[dpdk-dev] [PATCH] eal/ppc: remove fix of memory barrier for IBM POWER

[Pradeep Satyanarayana]

Shahaf Shuler <shahafs at mellanox.com> wrote on 03/23/2019 11:37:42 PM:

> From: Shahaf Shuler <shahafs at mellanox.com>
> To: "pradeep at us.ibm.com" <pradeep at us.ibm.com>, Thomas Monjalon
> <thomas at monjalon.net>
> Cc: "bruce.richardson at intel.com" <bruce.richardson at intel.com>, Chao
> Zhu <chaozhu at linux.vnet.ibm.com>, Dekel Peled <dekelp at mellanox.com>,
> "dev at dpdk.org" <dev at dpdk.org>, David Christensen <drc at ibm.com>,
> "honnappa.nagarahalli at arm.com" <honnappa.nagarahalli at arm.com>,
> "konstantin.ananyev at intel.com" <konstantin.ananyev at intel.com>,
> "ola.liljedahl at arm.com" <ola.liljedahl at arm.com>, Ori Kam
> <orika at mellanox.com>, David Wilder <wilder at us.ibm.com>, Yongseok Koh
> <yskoh at mellanox.com>
> Date: 03/23/2019 11:37 PM
> Subject: RE: [PATCH] eal/ppc: remove fix of memory barrier for IBM POWER
>
> Pradeep,
>
> Pradeep Satyanarayana wrote on Saturday, March 23, 2019 12:58 AM
> >Thomas Monjalon <thomas at monjalon.net> wrote on 03/22/2019 10:51:17 AM:
> >> Date: 03/22/2019 10:51 AM
> >> Subject: Re: [PATCH] eal/ppc: remove fix of memory barrier for IBM
POWER
> >>
> >> 22/03/2019 16:30, Pradeep Satyanarayana:
> >> > Thomas Monjalon <thomas at monjalon.net> wrote on 03/22/2019 01:49:03
AM:
> >> > > 22/03/2019 02:40, Pradeep Satyanarayana:
> >> > > > - rte_[rw]mb (general memory barrier) --> should be lwsync
> >> > >
> >> > > This is what may be discussed.
> >> > > The assumption is that the general memory barrier should cover
> >> > > all cases (CPU caches, SMP and I/O).
> >> > > That's why we think it should "sync" for Power.
> >> >
> >> > In that case, at a minimum we must de-link rte_smp_[rw]mb from
rte_[rw]mb
> >> > and retain it as lwsync. Agreed?
> >>
> >> I have no clue about what is needed for SMP barrier in Power.
> >> As long as it works as expected, no problem.
> >>
> >
> >We will try that out and report back here, later next week
>
> Till then, i think there are 2 orthogonal issues:
> 1. ppc rte_wmb is incorrect
> 2. ppc rte_smp_[rw]mb may be improved.
>
> for #1 the current patch from Dekel seems to be OK. do you agree?
> for #2 i guess you will check and come back w/ patch/answer?

That has been the line of thinking. However, we need to do some extensive
testing
to confirm that it all holds up.

Thanks
Pradeep
pradeep at us.ibm.com