[PATCH v2 1/3] cgroup: Iterate tasks that did not finish do_exit()

["Michal Koutný" <mkoutny@suse.com>]

PF_EXITING is set earlier than actual removal from css_set when a task
is exitting. This can confuse cgroup.procs readers who see no PF_EXITING
tasks, however, rmdir is checking against css_set membership so it can
transitionally fail with EBUSY.

Fix this by listing tasks that weren't unlinked from css_set active
lists.
It may happen that other users of the task iterator (without
CSS_TASK_ITER_PROCS) spot a PF_EXITING task before cgroup_exit(). This
is equal to the state before commit c03cd7738a83 ("cgroup: Include dying
leaders with live threads in PROCS iterations") but it may be reviewed
later.

Reported-by: Suren Baghdasaryan <surenb@google.com>
Fixes: c03cd7738a83 ("cgroup: Include dying leaders with live threads in PROCS iterations")
Signed-off-by: Michal Koutný <mkoutny@suse.com>
---
 include/linux/cgroup.h |  1 +
 kernel/cgroup/cgroup.c | 23 ++++++++++++++++-------
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index d7ddebd0cdec..e75d2191226b 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -62,6 +62,7 @@ struct css_task_iter {
 	struct list_head		*mg_tasks_head;
 	struct list_head		*dying_tasks_head;
 
+	struct list_head		*cur_tasks_head;
 	struct css_set			*cur_cset;
 	struct css_set			*cur_dcset;
 	struct task_struct		*cur_task;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 735af8f15f95..a6e3619e013b 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4404,12 +4404,16 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 		}
 	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
 
-	if (!list_empty(&cset->tasks))
+	if (!list_empty(&cset->tasks)) {
 		it->task_pos = cset->tasks.next;
-	else if (!list_empty(&cset->mg_tasks))
+		it->cur_tasks_head = &cset->tasks;
+	} else if (!list_empty(&cset->mg_tasks)) {
 		it->task_pos = cset->mg_tasks.next;
-	else
+		it->cur_tasks_head = &cset->mg_tasks;
+	} else {
 		it->task_pos = cset->dying_tasks.next;
+		it->cur_tasks_head = &cset->dying_tasks;
+	}
 
 	it->tasks_head = &cset->tasks;
 	it->mg_tasks_head = &cset->mg_tasks;
@@ -4467,10 +4471,14 @@ static void css_task_iter_advance(struct css_task_iter *it)
 		else
 			it->task_pos = it->task_pos->next;
 
-		if (it->task_pos == it->tasks_head)
+		if (it->task_pos == it->tasks_head) {
 			it->task_pos = it->mg_tasks_head->next;
-		if (it->task_pos == it->mg_tasks_head)
+			it->cur_tasks_head = it->mg_tasks_head;
+		}
+		if (it->task_pos == it->mg_tasks_head) {
 			it->task_pos = it->dying_tasks_head->next;
+			it->cur_tasks_head = it->dying_tasks_head;
+		}
 		if (it->task_pos == it->dying_tasks_head)
 			css_task_iter_advance_css_set(it);
 	} else {
@@ -4489,11 +4497,12 @@ static void css_task_iter_advance(struct css_task_iter *it)
 			goto repeat;
 
 		/* and dying leaders w/o live member threads */
-		if (!atomic_read(&task->signal->live))
+		if (it->cur_tasks_head == it->dying_tasks_head &&
+		    !atomic_read(&task->signal->live))
 			goto repeat;
 	} else {
 		/* skip all dying ones */
-		if (task->flags & PF_EXITING)
+		if (it->cur_tasks_head == it->dying_tasks_head)
 			goto repeat;
 	}
 }
-- 
2.24.1