dpdk.git
6 years agodoc: add guidelines for bugzilla reference in patch
Marko Kovacevic [Tue, 29 May 2018 11:01:24 +0000 (12:01 +0100)]
doc: add guidelines for bugzilla reference in patch

Added contribution guideline for adding tags
when sending patches that have been raised on
Bugzilla

Signed-off-by: Marko Kovacevic <marko.kovacevic@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
6 years agodoc: add VXLAN and NVGRE encapsulation in release notes
Mohammad Abdul Awal [Mon, 28 May 2018 16:12:22 +0000 (17:12 +0100)]
doc: add VXLAN and NVGRE encapsulation in release notes

Signed-off-by: Mohammad Abdul Awal <mohammad.abdul.awal@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
6 years agodoc: add port representor in release notes
Mohammad Abdul Awal [Mon, 28 May 2018 16:12:21 +0000 (17:12 +0100)]
doc: add port representor in release notes

Signed-off-by: Mohammad Abdul Awal <mohammad.abdul.awal@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
6 years agodoc: postpone devargs genericisation notice
Gaetan Rivet [Mon, 28 May 2018 16:10:35 +0000 (18:10 +0200)]
doc: postpone devargs genericisation notice

Device querying and declaration has been postponed to 18.08.
Additionally, while working on the feature, some changes previously
announced won't be enacted.

Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com>
6 years agoversion: 18.05-rc6
Thomas Monjalon [Mon, 28 May 2018 01:29:40 +0000 (03:29 +0200)]
version: 18.05-rc6

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
6 years agocompressdev: fix export of unknown symbols
Thomas Monjalon [Sun, 27 May 2018 22:24:35 +0000 (00:24 +0200)]
compressdev: fix export of unknown symbols

The *_callback_* functions are not implemented,
so they are removed from the export map file.

Fixes: ed7dd94f7f66 ("compressdev: add basic device management")

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
6 years agobus/fslmc: fix export of unknown symbol
Thomas Monjalon [Sun, 27 May 2018 22:24:07 +0000 (00:24 +0200)]
bus/fslmc: fix export of unknown symbol

The function dpdmai_set_tx_queue() is not implemented,
so it is removed from the export map file.

Fixes: 23e8fcb0186c ("bus/fslmc: support MC DPDMAI object")

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
6 years agovfio: fix export of renamed symbols
Thomas Monjalon [Sun, 27 May 2018 22:23:35 +0000 (00:23 +0200)]
vfio: fix export of renamed symbols

The functions
- vfio_get_container_fd
- vfio_get_group_fd
- vfio_get_group_no
have been renamed to
- rte_vfio_get_container_fd
- rte_vfio_get_group_fd
- rte_vfio_get_group_num

The old names are removed from the map file.

Fixes: 964b2f3bfb07 ("vfio: export some internal functions")

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
6 years agobaseband/turbo_sw: shorten internal buffers names
Kamil Chalupnik [Thu, 24 May 2018 12:41:37 +0000 (14:41 +0200)]
baseband/turbo_sw: shorten internal buffers names

Internal buffers names have been shortened to meet ring names size
requirements after device name changed.

Fixes: 7ce00bf31bbe ("bbdev: change names of baseband devices")

Signed-off-by: Kamil Chalupnik <kamilx.chalupnik@intel.com>
Acked-by: Amr Mokhtar <amr.mokhtar@intel.com>
6 years agodoc: add packet framework update in release notes
Jasvinder Singh [Fri, 25 May 2018 14:15:23 +0000 (15:15 +0100)]
doc: add packet framework update in release notes

Signed-off-by: Jasvinder Singh <jasvinder.singh@intel.com>
6 years agodoc: update IP pipeline application guide
Jasvinder Singh [Thu, 24 May 2018 11:59:43 +0000 (12:59 +0100)]
doc: update IP pipeline application guide

Update sample app user guide with ip pipeline documentation.

Signed-off-by: Jasvinder Singh <jasvinder.singh@intel.com>
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
6 years agodoc: add compression level guide for ISA-L
Lee Daly [Thu, 24 May 2018 11:04:49 +0000 (12:04 +0100)]
doc: add compression level guide for ISA-L

This expands the ISA-L documentation to give more a detailed explanation
of the mapping between the compressdev API levels and PMD levels.

Signed-off-by: Lee Daly <lee.daly@intel.com>
Acked-by: Marko Kovacevic <marko.kovacevic@intel.com>
6 years agodoc: announce ethdev CRC strip flag deprecation
Ferruh Yigit [Tue, 17 Apr 2018 13:39:49 +0000 (14:39 +0100)]
doc: announce ethdev CRC strip flag deprecation

Make CRC stripping default behavior, deprecate flag
DEV_RX_OFFLOAD_CRC_STRIP.

Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
6 years agodoc: announce removal of indirect mbuf check macro
Yongseok Koh [Fri, 25 May 2018 01:20:06 +0000 (18:20 -0700)]
doc: announce removal of indirect mbuf check macro

Link: http://dpdk.org/ml/archives/dev/2018-April/099476.html
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
6 years agoeal: deprecate function to set default mbuf pool
Olivier Matz [Thu, 24 May 2018 09:44:07 +0000 (11:44 +0200)]
eal: deprecate function to set default mbuf pool

Deprecate rte_eal_mbuf_default_mempool_ops(), it shall be replaced by
rte_mbuf_best_mempool_ops().

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
6 years agodoc: announce deprecation of EAL runtime path
Anatoly Burakov [Fri, 25 May 2018 13:38:43 +0000 (14:38 +0100)]
doc: announce deprecation of EAL runtime path

Most of this work was already done, but runtime config path is
considered to be part of public API because of high likelihood of
it being used by various tools in the DPDK ecosystem, and thus
requires a deprecation notice.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Harry van Haaren <harry.van.haaren@intel.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
6 years agodoc: add memory changes in release notes
Anatoly Burakov [Fri, 25 May 2018 13:41:03 +0000 (14:41 +0100)]
doc: add memory changes in release notes

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
6 years agodoc: update guides for memory subsystem
Anatoly Burakov [Fri, 25 May 2018 13:41:02 +0000 (14:41 +0100)]
doc: update guides for memory subsystem

Document new command-line switches and the principles behind the
new memory subsystem. Also, replace outdated malloc heap picture.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
6 years agomemzone: clarify support for zero-length memzones
Anatoly Burakov [Fri, 25 May 2018 13:39:45 +0000 (14:39 +0100)]
memzone: clarify support for zero-length memzones

Currently, memzone allocation with length set to 0 that are also
IOVA-contiguous is not supported. Document this limitation.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
6 years agomem: document callbacks not being supported in some cases
Anatoly Burakov [Fri, 25 May 2018 13:39:44 +0000 (14:39 +0100)]
mem: document callbacks not being supported in some cases

Mem event and validator callbacks may not be supported under all
circumstances (such as when running in legacy memory mode, or on
FreeBSD), and this case needs to be handled by any code that will
use these callbacks. Spell this out more clearly, because it's not
immediately obvious that this is an expected use case.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
6 years agodoc: add IPC guide
Anatoly Burakov [Fri, 25 May 2018 16:56:21 +0000 (17:56 +0100)]
doc: add IPC guide

Describe all the capabilities of DPDK IPC, and provide some
insight into how to best make use of it.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
6 years agodoc: add tested platforms for NXP SoCs
Shreyansh Jain [Fri, 25 May 2018 14:48:17 +0000 (20:18 +0530)]
doc: add tested platforms for NXP SoCs

Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
6 years agodoc: add tested platforms for Cavium SoCs
Jerin Jacob [Sun, 27 May 2018 19:13:57 +0000 (00:43 +0530)]
doc: add tested platforms for Cavium SoCs

Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
6 years agodoc: fix a typo in flow API howto
Jerin Jacob [Sun, 27 May 2018 18:55:58 +0000 (00:25 +0530)]
doc: fix a typo in flow API howto

Fixes: 3e0ceb9f17ff ("doc: add basic howto for flow API")
Cc: stable@dpdk.org
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
6 years agodoc: remove old deprecation notice for i40e
Kirill Rybalchenko [Fri, 25 May 2018 09:17:00 +0000 (10:17 +0100)]
doc: remove old deprecation notice for i40e

New default configuration without flexible payload
is implemented now.

Fixes: d2f9fe8ae309 ("net/i40e: turn off flexible payload on driver init")
Cc: stable@dpdk.org
Signed-off-by: Kirill Rybalchenko <kirill.rybalchenko@intel.com>
6 years agoethdev: add missing TM function to export map
Ben Shelton [Fri, 25 May 2018 19:59:43 +0000 (14:59 -0500)]
ethdev: add missing TM function to export map

The rte_tm_get_number_of_leaf_nodes() API function was added in DPDK
17.08.  However, it was added to the .map file with the wrong function
name (rte_tm_get_leaf_nodes), which was subsequently removed in commit
3e8ea3d ('lib: remove unused map symbols').

Add it back under the 17.08 release with the correct function name.

Fixes: 5d109deffa87 ("ethdev: add traffic management API")
Cc: stable@dpdk.org
Signed-off-by: Ben Shelton <benjamin.h.shelton@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
6 years agodoc: add vhost interrupt mode in release notes
Zhihong Wang [Fri, 25 May 2018 11:40:24 +0000 (19:40 +0800)]
doc: add vhost interrupt mode in release notes

Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
Acked-by: Marko Kovacevic <marko.kovacevic@intel.com>
6 years agodoc: add vDPA in release notes
Zhihong Wang [Fri, 25 May 2018 11:40:22 +0000 (19:40 +0800)]
doc: add vDPA in release notes

Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
Acked-by: Marko Kovacevic <marko.kovacevic@intel.com>
6 years agodoc: add vDPA in vhost guide
Zhihong Wang [Fri, 25 May 2018 11:40:20 +0000 (19:40 +0800)]
doc: add vDPA in vhost guide

Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
Acked-by: Marko Kovacevic <marko.kovacevic@intel.com>
6 years agonet/tap: fix keep-alive queue not detached
Ophir Munk [Thu, 24 May 2018 23:10:40 +0000 (23:10 +0000)]
net/tap: fix keep-alive queue not detached

The TAP keep-alive queue was created in order to keep the TAP device
in Linux even in case all of its Rx/Tx queues are released (in Linux
terminology: even in case all of the TAP device file descriptors are
closed), however, the keep-alive queue itself is attached to the TAP
device like all other Rx/Tx queues and therefore the kernel will
enqueue to it some Rx packets based on the kernel RSS distribution
rules. Those packets are unknown to the application and will remain
lost in the keep-alive queue.
All queues are attached by default to the TAP device after they are
created though TUNSETIFF ioctl call.
The fix is to detach the keep-alive queue after its creation through
TUNSETQUEUE ioctl call.

Fixes: 3101191c63ab ("net/tap: fix device removal when no queue exist")
Cc: stable@dpdk.org
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
6 years agonet/qede: fix slow path completion timeout
Shahed Shaikh [Wed, 23 May 2018 18:48:53 +0000 (11:48 -0700)]
net/qede: fix slow path completion timeout

In 100G mode, we poll firmware slow path completion for every 1 second,
which is not enough and may result in completion timeout if
driver misses that window.

Patch "eal: set affinity for control threads" exposed this issue since
alarm callback runs in control thread context.

Fix this issue by update polling period to 100ms.

Fixes: d651ee4919cd ("eal: set affinity for control threads")
Fixes: 2af14ca79c0a ("net/qede: support 100G")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
6 years agonet/mlx5: fix generic tunnel offload compatibility check
Shahaf Shuler [Thu, 24 May 2018 05:28:59 +0000 (08:28 +0300)]
net/mlx5: fix generic tunnel offload compatibility check

On some distros, the inbox rdma-core tree can contain the Software
Parser enum while the remaining structs still missing.

Fixes: 5f8ba81c4228 ("net/mlx5: support generic tunnel offloading")

Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
6 years agonet/mlx5: fix SW parser offset
Yongseok Koh [Wed, 23 May 2018 11:27:09 +0000 (04:27 -0700)]
net/mlx5: fix SW parser offset

This is to fix the offloads introduced by commits
5f8ba81 net/mlx5: support generic tunnel offloading
5355f44 ethdev: introduce generic IP/UDP tunnel checksum and TSO

Fixes: 8589e944d075 ("net/mlx5: fix setting offsets for SW parser")

Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
6 years agodoc: convert virtio guide to new offload API
Tiwei Bie [Fri, 25 May 2018 06:17:48 +0000 (14:17 +0800)]
doc: convert virtio guide to new offload API

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
6 years agonet/nfp: fix lock file usage
Alejandro Lucero [Wed, 23 May 2018 12:28:56 +0000 (13:28 +0100)]
net/nfp: fix lock file usage

DPDK apps can be executed as non-root users but current NFP lock
file for avoiding concurrent accesses to CPP interface is precluding
this option or requires to modify system file permissions.

When the NFP device is bound to VFIO, this driver does not allow this
concurrent access, so the lock file is not required at all.

OVS-DPDK as executed in RedHat distributions is the main NFP user
needing this fix.

Fixes: c7e9729da6b5 ("net/nfp: support CPP")

Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
6 years agodoc: add note for maximum queues setting in vhost sample
Xiao Wang [Thu, 24 May 2018 12:05:07 +0000 (20:05 +0800)]
doc: add note for maximum queues setting in vhost sample

If the NIC has a queue number larger than 128, then we need to change
the ``MAX_QUEUES`` to a larger number to make sure we allocate a big
enough memory pool for device setup.

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Marko Kovacevic <marko.kovacevic@intel.com>
6 years agonet/virtio-user: fix crash in server mode
Zhiyong Yang [Thu, 24 May 2018 15:51:01 +0000 (23:51 +0800)]
net/virtio-user: fix crash in server mode

For virtio-user server mode, one use case comes across segmentation fault.
step 1: Launch vhost side as client firstly.
step 2: launch virtio-user side as server.

The cause is: after registering virtio_interrupt_handler into
eal-intr-thread, two threads (main thread and eal-intr-thread) have
sync issues, so add rxvq pointer checking in function virtio_notify_peers
to decide if the code can continue.

Fixes: bd8f50a45d0f ("net/virtio-user: support server mode")
Cc: stable@dpdk.org
Signed-off-by: Zhiyong Yang <zhiyong.yang@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
6 years agodoc: update qede guide and features
Rasesh Mody [Wed, 23 May 2018 00:09:06 +0000 (17:09 -0700)]
doc: update qede guide and features

Add LINUX VFIO support to feature list.

Add GRE tunneling offload to supported feature list.

Update firmware references to use newer FW image 8.33.12.0. Update
management FW version as well to 8.34.x.x.

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
6 years agodoc: drop support of Mellanox OFED 4.2
Shahaf Shuler [Thu, 24 May 2018 13:47:27 +0000 (16:47 +0300)]
doc: drop support of Mellanox OFED 4.2

Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
6 years agodoc: remove deprecated terms from liquidio guide
Shijith Thotton [Wed, 23 May 2018 17:35:54 +0000 (13:35 -0400)]
doc: remove deprecated terms from liquidio guide

Remove reference to deprecated ethdev offload parameter from liquidio
documentation.

Fixes: dd6aab16711c ("net/liquidio: move to new offload API")

Signed-off-by: Shijith Thotton <shijith.thotton@caviumnetworks.com>
6 years agodoc: remove deprecated terms from octeontx guide
Jerin Jacob [Thu, 24 May 2018 08:08:56 +0000 (13:38 +0530)]
doc: remove deprecated terms from octeontx guide

Remove reference to deprecated ethdev offload parameter from octeontx
documentation.

Fixes: a92870896b4a ("net/octeontx: use the new offload APIs")
Cc: stable@dpdk.org
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
6 years agodoc: remove deprecated terms from thunderx guide
Jerin Jacob [Thu, 24 May 2018 08:08:55 +0000 (13:38 +0530)]
doc: remove deprecated terms from thunderx guide

Remove reference to deprecated ethdev offload parameter from thunderx
documentation.

Fixes: c97da2cbc2c2 ("net/thunderx: convert to new offload API")
Cc: stable@dpdk.org
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
6 years agodoc: convert fm10k guide to new offload API
Qi Zhang [Wed, 23 May 2018 02:56:07 +0000 (10:56 +0800)]
doc: convert fm10k guide to new offload API

Cleanup document to convert old rxmode and txq_flags to new offload
bit mask.

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
6 years agodoc: convert ixgbe guide to new offload API
Qi Zhang [Wed, 23 May 2018 02:56:06 +0000 (10:56 +0800)]
doc: convert ixgbe guide to new offload API

Cleanup document to convert old rxmode flags to new offload
bit mask.

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
6 years agonet/nfp: remove reference to old offload API
Alejandro Lucero [Wed, 23 May 2018 10:14:44 +0000 (11:14 +0100)]
net/nfp: remove reference to old offload API

This was missed in a previous patch for using new offload API.

It turns out the line can be removed because that internal PMD
crc_len data is not being used.

Fixes: a922c6a789ff ("net/nfp: support new HW offloads API")

Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
6 years agoexamples/performance-thread: convert license to SPDX
Pablo de Lara [Wed, 18 Apr 2018 07:57:51 +0000 (08:57 +0100)]
examples/performance-thread: convert license to SPDX

Convert dual license headers with Intel and Hasan Alayli
names to SPDX.

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Hasan Alayli <halayli@gmail.com>
6 years agoexpamples/ip_pipeline: convert to SPDX license tag
Gavin Hu [Fri, 18 May 2018 11:25:38 +0000 (07:25 -0400)]
expamples/ip_pipeline: convert to SPDX license tag

Signed-off-by: Gavin Hu <gavin.hu@linaro.org>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
6 years agoexamples/l3fwd: convert to SPDX license tags
Gavin Hu [Fri, 18 May 2018 11:25:37 +0000 (07:25 -0400)]
examples/l3fwd: convert to SPDX license tags

Signed-off-by: Gavin Hu <gavin.hu@linaro.org>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
6 years agonet/i40e: convert to SPDX license tag
Gavin Hu [Fri, 18 May 2018 11:25:39 +0000 (07:25 -0400)]
net/i40e: convert to SPDX license tag

Signed-off-by: Gavin Hu <gavin.hu@linaro.org>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
6 years agonet/bnx2x: change copyright info to Cavium
Rasesh Mody [Wed, 23 May 2018 20:56:56 +0000 (13:56 -0700)]
net/bnx2x: change copyright info to Cavium

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
6 years agonet/bnx2x: use SPDX tag
Rasesh Mody [Wed, 23 May 2018 06:27:39 +0000 (23:27 -0700)]
net/bnx2x: use SPDX tag

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
6 years agonet/qede: change copyright info to Cavium
Rasesh Mody [Wed, 23 May 2018 20:56:55 +0000 (13:56 -0700)]
net/qede: change copyright info to Cavium

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
6 years agonet/qede: use SPDX tag
Rasesh Mody [Wed, 23 May 2018 06:27:38 +0000 (23:27 -0700)]
net/qede: use SPDX tag

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
6 years agouse SPDX tag for 6WIND copyrighted files
Olivier Matz [Thu, 3 May 2018 07:30:11 +0000 (09:30 +0200)]
use SPDX tag for 6WIND copyrighted files

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
6 years agouse SPDX license tag in Mellanox copyrighted files
Thomas Monjalon [Tue, 1 May 2018 20:07:11 +0000 (22:07 +0200)]
use SPDX license tag in Mellanox copyrighted files

Some files were left with full license and wrong copyright format.
They are switched to this format:
SPDX-License-Identifier: BSD-3-Clause
Copyright 2017 Mellanox Technologies, Ltd

Fixes: 5feecc57d90b ("align SPDX Mellanox copyrights")

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
6 years agoeal: convert dual-license to SPDX
Pablo de Lara [Wed, 11 Apr 2018 23:08:01 +0000 (00:08 +0100)]
eal: convert dual-license to SPDX

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
6 years agoeal: add missing SPDX identifiers
Hemant Agrawal [Mon, 9 Apr 2018 08:58:34 +0000 (14:28 +0530)]
eal: add missing SPDX identifiers

Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
6 years agokernel: add missing SPDX license identifiers
Hemant Agrawal [Mon, 9 Apr 2018 08:58:38 +0000 (14:28 +0530)]
kernel: add missing SPDX license identifiers

Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
6 years agodoc: advise to specify LTS branch when backporting patches
Luca Boccassi [Thu, 17 May 2018 13:53:35 +0000 (14:53 +0100)]
doc: advise to specify LTS branch when backporting patches

We have many stable branches being maintained at the same time, and
sometimes it's not clear which branch a patch is being backported for.
Note in the guidelines that it should be specified via the cover letter,
annotation or using --subject-prefix.
Also note to send only to stable@dpdk.org, not dev@dpdk.org.

Signed-off-by: Luca Boccassi <bluca@debian.org>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
6 years agodoc: add contribution guidelines for stable tags
Marko Kovacevic [Tue, 16 Jan 2018 09:12:47 +0000 (09:12 +0000)]
doc: add contribution guidelines for stable tags

Added contribution guideline for adding stable
tags when sending patches all fix patches to the
master branch that are candidates for backporting

Signed-off-by: Marko Kovacevic <marko.kovacevic@intel.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
6 years agodoc: add contribution guidelines for coverity tags
Marko Kovacevic [Tue, 16 Jan 2018 09:12:46 +0000 (09:12 +0000)]
doc: add contribution guidelines for coverity tags

Added contribution guideline for adding tags
when sending patches that have been raised by
coverity

Signed-off-by: Marko Kovacevic <marko.kovacevic@intel.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
6 years agodoc: add tested platforms with Mellanox NICs
Raslan Darawsheh [Wed, 23 May 2018 11:54:36 +0000 (14:54 +0300)]
doc: add tested platforms with Mellanox NICs

Signed-off-by: Raslan Darawsheh <rasland@mellanox.com>
6 years agodoc: add tested Intel platforms with Intel NICs
Yulong Pei [Tue, 22 May 2018 09:34:56 +0000 (17:34 +0800)]
doc: add tested Intel platforms with Intel NICs

Add tested Intel platforms with Intel NICs to the release note.

Signed-off-by: Yulong Pei <yulong.pei@intel.com>
6 years agoversion: 18.05-rc5
Thomas Monjalon [Tue, 22 May 2018 23:44:00 +0000 (01:44 +0200)]
version: 18.05-rc5

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
6 years agonet/tap: fix vdev data sharing for tun
Vipin Varghese [Tue, 22 May 2018 11:01:54 +0000 (16:31 +0530)]
net/tap: fix vdev data sharing for tun

Enables TUN PMD sharing by attaching the port from the shared data.

Fixes: ee27edbe0c10 ("drivers/net: share vdev data to secondary process")

Signed-off-by: Vipin Varghese <vipin.varghese@intel.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
6 years agonet/tap: fix protocol field
Vipin Varghese [Tue, 22 May 2018 10:47:14 +0000 (16:17 +0530)]
net/tap: fix protocol field

The TX function is shared between TAP and TUN PMD. Checking TUN-TAP
type field will ensure the TAP PMD will always have protocol field
as 0.

Fixes: 204d026a3922 ("net/tap: support tun")

Signed-off-by: Vipin Varghese <vipin.varghese@intel.com>
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
6 years agodoc: update release notes for mlx drivers
Shahaf Shuler [Thu, 17 May 2018 07:48:34 +0000 (10:48 +0300)]
doc: update release notes for mlx drivers

Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
6 years agonet/liquidio: fix link state fetching during start
Chuhong Yao [Tue, 22 May 2018 14:33:29 +0000 (22:33 +0800)]
net/liquidio: fix link state fetching during start

Clear link state information during device start for fetching new state
before function completion.

Fixes: 605164c8e79d ("net/liquidio: add API to validate VF MTU")
Cc: stable@dpdk.org
Signed-off-by: Chuhong Yao <ych@panath.cn>
Acked-by: Shijith Thotton <shijith.thotton@caviumnetworks.com>
6 years agonet/bnxt: fix Rx checksum flags
Ajit Khaparde [Tue, 22 May 2018 18:13:47 +0000 (11:13 -0700)]
net/bnxt: fix Rx checksum flags

For frames where the hardware is not able to calculate checksum
we are indicating such frames to be bad. And that is incorrect.
Indicate PKT_RX_IP_CKSUM_UNKNOWN or PKT_RX_L4_CKSUM_UNKNOWN
for such frames.

Fixes: 7ec39d8c524b ("net/bnxt: update status of Rx IP/L4 CKSUM")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
6 years agonet/bnxt: fix xstats for VF
Ajit Khaparde [Tue, 22 May 2018 18:13:46 +0000 (11:13 -0700)]
net/bnxt: fix xstats for VF

Query of port stats is permitted for VF interfaces as well.
Fix the code to allow VFs to query port stats.

Fixes: bfb9c2260be2 ("net/bnxt: support xstats get/reset")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
6 years agonet/bnxt: fix VF resource allocation
Ajit Khaparde [Tue, 22 May 2018 18:13:45 +0000 (11:13 -0700)]
net/bnxt: fix VF resource allocation

If the resource requirement of a VF is more than what is allotted
to it by the FW, a VF can request to reallocate some of the resources.

This is possible only when the NIC is running the Resource Manager aware
CHiMP FW.

If necessary, calculate Tx and Rx ring count using the new RM API.
Otherwise use the Tx and Rx ring count as-is. Update the cp ring count
based on the Tx and Rx ring count.

Fixes: b7778e8a1c00 ("net/bnxt: refactor to properly allocate resources for PF/VF")

Signed-off-by: Jay Ding <jay.ding@broadcom.com>
Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Reviewed-by: Ray Jui <ray.jui@broadcom.com>
Reviewed-by: Randy Schacher <stuart.schacher@broadcom.com>
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
6 years agonet/bnxt: use first completion ring for fwd and async event
Ajit Khaparde [Tue, 22 May 2018 18:13:44 +0000 (11:13 -0700)]
net/bnxt: use first completion ring for fwd and async event

In order to save completion resource, use the first completion ring from
PF or VF as the default completion ring for async event & HWRM forward
response handling. Add bnxt_hwrm_set_async_event_cr() to set
async_event_cr for either PF or VF.

Fixes: 7bc8e9a227cc ("net/bnxt: support async link notification")

Signed-off-by: Qingmin Liu <qingmin.liu@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
6 years agonet/bnxt: fix RSS hash configuration
Ajit Khaparde [Tue, 22 May 2018 18:13:43 +0000 (11:13 -0700)]
net/bnxt: fix RSS hash configuration

While configuring RSS, the FW needs to know the rss_hash_mode that needs
to be initialized.
Set hash mode to HWRM_VNIC_RSS_CFG_INPUT_HASH_MODE_FLAGS_DEFAULT
to allow the FW to use the global mode already configured in the device.

Fixes: bcd4bcc4426f ("net/bnxt: configure RSS")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
6 years agonet/bnxt: fix Tx and Rx burst for secondary process
Ajit Khaparde [Tue, 22 May 2018 18:13:42 +0000 (11:13 -0700)]
net/bnxt: fix Tx and Rx burst for secondary process

We were initializing Tx and Rx burst functions only for primary
processes. Fixing it in this patch.

Fixes: 88920136688c ("net/bnxt: support xstats get by id")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
6 years agonet/bnxt: add fallthrough comment
Ajit Khaparde [Tue, 22 May 2018 18:13:41 +0000 (11:13 -0700)]
net/bnxt: add fallthrough comment

The FALLTHROUGH comment for cascading switch cases was missing in
a few places. This patch adds that.

Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
6 years agoapp/testpmd: fix descriptor number for Rx queue setup
Ferruh Yigit [Tue, 22 May 2018 16:37:20 +0000 (17:37 +0100)]
app/testpmd: fix descriptor number for Rx queue setup

Wrong index used to select descriptor number, causing setting up queue
with wrong number of descriptors.

Fixes: d44f8a485f5d ("app/testpmd: enable per queue configure")

Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
6 years agoapp/testpmd: fix log of start command
Bernard Iremonger [Tue, 22 May 2018 15:10:38 +0000 (16:10 +0100)]
app/testpmd: fix log of start command

Application can provide 0 for ring size to use default values. To not
log zero for that case get configured ring size from device.

Call the rte_eth_rxq_info_get() and rte_eth_txq_info_get() functions
to update the number of rx and tx descriptors.

Fixes: d44f8a485f5d ("app/testpmd: enable per queue configure")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
6 years agonet/mlx5: remove redundant checks
Yongseok Koh [Tue, 22 May 2018 08:59:43 +0000 (01:59 -0700)]
net/mlx5: remove redundant checks

Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Xueming Li <xuemingl@mellanox.com>
6 years agonet/mlx5: fix setting offsets for SW parser
Yongseok Koh [Tue, 22 May 2018 08:59:42 +0000 (01:59 -0700)]
net/mlx5: fix setting offsets for SW parser

Since ConnectX-5, SW parser just complements HW parser. SW parser starts to
engage only if HW parser can't reach a header. For the older devices, HW
parser will not kick in if any of SWP offsets is set. Therefore, all of the
L3 offsets should be set regardless of HW offload. As IPv6 doesn't have
header checksum, the mbuf can't have PKT_TX_[OUTER_]IP_CKSUM if outer or
inner L3 is IPv6.

And if inner packet isn't IP, the inner offsets shouldn't be set.

Fixes: 5f8ba81c4228 ("net/mlx5: support generic tunnel offloading")

Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Xueming Li <xuemingl@mellanox.com>
6 years agonet/ixgbe: remove unnecessary macro
Qi Zhang [Tue, 22 May 2018 14:12:47 +0000 (22:12 +0800)]
net/ixgbe: remove unnecessary macro

Since we move to new offload APIs, IXGBE_SIMPLE_FLAGS is not used.

Fixes: 51215925a32f ("net/ixgbe: convert to new Tx offloads API")

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
6 years agonet/failsafe: fix duplicate event registration
Matan Azrad [Tue, 22 May 2018 12:38:47 +0000 (12:38 +0000)]
net/failsafe: fix duplicate event registration

When the fail-safe device is reconfigured, it attempts to register
again for the sub-devices LSC and RMV events.

Prevent an event registration if it is already done.

Fixes: 598fb8aec6f6 ("net/failsafe: support device removal")
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Gaetan Rivet <gaetan.rivet@6wind.com>
6 years agonet/failsafe: fix removed sub-device cleanup
Matan Azrad [Tue, 22 May 2018 12:38:46 +0000 (12:38 +0000)]
net/failsafe: fix removed sub-device cleanup

The fail-safe PMD registers to RMV event for each removable sub-device
port in order to cleanup the sub-device resources and switch the Tx
sub-device directly when it is plugged-out.

During removal time, the fail-safe PMD stops and closes the sub-device
but it doesn't unregister the LSC and RMV callbacks of the sub-device
port.

It can lead the callbacks to be called for a port which is no more
associated with the fail-safe sub-device, because there is not a
guarantee that a sub-device gets the same port ID for each plug-in
process. This port, for example, may belong to another sub-device of a
different fail-safe device.

Unregister the LSC and RMV callbacks for sub-devices which are not
used.

Fixes: 598fb8aec6f6 ("net/failsafe: support device removal")
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Gaetan Rivet <gaetan.rivet@6wind.com>
6 years agonet/vhost: convert to new Rx/Tx offload API
Maxime Coquelin [Tue, 22 May 2018 12:50:19 +0000 (14:50 +0200)]
net/vhost: convert to new Rx/Tx offload API

Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
6 years agonet/mlx4: refactor RSS conversion functions
Adrien Mazarguil [Mon, 21 May 2018 15:50:12 +0000 (17:50 +0200)]
net/mlx4: refactor RSS conversion functions

Since commit 97b2217ae5bc ("net/mlx4: advertise supported RSS hash
functions"), this PMD includes two similar-looking functions that convert
RSS hash fields between Verbs and DPDK formats.

This patch refactors them as a single two-way function and gets rid of
redundant helper macros.

Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
6 years agonet/mlx4: fix default in RSS converter
Adrien Mazarguil [Mon, 21 May 2018 15:50:09 +0000 (17:50 +0200)]
net/mlx4: fix default in RSS converter

Below commit documents 0 as a value standing for a default set of RSS hash
types, however the mlx4 PMD doesn't interpret it correctly and still uses
its own internal special value for that (-1).

Also, its function prototype was not updated.

Fixes: ac8d22de2394 ("ethdev: flatten RSS configuration in flow API")
Fixes: 1d173da83ef2 ("net/mlx4: fix default RSS hash fields")
Cc: stable@dpdk.org
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
6 years agonet/i40e: remove dependency on old Rx flags
Qi Zhang [Tue, 22 May 2018 01:01:20 +0000 (09:01 +0800)]
net/i40e: remove dependency on old Rx flags

Cleanup remain dependency on old rxmode flags since we move to
new offload APIs.

Fixes: c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API")
Fixes: e0cb96204b71 ("net/i40e: add support for representor ports")

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
6 years agonet/bonding: export mode 4 slave info routine
Chas Williams [Thu, 17 May 2018 23:22:51 +0000 (19:22 -0400)]
net/bonding: export mode 4 slave info routine

rte_eth_bond_8023ad_slave_info() wasn't exported in the original work.
Useful to extract information about the current 802.3ad state.

Fixes: 46fb43683679 ("bond: add mode 4")
Cc: stable@dpdk.org
Signed-off-by: Chas Williams <chas3@att.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
6 years agonet/vdev_netvsc: fix automatic probing
Matan Azrad [Mon, 21 May 2018 16:23:30 +0000 (16:23 +0000)]
net/vdev_netvsc: fix automatic probing

The vdev_netvsc driver allows an automatic probe in Hyper-V VM systems
unless it was already specified by the EAL command line.

The detection of a specified NetVSC device is wrongly done by comparing
the vdev_netvsc driver name to all the vdev devices names, including
the suffix device index. Thus, if the user specifies the vdev_netvsc
device by adding an index to the device name, the comparison fails.
Consequently, the vdev_netvsc driver may automatically probe NetVSC
devices, despite the NetVSC device that was specified by the EAL command
line.

Compare the vdev_netvsc driver name to the devices names without the
index.

Fixes: 56252de779a6 ("net/vdev_netvsc: add automatic probing")
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
6 years agonet/ark: fix call to probing finish function for first port
Ed Czeck [Mon, 21 May 2018 19:29:07 +0000 (15:29 -0400)]
net/ark: fix call to probing finish function for first port

Fixes: fbe90cdd776c ("ethdev: add probing finish function")

Signed-off-by: Ed Czeck <ed.czeck@atomicrules.com>
Acked-by: John Miller <john.miller@atomicrules.com>
Reviewed-by: Thomas Monjalon <thomas@monjalon.net>
6 years agonet/i40e: fix shifts of signed values
Ferruh Yigit [Mon, 21 May 2018 14:45:59 +0000 (15:45 +0100)]
net/i40e: fix shifts of signed values

Following error reported by cppcheck:
(error) Shifting signed 32-bit value by 31 bits is
undefined behaviour. The patch fixes it.

Fixes: 8db9e2a1b232 ("i40e: base driver")
Cc: stable@dpdk.org
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
6 years agonet/e1000: fix build of igb only
Harry van Haaren [Mon, 21 May 2018 09:31:41 +0000 (10:31 +0100)]
net/e1000: fix build of igb only

This commit fixes a compilation error if EM_PMD is
not defined, bug IGB_PMD is. The root cause of the
issue was that log init variables are declared as
extern in a header file, while the definition of the
variables was in e1000_ethdev.c. Hence, the definitions
were not available if the e1000 PMD is disabled.

To fix this, a new file is added e1000_logs.c, which
matches the e1000_logs.h header. The log variables are
always compiled in, but the PMD logs are only registered
if a PMD is enabled in the configuration. Extra checks
are added in order to avoid duplicate registering.

Fixes: ed5bbb767c3e ("net/e1000: implement dynamic logging")
Cc: stable@dpdk.org
Reported-by: Vipin Varghese <vipin.varghese@intel.com>
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
Acked-by: Vipin Varghese <vipin.varghese@intel.com>
6 years agonet/mlx5: fix count in xstats
David Marchand [Sun, 20 May 2018 08:13:58 +0000 (10:13 +0200)]
net/mlx5: fix count in xstats

With the commit af4f09f28294 ("net/mlx5: prefix all functions with mlx5"),
mlx5_xstats_get() is not compliant any longer with the api.
It always returns the caller max entries count while it should return how
many entries it wrote/wanted to write.

Fixes: af4f09f28294 ("net/mlx5: prefix all functions with mlx5")

Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
6 years agoethdev: update description of port name
Vipin Varghese [Fri, 18 May 2018 05:12:53 +0000 (10:42 +0530)]
ethdev: update description of port name

Change adds extra information on name parameter for API
rte_eth_dev_get_name_by_port and rte_eth_dev_get_port_by_name.

Signed-off-by: Vipin Varghese <vipin.varghese@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
6 years agonet/tap: fix device removal when no queue exist
Ophir Munk [Mon, 21 May 2018 07:54:33 +0000 (07:54 +0000)]
net/tap: fix device removal when no queue exist

TAP device is created following its first queue creation. Multiple
queues can be added or removed over time. In Linux terminology those
are file descriptors which are opened or closed over time. As long as
the number of opened file descriptors is positive - TAP device will
appear as a Linux device. In case all queues are released (the
equivalent of all file descriptors being closed) the TAP device will
be removed. This can lead to abnormalities in different scenarios
where the TAP device should exist even if all its queues are released.
In order to make TAP existence independent of its number of queues -
an extra file descriptor is opened on TAP creation and is closed on
TAP closure. Its only purpose is to serve as a keep-alive mechanism
for the TAP device.

Fixes: bf7b7f437b49 ("net/tap: create netdevice during probing")
Cc: stable@dpdk.org
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
6 years agoethdev: fix shallow copy of flow API RAW item
Adrien Mazarguil [Mon, 21 May 2018 11:44:28 +0000 (13:44 +0200)]
ethdev: fix shallow copy of flow API RAW item

Like original commit mentioned below, this fix synchronizes flow rule copy
function with testpmd's own implementation following "app/testpmd: fix copy
of raw flow item (revisited)".

It addresses a crash that occurs when feeding a RAW pattern item to
rte_flow_copy(). Besides external applications, two PMDs (bonding and
failsafe) rely on this function internally.

Note the scope of this patch is limited to the RAW pattern item and has no
impact on all others.

Fixes: 972bf3610611 ("ethdev: fix shallow copy of flow API RSS action")
Cc: stable@dpdk.org
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
6 years agoapp/testpmd: fix copy of raw flow item - revisited
Adrien Mazarguil [Mon, 21 May 2018 11:44:26 +0000 (13:44 +0200)]
app/testpmd: fix copy of raw flow item - revisited

While previous fix with the same title does address the main issue, root
cause is that proper handling of spec/last/mask was overlooked in the
original patch.

Mask and last fields must be taken into account at all times.

Fixes: d0ad8648b1c5 ("app/testpmd: fix RSS flow action configuration")
Fixes: 67af7ecc52ec ("app/testpmd: fix copy of raw flow item")
Cc: stable@dpdk.org
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
6 years agonet/cxgbevf: fix inter-VM traffic when physical link down
Shagun Agrawal [Mon, 21 May 2018 08:05:07 +0000 (13:35 +0530)]
net/cxgbevf: fix inter-VM traffic when physical link down

Add force_link_up devargs to always force link as up for VFs.
This enables VFs on the same NIC to send traffic to each other
even when physical link is down.

Also add RTE_PMD_REGISTER_PARAM_STRING to export all supported
devargs.

Fixes: 011ebc236ddc ("net/cxgbe: add skeleton VF driver")

Signed-off-by: Shagun Agrawal <shaguna@chelsio.com>
Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
6 years agonet/i40e: fix corruption of VF stats
Remy Horton [Fri, 18 May 2018 11:49:48 +0000 (12:49 +0100)]
net/i40e: fix corruption of VF stats

The resetting of stats on a VF involves the setting of an offset
that is subtracted from future calls, rather zeroing of counters.
However doing a stats reset on the port representor was also
adjusting the values forwarded to the VF, which had the effect of
corrupting the VF's counters. The fix is for the port representor
to maintain its own stats offset, so the port representor and VF
maintain independently-resettable counters.

Fixes: e0cb96204b71 ("net/i40e: add support for representor ports")

Signed-off-by: Remy Horton <remy.horton@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
6 years agonet/ixgbe: fix config VLAN strip on the fly
Wei Dai [Sat, 19 May 2018 10:11:19 +0000 (18:11 +0800)]
net/ixgbe: fix config VLAN strip on the fly

The old ixgbe_vlan_offload_set() is called by
rte_eth_dev_set_vlan_offload() which is meant to config VLAN
strip/filter/extend on all queues.
This old function is also called by rte_eth_dev_start()/ixgbe_dev_start()
which need support per-queue VALN strip on only parts of queues.

So add new function ixgbe_vlan_offload_config() =
old ixgbe_vlan_offload_set().
This new function is called by ixgbe_dev_start() to support VLAN strip
per-queue configuration.

New ixgbe_vlan_offload_set() = codes to align VLAN strip flags on all
queues with port level setting + new ixgbe_vlan_offload_configure().
The 2nd function is called by rte_eth_dev_set_vlan_offload to support
configure VLAN strip on all queues of whole port.

Fixes: 216f78f4d53f ("net/ixgbe: support VLAN strip per queue offloading in PF")
Fixes: 860a94d3c692 ("net/ixgbe: support VLAN strip per queue offloading in VF")

Signed-off-by: Wei Dai <wei.dai@intel.com>
Signed-off-by: Yanglong Wu <yanglong.wu@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
6 years agonet/qede: fix unicast filter routine return code
Shahed Shaikh [Sun, 20 May 2018 00:15:46 +0000 (17:15 -0700)]
net/qede: fix unicast filter routine return code

There is no need to return failure (-EEXIST) when the requested
filter is already configured.

Fixes: d6cb17535f88 ("net/qede: fix VLAN filters")
Fixes: 77fac1b54fc9 ("net/qede: fix filtering code")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>