css_set_lock);
                css_set_move_task(tsk, cset, NULL, false);
+               list_add_tail(&tsk->cg_list, &cset->dying_tasks);
                cset->nr_tasks--;
                spin_unlock_irq(&css_set_lock);
        } else {
@@ -5664,6 +5687,13 @@ void cgroup_release(struct task_struct *task)
        do_each_subsys_mask(ss, ssid, have_release_callback) {
                ss->release(task);
        } while_each_subsys_mask();
+
+       if (use_task_css_set_links) {
+               spin_lock_irq(&css_set_lock);
+               css_set_skip_task_iters(task_css_set(task), task);
+               list_del_init(&task->cg_list);
+               spin_unlock_irq(&css_set_lock);
+       }
 }
 
 void cgroup_free(struct task_struct *task)