Re: [dpdk-dev] [PATCH v6] net/memif: zero-copy slave

[Thomas Monjalon <thomas@monjalon.net>]

11/11/2019 16:21, Ferruh Yigit:
> On 11/4/2019 11:03 AM, Jakub Grajciar wrote:
> > Zero-copy slave support for memif PMD.
> > Slave interface exposes DPDK memory to
> > master interface. Only single file segments
> > are supported (EAL option --single-file-segments).
> > 
> > Signed-off-by: Jakub Grajciar <jgrajcia@cisco.com>
> > ---
> >  doc/guides/nics/memif.rst                     |  42 +-
> >  drivers/net/memif/Makefile                    |   1 +
> >  drivers/net/memif/memif_socket.c              |  65 +--
> >  drivers/net/memif/meson.build                 |   1 +
> >  drivers/net/memif/rte_eth_memif.c             | 449 +++++++++++++++++-
> >  drivers/net/memif/rte_eth_memif.h             |  11 +-
> >  lib/librte_eal/common/eal_common_mcfg.c       |   7 +
> >  .../common/include/rte_eal_memconfig.h        |  13 +
> >  lib/librte_eal/rte_eal_version.map            |   1 +
> >  9 files changed, 516 insertions(+), 74 deletions(-)
> 
> net/memif part looks good to me,
> 
> @David, @Anatoly, any concern on new eal API, is it good to go?

I didn't get into details of this PMD,
but requesting an EAL property looks strange to me.
Is memif using directly some EAL memory?
Or is it using memory from mempool?
If it is from mempool, then the property should be requested to mempool.
Reminder: mempool memory is not always from EAL.