Re: process time < thread time?

[Peter Zijlstra <peterz@infradead.org>]

On Thu, 2011-09-01 at 11:56 +0200, Thomas Gleixner wrote:
> The untested patch below should cure this.
> 

> diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
> index 58f405b..42378cb 100644
> --- a/kernel/posix-cpu-timers.c
> +++ b/kernel/posix-cpu-timers.c
> @@ -250,7 +250,7 @@ void thread_group_cputime(struct task_struct *tsk,
> struct task_cputime *times)
>         do {
>                 times->utime = cputime_add(times->utime, t->utime);
>                 times->stime = cputime_add(times->stime, t->stime);
> -               times->sum_exec_runtime += t->se.sum_exec_runtime;
> +               times->sum_exec_runtime += task_sched_runtime(t);
>         } while_each_thread(tsk, t);
>  out:
>         rcu_read_unlock(); 

I think we just deadlocked:

cpu_clock_sample_group()
  CPUCLOCK_SCHED: thread_group_sched_runtime()
    task_rq_lock()        <-.
    thread_group_cputime()  |
      task_sched_runtime()  |
       task_rq_lock() ------'


Also, having to take locks here is sad, but yeah if we want to cure this
there's not much we can do about that.