On 2018-11-19 07:08:44 [-0800], Dave Hansen wrote:
> On 11/19/18 7:06 AM, Sebastian Andrzej Siewior wrote:
> > On 2018-11-19 07:04:35 [-0800], Dave Hansen wrote:
> >> Does the local_bh_disable() itself survive?
> > Not in __fpu__restore_sig(). I do have:
> > | static inline void __fpregs_changes_begin(void)
> > | {
> > | preempt_disable();
> > | local_bh_disable();
> > | }
> >
> > and __fpregs_changes_begin() is introduced as part of the series.
>
> OK, so can we just comment *that*, please? Basically, why do we need botj?
let me do this then.
local_bh_disable() should be enough. However I had a discussion with
PeterZ that this (local_bh_disable()) also acting as preempt_disable())
is an implementation detail and should be avoided. It is not true
Preempt-RT for instance.
Sebastian
