[lkml]   [2009]   [Apr]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [PATCH] Document that wake_up(), complete() and co. imply a full memory barrier
    On 04/22, Ingo Molnar wrote:
    > * Oleg Nesterov <> wrote:
    > > So, I think that try_to_wake_up() implies that the LOADS after it
    > > can't be reordered with STOREs before it (and wmb() of course).
    > Note that the patch David sent says "full memory barrier", not "full
    > memory barrier wrt. task->state":
    > + (*) wake_up(), try_to_wake_up() and co. imply a full memory barrier.
    > +
    > + (*) complete() and co. imply a full memory barrier.
    > These statements are not true in that form, as this code does not
    > imply a full memory barrier. It does imply one on task->state
    > _alone_ (and a couple of other wq-internal variables it happens to
    > read for sure).
    > But even that one isnt entirely true in the two sub-cases i noted:
    > the !wq case (which can happen in object state teardown) and the
    > special ->func handler (which can happen in custom wakeup code a'la
    > eventpoll).
    > So adding a comment that says "this is a full memory barrier" is
    > simply not true to that extent, and is easily misunderstood. Adding
    > "this is a fully memory barrier for task->state dependent data flow"
    > would be more correct. (with a 'as long as wq is not NULL, and as
    > long as the code using this isnt overriding ->func)
    > Agreed?

    Yes sure.

    Except... not that it really matters, but the reading of ->state is
    not "special". I mean,


    in this case try_to_wake_up() acts as a barrier for STORE/LOAD. But
    probably we should not rely on this. So personally I agree with
    "for task->state dependent data flow" above.


     \ /
      Last update: 2009-04-22 17:15    [W:0.022 / U:3.248 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site