[v3] net/nfb: new netcope driver

Message ID 1551451054-111249-1-git-send-email-cernay@netcope.com
State Superseded, archived
Delegated to: Ferruh Yigit
Headers show
Series
  • [v3] net/nfb: new netcope driver
Related show

Checks

Context Check Description
ci/intel-Performance-Testing success Performance Testing PASS
ci/mellanox-Performance-Testing success Performance Testing PASS
ci/Intel-compilation success Compilation OK
ci/checkpatch warning coding style issues

Commit Message

Rastislav Cernay March 1, 2019, 2:37 p.m.
From: Rastislav Cernay <cernay@netcope.com>

Added new net driver for Netcope nfb cards

Signed-off-by: Rastislav Cernay <cernay@netcope.com>
---
v2: remove unnecessary cast
    remove unnecessary zeroing
    move declaration to not mix with code
    restore skeleton example
v3: add release notes
    add doc to doc index
    add architecture limits to doc
    edit features list
    add .map file
    change link to dependecies to official vendor site
    move declarations out of code
    remove false comments (rte_errno is set)
    comments to c89 style
    remove log from main rx loop
    remove redundant code
 MAINTAINERS                             |   7 +
 config/common_base                      |   4 +
 devtools/test-build.sh                  |   1 +
 doc/guides/nics/features/nfb.ini        |  18 +
 doc/guides/nics/index.rst               |   1 +
 doc/guides/nics/nfb.rst                 | 143 ++++++++
 doc/guides/rel_notes/release_19_02.rst  |   5 +
 drivers/net/Makefile                    |   1 +
 drivers/net/meson.build                 |   1 +
 drivers/net/nfb/Makefile                |  41 +++
 drivers/net/nfb/meson.build             |   9 +
 drivers/net/nfb/nfb.h                   |  50 +++
 drivers/net/nfb/nfb_ethdev.c            | 589 ++++++++++++++++++++++++++++++++
 drivers/net/nfb/nfb_rx.c                | 127 +++++++
 drivers/net/nfb/nfb_rx.h                | 213 ++++++++++++
 drivers/net/nfb/nfb_rxmode.c            | 100 ++++++
 drivers/net/nfb/nfb_rxmode.h            |  78 +++++
 drivers/net/nfb/nfb_stats.c             |  78 +++++
 drivers/net/nfb/nfb_stats.h             |  48 +++
 drivers/net/nfb/nfb_tx.c                | 113 ++++++
 drivers/net/nfb/nfb_tx.h                | 204 +++++++++++
 drivers/net/nfb/rte_nfb_pmd_version.map |   4 +
 mk/rte.app.mk                           |   1 +
 23 files changed, 1836 insertions(+)
 create mode 100644 doc/guides/nics/features/nfb.ini
 create mode 100644 doc/guides/nics/nfb.rst
 create mode 100644 drivers/net/nfb/Makefile
 create mode 100644 drivers/net/nfb/meson.build
 create mode 100644 drivers/net/nfb/nfb.h
 create mode 100644 drivers/net/nfb/nfb_ethdev.c
 create mode 100644 drivers/net/nfb/nfb_rx.c
 create mode 100644 drivers/net/nfb/nfb_rx.h
 create mode 100644 drivers/net/nfb/nfb_rxmode.c
 create mode 100644 drivers/net/nfb/nfb_rxmode.h
 create mode 100644 drivers/net/nfb/nfb_stats.c
 create mode 100644 drivers/net/nfb/nfb_stats.h
 create mode 100644 drivers/net/nfb/nfb_tx.c
 create mode 100644 drivers/net/nfb/nfb_tx.h
 create mode 100644 drivers/net/nfb/rte_nfb_pmd_version.map

Comments

Stephen Hemminger March 1, 2019, 6:47 p.m. | #1
On Fri,  1 Mar 2019 15:37:34 +0100
Rastislav Cernay <cernay@netcope.com> wrote:

> +/**
> + * Default MAC addr
> + */
> +static struct ether_addr eth_addr = {
> +	.addr_bytes = { 0x00, 0x11, 0x17, 0x00, 0x00, 0x00 }

You might want to consider using a random ethernet address.
What does the device do on Linux?
Stephen Hemminger March 1, 2019, 6:50 p.m. | #2
On Fri,  1 Mar 2019 15:37:34 +0100
Rastislav Cernay <cernay@netcope.com> wrote:

> From: Rastislav Cernay <cernay@netcope.com>
> 
> Added new net driver for Netcope nfb cards
> 
> Signed-off-by: Rastislav Cernay <cernay@netcope.com>
> ---

Please fix these obvious style issues from checkpatches

ERROR:SPACING: space required before the open brace '{'
#934: FILE: drivers/net/nfb/nfb_ethdev.c:380:
+	if (!is_valid_assigned_ether_addr(mac_addr)){

WARNING:ONE_SEMICOLON: Statements terminations use 1 semicolon
#935: FILE: drivers/net/nfb/nfb_ethdev.c:381:
+		return -EINVAL;;
David Marchand March 4, 2019, 9:53 a.m. | #3
On Fri, Mar 1, 2019 at 7:50 PM Stephen Hemminger <stephen@networkplumber.org>
wrote:

> On Fri,  1 Mar 2019 15:37:34 +0100
> Rastislav Cernay <cernay@netcope.com> wrote:
>
> > From: Rastislav Cernay <cernay@netcope.com>
> >
> > Added new net driver for Netcope nfb cards
> >
> > Signed-off-by: Rastislav Cernay <cernay@netcope.com>
> > ---
>
> Please fix these obvious style issues from checkpatches
>
> ERROR:SPACING: space required before the open brace '{'
> #934: FILE: drivers/net/nfb/nfb_ethdev.c:380:
> +       if (!is_valid_assigned_ether_addr(mac_addr)){
>
> WARNING:ONE_SEMICOLON: Statements terminations use 1 semicolon
> #935: FILE: drivers/net/nfb/nfb_ethdev.c:381:
> +               return -EINVAL;;
>


And if you look carefully at checkpatches.sh output, you can see:
[dmarchan@dmarchan dpdk]$ ./devtools/checkpatches.sh

### net/nfb: new netcope driver

[snip]

total: 1 errors, 2 warnings, 1884 lines checked
./devtools/checkpatches.sh: line 65: res: command not found

I will post a fix on checkpatches.sh for this, then a new warning appears:

Warning in /doc/guides/nics/nfb.rst:
Using explicit .svg extension instead of .*
David Marchand March 4, 2019, 11:34 a.m. | #4
On Fri, Mar 1, 2019 at 3:38 PM Rastislav Cernay <cernay@netcope.com> wrote:

> diff --git a/drivers/net/nfb/nfb_stats.c b/drivers/net/nfb/nfb_stats.c
> new file mode 100644
> index 0000000..ffc27a5
> --- /dev/null
> +++ b/drivers/net/nfb/nfb_stats.c
> @@ -0,0 +1,78 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2018 Cesnet
> + * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
> + * All rights reserved.
> + */
> +
> +#include "nfb_stats.h"
> +#include "nfb.h"
> +
> +int
> +nfb_eth_stats_get(struct rte_eth_dev *dev,
> +       struct rte_eth_stats *stats)
> +{
> +       uint16_t i;
> +       uint16_t nb_rx = dev->data->nb_rx_queues;
> +       uint16_t nb_tx = dev->data->nb_tx_queues;
> +       uint64_t rx_total = 0;
> +       uint64_t tx_total = 0;
> +       uint64_t tx_err_total = 0;
> +       uint64_t rx_total_bytes = 0;
> +       uint64_t tx_total_bytes = 0;
> +
> +       struct ndp_rx_queue *rx_queue = *((struct ndp_rx_queue **)
> +               dev->data->rx_queues);
> +       struct ndp_tx_queue *tx_queue = *((struct ndp_tx_queue **)
> +               dev->data->tx_queues);
> +
> +       for (i = 0; i < nb_rx; i++) {
> +               if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) {
> +                       stats->q_ipackets[i] = rx_queue[i].rx_pkts;
> +                       stats->q_ibytes[i] = rx_queue[i].rx_bytes;
> +               }
> +               rx_total += stats->q_ipackets[i];
> +               rx_total_bytes += stats->q_ibytes[i];
> +       }
>

What is the point of adding when i >= RTE_ETHDEV_QUEUE_STAT_CNTRS ?
Hopefully, ethdev passes a zero'd structure, but still I find it confusing.



> +
> +       for (i = 0; i < nb_tx; i++) {
> +               if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) {
> +                       stats->q_opackets[i] = tx_queue[i].tx_pkts;
> +                       stats->q_obytes[i] = tx_queue[i].tx_bytes;
> +                       stats->q_errors[i] = tx_queue[i].err_pkts;
> +               }
> +               tx_total += stats->q_opackets[i];
> +               tx_total_bytes += stats->q_obytes[i];
> +               tx_err_total += stats->q_errors[i];
> +       }
>

Idem.
Besides, q_errors[] is for reception errors.

+
> +       stats->ipackets = rx_total;
> +       stats->opackets = tx_total;
> +       stats->ibytes = rx_total_bytes;
> +       stats->obytes = tx_total_bytes;
> +       stats->oerrors = tx_err_total;
> +       return 0;
> +}
>
>
David Marchand March 4, 2019, 12:35 p.m. | #5
On Mon, Mar 4, 2019 at 1:30 PM Rastislav Černay <cernay@netcope.com> wrote:

> >>> What is the point of adding when i >= RTE_ETHDEV_QUEUE_STAT_CNTRS ?
>
> struct rte_eth_stats {
> ...
> uint64_t q_opackets[RTE_ETHDEV_QUEUE_STAT_CNTRS]
> ...
> }
>
> As there can be more queues (nb_tx) then RTE_ETHDEV_QUEUE_STAT_CNTRS (16)
> and struct rte_eth_stats eth_stats is allocated statically,
> there is need to check so it does not write garbage somewhere.
>

How about looping on min(nb_tx, RTE_ETHDEV_QUEUE_STAT_CNTRS) ?



> >>> Besides, q_errors[] is for reception errors.
> I will fix that, meanwhile could q_errors[] be renamed to q_ierrors[]?
> Also could there be a way to publish output errors per queue, for example
> q_oerrors[]?
>

At the moment, no, this would be a api breakage, and adding oerrors would
be a abi breakage.
This can be discussed yes, I just sent a series about q_errors[].

You can still export this via xstats.
David Marchand March 4, 2019, 12:48 p.m. | #6
On Mon, Mar 4, 2019 at 1:35 PM David Marchand <david.marchand@redhat.com>
wrote:

>
>
> On Mon, Mar 4, 2019 at 1:30 PM Rastislav Černay <cernay@netcope.com>
> wrote:
>
>> >>> What is the point of adding when i >= RTE_ETHDEV_QUEUE_STAT_CNTRS ?
>>
>> struct rte_eth_stats {
>> ...
>> uint64_t q_opackets[RTE_ETHDEV_QUEUE_STAT_CNTRS]
>> ...
>> }
>>
>> As there can be more queues (nb_tx) then RTE_ETHDEV_QUEUE_STAT_CNTRS
>> (16) and struct rte_eth_stats eth_stats is allocated statically,
>> there is need to check so it does not write garbage somewhere.
>>
>
> How about looping on min(nb_tx, RTE_ETHDEV_QUEUE_STAT_CNTRS) ?
>

Or add the tx_queue[i].tx_xxx; to the associated global stats and only
fills q_xxx depending on the check.
Rastislav Cernay March 4, 2019, 2:07 p.m. | #7
Typically device works in promiscuous mode and filtering/processing is done
after
packets are received, use of MACS is a marginal case so we are not exactly
focused
on it. I will add random ethernet address so card can work in initial state
with multiple
devices.




On Fri, Mar 1, 2019 at 7:47 PM Stephen Hemminger <stephen@networkplumber.org>
wrote:

> On Fri,  1 Mar 2019 15:37:34 +0100
> Rastislav Cernay <cernay@netcope.com> wrote:
>
> > +/**
> > + * Default MAC addr
> > + */
> > +static struct ether_addr eth_addr = {
> > +     .addr_bytes = { 0x00, 0x11, 0x17, 0x00, 0x00, 0x00 }
>
> You might want to consider using a random ethernet address.
> What does the device do on Linux?
>
Rastislav Cernay March 4, 2019, 2:33 p.m. | #8
>>> What is the point of adding when i >= RTE_ETHDEV_QUEUE_STAT_CNTRS ?

struct rte_eth_stats {
...
uint64_t q_opackets[RTE_ETHDEV_QUEUE_STAT_CNTRS]
...
}

As there can be more queues (nb_tx) then RTE_ETHDEV_QUEUE_STAT_CNTRS (16)
and struct rte_eth_stats eth_stats is allocated statically,
there is need to check so it does not write garbage somewhere.

>>> Besides, q_errors[] is for reception errors.
I will fix that, meanwhile could q_errors[] be renamed to q_ierrors[]? Also
could there be a way to publish output errors per queue, for example
q_oerrors[]?



On Mon, Mar 4, 2019 at 12:35 PM David Marchand <david.marchand@redhat.com>
wrote:

>
> On Fri, Mar 1, 2019 at 3:38 PM Rastislav Cernay <cernay@netcope.com>
> wrote:
>
>> diff --git a/drivers/net/nfb/nfb_stats.c b/drivers/net/nfb/nfb_stats.c
>> new file mode 100644
>> index 0000000..ffc27a5
>> --- /dev/null
>> +++ b/drivers/net/nfb/nfb_stats.c
>> @@ -0,0 +1,78 @@
>> +/* SPDX-License-Identifier: BSD-3-Clause
>> + * Copyright(c) 2018 Cesnet
>> + * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
>> + * All rights reserved.
>> + */
>> +
>> +#include "nfb_stats.h"
>> +#include "nfb.h"
>> +
>> +int
>> +nfb_eth_stats_get(struct rte_eth_dev *dev,
>> +       struct rte_eth_stats *stats)
>> +{
>> +       uint16_t i;
>> +       uint16_t nb_rx = dev->data->nb_rx_queues;
>> +       uint16_t nb_tx = dev->data->nb_tx_queues;
>> +       uint64_t rx_total = 0;
>> +       uint64_t tx_total = 0;
>> +       uint64_t tx_err_total = 0;
>> +       uint64_t rx_total_bytes = 0;
>> +       uint64_t tx_total_bytes = 0;
>> +
>> +       struct ndp_rx_queue *rx_queue = *((struct ndp_rx_queue **)
>> +               dev->data->rx_queues);
>> +       struct ndp_tx_queue *tx_queue = *((struct ndp_tx_queue **)
>> +               dev->data->tx_queues);
>> +
>> +       for (i = 0; i < nb_rx; i++) {
>> +               if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) {
>> +                       stats->q_ipackets[i] = rx_queue[i].rx_pkts;
>> +                       stats->q_ibytes[i] = rx_queue[i].rx_bytes;
>> +               }
>> +               rx_total += stats->q_ipackets[i];
>> +               rx_total_bytes += stats->q_ibytes[i];
>> +       }
>>
>
> What is the point of adding when i >= RTE_ETHDEV_QUEUE_STAT_CNTRS ?
> Hopefully, ethdev passes a zero'd structure, but still I find it confusing.
>
>
>
>> +
>> +       for (i = 0; i < nb_tx; i++) {
>> +               if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) {
>> +                       stats->q_opackets[i] = tx_queue[i].tx_pkts;
>> +                       stats->q_obytes[i] = tx_queue[i].tx_bytes;
>> +                       stats->q_errors[i] = tx_queue[i].err_pkts;
>> +               }
>> +               tx_total += stats->q_opackets[i];
>> +               tx_total_bytes += stats->q_obytes[i];
>> +               tx_err_total += stats->q_errors[i];
>> +       }
>>
>
> Idem.
> Besides, q_errors[] is for reception errors.
>
> +
>> +       stats->ipackets = rx_total;
>> +       stats->opackets = tx_total;
>> +       stats->ibytes = rx_total_bytes;
>> +       stats->obytes = tx_total_bytes;
>> +       stats->oerrors = tx_err_total;
>> +       return 0;
>> +}
>>
>>
> --
> David Marchand
>
Rastislav Cernay March 4, 2019, 3:15 p.m. | #9
>>>How about looping on min(nb_tx, RTE_ETHDEV_QUEUE_STAT_CNTRS) ?
This would lead to incomplete tx_total (and other total) stats. Maybe I
could just
add commentary, why it is written like this and leave it be?


On Mon, Mar 4, 2019 at 1:48 PM David Marchand <david.marchand@redhat.com>
wrote:

> On Mon, Mar 4, 2019 at 1:35 PM David Marchand <david.marchand@redhat.com>
> wrote:
>
>>
>>
>> On Mon, Mar 4, 2019 at 1:30 PM Rastislav Černay <cernay@netcope.com>
>> wrote:
>>
>>> >>> What is the point of adding when i >= RTE_ETHDEV_QUEUE_STAT_CNTRS ?
>>>
>>> struct rte_eth_stats {
>>> ...
>>> uint64_t q_opackets[RTE_ETHDEV_QUEUE_STAT_CNTRS]
>>> ...
>>> }
>>>
>>> As there can be more queues (nb_tx) then RTE_ETHDEV_QUEUE_STAT_CNTRS
>>> (16) and struct rte_eth_stats eth_stats is allocated statically,
>>> there is need to check so it does not write garbage somewhere.
>>>
>>
>> How about looping on min(nb_tx, RTE_ETHDEV_QUEUE_STAT_CNTRS) ?
>>
>
> Or add the tx_queue[i].tx_xxx; to the associated global stats and only
> fills q_xxx depending on the check.
>
>
> --
> David Marchand
>
Rami Rosen March 5, 2019, 8:31 p.m. | #10
Hi,

Added new net driver for Netcope nfb cards

Signed-off-by: Rastislav Cernay <cernay at netcope.com>
Reviewed-by: Rami Rosen <ramirose@gmail.com>
---
v2: remove unnecessary cast
    remove unnecessary zeroing
    move declaration to not mix with code
    restore skeleton example
v3: add release notes
    add doc to doc index
    add architecture limits to doc
    edit features list
    add .map file
    change link to dependecies to official vendor site
    move declarations out of code
    remove false comments (rte_errno is set)
    comments to c89 style
    remove log from main rx loop
    remove redundant code
 MAINTAINERS                             |   7 +
 config/common_base                      |   4 +
 devtools/test-build.sh                  |   1 +
 doc/guides/nics/features/nfb.ini        |  18 +
 doc/guides/nics/index.rst               |   1 +
 doc/guides/nics/nfb.rst                 | 143 ++++++++
 doc/guides/rel_notes/release_19_02.rst  |   5 +
 drivers/net/Makefile                    |   1 +
 drivers/net/meson.build                 |   1 +
 drivers/net/nfb/Makefile                |  41 +++
 drivers/net/nfb/meson.build             |   9 +
 drivers/net/nfb/nfb.h                   |  50 +++
 drivers/net/nfb/nfb_ethdev.c            | 589
++++++++++++++++++++++++++++++++
 drivers/net/nfb/nfb_rx.c                | 127 +++++++
 drivers/net/nfb/nfb_rx.h                | 213 ++++++++++++
 drivers/net/nfb/nfb_rxmode.c            | 100 ++++++
 drivers/net/nfb/nfb_rxmode.h            |  78 +++++
 drivers/net/nfb/nfb_stats.c             |  78 +++++
 drivers/net/nfb/nfb_stats.h             |  48 +++
 drivers/net/nfb/nfb_tx.c                | 113 ++++++
 drivers/net/nfb/nfb_tx.h                | 204 +++++++++++
 drivers/net/nfb/rte_nfb_pmd_version.map |   4 +
 mk/rte.app.mk                           |   1 +
 23 files changed, 1836 insertions(+)
 create mode 100644 doc/guides/nics/features/nfb.ini
 create mode 100644 doc/guides/nics/nfb.rst
 create mode 100644 drivers/net/nfb/Makefile
 create mode 100644 drivers/net/nfb/meson.build
 create mode 100644 drivers/net/nfb/nfb.h
 create mode 100644 drivers/net/nfb/nfb_ethdev.c
 create mode 100644 drivers/net/nfb/nfb_rx.c
 create mode 100644 drivers/net/nfb/nfb_rx.h
 create mode 100644 drivers/net/nfb/nfb_rxmode.c
 create mode 100644 drivers/net/nfb/nfb_rxmode.h
 create mode 100644 drivers/net/nfb/nfb_stats.c
 create mode 100644 drivers/net/nfb/nfb_stats.h
 create mode 100644 drivers/net/nfb/nfb_tx.c
 create mode 100644 drivers/net/nfb/nfb_tx.h
 create mode 100644 drivers/net/nfb/rte_nfb_pmd_version.map

Minors:

+int
+nfb_eth_rx_queue_init(struct nfb_device *nfb,
+ uint16_t rx_queue_id,
+ uint16_t port_id,
+ struct rte_mempool *mb_pool,
+ struct ndp_rx_queue *rxq)
+{
+ if (nfb == NULL)
+ return -EINVAL;
+
+ rxq->queue = ndp_open_rx_queue(nfb, rx_queue_id);
+ if (rxq->queue == NULL)
+ return -EINVAL;
+
+ rxq->nfb = nfb;
+ rxq->rx_queue_id = rx_queue_id;
+ rxq->in_port = port_id;
+ rxq->mb_pool = mb_pool;

maybe better to have the following declaration at the beginning
of the method (though not sure it will cause a compilation error
under most compilers)

+
+ const struct rte_pktmbuf_pool_private *mbp_priv =
+ rte_mempool_get_priv(mb_pool);


static __rte_always_inline uint16_t
+nfb_eth_ndp_tx(void *queue,
+ struct rte_mbuf **bufs,
+ uint16_t nb_pkts)
+{
...
...
Should be "TX invalid arguments!\n"):

+ if (unlikely(ndp->queue == NULL || nb_pkts == 0)) {
+ RTE_LOG(ERR, PMD, "RX invalid arguments!\n");
+ return 0;
+ }
+
Luca Boccassi March 5, 2019, 10:41 p.m. | #11
On Fri, 2019-03-01 at 15:37 +0100, Rastislav Cernay wrote:
> From: Rastislav Cernay <cernay@netcope.com>
> 
> Added new net driver for Netcope nfb cards
> 
> Signed-off-by: Rastislav Cernay <cernay@netcope.com>
> ---
> v2: remove unnecessary cast
>     remove unnecessary zeroing
>     move declaration to not mix with code
>     restore skeleton example
> v3: add release notes
>     add doc to doc index
>     add architecture limits to doc
>     edit features list
>     add .map file
>     change link to dependecies to official vendor site
>     move declarations out of code
>     remove false comments (rte_errno is set)
>     comments to c89 style
>     remove log from main rx loop
>     remove redundant code
>  MAINTAINERS                             |   7 +
>  config/common_base                      |   4 +
>  devtools/test-build.sh                  |   1 +
>  doc/guides/nics/features/nfb.ini        |  18 +
>  doc/guides/nics/index.rst               |   1 +
>  doc/guides/nics/nfb.rst                 | 143 ++++++++
>  doc/guides/rel_notes/release_19_02.rst  |   5 +
>  drivers/net/Makefile                    |   1 +
>  drivers/net/meson.build                 |   1 +
>  drivers/net/nfb/Makefile                |  41 +++
>  drivers/net/nfb/meson.build             |   9 +
>  drivers/net/nfb/nfb.h                   |  50 +++
>  drivers/net/nfb/nfb_ethdev.c            | 589
> ++++++++++++++++++++++++++++++++
>  drivers/net/nfb/nfb_rx.c                | 127 +++++++
>  drivers/net/nfb/nfb_rx.h                | 213 ++++++++++++
>  drivers/net/nfb/nfb_rxmode.c            | 100 ++++++
>  drivers/net/nfb/nfb_rxmode.h            |  78 +++++
>  drivers/net/nfb/nfb_stats.c             |  78 +++++
>  drivers/net/nfb/nfb_stats.h             |  48 +++
>  drivers/net/nfb/nfb_tx.c                | 113 ++++++
>  drivers/net/nfb/nfb_tx.h                | 204 +++++++++++
>  drivers/net/nfb/rte_nfb_pmd_version.map |   4 +
>  mk/rte.app.mk                           |   1 +
>  23 files changed, 1836 insertions(+)
>  create mode 100644 doc/guides/nics/features/nfb.ini
>  create mode 100644 doc/guides/nics/nfb.rst
>  create mode 100644 drivers/net/nfb/Makefile
>  create mode 100644 drivers/net/nfb/meson.build
>  create mode 100644 drivers/net/nfb/nfb.h
>  create mode 100644 drivers/net/nfb/nfb_ethdev.c
>  create mode 100644 drivers/net/nfb/nfb_rx.c
>  create mode 100644 drivers/net/nfb/nfb_rx.h
>  create mode 100644 drivers/net/nfb/nfb_rxmode.c
>  create mode 100644 drivers/net/nfb/nfb_rxmode.h
>  create mode 100644 drivers/net/nfb/nfb_stats.c
>  create mode 100644 drivers/net/nfb/nfb_stats.h
>  create mode 100644 drivers/net/nfb/nfb_tx.c
>  create mode 100644 drivers/net/nfb/nfb_tx.h
>  create mode 100644 drivers/net/nfb/rte_nfb_pmd_version.map
> 

<...>

> diff --git a/drivers/net/nfb/meson.build
> b/drivers/net/nfb/meson.build
> new file mode 100644
> index 0000000..d7dccba
> --- /dev/null
> +++ b/drivers/net/nfb/meson.build
> @@ -0,0 +1,9 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright(c) 2018 Cesnet
> +# Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
> +# All rights reserved.
> +
> +dep = cc.find_library('nfb', required: true)

This unconditionally breaks the build, please look at how
drivers/net/pcap/meson.build checks for dependencies for an example (I
assume libnfd does not provide a pkg-config file?)

> +build = dep.found()
> +ext_deps += dep
> +sources = files('nfb_rx.c', 'nfb_tx.c', 'nfb_stats.c',
> 'nfb_ethdev.c', 'nfb_rxmode.c')

<...>

> diff --git a/drivers/net/nfb/rte_nfb_pmd_version.map
> b/drivers/net/nfb/rte_nfb_pmd_version.map
> new file mode 100644
> index 0000000..97fd251
> --- /dev/null
> +++ b/drivers/net/nfb/rte_nfb_pmd_version.map
> @@ -0,0 +1,4 @@
> +DPDK_19.02 {
> +
> +        local: *;
> +};

These are all new symbols so they should be marked as experimental,
please see doc/guides/contributing/versioning.rst

> diff --git a/mk/rte.app.mk b/mk/rte.app.mk
> index 8a4f0f4..32e88b5 100644
> --- a/mk/rte.app.mk
> +++ b/mk/rte.app.mk
> @@ -196,6 +196,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_SOFTNIC)      +=
> -lrte_pmd_softnic
>  endif
>  _LDLIBS-$(CONFIG_RTE_LIBRTE_SFC_EFX_PMD)    += -lrte_pmd_sfc_efx
>  _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_SZEDATA2)   += -lrte_pmd_szedata2
> -lsze2
> +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_NFB)        += -lrte_pmd_nfb -lnfb
> -lfdt

Why is -lfdt added? I don't see any symbols from libfdt used in the
rest of the patch?

>  _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_TAP)        += -lrte_pmd_tap
>  _LDLIBS-$(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD) +=
> -lrte_pmd_thunderx_nicvf
>  _LDLIBS-$(CONFIG_RTE_LIBRTE_VDEV_NETVSC_PMD) +=
> -lrte_pmd_vdev_netvsc
Luca Boccassi March 6, 2019, 1:25 p.m. | #12
On Wed, 2019-03-06 at 15:51 +0100, Rastislav Černay wrote:
> > 
> > --Why is -lfdt added? I don't see any symbols from libfdt used in
> > the
> > --rest of the patch?
> > 
> 
> Hi,
> libnfb is dependent on fdt and there is a special case, where some
> functions are defined in header (netcope/rxmac.h, netcope/txmac.h).
> So if one wants to use functions, from these headers fdt needs to be
> linked
> manually, not just through nfb. I also added fdt to meson.build
> so it is little clearer, however if libnfb is installed libfdt is
> always
> installed too.

This is a perfect use case for pkg-config. Please consider shipping a
libnfb.pc file in libnfb, so that you can define a Libs.private: -fdt
and users don't have to worry about these things themselves.
Rastislav Cernay March 6, 2019, 2:51 p.m. | #13
>
>
> --Why is -lfdt added? I don't see any symbols from libfdt used in the
> --rest of the patch?
>

Hi,
libnfb is dependent on fdt and there is a special case, where some
functions are defined in header (netcope/rxmac.h, netcope/txmac.h).
So if one wants to use functions, from these headers fdt needs to be linked
manually, not just through nfb. I also added fdt to meson.build
so it is little clearer, however if libnfb is installed libfdt is always
installed too.

Patch

diff --git a/MAINTAINERS b/MAINTAINERS
index 6610440..c6bffde 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -654,6 +654,13 @@  F: drivers/net/szedata2/
 F: doc/guides/nics/szedata2.rst
 F: doc/guides/nics/features/szedata2.ini
 
+Netcope nfb
+M: Rastislav Cernay <cernay@netcope.com>
+M: Jan Remes <remes@netcope.com>
+F: drivers/net/nfb/
+F: doc/guides/nics/nfb.rst
+F: doc/guides/nics/features/nfb.ini
+
 Netronome nfp
 M: Alejandro Lucero <alejandro.lucero@netronome.com>
 F: drivers/net/nfp/
diff --git a/config/common_base b/config/common_base
index 7c6da51..1ab0a6b 100644
--- a/config/common_base
+++ b/config/common_base
@@ -360,6 +360,10 @@  CONFIG_RTE_LIBRTE_SFC_EFX_DEBUG=n
 # Compile software PMD backed by SZEDATA2 device
 #
 CONFIG_RTE_LIBRTE_PMD_SZEDATA2=n
+#
+# Compile software PMD backed by NFB device
+#
+CONFIG_RTE_LIBRTE_PMD_NFB=n
 
 #
 # Compile burst-oriented Cavium Thunderx NICVF PMD driver
diff --git a/devtools/test-build.sh b/devtools/test-build.sh
index 42f4ad0..ab57ab8 100755
--- a/devtools/test-build.sh
+++ b/devtools/test-build.sh
@@ -18,6 +18,7 @@  default_path=$PATH
 # - DPDK_DEP_SSL (y/[n])
 # - DPDK_DEP_IPSEC_MB (y/[n])
 # - DPDK_DEP_SZE (y/[n])
+# - DPDK_DEP_NFB (y/[n])
 # - DPDK_DEP_ZLIB (y/[n])
 # - DPDK_MAKE_JOBS (int)
 # - DPDK_NOTIFY (notify-send)
diff --git a/doc/guides/nics/features/nfb.ini b/doc/guides/nics/features/nfb.ini
new file mode 100644
index 0000000..e1c5266
--- /dev/null
+++ b/doc/guides/nics/features/nfb.ini
@@ -0,0 +1,18 @@ 
+;
+; Supported features of the 'nfb' network poll mode driver.
+;
+; Refer to default.ini for the full list of available PMD features.
+;
+[Features]
+Speed capabilities   = P
+Link status          = Y
+Queue start/stop     = Y
+Promiscuous mode     = Y
+Allmulticast mode    = Y
+Basic stats          = Y
+Extended stats       = Y
+Stats per queue      = Y
+Other kdrv           = Y
+x86-64               = Y
+Usage doc            = Y
+Scattered Tx         = Y
diff --git a/doc/guides/nics/index.rst b/doc/guides/nics/index.rst
index 5c80e3b..079972e 100644
--- a/doc/guides/nics/index.rst
+++ b/doc/guides/nics/index.rst
@@ -39,6 +39,7 @@  Network Interface Controller Drivers
     mvneta
     mvpp2
     netvsc
+    nfb
     nfp
     octeontx
     qede
diff --git a/doc/guides/nics/nfb.rst b/doc/guides/nics/nfb.rst
new file mode 100644
index 0000000..8c0be40
--- /dev/null
+++ b/doc/guides/nics/nfb.rst
@@ -0,0 +1,143 @@ 
+..  SPDX-License-Identifier: BSD-3-Clause
+    Copyright 2015 - 2016 CESNET
+
+NFB poll mode driver library
+=================================
+
+The NFB poll mode driver library implements support for the Netcope
+FPGA Boards (**NFB-***), FPGA-based programmable NICs.
+The NFB PMD uses interface provided by the libnfb library to communicate
+with the NFB cards over the nfb layer.
+
+More information about the
+`NFB cards <http://www.netcope.com/en/products/fpga-boards>`_
+and used technology
+(`Netcope Development Kit <http://www.netcope.com/en/products/fpga-development-kit>`_)
+can be found on the `Netcope Technologies website <http://www.netcope.com/>`_.
+
+.. note::
+
+   This driver has external dependencies.
+   Therefore it is disabled in default configuration files.
+   It can be enabled by setting ``CONFIG_RTE_LIBRTE_PMD_NFB=y``
+   and recompiling.
+
+.. note::
+
+   Currently the driver is supported only on x86_64 architectures.
+   Only x86_64 versions of the external libraries are provided.
+
+Prerequisites
+-------------
+
+This PMD requires kernel modules which are responsible for initialization and
+allocation of resources needed for nfb layer function.
+Communication between PMD and kernel modules is mediated by libnfb library.
+These kernel modules and library are not part of DPDK and must be installed
+separately:
+
+*  **libnfb library**
+
+   The library provides API for initialization of nfb transfers, receiving and
+   transmitting data segments.
+
+*  **Kernel modules**
+
+   * nfb
+
+   Kernel modules manage initialization of hardware, allocation and
+   sharing of resources for user space applications.
+
+Dependencies can be found here:
+`Netcope common <https://www.netcope.com/en/company/community-support/dpdk-libsze2#NFB>`_.
+
+Versions of the packages
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+The minimum version of the provided packages:
+
+* for DPDK from 19.02
+
+Configuration
+-------------
+
+These configuration options can be modified before compilation in the
+``.config`` file:
+
+*  ``CONFIG_RTE_LIBRTE_PMD_NFB`` default value: **n**
+
+   Value **y** enables compilation of nfb PMD.
+
+Using the NFB PMD
+----------------------
+
+Kernel modules have to be loaded before running the DPDK application.
+
+NFB card architecture
+---------------------
+
+The NFB cards are multi-port multi-queue cards, where (generally) data from any
+Ethernet port may be sent to any queue.
+They are represented in DPDK as a single port.
+
+NFB-200G2QL card employs an addon cable which allows to connect it to two
+physical PCI-E slots at the same time (see the diagram below).
+This is done to allow 200 Gbps of traffic to be transferred through the PCI-E
+bus (note that a single PCI-E 3.0 x16 slot provides only 125 Gbps theoretical
+throughput).
+
+Although each slot may be connected to a different CPU and therefore to a different
+NUMA node, the card is represented as a single port in DPDK. To work with data
+from the individual queues on the right NUMA node, connection of NUMA nodes on
+first and last queue (each NUMA node has half of the queues) need to be checked.
+
+.. figure:: img/szedata2_nfb200g_architecture.svg
+    :align: center
+
+    NFB-200G2QL high-level diagram
+
+Limitations
+-----------
+
+Driver is usable only on Linux architecture.
+
+Since a card is always represented as a single port, but can be connected to two
+NUMA nodes, there is need for manual check where master/slave is connected.
+
+Example of usage
+----------------
+
+Read packets from 0. and 1. receive queue and write them to 0. and 1.
+transmit queue:
+
+.. code-block:: console
+
+   $RTE_TARGET/app/testpmd -l 0-3 -n 2 \
+   -- --port-topology=chained --rxq=2 --txq=2 --nb-cores=2 -i -a
+
+Example output:
+
+.. code-block:: console
+
+   [...]
+   EAL: PCI device 0000:06:00.0 on NUMA socket -1
+   EAL:   probe driver: 1b26:c1c1 net_nfb
+   PMD: Initializing NFB device (0000:06:00.0)
+   PMD: Available DMA queues RX: 8 TX: 8
+   PMD: NFB device (0000:06:00.0) successfully initialized
+   Interactive-mode selected
+   Auto-start selected
+   Configuring Port 0 (socket 0)
+   Port 0: 00:11:17:00:00:00
+   Checking link statuses...
+   Port 0 Link Up - speed 10000 Mbps - full-duplex
+   Done
+   Start automatic packet forwarding
+     io packet forwarding - CRC stripping disabled - packets/burst=32
+     nb forwarding cores=2 - nb forwarding ports=1
+     RX queues=2 - RX desc=128 - RX free threshold=0
+     RX threshold registers: pthresh=0 hthresh=0 wthresh=0
+     TX queues=2 - TX desc=512 - TX free threshold=0
+     TX threshold registers: pthresh=0 hthresh=0 wthresh=0
+     TX RS bit threshold=0 - TXQ flags=0x0
+   testpmd>
diff --git a/doc/guides/rel_notes/release_19_02.rst b/doc/guides/rel_notes/release_19_02.rst
index 3372c4d..3a59ac4 100644
--- a/doc/guides/rel_notes/release_19_02.rst
+++ b/doc/guides/rel_notes/release_19_02.rst
@@ -54,6 +54,11 @@  New Features
      Also, make sure to start the actual text at the margin.
      =========================================================
 
+* **Added NFB net PMD.**
+
+  Added the new ``nfb`` net driver for Netcope NFB cards. See
+  the :doc:`../nics/nfb` NIC guide for more details on this new driver.
+
 * **Added support to free hugepages exactly as originally allocated.**
 
   Some applications using memory event callbacks (especially for managing
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 670d7f7..013c551 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -38,6 +38,7 @@  DIRS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5
 DIRS-$(CONFIG_RTE_LIBRTE_MVNETA_PMD) += mvneta
 DIRS-$(CONFIG_RTE_LIBRTE_MVPP2_PMD) += mvpp2
 DIRS-$(CONFIG_RTE_LIBRTE_NETVSC_PMD) += netvsc
+DIRS-$(CONFIG_RTE_LIBRTE_PMD_NFB) += nfb
 DIRS-$(CONFIG_RTE_LIBRTE_NFP_PMD) += nfp
 DIRS-$(CONFIG_RTE_LIBRTE_BNXT_PMD) += bnxt
 DIRS-$(CONFIG_RTE_LIBRTE_PMD_NULL) += null
diff --git a/drivers/net/meson.build b/drivers/net/meson.build
index 45da3bb..6733a19 100644
--- a/drivers/net/meson.build
+++ b/drivers/net/meson.build
@@ -27,6 +27,7 @@  drivers = ['af_packet',
 	'mvneta',
 	'mvpp2',
 	'netvsc',
+	'nfb',
 	'nfp',
 	'null', 'octeontx', 'pcap', 'qede', 'ring',
 	'sfc',
diff --git a/drivers/net/nfb/Makefile b/drivers/net/nfb/Makefile
new file mode 100644
index 0000000..ee8c7df
--- /dev/null
+++ b/drivers/net/nfb/Makefile
@@ -0,0 +1,41 @@ 
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2018 Cesnet
+# Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+# All rights reserved.
+
+include $(RTE_SDK)/mk/rte.vars.mk
+
+#
+# library name
+#
+LIB = librte_pmd_nfb.a
+
+INCLUDES :=-I$(SRCDIR)
+
+
+CFLAGS += -O3
+CFLAGS += $(WERROR_FLAGS)
+LDLIBS += -lnfb
+LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
+LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs
+LDLIBS += -lrte_bus_pci
+
+EXPORT_MAP := rte_pmd_nfb_version.map
+
+LIBABIVER := 1
+
+#
+# all source are stored in SRCS-y
+#
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_NFB) += nfb_ethdev.c
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_NFB) += nfb_rx.c
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_NFB) += nfb_tx.c
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_NFB) += nfb_stats.c
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_NFB) += nfb_rxmode.c
+
+#
+# Export include files
+#
+SYMLINK-y-include +=
+
+include $(RTE_SDK)/mk/rte.lib.mk
diff --git a/drivers/net/nfb/meson.build b/drivers/net/nfb/meson.build
new file mode 100644
index 0000000..d7dccba
--- /dev/null
+++ b/drivers/net/nfb/meson.build
@@ -0,0 +1,9 @@ 
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2018 Cesnet
+# Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+# All rights reserved.
+
+dep = cc.find_library('nfb', required: true)
+build = dep.found()
+ext_deps += dep
+sources = files('nfb_rx.c', 'nfb_tx.c', 'nfb_stats.c', 'nfb_ethdev.c', 'nfb_rxmode.c')
diff --git a/drivers/net/nfb/nfb.h b/drivers/net/nfb/nfb.h
new file mode 100644
index 0000000..42671a1
--- /dev/null
+++ b/drivers/net/nfb/nfb.h
@@ -0,0 +1,50 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#ifndef _NFB_H_
+#define _NFB_H_
+
+#include <nfb/nfb.h>
+#include <nfb/ndp.h>
+#include <netcope/rxmac.h>
+#include <netcope/txmac.h>
+
+#include "nfb_rx.h"
+#include "nfb_tx.h"
+
+/* PCI Vendor ID */
+#define PCI_VENDOR_ID_NETCOPE 0x1b26
+
+/* PCI Device IDs */
+#define PCI_DEVICE_ID_NFB_40G2  0xcb80
+#define PCI_DEVICE_ID_NFB_100G2 0xc2c1
+#define PCI_DEVICE_ID_NFB_200G2QL 0xc250
+
+/* Max index of ndp rx/tx queues */
+#define RTE_ETH_NDP_MAX_RX_QUEUES 32
+#define RTE_ETH_NDP_MAX_TX_QUEUES 32
+
+/* Max index of rx/tx dmas */
+#define RTE_MAX_NC_RXMAC 256
+#define RTE_MAX_NC_TXMAC 256
+
+#define RTE_NFB_DRIVER_NAME net_nfb
+
+struct pmd_internals {
+	uint16_t         max_rxmac;
+	uint16_t         max_txmac;
+	struct nc_rxmac *rxmac[RTE_MAX_NC_RXMAC];
+	struct nc_txmac *txmac[RTE_MAX_NC_TXMAC];
+
+	char             nfb_dev[PATH_MAX];
+	struct nfb_device *nfb;
+	/* Place to remember if filter was promiscuous or filtering by table,
+	 * when disabling allmulticast
+	 */
+	enum nc_rxmac_mac_filter rx_filter_original;
+};
+
+#endif /* _NFB_H_ */
diff --git a/drivers/net/nfb/nfb_ethdev.c b/drivers/net/nfb/nfb_ethdev.c
new file mode 100644
index 0000000..ae259ed
--- /dev/null
+++ b/drivers/net/nfb/nfb_ethdev.c
@@ -0,0 +1,589 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#include <stdint.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <err.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+
+#include <nfb/nfb.h>
+#include <nfb/ndp.h>
+#include <netcope/rxmac.h>
+#include <netcope/txmac.h>
+
+#include <rte_mbuf.h>
+#include <rte_ethdev.h>
+#include <rte_ethdev_pci.h>
+#include <rte_malloc.h>
+#include <rte_memcpy.h>
+#include <rte_kvargs.h>
+#include <rte_dev.h>
+#include <rte_common.h>
+
+#include "nfb_stats.h"
+#include "nfb_rx.h"
+#include "nfb_tx.h"
+#include "nfb_rxmode.h"
+#include "nfb.h"
+
+/**
+ * Default MAC addr
+ */
+static struct ether_addr eth_addr = {
+	.addr_bytes = { 0x00, 0x11, 0x17, 0x00, 0x00, 0x00 }
+};
+
+/**
+ * Open all RX DMA queues
+ *
+ * @param dev
+ *   Pointer to nfb device.
+ * @param[out] rxmac
+ *   Pointer to output array of nc_rxmac
+ * @param[out] max_rxmac
+ *   Pointer to output max index of rxmac
+ */
+static void
+nfb_nc_rxmac_init(struct nfb_device *nfb,
+	struct nc_rxmac *rxmac[RTE_MAX_NC_RXMAC],
+	uint16_t *max_rxmac)
+{
+	*max_rxmac = 0;
+	while ((rxmac[*max_rxmac] = nc_rxmac_open_index(nfb, *max_rxmac)))
+		++(*max_rxmac);
+}
+
+/**
+ * Open all TX DMA queues
+ *
+ * @param dev
+ *   Pointer to nfb device.
+ * @param[out] txmac
+ *   Pointer to output array of nc_txmac
+ * @param[out] max_rxmac
+ *   Pointer to output max index of txmac
+ */
+static void
+nfb_nc_txmac_init(struct nfb_device *nfb,
+	struct nc_txmac *txmac[RTE_MAX_NC_TXMAC],
+	uint16_t *max_txmac)
+{
+	*max_txmac = 0;
+	while ((txmac[*max_txmac] = nc_txmac_open_index(nfb, *max_txmac)))
+		++(*max_txmac);
+}
+
+/**
+ * Close all RX DMA queues
+ *
+ * @param rxmac
+ *   Pointer to array of nc_rxmac
+ * @param max_rxmac
+ *   Maximum index of rxmac
+ */
+static void
+nfb_nc_rxmac_deinit(struct nc_rxmac *rxmac[RTE_MAX_NC_RXMAC],
+	uint16_t max_rxmac)
+{
+	for (; max_rxmac > 0; --max_rxmac) {
+		nc_rxmac_close(rxmac[max_rxmac]);
+		rxmac[max_rxmac] = NULL;
+	}
+}
+
+/**
+ * Close all TX DMA queues
+ *
+ * @param txmac
+ *   Pointer to array of nc_txmac
+ * @param max_txmac
+ *   Maximum index of txmac
+ */
+static void
+nfb_nc_txmac_deinit(struct nc_txmac *txmac[RTE_MAX_NC_TXMAC],
+	uint16_t max_txmac)
+{
+	for (; max_txmac > 0; --max_txmac) {
+		nc_txmac_close(txmac[max_txmac]);
+		txmac[max_txmac] = NULL;
+	}
+}
+
+/**
+ * DPDK callback to start the device.
+ *
+ * Start device by starting all configured queues.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int
+nfb_eth_dev_start(struct rte_eth_dev *dev)
+{
+	int ret;
+	uint16_t i;
+	uint16_t nb_rx = dev->data->nb_rx_queues;
+	uint16_t nb_tx = dev->data->nb_tx_queues;
+
+	for (i = 0; i < nb_rx; i++) {
+		ret = nfb_eth_rx_queue_start(dev, i);
+		if (ret != 0)
+			goto err_rx;
+	}
+
+	for (i = 0; i < nb_tx; i++) {
+		ret = nfb_eth_tx_queue_start(dev, i);
+		if (ret != 0)
+			goto err_tx;
+	}
+
+	return 0;
+
+err_tx:
+	for (i = 0; i < nb_tx; i++)
+		nfb_eth_tx_queue_stop(dev, i);
+err_rx:
+	for (i = 0; i < nb_rx; i++)
+		nfb_eth_rx_queue_stop(dev, i);
+	return ret;
+}
+
+/**
+ * DPDK callback to stop the device.
+ *
+ * Stop device by stopping all configured queues.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ */
+static void
+nfb_eth_dev_stop(struct rte_eth_dev *dev)
+{
+	uint16_t i;
+	uint16_t nb_rx = dev->data->nb_rx_queues;
+	uint16_t nb_tx = dev->data->nb_tx_queues;
+
+	for (i = 0; i < nb_tx; i++)
+		nfb_eth_tx_queue_stop(dev, i);
+
+	for (i = 0; i < nb_rx; i++)
+		nfb_eth_rx_queue_stop(dev, i);
+}
+
+/**
+ * DPDK callback for Ethernet device configuration.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int
+nfb_eth_dev_configure(struct rte_eth_dev *dev __rte_unused)
+{
+	return 0;
+}
+
+/**
+ * DPDK callback to get information about the device.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param[out] info
+ *   Info structure output buffer.
+ */
+static void
+nfb_eth_dev_info(struct rte_eth_dev *dev,
+	struct rte_eth_dev_info *dev_info)
+{
+	dev_info->max_mac_addrs = 1;
+	dev_info->max_rx_pktlen = (uint32_t)-1;
+	dev_info->max_rx_queues = dev->data->nb_rx_queues;
+	dev_info->max_tx_queues = dev->data->nb_tx_queues;
+	dev_info->speed_capa = ETH_LINK_SPEED_100G;
+}
+
+/**
+ * DPDK callback to close the device.
+ *
+ * Destroy all queues and objects, free memory.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ */
+static void
+nfb_eth_dev_close(struct rte_eth_dev *dev)
+{
+	uint16_t i;
+	uint16_t nb_rx = dev->data->nb_rx_queues;
+	uint16_t nb_tx = dev->data->nb_tx_queues;
+
+	nfb_eth_dev_stop(dev);
+
+	for (i = 0; i < nb_rx; i++) {
+		nfb_eth_rx_queue_release(dev->data->rx_queues[i]);
+		dev->data->rx_queues[i] = NULL;
+	}
+	dev->data->nb_rx_queues = 0;
+	for (i = 0; i < nb_tx; i++) {
+		nfb_eth_tx_queue_release(dev->data->tx_queues[i]);
+		dev->data->tx_queues[i] = NULL;
+	}
+	dev->data->nb_tx_queues = 0;
+}
+
+/**
+ * DPDK callback to retrieve physical link information.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param[out] link
+ *   Storage for current link status.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int
+nfb_eth_link_update(struct rte_eth_dev *dev,
+	int wait_to_complete __rte_unused)
+{
+	uint16_t i;
+	struct nc_rxmac_status status;
+	struct rte_eth_link link;
+	memset(&link, 0, sizeof(link));
+
+	struct pmd_internals *internals = dev->data->dev_private;
+
+	status.speed = MAC_SPEED_UNKNOWN;
+
+	link.link_speed = ETH_SPEED_NUM_NONE;
+	link.link_status = ETH_LINK_DOWN;
+	link.link_duplex = ETH_LINK_FULL_DUPLEX;
+	link.link_autoneg = ETH_LINK_SPEED_FIXED;
+
+	if (internals->rxmac[0] != NULL) {
+		nc_rxmac_read_status(internals->rxmac[0], &status);
+
+		switch (status.speed) {
+		case MAC_SPEED_10G:
+			link.link_speed = ETH_SPEED_NUM_10G;
+			break;
+		case MAC_SPEED_40G:
+			link.link_speed = ETH_SPEED_NUM_40G;
+			break;
+		case MAC_SPEED_100G:
+			link.link_speed = ETH_SPEED_NUM_100G;
+			break;
+		default:
+			link.link_speed = ETH_SPEED_NUM_NONE;
+			break;
+		}
+	}
+
+	for (i = 0; i < internals->max_rxmac; ++i) {
+		nc_rxmac_read_status(internals->rxmac[i], &status);
+
+		if (status.enabled && status.link_up) {
+			link.link_status = ETH_LINK_UP;
+			break;
+		}
+	}
+
+	rte_eth_linkstatus_set(dev, &link);
+
+	return 0;
+}
+
+/**
+ * DPDK callback to bring the link UP.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int
+nfb_eth_dev_set_link_up(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = (struct pmd_internals *)
+		dev->data->dev_private;
+
+	uint16_t i;
+	for (i = 0; i < internals->max_rxmac; ++i)
+		nc_rxmac_enable(internals->rxmac[i]);
+
+	for (i = 0; i < internals->max_txmac; ++i)
+		nc_txmac_enable(internals->txmac[i]);
+
+	return 0;
+}
+
+/**
+ * DPDK callback to bring the link DOWN.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int
+nfb_eth_dev_set_link_down(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = (struct pmd_internals *)
+		dev->data->dev_private;
+
+	uint16_t i;
+	for (i = 0; i < internals->max_rxmac; ++i)
+		nc_rxmac_disable(internals->rxmac[i]);
+
+	for (i = 0; i < internals->max_txmac; ++i)
+		nc_txmac_disable(internals->txmac[i]);
+
+	return 0;
+}
+
+/**
+ * DPDK callback to set primary MAC address.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param mac_addr
+ *   MAC address to register.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int
+nfb_eth_mac_addr_set(struct rte_eth_dev *dev,
+	struct ether_addr *mac_addr)
+{
+	unsigned i;
+	unsigned long long mac = 0;
+	struct rte_eth_dev_data *data = dev->data;
+	struct pmd_internals *internals = (struct pmd_internals *)
+		data->dev_private;
+
+	if (!is_valid_assigned_ether_addr(mac_addr)){
+		return -EINVAL;;
+	}
+
+	for (i = 0; i < 6; i++) {
+		mac <<= 8;
+		mac |= mac_addr->addr_bytes[i] & 0xFF;
+	}
+
+	for (i = 0; i < internals->max_rxmac; ++i)
+		nc_rxmac_set_mac(internals->rxmac[i], 0, mac, 1);
+
+	ether_addr_copy(mac_addr, data->mac_addrs);
+	return 0;
+}
+
+static const struct eth_dev_ops ops = {
+	.dev_start = nfb_eth_dev_start,
+	.dev_stop = nfb_eth_dev_stop,
+	.dev_set_link_up = nfb_eth_dev_set_link_up,
+	.dev_set_link_down = nfb_eth_dev_set_link_down,
+	.dev_close = nfb_eth_dev_close,
+	.dev_configure = nfb_eth_dev_configure,
+	.dev_infos_get = nfb_eth_dev_info,
+	.promiscuous_enable = nfb_eth_promiscuous_enable,
+	.promiscuous_disable = nfb_eth_promiscuous_disable,
+	.allmulticast_enable = nfb_eth_allmulticast_enable,
+	.allmulticast_disable = nfb_eth_allmulticast_disable,
+	.rx_queue_start = nfb_eth_rx_queue_start,
+	.rx_queue_stop = nfb_eth_rx_queue_stop,
+	.tx_queue_start = nfb_eth_tx_queue_start,
+	.tx_queue_stop = nfb_eth_tx_queue_stop,
+	.rx_queue_setup = nfb_eth_rx_queue_setup,
+	.tx_queue_setup = nfb_eth_tx_queue_setup,
+	.rx_queue_release = nfb_eth_rx_queue_release,
+	.tx_queue_release = nfb_eth_tx_queue_release,
+	.link_update = nfb_eth_link_update,
+	.stats_get = nfb_eth_stats_get,
+	.stats_reset = nfb_eth_stats_reset,
+	.mac_addr_set = nfb_eth_mac_addr_set,
+};
+
+/**
+ * DPDK callback to initialize an ethernet device
+ *
+ * @param dev
+ *   Pointer to ethernet device structure
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int
+nfb_eth_dev_init(struct rte_eth_dev *dev)
+{
+	struct rte_eth_dev_data *data = dev->data;
+	struct pmd_internals *internals = (struct pmd_internals *)
+		data->dev_private;
+	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
+	struct rte_pci_addr *pci_addr = &pci_dev->addr;
+
+	RTE_LOG(INFO, PMD, "Initializing NFB device (" PCI_PRI_FMT ")\n",
+		pci_addr->domain, pci_addr->bus, pci_addr->devid,
+		pci_addr->function);
+
+	snprintf(internals->nfb_dev, PATH_MAX,
+		"/dev/nfb/by-pci-slot/" PCI_PRI_FMT,
+		pci_addr->domain, pci_addr->bus, pci_addr->devid,
+		pci_addr->function);
+
+	/*
+	 * Get number of available DMA RX and TX queues, which is maximum
+	 * number of queues that can be created and store it in private device
+	 * data structure.
+	 */
+	internals->nfb = nfb_open(internals->nfb_dev);
+	if (internals->nfb == NULL) {
+		RTE_LOG(ERR, PMD, "nfb_open(): failed to open %s",
+			internals->nfb_dev);
+		return -EINVAL;
+	}
+	data->nb_rx_queues = ndp_get_rx_queue_available_count(internals->nfb);
+	data->nb_tx_queues = ndp_get_tx_queue_available_count(internals->nfb);
+
+	RTE_LOG(INFO, PMD, "Available NDP queues RX: %u TX: %u\n",
+		data->nb_rx_queues, data->nb_tx_queues);
+
+	nfb_nc_rxmac_init(internals->nfb,
+		internals->rxmac,
+		&internals->max_rxmac);
+	nfb_nc_txmac_init(internals->nfb,
+		internals->txmac,
+		&internals->max_txmac);
+
+	/* Set rx, tx burst functions */
+	dev->rx_pkt_burst = nfb_eth_ndp_rx;
+	dev->tx_pkt_burst = nfb_eth_ndp_tx;
+
+	/* Set function callbacks for Ethernet API */
+	dev->dev_ops = &ops;
+
+	/* Get link state */
+	nfb_eth_link_update(dev, 0);
+
+	/* Allocate space for one mac address */
+	data->mac_addrs = rte_zmalloc(data->name, sizeof(struct ether_addr),
+		RTE_CACHE_LINE_SIZE);
+	if (data->mac_addrs == NULL) {
+		RTE_LOG(ERR, PMD, "Could not alloc space for MAC address!\n");
+		nfb_close(internals->nfb);
+		return -EINVAL;
+	}
+
+	nfb_eth_mac_addr_set(dev, &eth_addr);
+
+	data->promiscuous = nfb_eth_promiscuous_get(dev);
+	data->all_multicast = nfb_eth_allmulticast_get(dev);
+	internals->rx_filter_original = data->promiscuous;
+
+	RTE_LOG(INFO, PMD, "NFB device ("
+		PCI_PRI_FMT ") successfully initialized\n",
+		pci_addr->domain, pci_addr->bus, pci_addr->devid,
+		pci_addr->function);
+
+	return 0;
+}
+
+/**
+ * DPDK callback to uninitialize an ethernet device
+ *
+ * @param dev
+ *   Pointer to ethernet device structure
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int
+nfb_eth_dev_uninit(struct rte_eth_dev *dev)
+{
+	struct rte_eth_dev_data *data = dev->data;
+	struct pmd_internals *internals = (struct pmd_internals *)
+		data->dev_private;
+
+	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
+	struct rte_pci_addr *pci_addr = &pci_dev->addr;
+
+	dev->data->mac_addrs = NULL;
+
+	nfb_nc_rxmac_deinit(internals->rxmac, internals->max_rxmac);
+	nfb_nc_txmac_deinit(internals->txmac, internals->max_txmac);
+
+	RTE_LOG(INFO, PMD, "NFB device ("
+		PCI_PRI_FMT ") successfully uninitialized\n",
+		pci_addr->domain, pci_addr->bus, pci_addr->devid,
+		pci_addr->function);
+
+	return 0;
+}
+
+static const struct rte_pci_id nfb_pci_id_table[] = {
+	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_NETCOPE, PCI_DEVICE_ID_NFB_40G2) },
+	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_NETCOPE, PCI_DEVICE_ID_NFB_100G2) },
+	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_NETCOPE, PCI_DEVICE_ID_NFB_200G2QL) },
+	{ .vendor_id = 0, }
+};
+
+/**
+ * DPDK callback to register a PCI device.
+ *
+ * This function spawns Ethernet devices out of a given PCI device.
+ *
+ * @param[in] pci_drv
+ *   PCI driver structure (nfb_driver).
+ * @param[in] pci_dev
+ *   PCI device information.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int nfb_eth_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
+	struct rte_pci_device *pci_dev)
+{
+	return rte_eth_dev_pci_generic_probe(pci_dev,
+		sizeof(struct pmd_internals), nfb_eth_dev_init);
+}
+
+/**
+ * DPDK callback to remove a PCI device.
+ *
+ * This function removes all Ethernet devices belong to a given PCI device.
+ *
+ * @param[in] pci_dev
+ *   Pointer to the PCI device.
+ *
+ * @return
+ *   0 on success, the function cannot fail.
+ */
+static int nfb_eth_pci_remove(struct rte_pci_device *pci_dev)
+{
+	return rte_eth_dev_pci_generic_remove(pci_dev, nfb_eth_dev_uninit);
+}
+
+static struct rte_pci_driver nfb_eth_driver = {
+	.id_table = nfb_pci_id_table,
+	.probe = nfb_eth_pci_probe,
+	.remove = nfb_eth_pci_remove,
+};
+
+RTE_PMD_REGISTER_PCI(RTE_NFB_DRIVER_NAME, nfb_eth_driver);
+RTE_PMD_REGISTER_PCI_TABLE(RTE_NFB_DRIVER_NAME, nfb_pci_id_table);
+RTE_PMD_REGISTER_KMOD_DEP(RTE_NFB_DRIVER_NAME, "* nfb");
diff --git a/drivers/net/nfb/nfb_rx.c b/drivers/net/nfb/nfb_rx.c
new file mode 100644
index 0000000..fbad6e5
--- /dev/null
+++ b/drivers/net/nfb/nfb_rx.c
@@ -0,0 +1,127 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#include "nfb_rx.h"
+#include "nfb.h"
+
+int
+nfb_eth_rx_queue_start(struct rte_eth_dev *dev, uint16_t rxq_id)
+{
+	struct ndp_rx_queue *rxq = dev->data->rx_queues[rxq_id];
+	int ret;
+
+	if (rxq->queue == NULL) {
+		RTE_LOG(ERR, PMD, "RX NDP queue is NULL!\n");
+		return -EINVAL;
+	}
+
+	ret = ndp_queue_start(rxq->queue);
+	if (ret != 0)
+		goto err;
+	dev->data->rx_queue_state[rxq_id] = RTE_ETH_QUEUE_STATE_STARTED;
+	return 0;
+
+err:
+	return -EINVAL;
+}
+
+int
+nfb_eth_rx_queue_stop(struct rte_eth_dev *dev, uint16_t rxq_id)
+{
+	struct ndp_rx_queue *rxq = dev->data->rx_queues[rxq_id];
+	int ret;
+
+	if (rxq->queue == NULL) {
+		RTE_LOG(ERR, PMD, "RX NDP queue is NULL!\n");
+		return -EINVAL;
+	}
+
+	ret = ndp_queue_stop(rxq->queue);
+	if (ret != 0)
+		return -EINVAL;
+
+	dev->data->rx_queue_state[rxq_id] = RTE_ETH_QUEUE_STATE_STOPPED;
+	return 0;
+}
+
+int
+nfb_eth_rx_queue_setup(struct rte_eth_dev *dev,
+		uint16_t rx_queue_id,
+		uint16_t nb_rx_desc __rte_unused,
+		unsigned int socket_id,
+		const struct rte_eth_rxconf *rx_conf __rte_unused,
+		struct rte_mempool *mb_pool)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+
+	struct ndp_rx_queue *rxq;
+	int ret;
+
+	rxq = rte_zmalloc_socket("ndp rx queue",
+			sizeof(struct ndp_rx_queue),
+			RTE_CACHE_LINE_SIZE, socket_id);
+
+	if (rxq == NULL) {
+		RTE_LOG(ERR, PMD, "rte_zmalloc_socket() failed for rx queue id "
+				"%" PRIu16 "!\n", rx_queue_id);
+		return -ENOMEM;
+	}
+
+	ret = nfb_eth_rx_queue_init(internals->nfb,
+		rx_queue_id,
+		dev->data->port_id,
+		mb_pool,
+		rxq);
+
+	if (ret == 0)
+		dev->data->rx_queues[rx_queue_id] = rxq;
+	else
+		rte_free(rxq);
+
+	return ret;
+}
+
+int
+nfb_eth_rx_queue_init(struct nfb_device *nfb,
+		uint16_t rx_queue_id,
+		uint16_t port_id,
+		struct rte_mempool *mb_pool,
+		struct ndp_rx_queue *rxq)
+{
+	if (nfb == NULL)
+		return -EINVAL;
+
+	rxq->queue = ndp_open_rx_queue(nfb, rx_queue_id);
+	if (rxq->queue == NULL)
+		return -EINVAL;
+
+	rxq->nfb = nfb;
+	rxq->rx_queue_id = rx_queue_id;
+	rxq->in_port = port_id;
+	rxq->mb_pool = mb_pool;
+
+	const struct rte_pktmbuf_pool_private *mbp_priv =
+		rte_mempool_get_priv(mb_pool);
+	rxq->buf_size = (uint16_t)(mbp_priv->mbuf_data_room_size -
+		RTE_PKTMBUF_HEADROOM);
+
+	rxq->rx_pkts = 0;
+	rxq->rx_bytes = 0;
+	rxq->err_pkts = 0;
+
+	return 0;
+}
+
+void
+nfb_eth_rx_queue_release(void *q)
+{
+	struct ndp_rx_queue *rxq = (struct ndp_rx_queue *)q;
+	if (rxq->queue != NULL) {
+		ndp_close_rx_queue(rxq->queue);
+		rte_free(rxq);
+		rxq->queue = NULL;
+	}
+}
diff --git a/drivers/net/nfb/nfb_rx.h b/drivers/net/nfb/nfb_rx.h
new file mode 100644
index 0000000..7d2dbd4
--- /dev/null
+++ b/drivers/net/nfb/nfb_rx.h
@@ -0,0 +1,213 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#ifndef _NFB_RX_H_
+#define _NFB_RX_H_
+
+#include <stdint.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <err.h>
+#include <sys/types.h>
+
+#include <sys/mman.h>
+
+#include <nfb/nfb.h>
+#include <nfb/ndp.h>
+
+#include <rte_mbuf.h>
+#include <rte_ethdev.h>
+#include <rte_malloc.h>
+#include <rte_memcpy.h>
+#include <rte_dev.h>
+
+struct ndp_rx_queue {
+	struct nfb_device *nfb;	     /* nfb dev structure */
+	struct ndp_queue *queue;     /* rx queue */
+	uint16_t rx_queue_id;	     /* index */
+	uint8_t in_port;	     /* port */
+
+	struct rte_mempool *mb_pool; /* memory pool to allocate packets */
+	uint16_t buf_size;           /* mbuf size */
+
+	volatile uint64_t rx_pkts;   /* packets read */
+	volatile uint64_t rx_bytes;  /* bytes read */
+	volatile uint64_t err_pkts;  /* erroneous packets */
+};
+
+/**
+ * Initialize ndp_rx_queue structure
+ *
+ * @param nfb
+ *   Pointer to nfb device structure.
+ * @param rx_queue_id
+ *   RX queue index.
+ * @param port_id
+ *   Device [external] port identifier.
+ * @param mb_pool
+ *   Memory pool for buffer allocations.
+ * @param[out] rxq
+ *   Pointer to ndp_rx_queue output structure
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+int
+nfb_eth_rx_queue_init(struct nfb_device *nfb,
+	uint16_t rx_queue_id,
+	uint16_t port_id,
+	struct rte_mempool *mb_pool,
+	struct ndp_rx_queue *rxq);
+
+/**
+ * DPDK callback to setup a RX queue for use.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param idx
+ *   RX queue index.
+ * @param desc
+ *   Number of descriptors to configure in queue.
+ * @param socket
+ *   NUMA socket on which memory must be allocated.
+ * @param[in] conf
+ *   Thresholds parameters.
+ * @param mb_pool
+ *   Memory pool for buffer allocations.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+int
+nfb_eth_rx_queue_setup(struct rte_eth_dev *dev,
+	uint16_t rx_queue_id,
+	uint16_t nb_rx_desc __rte_unused,
+	unsigned int socket_id,
+	const struct rte_eth_rxconf *rx_conf __rte_unused,
+	struct rte_mempool *mb_pool);
+
+/**
+ * DPDK callback to release a RX queue.
+ *
+ * @param dpdk_rxq
+ *   Generic RX queue pointer.
+ */
+void
+nfb_eth_rx_queue_release(void *q);
+
+/**
+ * Start traffic on Rx queue.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param txq_id
+ *   RX queue index.
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+int
+nfb_eth_rx_queue_start(struct rte_eth_dev *dev, uint16_t rxq_id);
+
+/**
+ * Stop traffic on Rx queue.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param txq_id
+ *   RX queue index.
+ */
+int
+nfb_eth_rx_queue_stop(struct rte_eth_dev *dev, uint16_t rxq_id);
+
+/**
+ * DPDK callback for RX.
+ *
+ * @param dpdk_rxq
+ *   Generic pointer to RX queue structure.
+ * @param[out] bufs
+ *   Array to store received packets.
+ * @param nb_pkts
+ *   Maximum number of packets in array.
+ *
+ * @return
+ *   Number of packets successfully received (<= nb_pkts).
+ */
+static __rte_always_inline uint16_t
+nfb_eth_ndp_rx(void *queue,
+	struct rte_mbuf **bufs,
+	uint16_t nb_pkts)
+{
+	struct ndp_rx_queue *ndp = queue;
+	uint16_t packet_size;
+	uint64_t num_bytes = 0;
+	uint16_t num_rx;
+	unsigned int i;
+
+	const uint16_t buf_size = ndp->buf_size;
+
+	struct rte_mbuf *mbuf;
+	struct ndp_packet packets[nb_pkts];
+
+	struct rte_mbuf *mbufs[nb_pkts];
+
+	if (unlikely(ndp->queue == NULL || nb_pkts == 0)) {
+		RTE_LOG(ERR, PMD, "RX invalid arguments!\n");
+		return 0;
+	}
+
+	/* returns either all or nothing */
+	i = rte_pktmbuf_alloc_bulk(ndp->mb_pool, mbufs, nb_pkts);
+	if (unlikely(i != 0))
+		return 0;
+
+	num_rx = ndp_rx_burst_get(ndp->queue, packets, nb_pkts);
+
+	if (unlikely(num_rx != nb_pkts)) {
+		for (i = num_rx; i < nb_pkts; i++)
+			rte_pktmbuf_free(mbufs[i]);
+	}
+
+	nb_pkts = num_rx;
+
+	num_rx = 0;
+	/*
+	 * Reads the given number of packets from NDP queue given
+	 * by queue and copies the packet data into a newly allocated mbuf
+	 * to return.
+	 */
+	for (i = 0; i < nb_pkts; ++i) {
+		mbuf = mbufs[i];
+
+		/* get the space available for data in the mbuf */
+		packet_size = packets[i].data_length;
+
+		if (likely(packet_size <= buf_size)) {
+			/* NDP packet will fit in one mbuf, go ahead and copy */
+			rte_memcpy(rte_pktmbuf_mtod(mbuf, void *),
+				packets[i].data, packet_size);
+
+			mbuf->data_len = (uint16_t)packet_size;
+
+			mbuf->pkt_len = packet_size;
+			mbuf->port = ndp->in_port;
+			bufs[num_rx++] = mbuf;
+			num_bytes += packet_size;
+		} else {
+			/*
+			 * NDP packet will not fit in one mbuf,
+			 * scattered mode is not enabled, drop packet
+			 */
+			rte_pktmbuf_free(mbuf);
+		}
+	}
+
+	ndp_rx_burst_put(ndp->queue);
+
+	ndp->rx_pkts += num_rx;
+	ndp->rx_bytes += num_bytes;
+	return num_rx;
+}
+
+#endif /* _NFB_RX_H_ */
diff --git a/drivers/net/nfb/nfb_rxmode.c b/drivers/net/nfb/nfb_rxmode.c
new file mode 100644
index 0000000..e98ed07
--- /dev/null
+++ b/drivers/net/nfb/nfb_rxmode.c
@@ -0,0 +1,100 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#include "nfb_rxmode.h"
+#include "nfb.h"
+
+void
+nfb_eth_promiscuous_enable(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = (struct pmd_internals *)
+		dev->data->dev_private;
+	uint16_t i;
+
+	internals->rx_filter_original = RXMAC_MAC_FILTER_PROMISCUOUS;
+
+	for (i = 0; i < internals->max_rxmac; ++i) {
+		nc_rxmac_mac_filter_enable(internals->rxmac[i],
+			RXMAC_MAC_FILTER_PROMISCUOUS);
+	}
+}
+
+void
+nfb_eth_promiscuous_disable(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = (struct pmd_internals *)
+		dev->data->dev_private;
+	uint16_t i;
+
+	internals->rx_filter_original = RXMAC_MAC_FILTER_TABLE;
+
+	/* if promisc is not enabled, do nothing */
+	if (!nfb_eth_promiscuous_get(dev))
+		return;
+
+	for (i = 0; i < internals->max_rxmac; ++i) {
+		nc_rxmac_mac_filter_enable(internals->rxmac[i],
+			RXMAC_MAC_FILTER_TABLE);
+	}
+}
+
+int
+nfb_eth_promiscuous_get(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = (struct pmd_internals *)
+		dev->data->dev_private;
+
+	struct nc_rxmac_status status;
+	status.mac_filter = RXMAC_MAC_FILTER_PROMISCUOUS;
+
+	nc_rxmac_read_status(internals->rxmac[0], &status);
+
+	return (status.mac_filter == RXMAC_MAC_FILTER_PROMISCUOUS);
+}
+
+void
+nfb_eth_allmulticast_enable(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = (struct pmd_internals *)
+		dev->data->dev_private;
+
+	uint16_t i;
+	for (i = 0; i < internals->max_rxmac; ++i) {
+		nc_rxmac_mac_filter_enable(internals->rxmac[i],
+			RXMAC_MAC_FILTER_TABLE_BCAST_MCAST);
+	}
+}
+
+void
+nfb_eth_allmulticast_disable(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = (struct pmd_internals *)
+		dev->data->dev_private;
+
+	uint16_t i;
+
+	/* if multicast is not enabled do nothing */
+	if (!nfb_eth_allmulticast_get(dev))
+		return;
+
+	for (i = 0; i < internals->max_rxmac; ++i) {
+		nc_rxmac_mac_filter_enable(internals->rxmac[i],
+			internals->rx_filter_original);
+	}
+}
+
+int
+nfb_eth_allmulticast_get(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = (struct pmd_internals *)
+		dev->data->dev_private;
+
+	struct nc_rxmac_status status;
+	status.mac_filter = RXMAC_MAC_FILTER_PROMISCUOUS;
+	nc_rxmac_read_status(internals->rxmac[0], &status);
+
+	return (status.mac_filter == RXMAC_MAC_FILTER_TABLE_BCAST_MCAST);
+}
diff --git a/drivers/net/nfb/nfb_rxmode.h b/drivers/net/nfb/nfb_rxmode.h
new file mode 100644
index 0000000..e381b73
--- /dev/null
+++ b/drivers/net/nfb/nfb_rxmode.h
@@ -0,0 +1,78 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#ifndef _NFB_RXMODE_H_
+#define _NFB_RXMODE_H_
+
+#include <stdint.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <err.h>
+#include <sys/types.h>
+
+#include <sys/mman.h>
+
+#include <nfb/nfb.h>
+#include <nfb/ndp.h>
+
+#include <rte_ethdev.h>
+#include <rte_dev.h>
+
+/**
+ * Getter for promiscuous mode
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @return 1 if enabled 0 otherwise
+ */
+int
+nfb_eth_promiscuous_get(struct rte_eth_dev *dev);
+
+/**
+ * DPDK callback to enable promiscuous mode.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ */
+void
+nfb_eth_promiscuous_enable(struct rte_eth_dev *dev);
+
+/**
+ * DPDK callback to disable promiscuous mode.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ */
+void
+nfb_eth_promiscuous_disable(struct rte_eth_dev *dev);
+
+/**
+ * Getter for allmulticast mode
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @return 1 if enabled 0 otherwise
+ */
+int
+nfb_eth_allmulticast_get(struct rte_eth_dev *dev);
+
+/**
+ * DPDK callback to enable allmulticast mode.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ */
+void
+nfb_eth_allmulticast_enable(struct rte_eth_dev *dev);
+
+/**
+ * DPDK callback to disable allmulticast mode.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ */
+void
+nfb_eth_allmulticast_disable(struct rte_eth_dev *dev);
+
+#endif /* _NFB_RXMODE_H_ */
diff --git a/drivers/net/nfb/nfb_stats.c b/drivers/net/nfb/nfb_stats.c
new file mode 100644
index 0000000..ffc27a5
--- /dev/null
+++ b/drivers/net/nfb/nfb_stats.c
@@ -0,0 +1,78 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#include "nfb_stats.h"
+#include "nfb.h"
+
+int
+nfb_eth_stats_get(struct rte_eth_dev *dev,
+	struct rte_eth_stats *stats)
+{
+	uint16_t i;
+	uint16_t nb_rx = dev->data->nb_rx_queues;
+	uint16_t nb_tx = dev->data->nb_tx_queues;
+	uint64_t rx_total = 0;
+	uint64_t tx_total = 0;
+	uint64_t tx_err_total = 0;
+	uint64_t rx_total_bytes = 0;
+	uint64_t tx_total_bytes = 0;
+
+	struct ndp_rx_queue *rx_queue = *((struct ndp_rx_queue **)
+		dev->data->rx_queues);
+	struct ndp_tx_queue *tx_queue = *((struct ndp_tx_queue **)
+		dev->data->tx_queues);
+
+	for (i = 0; i < nb_rx; i++) {
+		if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) {
+			stats->q_ipackets[i] = rx_queue[i].rx_pkts;
+			stats->q_ibytes[i] = rx_queue[i].rx_bytes;
+		}
+		rx_total += stats->q_ipackets[i];
+		rx_total_bytes += stats->q_ibytes[i];
+	}
+
+	for (i = 0; i < nb_tx; i++) {
+		if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) {
+			stats->q_opackets[i] = tx_queue[i].tx_pkts;
+			stats->q_obytes[i] = tx_queue[i].tx_bytes;
+			stats->q_errors[i] = tx_queue[i].err_pkts;
+		}
+		tx_total += stats->q_opackets[i];
+		tx_total_bytes += stats->q_obytes[i];
+		tx_err_total += stats->q_errors[i];
+	}
+
+	stats->ipackets = rx_total;
+	stats->opackets = tx_total;
+	stats->ibytes = rx_total_bytes;
+	stats->obytes = tx_total_bytes;
+	stats->oerrors = tx_err_total;
+	return 0;
+}
+
+void
+nfb_eth_stats_reset(struct rte_eth_dev *dev)
+{
+	uint16_t i;
+	uint16_t nb_rx = dev->data->nb_rx_queues;
+	uint16_t nb_tx = dev->data->nb_tx_queues;
+
+	struct ndp_rx_queue *rx_queue = *((struct ndp_rx_queue **)
+		dev->data->rx_queues);
+	struct ndp_tx_queue *tx_queue = *((struct ndp_tx_queue **)
+		dev->data->tx_queues);
+
+	for (i = 0; i < nb_rx; i++) {
+		rx_queue[i].rx_pkts = 0;
+		rx_queue[i].rx_bytes = 0;
+		rx_queue[i].err_pkts = 0;
+	}
+	for (i = 0; i < nb_tx; i++) {
+		tx_queue[i].tx_pkts = 0;
+		tx_queue[i].tx_bytes = 0;
+		tx_queue[i].err_pkts = 0;
+	}
+}
diff --git a/drivers/net/nfb/nfb_stats.h b/drivers/net/nfb/nfb_stats.h
new file mode 100644
index 0000000..ce0591a
--- /dev/null
+++ b/drivers/net/nfb/nfb_stats.h
@@ -0,0 +1,48 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#ifndef _NFB_STATS_H_
+#define _NFB_STATS_H_
+
+#include <stdint.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <err.h>
+#include <sys/types.h>
+
+#include <sys/mman.h>
+
+#include <nfb/nfb.h>
+#include <nfb/ndp.h>
+
+#include <rte_mbuf.h>
+#include <rte_ethdev.h>
+#include <rte_malloc.h>
+#include <rte_memcpy.h>
+#include <rte_dev.h>
+
+/**
+ * DPDK callback to get device statistics.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param[out] stats
+ *   Stats structure output buffer.
+ *
+ * @return
+ *   0 on success and stats is filled, negative errno value otherwise.
+ */
+int nfb_eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats);
+
+/**
+ * DPDK callback to clear device statistics.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ */
+void nfb_eth_stats_reset(struct rte_eth_dev *dev);
+
+#endif /* _NFB_STATS_H_ */
diff --git a/drivers/net/nfb/nfb_tx.c b/drivers/net/nfb/nfb_tx.c
new file mode 100644
index 0000000..1a4542f
--- /dev/null
+++ b/drivers/net/nfb/nfb_tx.c
@@ -0,0 +1,113 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#include "nfb_tx.h"
+#include "nfb.h"
+
+int
+nfb_eth_tx_queue_start(struct rte_eth_dev *dev, uint16_t txq_id)
+{
+	struct ndp_tx_queue *txq = dev->data->tx_queues[txq_id];
+	int ret;
+
+	if (txq->queue == NULL) {
+		RTE_LOG(ERR, PMD, "RX NDP queue is NULL!\n");
+		return -EINVAL;
+	}
+
+	ret = ndp_queue_start(txq->queue);
+	if (ret != 0)
+		goto err;
+	dev->data->tx_queue_state[txq_id] = RTE_ETH_QUEUE_STATE_STARTED;
+	return 0;
+
+err:
+	return -EINVAL;
+}
+
+int
+nfb_eth_tx_queue_stop(struct rte_eth_dev *dev, uint16_t txq_id)
+{
+	struct ndp_tx_queue *txq = dev->data->tx_queues[txq_id];
+	int ret;
+
+	if (txq->queue == NULL) {
+		RTE_LOG(ERR, PMD, "TX NDP queue is NULL!\n");
+		return -EINVAL;
+	}
+
+	ret = ndp_queue_stop(txq->queue);
+	if (ret != 0)
+		return -EINVAL;
+	dev->data->tx_queue_state[txq_id] = RTE_ETH_QUEUE_STATE_STOPPED;
+	return 0;
+}
+
+int
+nfb_eth_tx_queue_setup(struct rte_eth_dev *dev,
+	uint16_t tx_queue_id,
+	uint16_t nb_tx_desc __rte_unused,
+	unsigned int socket_id,
+	const struct rte_eth_txconf *tx_conf __rte_unused)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+	int ret;
+	struct ndp_tx_queue *txq;
+
+	txq = rte_zmalloc_socket("ndp tx queue",
+		sizeof(struct ndp_tx_queue),
+		RTE_CACHE_LINE_SIZE, socket_id);
+
+	if (txq == NULL) {
+		RTE_LOG(ERR, PMD, "rte_zmalloc_socket() failed for tx queue id "
+			"%" PRIu16 "!\n", tx_queue_id);
+		return -ENOMEM;
+	}
+
+	ret = nfb_eth_tx_queue_init(internals->nfb,
+		tx_queue_id,
+		txq);
+
+	if (ret == 0)
+		dev->data->tx_queues[tx_queue_id] = txq;
+	else
+		rte_free(txq);
+
+	return ret;
+}
+
+int
+nfb_eth_tx_queue_init(struct nfb_device *nfb,
+	uint16_t tx_queue_id,
+	struct ndp_tx_queue *txq)
+{
+	if (nfb == NULL)
+		return -EINVAL;
+
+	txq->queue = ndp_open_tx_queue(nfb, tx_queue_id);
+	if (txq->queue == NULL)
+		return -EINVAL;
+
+	txq->nfb = nfb;
+	txq->tx_queue_id = tx_queue_id;
+
+	txq->tx_pkts = 0;
+	txq->tx_bytes = 0;
+	txq->err_pkts = 0;
+
+	return 0;
+}
+
+void
+nfb_eth_tx_queue_release(void *q)
+{
+	struct ndp_tx_queue *txq = (struct ndp_tx_queue *)q;
+	if (txq->queue != NULL) {
+		ndp_close_tx_queue(txq->queue);
+		rte_free(txq);
+		txq->queue = NULL;
+	}
+}
diff --git a/drivers/net/nfb/nfb_tx.h b/drivers/net/nfb/nfb_tx.h
new file mode 100644
index 0000000..b17f776
--- /dev/null
+++ b/drivers/net/nfb/nfb_tx.h
@@ -0,0 +1,204 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Cesnet
+ * Copyright(c) 2018 Netcope Technologies, a.s. <info@netcope.com>
+ * All rights reserved.
+ */
+
+#ifndef _NFB_TX_H_
+#define _NFB_TX_H_
+
+#include <stdint.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <err.h>
+#include <sys/types.h>
+
+#include <sys/mman.h>
+
+#include <nfb/nfb.h>
+#include <nfb/ndp.h>
+
+#include <rte_mbuf.h>
+#include <rte_ethdev.h>
+#include <rte_malloc.h>
+#include <rte_memcpy.h>
+#include <rte_dev.h>
+
+struct ndp_tx_queue {
+	struct nfb_device *nfb;     /* nfb dev structure */
+	struct ndp_queue *queue;    /* tx queue */
+	uint16_t          tx_queue_id;       /* index */
+	volatile uint64_t tx_pkts;  /* packets transmitted */
+	volatile uint64_t tx_bytes; /* bytes transmitted */
+	volatile uint64_t err_pkts; /* erroneous packets */
+};
+
+/**
+ * DPDK callback to setup a TX queue for use.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param idx
+ *   RX queue index.
+ * @param desc
+ *   Number of descriptors to configure in queue.
+ * @param socket
+ *   NUMA socket on which memory must be allocated.
+ * @param[in] conf
+ *   Thresholds parameters.
+ * @param mp
+ *   Memory pool for buffer allocations.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+int
+nfb_eth_tx_queue_setup(struct rte_eth_dev *dev,
+	uint16_t tx_queue_id,
+	uint16_t nb_tx_desc __rte_unused,
+	unsigned int socket_id,
+	const struct rte_eth_txconf *tx_conf __rte_unused);
+
+/**
+ * Initialize ndp_tx_queue structure
+ *
+ * @param nfb
+ *   Pointer to nfb device structure.
+ * @param tx_queue_id
+ *   TX queue index.
+ * @param[out] txq
+ *   Pointer to ndp_tx_queue output structure
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+int
+nfb_eth_tx_queue_init(struct nfb_device *nfb,
+	uint16_t tx_queue_id,
+	struct ndp_tx_queue *txq);
+
+/**
+ * DPDK callback to release a RX queue.
+ *
+ * @param dpdk_rxq
+ *   Generic RX queue pointer.
+ */
+void
+nfb_eth_tx_queue_release(void *q);
+
+/**
+ * Start traffic on Tx queue.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param txq_id
+ *   TX queue index.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+int
+nfb_eth_tx_queue_start(struct rte_eth_dev *dev, uint16_t txq_id);
+
+/**
+ * Stop traffic on Tx queue.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param txq_id
+ *   TX queue index.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+int
+nfb_eth_tx_queue_stop(struct rte_eth_dev *dev, uint16_t txq_id);
+
+/**
+ * DPDK callback for TX.
+ *
+ * @param dpdk_txq
+ *   Generic pointer to TX queue structure.
+ * @param bufs
+ *   Packets to transmit.
+ * @param nb_pkts
+ *   Number of packets in array.
+ *
+ * @return
+ *   Number of packets successfully transmitted (<= nb_pkts).
+ */
+static __rte_always_inline uint16_t
+nfb_eth_ndp_tx(void *queue,
+	struct rte_mbuf **bufs,
+	uint16_t nb_pkts)
+{
+	int i;
+	struct rte_mbuf *mbuf;
+	struct ndp_tx_queue *ndp = queue;
+	uint16_t num_tx = 0;
+	uint64_t num_bytes = 0;
+
+	void *dst;
+	uint32_t pkt_len;
+	uint8_t mbuf_segs;
+
+	struct ndp_packet packets[nb_pkts];
+
+	if (unlikely(ndp->queue == NULL || nb_pkts == 0)) {
+		RTE_LOG(ERR, PMD, "RX invalid arguments!\n");
+		return 0;
+	}
+
+	for (i = 0; i < nb_pkts; i++) {
+		packets[i].data_length = bufs[i]->pkt_len;
+		packets[i].header_length = 0;
+	}
+
+	num_tx = ndp_tx_burst_get(ndp->queue, packets, nb_pkts);
+
+	if (unlikely(num_tx != nb_pkts))
+		return 0;
+
+	for (i = 0; i < nb_pkts; ++i) {
+		mbuf = bufs[i];
+
+		pkt_len = mbuf->pkt_len;
+		mbuf_segs = mbuf->nb_segs;
+
+		num_bytes += pkt_len;
+		if (mbuf_segs == 1) {
+			/*
+			 * non-scattered packet,
+			 * transmit from one mbuf
+			 */
+			rte_memcpy(packets[i].data,
+				rte_pktmbuf_mtod(mbuf, const void *),
+				pkt_len);
+		} else {
+			/* scattered packet, transmit from more mbufs */
+			struct rte_mbuf *m = mbuf;
+			while (m) {
+				dst = packets[i].data;
+
+				rte_memcpy(dst,
+					rte_pktmbuf_mtod(m,
+					const void *),
+					m->data_len);
+				dst = ((uint8_t *)(dst)) +
+					m->data_len;
+				m = m->next;
+			}
+		}
+
+		rte_pktmbuf_free(mbuf);
+	}
+
+	ndp_tx_burst_flush(ndp->queue);
+
+	ndp->tx_pkts += num_tx;
+	ndp->err_pkts += nb_pkts - num_tx;
+	ndp->tx_bytes += num_bytes;
+	return num_tx;
+}
+
+#endif /* _NFB_TX_H_ */
diff --git a/drivers/net/nfb/rte_nfb_pmd_version.map b/drivers/net/nfb/rte_nfb_pmd_version.map
new file mode 100644
index 0000000..97fd251
--- /dev/null
+++ b/drivers/net/nfb/rte_nfb_pmd_version.map
@@ -0,0 +1,4 @@ 
+DPDK_19.02 {
+
+        local: *;
+};
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 8a4f0f4..32e88b5 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -196,6 +196,7 @@  _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_SOFTNIC)      += -lrte_pmd_softnic
 endif
 _LDLIBS-$(CONFIG_RTE_LIBRTE_SFC_EFX_PMD)    += -lrte_pmd_sfc_efx
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_SZEDATA2)   += -lrte_pmd_szedata2 -lsze2
+_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_NFB)        += -lrte_pmd_nfb -lnfb -lfdt
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_TAP)        += -lrte_pmd_tap
 _LDLIBS-$(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD) += -lrte_pmd_thunderx_nicvf
 _LDLIBS-$(CONFIG_RTE_LIBRTE_VDEV_NETVSC_PMD) += -lrte_pmd_vdev_netvsc