Hi，
> -邮件原件-
> 发件人: Dybkowski, AdamX
> 发送时间: 2021年5月19日 21:17
> 收件人: Feifei Wang ; Griffin, John
> ; Trahe, Fiona ; Jain,
> Deepak K ; Jerin Jacob
> ; Herbert Guan
>
> 抄送: dev@dpdk.org; david.march...@redhat.com; nd ;
> sta...@dpdk.org; Ruifeng Wang
> 主题: RE: [dpdk-dev] [PATCH v3] cryp
Hi, Ferruh
Thanks for your comments.
Please see below.
> -邮件原件-
> 发件人: Ferruh Yigit
> 发送时间: 2021年5月19日 16:12
> 收件人: Feifei Wang ; John Griffin
> ; Fiona Trahe ; Deepak
> Kumar Jain ; Jerin Jacob
> ; Herbert Guan
>
> 抄送: dev@dpdk.org; david.march...@redhat.com; nd ;
> sta...@dpdk.org; Ru
> -Original Message-
> From: Wang, Haiyue
> Sent: Wednesday, May 19, 2021 4:00 PM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Wang, Haiyue
> ; sta...@dpdk.org; Wu, Jingjing
> ; Xing, Beilei
> Subject: [PATCH v1] net/iavf: fix RSS key access out of index
>
> The array rss_key has size 'vf->
On 2021/5/19 23:02, Ferruh Yigit wrote:
> On 5/19/2021 2:25 PM, Chengwen Feng wrote:
>> Currently, the SVE code is compiled only when -march supports SVE
>> (e.g. '-march=armv8.2a+sve'), there maybe some problem[1] with this
>> approach.
>>
>> The solution:
>> a. If the minimum instruction set s
On 5/19/2021 9:42 PM, Thomas Monjalon wrote:
> 12/05/2021 18:04, Ferruh Yigit:
>> PMD updates are expected in alphabetical order based on their vendor
>> name. Clarify this expectation in the section comment.
>>
>> Signed-off-by: Ferruh Yigit
>> ---
>> - * Device abstraction libs and PMDs
>> +
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v21.05-rc4
There are only 48 new patches in this snapshot,
meaning this release cycle is almost closed.
Release notes:
https://doc.dpdk.org/guides/rel_notes/release_21_05.html
Please test and rep
06/05/2021 18:40, Conor Walsh:
> Currently the documentation describes how to add code snippets to the
> docs using code blocks. This can be problematic as the code snippets
> in the docs may fall out of sync with the actual code it is referencing
> within DPDK. This patch adds instructions to the
12/05/2021 18:04, Ferruh Yigit:
> PMD updates are expected in alphabetical order based on their vendor
> name. Clarify this expectation in the section comment.
>
> Signed-off-by: Ferruh Yigit
> ---
> - * Device abstraction libs and PMDs
> + * Device abstraction libs and PMDs (PMDs ordered
19/05/2021 19:47, Ferruh Yigit:
> On 5/19/2021 6:33 PM, Thomas Monjalon wrote:
> > The Doxygen comments are placed before the related lines,
> > but the markers were /**< instead of /**
> >
> > The struct rte_flow_item_integrity did not appear in Doxygen output
> > because there was no general com
On Wed, May 19, 2021 at 9:30 AM Andrew Rybchenko <
andrew.rybche...@oktetlabs.ru> wrote:
> On 5/19/21 7:27 PM, Thomas Monjalon wrote:
> > The Doxygen comments are placed before the related lines,
> > but the markers were /**< instead of /**
> >
> > Fixes: b10a421a1f3b ("ethdev: add packet integrit
> > After 4 years, rte_flow has evolved enough to not require special notes
> > about what could be added in future.
> > Part of the removed plans were obsolete anyway.
> >
> > Signed-off-by: Thomas Monjalon
>
> Acked-by: Ori Kam
Applied
From: Ferruh Yigit
%lx or %llx tend to be wrong for 32-bit platform
if used for fixed size variable like uint64_t.
A checkpatch warning will avoid this common mistake.
Signed-off-by: Ferruh Yigit
Signed-off-by: Thomas Monjalon
---
v2: proposal to reword the message and comment
---
devtools/ch
> -Original Message-
> From: Chautru, Nicolas
> Sent: Monday, May 17, 2021 11:23 PM
> To: Nipun Gupta ; Hemant Agrawal
> ; dev@dpdk.org; gak...@marvell.com
> Cc: david.march...@redhat.com
> Subject: RE: [PATCH v4 5/8] baseband/la12xx: add queue and modem config
> support
>
>
>
> > --
On 5/19/2021 6:59 PM, Thomas Monjalon wrote:
> 19/05/2021 19:47, Ferruh Yigit:
>> On 5/19/2021 6:33 PM, Thomas Monjalon wrote:
>>> The Doxygen comments are placed before the related lines,
>>> but the markers were /**< instead of /**
>>>
>>> The struct rte_flow_item_integrity did not appear in Doxy
19/05/2021 19:47, Ferruh Yigit:
> On 5/19/2021 6:33 PM, Thomas Monjalon wrote:
> > The Doxygen comments are placed before the related lines,
> > but the markers were /**< instead of /**
> >
> > The struct rte_flow_item_integrity did not appear in Doxygen output
> > because there was no general com
On 5/19/2021 6:33 PM, Thomas Monjalon wrote:
> The Doxygen comments are placed before the related lines,
> but the markers were /**< instead of /**
>
> The struct rte_flow_item_integrity did not appear in Doxygen output
> because there was no general comment for the struct.
>
> Fixes: b10a421a1f3
The Doxygen comments are placed before the related lines,
but the markers were /**< instead of /**
The struct rte_flow_item_integrity did not appear in Doxygen output
because there was no general comment for the struct.
Fixes: b10a421a1f3b ("ethdev: add packet integrity check flow rules")
Signed
19/05/2021 18:53, Ferruh Yigit:
> On 5/19/2021 5:27 PM, Thomas Monjalon wrote:
> > The Doxygen comments are placed before the related lines,
> > but the markers were /**< instead of /**
> >
> > Fixes: b10a421a1f3b ("ethdev: add packet integrity check flow rules")
> >
> > Signed-off-by: Thomas Mon
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon
> Subject: [PATCH] doc: remove obsolete future considerations in flow guide
>
> After 4 years, rte_flow has evolved enough to not require special notes
> about what could be added in future.
> Part of the removed plans were obsolete
On 5/19/2021 5:27 PM, Thomas Monjalon wrote:
> The Doxygen comments are placed before the related lines,
> but the markers were /**< instead of /**
>
> Fixes: b10a421a1f3b ("ethdev: add packet integrity check flow rules")
>
> Signed-off-by: Thomas Monjalon
> ---
> lib/ethdev/rte_flow.h | 18 +++
20/04/2021 00:06, Stephen Hemminger:
> The DPDK project is only committed to supporting upstream kernel
> versions that are still in support. The 3.16 kernel has reached
> End Of Life (in June 2020). The next LTS kernel is 4.4 and is
> supported until February 2020.
>
> This does not change the ex
On 5/19/21 7:27 PM, Thomas Monjalon wrote:
The Doxygen comments are placed before the related lines,
but the markers were /**< instead of /**
Fixes: b10a421a1f3b ("ethdev: add packet integrity check flow rules")
Signed-off-by: Thomas Monjalon
Acked-by: Andrew Rybchenko
The Doxygen comments are placed before the related lines,
but the markers were /**< instead of /**
Fixes: b10a421a1f3b ("ethdev: add packet integrity check flow rules")
Signed-off-by: Thomas Monjalon
---
lib/ethdev/rte_flow.h | 18 +-
1 file changed, 9 insertions(+), 9 deletions
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, May 19, 2021 4:44 AM
> To: McDaniel, Timothy
> Cc: dev@dpdk.org; Carrillo, Erik G ; Van Haaren,
> Harry ; Jerin Jacob ; Jerin
> Jacob
> Subject: Re: [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue
>
> 18/05/2021
19/05/2021 16:20, Thomas Monjalon:
> From: Asaf Penso
>
> The support of the new RTE_FLOW_ITEM_TYPE_INTEGRITY
> was added in the release notes 21.02 by mistake.
>
> The support of the Sub-Function representors was missing
> in the release notes and the mlx5 guide.
>
> Fixes: 79f8952783d0 ("net/
On 5/19/2021 2:25 PM, Chengwen Feng wrote:
> Currently, the SVE code is compiled only when -march supports SVE
> (e.g. '-march=armv8.2a+sve'), there maybe some problem[1] with this
> approach.
>
> The solution:
> a. If the minimum instruction set support SVE then compiles it.
> b. Else if the comp
From: Asaf Penso
The support of the new RTE_FLOW_ITEM_TYPE_INTEGRITY
was added in the release notes 21.02 by mistake.
The support of the Sub-Function representors was missing
in the release notes and the mlx5 guide.
Fixes: 79f8952783d0 ("net/mlx5: support integrity flow item")
Fixes: cb95feefdd
On Wed, May 19, 2021 at 6:58 PM Chengwen Feng wrote:
>
> Currently, the soc_kunpeng930 declares '-march=armv8.2-a+crypto+sve',
> but some compiler doesn't recognize the march because it doesn't
> support sve.
>
> To solve this bug we use the following scheme:
> 1. Define 'march_base' tuple which d
On 2021/5/19 20:34, David Marchand wrote:
> On Wed, May 19, 2021 at 1:57 PM Chengwen Feng wrote:
>>
>> Compile error with gcc8.3 and crossfile arm64_thunderx2_linux_gcc:
>> ../drivers/net/hns3/hns3_rxtx_vec_sve.c
>> cc1: error: switch ‘-mcpu=armv8.1-a’ conflicts with
>>
On 2021/5/19 20:37, David Marchand wrote:
> On Wed, May 19, 2021 at 2:17 PM fengchengwen wrote:
>> We also found compile error with gcc8.3 with arm64_kunpeng930_linux_gcc
>> (-march=-march=armv8.2-a+crypto+sve):
>> In file included from
>> ../dpdk-next-net/lib/eal/common/eal_common_options.
Thanks a lot, Ferruh
Already rebase and send v6, please review 2/2 patch.
On 2021/5/19 20:30, Ferruh Yigit wrote:
> On 5/19/2021 12:54 PM, Chengwen Feng wrote:
>> Compile error with gcc8.3 and crossfile arm64_thunderx2_linux_gcc:
>> ../drivers/net/hns3/hns3_rxtx_vec_sve.c
>> cc1: error:
Currently, the SVE code is compiled only when -march supports SVE
(e.g. '-march=armv8.2a+sve'), there maybe some problem[1] with this
approach.
The solution:
a. If the minimum instruction set support SVE then compiles it.
b. Else if the compiler support SVE then compiles it.
c. Otherwise don't com
Currently, the soc_kunpeng930 declares '-march=armv8.2-a+crypto+sve',
but some compiler doesn't recognize the march because it doesn't
support sve.
To solve this bug we use the following scheme:
1. Define 'march_base' tuple which defines support march, it should
arrange from lower to higher.
e.g.
This patch set contains two bugfixes for Kunpeng SVE compile.
---
v6:
* fix compile error with gcc8.3 and thunder2 of 2/2 patch
v5:
* make sure 'march_feature' parsed depend on 'march_base'
* only the kunpeng930 use the new option
v4:
* fix compile option combine problem of 1/2 patch
v3:
* fix che
Hi.
I checked how it works on QAT hardware, and it does no harm. All unit tests
still pass.
Verified on two QAT-enabled machines.
The question is: should this patch be simplified to just add a call to memset
(to zero the digest variable while still keeping it on the stack) at the
function begi
Hi.
I checked how it works on QAT hardware, and it does no harm. All unit tests
still pass.
Verified on two QAT-enabled machines.
The question is: should this patch be simplified to just add a call to memset
(to zero the digest variable while still keeping it on the stack) at the
function begi
On Wed, May 19, 2021 at 2:30 PM Ferruh Yigit wrote:
>
> On 5/19/2021 12:54 PM, Chengwen Feng wrote:
> > Compile error with gcc8.3 and crossfile arm64_thunderx2_linux_gcc:
> > ../drivers/net/hns3/hns3_rxtx_vec_sve.c
> > cc1: error: switch ‘-mcpu=armv8.1-a’ conflicts with
> > ‘-mar
On Wed, May 19, 2021 at 2:17 PM fengchengwen wrote:
> We also found compile error with gcc8.3 with arm64_kunpeng930_linux_gcc
> (-march=-march=armv8.2-a+crypto+sve):
> In file included from
> ../dpdk-next-net/lib/eal/common/eal_common_options.c:38:
> ../dpdk-next-net/lib/eal/arm/include/rte_
On Wed, May 19, 2021 at 1:57 PM Chengwen Feng wrote:
>
> Compile error with gcc8.3 and crossfile arm64_thunderx2_linux_gcc:
> ../drivers/net/hns3/hns3_rxtx_vec_sve.c
> cc1: error: switch ‘-mcpu=armv8.1-a’ conflicts with
> ‘-march=armv8.2-a’ switch [-Werror]
> ../dri
19/05/2021 10:55, Yan Xia:
> Add tested Intel platforms with Intel NICs to v21.05 release note.
>
> Signed-off-by: Yan Xia
Applied, thanks.
17/05/2021 14:39, Raslan Darawsheh:
> Add tested platforms with Mellanox NICs to the 21.05 release notes.
>
> Signed-off-by: Raslan Darawsheh
Applied, thanks
On 5/19/2021 12:54 PM, Chengwen Feng wrote:
> Compile error with gcc8.3 and crossfile arm64_thunderx2_linux_gcc:
> ../drivers/net/hns3/hns3_rxtx_vec_sve.c
> cc1: error: switch ‘-mcpu=armv8.1-a’ conflicts with
> ‘-march=armv8.2-a’ switch [-Werror]
> ../drivers/net/hns3/hns3_r
On 2021/5/19 17:27, Ferruh Yigit wrote:
> On 5/19/2021 9:08 AM, David Marchand wrote:
>> On Tue, May 18, 2021 at 6:28 PM Ferruh Yigit wrote:
>>>
>>> On 5/14/2021 3:12 PM, Honnappa Nagarahalli wrote:
>
> Currently, the SVE code is compiled only when -march supports SVE (e.g. '
19/05/2021 13:58, Ferruh Yigit:
> On 5/18/2021 5:43 PM, Thomas Monjalon wrote:
> > From: Asaf Penso
> >
> > Adding more information about the release milestones.
> > This includes the scope of change, expectations, etc.
> >
> > Signed-off-by: Asaf Penso
> > Signed-off-by: Thomas Monjalon
> > A
On 5/18/2021 5:43 PM, Thomas Monjalon wrote:
> From: Asaf Penso
>
> Adding more information about the release milestones.
> This includes the scope of change, expectations, etc.
>
> Signed-off-by: Asaf Penso
> Signed-off-by: Thomas Monjalon
> Acked-by: John McNamara
> Acked-by: Ajit Khaparde
Compile error with gcc8.3 and crossfile arm64_thunderx2_linux_gcc:
../drivers/net/hns3/hns3_rxtx_vec_sve.c
cc1: error: switch ‘-mcpu=armv8.1-a’ conflicts with
‘-march=armv8.2-a’ switch [-Werror]
../drivers/net/hns3/hns3_rxtx_vec_sve.c:5:10: fatal error:
arm_s
Compile error with gcc8.3 and crossfile arm64_thunderx2_linux_gcc:
../drivers/net/hns3/hns3_rxtx_vec_sve.c
cc1: error: switch ‘-mcpu=armv8.1-a’ conflicts with
‘-march=armv8.2-a’ switch [-Werror]
../drivers/net/hns3/hns3_rxtx_vec_sve.c:5:10: fatal error:
arm_s
13/05/2021 10:34, David Marchand:
> Hook check-symbol-maps.sh in the symbol check when in developer mode to
> help developers catch issues before submitting their changes.
>
> Signed-off-by: David Marchand
> Reviewed-by: Ray Kinsella
Series applied, thanks.
Hi,
> -Original Message-
> From: announce On Behalf Of Thomas
> Monjalon
> Sent: Wednesday, May 12, 2021 11:57 PM
> To: annou...@dpdk.org
> Subject: [dpdk-announce] release candidate 21.05-rc3
>
> A new DPDK release candidate is ready for testing:
> https://git.dpdk.org/dpdk/tag/?i
14/05/2021 11:03, Ferruh Yigit:
> GCC -> GNU Compiler Collection
> ID-> Identification/Identity/Identifier
> IP -> Internet Protocol
> QinQ-> IEEE 802.1Q in 802.1Q
> SoC -> System on a chip
> VEB -> Virtual Ethernet Bridge
> Windows ->
>
> Signed-off-by: Ferruh Yigit
App
Ping for review.
It looks too late for 21.05, moved as Deferred in patchwork.
25/04/2021 15:02, Min Hu (Connor):
> From: Chengchang Tang
>
> This patch add support for dump the device registers from a running
> application. It can help developers locate the problem.
>
> Signed-off-by: Chengcha
> > From the documentation:
> > "The SoC configuration is a combination of implementer and CPU part
> > number configuration and SoC-specific configuration."
> >
> > Align Qualcomm SoC configuration with the configuration of other server
> > SoCs (eMAG, Kunpeng 9x0): add a soc configuration to th
19/05/2021 11:57, Piotr Kubaj:
> Well, isn't FreeBSD already supported?
>
> Even https://www.dpdk.org/ mentions supporting FreeBSD.
Yes it is supposed to be supported.
But why are you adding all this code for PPC?
It doesn't seem to be all related to clang only.
PS: please do not top-post.
> O
On Mon, May 17, 2021 at 3:48 PM McDaniel, Timothy
wrote:
> > > @@ -387,4 +366,17 @@ Class of service can be specified in the devargs, as
> > follows
> > >
> > > .. code-block:: console
> > >
> > > - --vdev=dlb2_event,cos=<0..4>
> > > + --allow ea:00.0,cos=<0..4>
> > > +
> > > +Use
26/04/2021 17:34, Timothy McDaniel:
> Add dlb to usertools/dpdk-devbind.py so that it shows up
> as an eventdev, and is identified as Intel dlb.
>
> Signed-off-by: Timothy McDaniel
Applied (with DLB uppercased), thanks.
18/05/2021 17:01, Jerin Jacob:
> On Wed, May 12, 2021 at 11:55 PM McDaniel, Timothy
> wrote:
> >
> > From: Timothy McDaniel
> >
> > This commit fixes the following bugs in the vector based
> > dequeue path:
> > - extract hw sched type
> > - update xstats
> >
> > The default mode of operation was
On 5/19/2021 9:08 AM, David Marchand wrote:
> On Tue, May 18, 2021 at 6:28 PM Ferruh Yigit wrote:
>>
>> On 5/14/2021 3:12 PM, Honnappa Nagarahalli wrote:
>>>
>>>
Currently, the SVE code is compiled only when -march supports SVE (e.g. '-
march=armv8.2a+sve'), there maybe some proble
On Tue, May 18, 2021 at 06:43:03PM +0200, Thomas Monjalon wrote:
> From: Asaf Penso
>
> Adding more information about the release milestones.
> This includes the scope of change, expectations, etc.
>
> Signed-off-by: Asaf Penso
> Signed-off-by: Thomas Monjalon
> Acked-by: John McNamara
> Acke
Add tested Intel platforms with Intel NICs to v21.05 release note.
Signed-off-by: Yan Xia
---
doc/guides/rel_notes/release_21_05.rst | 121 +
1 file changed, 121 insertions(+)
diff --git a/doc/guides/rel_notes/release_21_05.rst
b/doc/guides/rel_notes/release_21_05.rst
i
16/03/2021 22:00, Stephen Hemminger:
> This resolves all the left over warnings and errors reported
> by the check-spdx-tag script.
>
> Stephen Hemminger (4):
> common/mlx5: add missing SPDX tag for windows headers
> devtools/check-spdx-tag.sh: ignore JSON files
> doc: add SPDX tag to custom
16/03/2021 22:00, Stephen Hemminger:
> Trivial file, but add SPDX license tag per policy
>
> Signed-off-by: Stephen Hemminger
I wrote this file in 2018. Adding copyright:
Copyright 2018 Mellanox Technologies, Ltd
> > These files were added without requires SPDX headers.
> >
> > Fixes: 7525ebd8ebb0 ("common/mlx5: add glue functions on Windows")
> > Cc: tal...@nvidia.com
> > Signed-off-by: Stephen Hemminger
> > ---
> > -/*
> > +/* SPDX-License-Identifier: BSD-3-Clause
> > * Copyright (C) Mellanox Technolo
> > The return value for a test when the required PMD is not loaded should
> > be TEST_SKIPPED, rather than TEST_FAILED.
> >
> > Fixes: 8bfdd8a7f0f1 ("test/crypto: refactor to use sub test suites")
> >
> > Signed-off-by: Ciara Power
>
> Acked-by: Fan Zhang
Applied, thanks
The array rss_key has size 'vf->vf_res->rss_key_size', the array index
should be less than that.
Cc: sta...@dpdk.org
Fixes: 69dd4c3d0898 ("net/avf: enable queue and device")
Signed-off-by: Haiyue Wang
---
drivers/net/iavf/iavf_ethdev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff
Hello,
I noticed a few failures on the alarm_autotest unit test in UNH lab.
The trace:
RTE>>alarm_autotest
check if the callback will be called
Callback setting flag - OK. [cb_arg = (nil)]
check if it will fail to set alarm with wrong ms values
check if it will fail to set alarm with null callbac
On 5/17/2021 10:07 AM, Feifei Wang wrote:
> In Arm platform, when "RTE_ARCH_ARM64_MEMCPY" is set as true, compiler
> will report variable uninitilized warning:
>
> ../drivers/crypto/qat/qat_sym_session.c:
> In function ‘partial_hash_compute’:
> ../lib/eal/include/generic/rte_byteorder.h:241:24: wa
On Tue, May 18, 2021 at 6:28 PM Ferruh Yigit wrote:
>
> On 5/14/2021 3:12 PM, Honnappa Nagarahalli wrote:
> >
> >
> >>
> >> Currently, the SVE code is compiled only when -march supports SVE (e.g. '-
> >> march=armv8.2a+sve'), there maybe some problem[1] with this approach.
> >>
> >> The solution:
On 4/12/2021 9:22 AM, Tianyu Li wrote:
> Fix the missing Tx-bps counter for memif zero-copy mode
> Before
> Rx-pps: 6891450 Rx-bps: 3528438928
> Tx-pps: 6891482 Tx-bps:0
> After
> Throughput (since last show)
> Rx-pps: 11157056 Rx-bps:
17/05/2021 11:07, Feifei Wang:
> In Arm platform, when "RTE_ARCH_ARM64_MEMCPY" is set as true, compiler
> will report variable uninitilized warning:
>
> ../drivers/crypto/qat/qat_sym_session.c:
> In function ‘partial_hash_compute’:
> ../lib/eal/include/generic/rte_byteorder.h:241:24: warning:
> ‘’
> -Original Message-
> From: Jerin Jacob
> Sent: Wednesday, April 14, 2021 2:51 AM
> To: Ruifeng Wang
> Cc: jer...@marvell.com; hemant.agra...@nxp.com; Ferruh Yigit
> ; tho...@monjalon.net; David Marchand
> ; dpdk-dev ; nd
> ; Honnappa Nagarahalli
> Subject: Re: [dpdk-dev] [PATCH 1/4] ex
18/05/2021 22:42, David Christensen:
> On 5/16/21 5:46 PM, Piotr Kubaj wrote:
> > __ppc_get_timebase() is only present when glibc is used.
> >
> > Signed-off-by: Piotr Kubaj
> > ---
> > lib/eal/ppc/include/rte_altivec.h | 3 +++
> > lib/eal/ppc/include/rte_cycles.h | 12
> > li
13/05/2021 10:23, Bruce Richardson:
> On Thu, May 13, 2021 at 09:10:37AM +0800, Min Hu (Connor) wrote:
> > Variable i is used as a denominator which may be zero, and
> > this may result in segmentation fault.
> >
> > This patch fixed it.
> >
> > Fixes: 948bc3d6d095 ("test: add reciprocal based di
72 matches
Mail list logo
