Re: Potential 2.2.8 scheduler bugs

Dimitris Michailidis (dimitris@darkside.engr.sgi.com)
Thu, 13 May 1999 16:19:48 -0700 (PDT)

On 13-May-99 Andrea Arcangeli wrote:
> On Thu, 13 May 1999, Ingo Molnar wrote:
>
>>> On another front, release() in exit.c contains the following piece
>>> of code: [...]
>
> I think that this race will never trigger but according to me rmb()
> may be
> still desiderable. We must make sure to read p->has_cpu after
> p->state.
>
> Maybe our CPU reads p->has_cpu and see 0, before reading p->state and
> seeing TASK_ZOMBIE, and between the two reads the other cpu scheduled
> the
> task `p' and the task `p' exits and p->state get set to ZOMBIE but
> do_exit
> has still to complete (has_cpu is 1 but the other CPU think it's 0
> because it read has_cpu out of order).
>

Consider what happens when the exiting process is scheduled for the
last time (when it is still runnable, not when it has changed its state
to zombie). The wmb() in __schedule_tail() should make all CPUs see
that has_cpu=1 for this process. This is before the process becomes a
zombie, so when a process sees that p->state= TASK_ZOMBIE it cannot
have a stale p->has_cpu=0. I don't see the need for a barrier in this
piece of code. It appears to me that

while (p->has_cpu)
;

should be enough.

------
Dimitris Michailidis dimitris@engr.sgi.com

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/