Messages in this thread | | | Subject | Re: [PATCH 1/3] futex: do not pagefault_disable in futex_atomic_cmpxchg_inatomic() | From | Peter Zijlstra <> | Date | Mon, 14 Mar 2011 10:13:17 +0100 |
| |
On Sun, 2011-03-13 at 17:55 -0700, Darren Hart wrote: > I wondered about the preempt vs pagefault disable
In current mainline they happen to be the same, but for -rt they're not.
Its also conceptually different, with preempt disable we dis-allow any scheduling, which thus also precludes most fault handlers.
Disabling pagefault can be done without also disabling preemption (as is done in -rt) and simply means that we'll never try to handle the fault and fallback to the exception table or give up and segfault the kernel.
Its not dis-similar to the whole rcu_read_lock() vs preempt_disable() stuff, for a while one implied the other.
| |