sched: Fix race in task_group()

Stefan reported a crash on a kernel before a3e5d1091c1 ("sched:
Don't call task_group() too many times in set_task_rq()"), he
found the reason to be that the multiple task_group()
invocations in set_task_rq() returned different values.

Looking at all that I found a lack of serialization and plain
wrong comments.

The below tries to fix it using an extra pointer which is
updated under the appropriate scheduler locks. Its not pretty,
but I can't really see another way given how all the cgroup
stuff works.

Reported-and-tested-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1340364965.18025.71.camel@twins
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 15 insertions, 2 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 9e65eff6af3b..b806b821e735 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -123,8 +123,17 @@ extern struct group_info init_groups;
 
 extern struct cred init_cred;
 
+extern struct task_group root_task_group;
+
+#ifdef CONFIG_CGROUP_SCHED
+# define INIT_CGROUP_SCHED(tsk)                                         \
+        .sched_task_group = &root_task_group,
+#else
+# define INIT_CGROUP_SCHED(tsk)
+#endif
+
 #ifdef CONFIG_PERF_EVENTS
-# define INIT_PERF_EVENTS(tsk)                                  \
+# define INIT_PERF_EVENTS(tsk)                                          \
         .perf_event_mutex =                                             \
                  __MUTEX_INITIALIZER(tsk.perf_event_mutex),             \
         .perf_event_list = LIST_HEAD_INIT(tsk.perf_event_list),
@@ -161,6 +170,7 @@ extern struct cred init_cred;
         },                                                              \
         .tasks          = LIST_HEAD_INIT(tsk.tasks),                    \
         INIT_PUSHABLE_TASKS(tsk)                                        \
+        INIT_CGROUP_SCHED(tsk)                                          \
         .ptraced        = LIST_HEAD_INIT(tsk.ptraced),                  \
         .ptrace_entry   = LIST_HEAD_INIT(tsk.ptrace_entry),             \
         .real_parent    = &tsk,                                         \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bc9952991710..fd9436a3a545 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1245,6 +1245,9 @@ struct task_struct {
         const struct sched_class *sched_class;
         struct sched_entity se;
         struct sched_rt_entity rt;
+#ifdef CONFIG_CGROUP_SCHED
+        struct task_group *sched_task_group;
+#endif
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
         /* list of struct preempt_notifier: */
@@ -2724,7 +2727,7 @@ extern int sched_group_set_rt_period(struct task_group *tg,
 extern long sched_group_rt_period(struct task_group *tg);
 extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
 #endif
-#endif
+#endif /* CONFIG_CGROUP_SCHED */
 
 extern int task_can_switch_user(struct user_struct *up,
                                         struct task_struct *tsk);