Re: [PATCH V5] powercap/drivers/idle_injection: Add an idle injection framework

[Peter Zijlstra]

On Wed, Jun 06, 2018 at 02:05:39PM +0200, Andrea Parri wrote:
> Hi Daniel, Viresh,
> 
> On Wed, Jun 06, 2018 at 04:15:28PM +0530, Viresh Kumar wrote:
> > On 06-06-18, 12:22, Daniel Lezcano wrote:
> > > (mb() are done in the atomic operations AFAICT).
> 
> To do my bit, not all atomic ops do/imply memory barriers; e.g.,
> 
>   [from Documentation/atomic_t.txt]
> 
>   - non-RMW operations [e.g., atomic_set()] are unordered
> 
>   - RMW operations that have no return value [e.g., atomic_inc()] are unordered

Quite so indeed.

> > AFAIU, it is required to make sure the operations are seen in a particular order
> > on another CPU and the compiler doesn't reorganize code to optimize it.
> > 
> > For example, in our case what if the compiler reorganizes the atomic-set
> > operation after wakeup-process ? But maybe that wouldn't happen across function
> > calls and we should be safe then.
> 
> IIUC, wake_up_process() implies a full memory barrier and a compiler barrier,
> due to:

Yes, the wakeup being a RELEASE (at least) is a fairly fundamental
property for causality. You expect the woken task to observe the
condition it got woken up on.