Messages in this thread | | | Date | Fri, 12 Jul 2019 12:10:12 +0200 | From | Steffen Klassert <> | Subject | Re: [PATCH] padata: use smp_mb in padata_reorder to avoid orphaned padata jobs |
| |
On Fri, Jul 12, 2019 at 06:06:36PM +0800, Herbert Xu wrote: > Daniel Jordan <daniel.m.jordan@oracle.com> wrote: > > > > CPU0 CPU1 > > > > padata_reorder padata_do_serial > > LOAD reorder_objects // 0 > > INC reorder_objects // 1 > > padata_reorder > > TRYLOCK pd->lock // failed > > UNLOCK pd->lock > > I think this can't happen because CPU1 won't call padata_reorder > at all as it's the wrong CPU so it gets pushed back onto a work > queue which will go back to CPU0. > > Steffen, could you please take a look at this as there clearly > is a problem here?
I'm currently travelling, will have a look at it when I'm back.
| |