Re: [RFC][PATCH] muptiple bugs in PI futexes

[Alexey Kuznetsov]

Hello!

> We actually need to do something about this, as we might loop for ever
> there. The robust cleanup code can fail (e.g. due to list corruption)
> and we would see exit_state != 0 and the OWNER_DIED bit would never be
> set, so we are stuck in a busy loop.

Yes...

It is possible to take read_lock(&tasklist_lock) before:

        inc_preempt_count();
        curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
        dec_preempt_count();

and drop it after lookup_pi_state().

In this case exiting task will set FUTEX_OWNER_DIED, but will
spin in exit_notify(), we will find valid pi_state and go slow path
taking rtmutex.

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