> -Original Message-
> From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
> Sent: Wednesday, June 5, 2019 8:05 PM
> To: Rong, Leyi ; Zhang, Qi Z
> Cc: dev@dpdk.org; Stillwell Jr, Paul M
> Subject: Re: [dpdk-dev] [PATCH 39/49] net/ice/base: slightly code update
>
>
>
> On 6/4/19
> -Original Message-
> From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
> Sent: Wednesday, June 5, 2019 12:56 AM
> To: Rong, Leyi ; Zhang, Qi Z
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 00/49] shared code update
>
> Hi Leyi,
>
> On 6/4/19 7:41 AM, Leyi Rong wrote:
> >
From: Michael Santana Francisco
Sent: Wednesday, June 5, 2019 5:39 PM
To: Honnappa Nagarahalli ; Aaron Conole
; tho...@monjalon.net
Cc: Ruifeng Wang (Arm Technology China) ; Gavin Hu (Arm
Technology China) ; Dharmik Thakkar
; jerin.ja...@caviumnetworks.com; ys...@mellanox.com;
dev@dpdk.org;
On 06/05, Li, Xiaoyun wrote:
>>
>> Yes, I agree, but I don't think it is the case here.
>>
>> >It will cause segment fault in enqueue/dequeue.
>>
>> Hmm, have you debug it? Which line caused the segfault?
>>
>> You can refer to test_rawdev_enqdeq function in skeleton_rawdev_test.c, what
>> it d
From: Stephen Hemminger
The vmbus scan code can just skip non-network devices.
More importantly, this fixes the bug where some vmbus devices
don't have all the attributes (like monitor_id) and a single
failure would cause the scan to break the loop.
Fixes: 831dba47bd36 ("bus/vmbus: add Hyper-V v
From: Stephen Hemminger
The vmbus scan code can just skip non-network devices.
More importantly, this fixes the bug where some vmbus devices
don't have all the attributes (like monitor_id) and a single
failure would cause the scan to break the loop.
Fixes: 831dba47bd36 ("bus/vmbus: add Hyper-V v
Adding defines for missing RTE_MACHINE_CPUFLAGs.
Signed-off-by: David Wilder
---
I am splitting my previous patch "meson: Update flags and values for ppc_64"
into two separate patches (not a series). This is the first patch.
Acked-by: David Christensen
Setting RTE_MAX_LCORE to reflect the largest available configuration.
Signed-off-by: David Wilder
---
I am splitting my previous patch "meson: Update flags and values for ppc_64"
into two separate patches (not a series). This is the second patch.
Updating values for both the meson and make buil
Traffic is only received on RX queue 0. Anyone run into this? The link
partner shows traffic received and transmitted on all configured queues (16 in
this case) so I don't think the link partner is dropping traffic in such a way
that the remaining traffic flows to a single RX queue on the SUT
Setting RTE_MAX_LCORE to reflect the largest available configuration.
Signed-off-by: David Wilder
---
I am splitting my previous patch "meson: Update flags and values for ppc_64"
into two separate patches (not a series). This is the second patch.
Updating values for both the meson and make buil
Adding defines for missing RTE_MACHINE_CPUFLAGs.
Signed-off-by: David Wilder
---
I am splitting my previous patch "meson: Update flags and values for ppc_64"
into two separate patches (not a series). This is the first patch.
config/ppc_64/meson.build | 2 ++
1 file changed, 2 insertions(+)
d
-Original Message-
From: Andrew Rybchenko
Date: Wednesday, June 5, 2019 at 1:17 AM
To: Yong Wang
Cc: "dev@dpdk.org" , "sta...@dpdk.org"
Subject: [PATCH 11/11] net/vmxnet3: fix Tx prepare to set positive rte_errno
Fixes: baf3bbae5556 ("net/vmxnet3: add Tx preparation")
Cc: sta...
On 6/5/19 5:36 PM, Honnappa Nagarahalli wrote:
Thomas Monjalon writes:
05/06/2019 21:40, Aaron Conole:
Thomas Monjalon writes:
The compilation of the master branch is failing for aarch64:
https://travis-ci.com/DPDK/dpdk
The log is so much verbose that I am not able to understand wh
> On Jun 5, 2019, at 5:08 PM, David Christensen wrote:
>
> Using a Mellanox ConnectX-5 @ 100Gb on a Supermicro system with DPDK 18.11.1
> and pktgen 3.6.6 from the Master branch (downloaded today). When I configure
> pktgen to use multiple queues, I'm able to set the number of TX queues
> c
Using a Mellanox ConnectX-5 @ 100Gb on a Supermicro system with DPDK
18.11.1 and pktgen 3.6.6 from the Master branch (downloaded today).
When I configure pktgen to use multiple queues, I'm able to set the
number of TX queues correctly but the number of RX queues doesn't look
correct. pktgen in
> >
> > Thomas Monjalon writes:
> >
> > > 05/06/2019 21:40, Aaron Conole:
> > >> Thomas Monjalon writes:
> > >>
> > >> > The compilation of the master branch is failing for aarch64:
> > >> >https://travis-ci.com/DPDK/dpdk
> > >> > The log is so much verbose that I am not able to understan
Adding support for meson build environment
for the new BBDEV PMD driver.
Signed-off-by: Nicolas Chautru
---
drivers/baseband/fpga_lte_fec/meson.build | 7 +++
drivers/baseband/meson.build | 2 +-
2 files changed, 8 insertions(+), 1 deletion(-)
create mode 100644 drivers/baseban
Supports for FEC 4G PMD Driver on FPGA card PAC N3000
Signed-off-by: Nicolas Chautru
---
config/common_base |6 +
drivers/baseband/Makefile |2 +
drivers/baseband/fpga_lte_fec/Makefile | 29 +
drivers/baseband/fpga_lt
Adding documentation related to the new PMD driver
in previous commit
Signed-off-by: Nicolas Chautru
---
doc/guides/bbdevs/fpga_lte_fec.rst | 318 +
doc/guides/bbdevs/index.rst| 1 +
2 files changed, 319 insertions(+)
create mode 100644 doc/guides/b
This is adding a new PMD driver for BBDEV device based on
FPGA implementation on PAC N3000 HW to provide FEC 4G acceleration.
v1 was shared earlier on this patchwork :
https://patches.dpdk.org/patch/53409/
The existing BBDEV test framework is still supported.
Main updates based on feedback duri
>
> Thomas Monjalon writes:
>
> > 05/06/2019 21:40, Aaron Conole:
> >> Thomas Monjalon writes:
> >>
> >> > The compilation of the master branch is failing for aarch64:
> >> > https://travis-ci.com/DPDK/dpdk
> >> > The log is so much verbose that I am not able to understand what is
> >> > reall
Thomas Monjalon writes:
> 05/06/2019 21:40, Aaron Conole:
>> Thomas Monjalon writes:
>>
>> > The compilation of the master branch is failing for aarch64:
>> >https://travis-ci.com/DPDK/dpdk
>> > The log is so much verbose that I am not able to understand
>> > what is really wrong.
>> > Plea
+David
(had similar questions)
> -Original Message-
> From: Stephen Hemminger
> Sent: Wednesday, June 5, 2019 11:48 AM
> To: Phil Yang (Arm Technology China)
> Cc: dev@dpdk.org; tho...@monjalon.net; jer...@marvell.com;
> hemant.agra...@nxp.com; Honnappa Nagarahalli
> ; Gavin Hu (Arm Tech
On Wed, 2019-06-05 at 21:22 +0100, Bruce Richardson wrote:
> After using meson to configure a build, we output a brief list of all
> components that are enabled. However, of more use to most users is a
> list of what is not being enabled, so that they can look for gaps and
> see about fixing those
For each driver where we optionally disable it, add in the reason why it's
being disabled, so the user knows how to fix it.
Signed-off-by: Bruce Richardson
---
drivers/raw/dpaa2_cmdif/meson.build | 1 +
drivers/raw/dpaa2_qdma/meson.build | 1 +
drivers/raw/ifpga_rawdev/meson.build | 1 +
3 fi
For each driver where we optionally disable it, add in the reason why it's
being disabled, so the user knows how to fix it.
Signed-off-by: Bruce Richardson
---
drivers/net/af_packet/meson.build | 1 +
drivers/net/af_xdp/meson.build | 1 +
drivers/net/avp/meson.build | 3 ++-
drive
For each driver where we optionally disable it, add in the reason why it's
being disabled, so the user knows how to fix it.
Signed-off-by: Bruce Richardson
---
drivers/mempool/dpaa/meson.build | 3 ++-
drivers/mempool/dpaa2/meson.build | 3 ++-
2 files changed, 4 insertions(+), 2 deletions(-)
For each driver where we optionally disable it, add in the reason why it's
being disabled, so the user knows how to fix it.
Signed-off-by: Bruce Richardson
---
drivers/event/dpaa/meson.build | 1 +
drivers/event/dpaa2/meson.build | 1 +
2 files changed, 2 insertions(+)
diff --git a/drivers/eve
For each driver where we optionally disable it, add in the reason why it's
being disabled, so the user knows how to fix it.
Signed-off-by: Bruce Richardson
---
drivers/crypto/aesni_gcm/meson.build | 5 +++--
drivers/crypto/aesni_mb/meson.build | 5 +++--
drivers/crypto/caam_jr/meson.build | 3
For each driver where we optionally disable it, add in the reason why it's
being disabled, so the user knows how to fix it.
Signed-off-by: Bruce Richardson
---
drivers/compress/isal/meson.build | 3 ++-
drivers/compress/zlib/meson.build | 1 +
2 files changed, 3 insertions(+), 1 deletion(-)
dif
For each driver where we optionally disable it, add in the reason why it's
being disabled, so the user knows how to fix it.
Signed-off-by: Bruce Richardson
---
drivers/common/dpaax/meson.build | 3 ++-
drivers/common/mvep/meson.build | 1 +
drivers/common/qat/meson.build | 1 +
3 files change
For each library where we optionally disable it, add in the reason why it's
being disabled, so the user knows how to fix it.
Signed-off-by: Bruce Richardson
---
lib/librte_kni/meson.build | 1 +
lib/librte_power/meson.build | 1 +
lib/librte_telemetry/meson.build | 1 +
lib/librte_vhos
For each driver where we optionally disable it, add in the reason why it's
being disabled, so the user knows how to fix it.
Signed-off-by: Bruce Richardson
---
drivers/bus/dpaa/meson.build | 3 ++-
drivers/bus/fslmc/meson.build | 3 ++-
drivers/bus/vmbus/meson.build | 1 +
3 files changed, 5 in
After using meson to configure a build, we output a brief list of all
components that are enabled. However, of more use to most users is a
list of what is not being enabled, so that they can look for gaps and
see about fixing those gaps, e.g. by installing driver dependencies.
This patchset adds s
When configuring with meson we print out a list of enabled components, but
it is also useful to list out the disabled components and the reasons why.
Signed-off-by: Bruce Richardson
---
doc/guides/contributing/coding_style.rst | 15 ++-
drivers/meson.build | 12 +
The documentation is clarified to point to steps on building the
SDK libraries which are now publicly available.
Signed-off-by: Nicolas Chautru
---
doc/guides/bbdevs/turbo_sw.rst | 84 +++---
1 file changed, 46 insertions(+), 38 deletions(-)
diff --git a/doc/
Adding compile flag to allow to build the turbo_sw PMD
without dependency to have the SDK libraries installed.
Signed-off-by: Nicolas Chautru
---
config/common_base | 3 +-
drivers/baseband/turbo_sw/Makefile | 13
drivers/baseband/turbo_sw/bb
Signed-off-by: Nicolas Chautru
---
drivers/baseband/meson.build | 2 +-
drivers/baseband/turbo_sw/meson.build | 30 ++
2 files changed, 31 insertions(+), 1 deletion(-)
create mode 100644 drivers/baseband/turbo_sw/meson.build
diff --git a/drivers/baseband/me
Update v2 : Splitting into 3 patches as recommended
(ignore previous v2 which had a typo)
Based on discussion with maintainer, pushing first a patch to help
maintenance of the baseband_turbo_sw which had been lacking.
The documentation is clarified to point to steps on building the
SDK libraries w
Adding compile flag to allow to build the turbo_sw PMD
without dependency to have the SDK libraries installed.
Signed-off-by: Nicolas Chautru
---
config/common_base | 3 +-
drivers/baseband/turbo_sw/Makefile | 13
drivers/baseband/turbo_sw/bb
The documentation is clarified to point to steps on building the
SDK libraries which are now publicly available.
Signed-off-by: Nicolas Chautru
---
doc/guides/bbdevs/turbo_sw.rst | 84 +++---
1 file changed, 46 insertions(+), 38 deletions(-)
diff --git a/doc/
From: Thomas Monjalon
Signed-off-by: Thomas Monjalon
---
VERSION | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/VERSION b/VERSION
index 5cfba53..746b4f3 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-19.05.0-rc3
+19.05.0-rc4
--
1.8.3.1
Updated in v2 : Split into 3 patches as recommended.
Based on discussion with maintainer, pushing first a patch to help
maintenance of the baseband_turbo_sw which had been lacking.
The documentation is clarified to point to steps on building the
SDK libraries which are now publicly available. (Co
05/06/2019 21:40, Aaron Conole:
> Thomas Monjalon writes:
>
> > The compilation of the master branch is failing for aarch64:
> > https://travis-ci.com/DPDK/dpdk
> > The log is so much verbose that I am not able to understand
> > what is really wrong.
> > Please help to diagnose and fix, thank
>-Original Message-
>From: David Marchand [mailto:david.march...@redhat.com]
>Sent: Tuesday, June 4, 2019 2:00 AM
>To: dev@dpdk.org
>Cc: tho...@monjalon.net; acon...@redhat.com; msant...@redhat.com; Dharmik
>Thakkar ;
>sta...@dpdk.org; Wang, Yipeng1 ; Gobriel, Sameh
>; Richardson, Bruce
>
>-Original Message-
>From: David Marchand [mailto:david.march...@redhat.com]
>Sent: Tuesday, June 4, 2019 2:00 AM
>To: dev@dpdk.org
>Cc: tho...@monjalon.net; acon...@redhat.com; msant...@redhat.com;
>sta...@dpdk.org; Wang, Yipeng1
>; Gobriel, Sameh ;
>Richardson, Bruce ; De Lara
>Guarch,
On Wed, Jun 5, 2019 at 6:00 PM Phil Yang
mailto:phil.y...@arm.com>> wrote:
This patch set added MCS lock library and its unit test.
The MCS lock (proposed by JOHN M. MELLOR-CRUMMEY and MICHAEL L. SCOTT) provides
scalability by spinning on a CPU/thread local variable which avoids expensive
cach
Thomas Monjalon writes:
> The compilation of the master branch is failing for aarch64:
> https://travis-ci.com/DPDK/dpdk
> The log is so much verbose that I am not able to understand
> what is really wrong.
> Please help to diagnose and fix, thanks.
A discussion about this:
http://mails.d
> >
> > Hi Wang,
> >
> > On 05/06/2019 06:54, Ruifeng Wang wrote:
> > > When a tbl8 group is getting attached to a tbl24 entry, lookup might
> > > fail even though the entry is configured in the table.
> > >
> > > For ex: consider a LPM table configured with 10.10.10.1/24.
> > > When a new entry 10
The compilation of the master branch is failing for aarch64:
https://travis-ci.com/DPDK/dpdk
The log is so much verbose that I am not able to understand
what is really wrong.
Please help to diagnose and fix, thanks.
Hi Ola,
Is it possible to add burst enqueue and dequeue functions as well, so we can
plug this into a mempool handler? Besides the mempool handler, I think the
all-or-nothing semantics would be useful for applications. Besides that, this
RFC looks good at a high level.
For a complete submissio
On Wed, Jun 05, 2019 at 05:45:41PM +0100, Bruce Richardson wrote:
> On Wed, Jun 05, 2019 at 04:24:09PM +, Jerin Jacob Kollanukkaran wrote:
> > > -Original Message-
> > > From: Neil Horman
> > > Sent: Sunday, May 26, 2019 12:14 AM
> > > To: dev@dpdk.org
> > > Cc: Neil Horman ; Jerin Jac
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, June 5, 2019 3:35 AM
> To: Rong, Leyi ; Zhang, Qi Z
> Cc: dev@dpdk.org; Sridhar, Vignesh ; Stillwell Jr,
> Paul M
> Subject: Re: [dpdk-dev] [PATCH 14/49] net/ice/base: refactor HW table init
> function
>
>
>
> On 6/4/19 7
The cmdline library used to be the only way to parse a
mac address. Now there is rte_ether_unformat_addr.
Signed-off-by: Stephen Hemminger
---
drivers/net/bonding/Makefile| 2 +-
drivers/net/bonding/meson.build | 2 +-
drivers/net/bonding/rte_eth_bond_args.c | 6 +-
3 fil
The cmdline_parse_ether_addr does not need to be used everywhere
in testpmd. Can use rte_ether_unformat_addr instead.
As an added bonus it eliminates some code for copying.
Signed-off-by: Stephen Hemminger
---
app/test-pmd/cmdline_flow.c | 5 ++---
app/test-pmd/config.c | 10 +++---
a
Now that there is a version of ether_aton in rte_ether, it can
be used by the cmdline ethernet address parser.
Note: ether_aton_r can not be used in cmdline because
the old code would accept either bytes XX:XX:XX:XX:XX:XX
or words :: and we need to keep compatiablity.
Signed-off-by: S
Using bit operations like or and xor is faster than a loop
on all architectures. Really just explicit unrolling.
Similar cast to uint16 unaligned is already done in
other functions here.
Signed-off-by: Stephen Hemminger
Reviewed-by: Andrew Rybchenko
---
lib/librte_net/rte_ether.h | 17 +++-
From: Bruce Richardson
When including the rte_ether.h header in applications with warnings
enabled, a warning was given because of the assumption of 2-byte alignment
of ethernet addresses when processing them.
.../include/rte_ether.h:149:2: warning: converting a packed ‘const
struct ether_addr
Make a function that can be used in place of eth_aton_r
to convert a string to rte_ether_addr. This function
allows both byte (xx:xx:xx:xx:xx:xx) and word (::)
format and has the same lack of error handling as the original.
This also allows ethdev to no longer have a hard dependency
on
Use rte_eth_unformat_addr, so that ethdev can be built and work
without the cmdline library. The dependency on cmdline was
an arrangement of convenience anyway.
Signed-off-by: Stephen Hemminger
---
lib/Makefile | 1 -
lib/librte_ethdev/Makefile| 2 +-
lib/librte_ethd
Formatting Ethernet address and getting a random value are
not in critical path so they should not be inlined.
Signed-off-by: Stephen Hemminger
Acked-by: Rami Rosen
Reviewed-by: Andrew Rybchenko
---
lib/librte_net/Makefile| 1 +
lib/librte_net/meson.build | 2 +-
lib/libr
This is a collection of patches around the ethernet address
manipulation routines in librte_net/rte_ether.
v4
fix meson build
reword commit messages
add bonding and tespmd patches
v3
rebase to use rte_ether prefix
drop aligning ethernet headers for now.
Bruce Richardson (1):
net
05/06/2019 19:38, Nicolas Chautru:
> Adding compile flag to allow to build the turbo_sw PMD
> without SDK libraries installed with limited capability.
> Update of documentation for buidling steps.
> Meson build support.
There are 3 different things which deserve 3 patches.
About the doc, I am sur
Adding compile flag to allow to build the turbo_sw PMD
without SDK libraries installed with limited capability.
Update of documentation for buidling steps.
Meson build support.
Signed-off-by: Nicolas Chautru
---
config/common_base | 3 +-
doc/guides/bbdevs/turbo_s
Based on discussion with maintainer, pushing first a patch to help
maintenance of the baseband_turbo_sw which had been lacking.
The documentation is clarified to point to steps on building the
SDK libraries which are now publicly available. (Cosmetic changes
to the webpage containing these SDK wil
05/06/2019 17:58, Phil Yang:
> This patch set added MCS lock library and its unit test.
It seems this patch is targetting 19.08,
however it missed the proposal deadline by 2 days.
+Cc techboard for a decision.
03/06/2019 18:56, Dharmik Thakkar:
> > On Jun 1, 2019, at 10:59 AM, David Marchand
> > wrote:
> > We have accumulated quite some fixes with Michael on app/test.
> > Do you mind if I take your patch as part of our series?
>
> Please, go ahead.
Superseded by https://patches.dpdk.org/patch/54336/
> >Replaced multiple neon instructions with single equivalent instruction.
> >This made simpler code and a bit higher performance.
> >Hash bulk lookup had 0.1% ~ 3% performance gain in tests on ARM A72
> >platforms.
> >
> >Signed-off-by: Ruifeng Wang
> >Reviewed-by: Gavin Hu
> >---
> [Wang, Yipen
Jerin Jacob Kollanukkaran writes:
>> -Original Message-
>> From: Jerin Jacob Kollanukkaran
>> Sent: Wednesday, April 10, 2019 8:10 PM
>> To: dev@dpdk.org; acon...@redhat.com
>> Cc: gavin...@arm.com; konstantin.anan...@intel.com
>> Subject: Re: [EXT] [PATCH 1/3] acl: fix arm argument types
12/04/2019 10:29, Bruce Richardson:
> Rather than having a separate version.map file for linux/BSD and an
> exports definition file for windows for each library, generate the
> latter from the former automatically at build time.
>
> Signed-off-by: Bruce Richardson
For an unknown reason, this pat
30/05/2019 14:48, Bruce Richardson:
> On Thu, May 30, 2019 at 03:38:36PM +0300, Ilya Maximets wrote:
> > Don't need to check dependencies if test apps will not be built anyway.
> >
> > Signed-off-by: Ilya Maximets
> Acked-by: Bruce Richardson
> Acked-by: Aaron Conole
> Acked-by: Luca Boccassi
On Wed, 5 Jun 2019 23:58:45 +0800
Phil Yang wrote:
> This patch set added MCS lock library and its unit test.
>
> The MCS lock (proposed by JOHN M. MELLOR-CRUMMEY and MICHAEL L. SCOTT)
> provides
> scalability by spinning on a CPU/thread local variable which avoids expensive
> cache bouncings.
On 5/17/19 11:15 AM, David Marchand wrote:
We currently have no check on the mempool pointer passed to
rte_eth_rx_queue_setup.
Let's avoid a plain crash when dereferencing it.
Suggested-by: Jens Freimann
Signed-off-by: David Marchand
Acked-by: Andrew Rybchenko
On Wed, Jun 05, 2019 at 04:24:09PM +, Jerin Jacob Kollanukkaran wrote:
> > -Original Message-
> > From: Neil Horman
> > Sent: Sunday, May 26, 2019 12:14 AM
> > To: dev@dpdk.org
> > Cc: Neil Horman ; Jerin Jacob Kollanukkaran
> > ; Bruce Richardson ;
> > Thomas Monjalon
> > Subject: [E
05/06/2019 16:11, Bruce Richardson:
> On CentOS/RHEL 7, we get build errors reported due to a variable being
> possibly unitialized. Setting a default init value fixes this issue.
>
> Fixes: c68d7aa354f6 ("crypto/aesni_mb: use architecture independent macros")
> Cc: roy.fan.zh...@intel.com
> Cc: s
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, June 5, 2019 5:24 AM
> To: Rong, Leyi ; Zhang, Qi Z
> Cc: dev@dpdk.org; Nowlin, Dan ; Stillwell Jr, Paul M
>
> Subject: Re: [dpdk-dev] [PATCH 47/49] net/ice/base: enable additional
> switch rules
>
>
>
> On 6/4/19 7:42 AM
17/05/2019 16:09, Konstantin Ananyev:
> clang 6.0 and onwards, for the external function call generates
> BPF_PSEUDO_CALL instruction:
> call pseudo +-off -> call another bpf function.
> More details about that change: https://lwn.net/Articles/741773/
> DPDK BPF implementation right now doesn't sup
On Wed, 5 Jun 2019 11:59:52 +0300
Andrew Rybchenko wrote:
> On 6/5/19 4:08 AM, Stephen Hemminger wrote:
> > Use rte_eth_unformat_addr, so that ethdev can be built and work
> > without the cmdline library. The dependency on cmdline was
> > an arrangement of convenience anyway.
> >
> > Signed-off-b
On Wed, 5 Jun 2019 11:55:21 +0300
Andrew Rybchenko wrote:
> On 6/5/19 4:08 AM, Stephen Hemminger wrote:
> > Make a function that coresponds with eth_aton_r which can
>
> I guess ether_aton_r
>
> > be used to convert string to rte_ether_addr.
> >
> > This also allows rte_ethdev to no longer de
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, June 5, 2019 9:28 AM
> To: Stillwell Jr, Paul M ; Rong, Leyi
> ; Zhang, Qi Z
> Cc: dev@dpdk.org; Raj, Victor
> Subject: Re: [dpdk-dev] [PATCH 07/49] net/ice/base: replay advanced rule
> after reset
>
>
>
> On 6/5/19 6:16
On Wed, 5 Jun 2019 11:44:42 +0300
Andrew Rybchenko wrote:
> On 6/5/19 4:08 AM, Stephen Hemminger wrote:
> > Formatting ethernet address and getting a random value are
> > not in critical path so they should not be inlined.
> >
> > Signed-off-by: Stephen Hemminger
> > Acked-by: Rami Rosen
>
>
On Wed, Jun 5, 2019 at 6:00 PM Phil Yang wrote:
> This patch set added MCS lock library and its unit test.
>
> The MCS lock (proposed by JOHN M. MELLOR-CRUMMEY and MICHAEL L. SCOTT)
> provides
> scalability by spinning on a CPU/thread local variable which avoids
> expensive
> cache bouncings. It
On 6/5/19 6:16 PM, Stillwell Jr, Paul M wrote:
-Original Message-
From: Maxime Coquelin
Sent: Wednesday, June 5, 2019 8:59 AM
To: Stillwell Jr, Paul M ; Rong, Leyi
; Zhang, Qi Z
Cc: dev@dpdk.org; Raj, Victor
Subject: Re: [dpdk-dev] [PATCH 07/49] net/ice/base: replay advanced rule
af
> -Original Message-
> From: Neil Horman
> Sent: Sunday, May 26, 2019 12:14 AM
> To: dev@dpdk.org
> Cc: Neil Horman ; Jerin Jacob Kollanukkaran
> ; Bruce Richardson ;
> Thomas Monjalon
> Subject: [EXT] [RFC PATCH 0/2] introduce __rte_internal tag
>
> Hey-
> Based on our recent conv
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, June 5, 2019 8:59 AM
> To: Stillwell Jr, Paul M ; Rong, Leyi
> ; Zhang, Qi Z
> Cc: dev@dpdk.org; Raj, Victor
> Subject: Re: [dpdk-dev] [PATCH 07/49] net/ice/base: replay advanced rule
> after reset
>
>
>
> On 6/5/19 5:53
> -Original Message-
> From: Neil Horman
> Sent: Sunday, May 26, 2019 12:14 AM
> To: dev@dpdk.org
> Cc: Neil Horman ; Jerin Jacob Kollanukkaran
> ; Bruce Richardson ;
> Thomas Monjalon
> Subject: [EXT] [RFC PATCH 1/2] Add __rte_internal tag for functions and
> version target
> This tag is
Unit test and perf test for MCS queued lock.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
---
MAINTAINERS | 1 +
app/test/Makefile | 1 +
app/test/autotest_data.py | 6 +
app/test/autotest_test_funcs.py | 32 ++
Let all architectures use generic MCS queued lock implementation.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
---
.../common/include/arch/arm/rte_mcslock.h | 23 ++
.../common/include/arch/ppc_64/rte_mcslock.h | 19 ++
If there are multiple threads contending, they all attempt to take the
spinlock lock at the same time once it is released. This results in a
huge amount of processor bus traffic, which is a huge performance
killer. Thus, if we somehow order the lock-takers so that they know who
is next in line for
This patch set added MCS lock library and its unit test.
The MCS lock (proposed by JOHN M. MELLOR-CRUMMEY and MICHAEL L. SCOTT) provides
scalability by spinning on a CPU/thread local variable which avoids expensive
cache bouncings. It provides fairness by maintaining a list of acquirers and
passin
On 6/5/19 5:53 PM, Stillwell Jr, Paul M wrote:
diff --git a/drivers/net/ice/base/ice_switch.c
b/drivers/net/ice/base/ice_switch.c
index c53021aed..ca0497ca7 100644
--- a/drivers/net/ice/base/ice_switch.c
+++ b/drivers/net/ice/base/ice_switch.c
@@ -3033,6 +3033,27 @@ ice_rem_sw_rule_info(struct
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, June 5, 2019 1:59 AM
> To: Rong, Leyi ; Zhang, Qi Z
> Cc: dev@dpdk.org; Raj, Victor ; Stillwell Jr, Paul M
>
> Subject: Re: [dpdk-dev] [PATCH 07/49] net/ice/base: replay advanced rule
> after reset
>
>
>
> On 6/4/19 7:42
On Wed, Jun 5, 2019 at 10:50 AM David Marchand
wrote:
>
>
> On Tue, Jun 4, 2019 at 5:45 PM Arnon Warshavsky wrote:
>
>> This patch changes some void functions to return a value,
>> so that the init sequence may tear down orderly
>> instead of calling panic.
>>
>
> All we care about in this patch
When esn is used then high-order 32 bits are included in ICV
calculation however are not transmitted. Update packet length
to be consistent with auth data offset and length before crypto
operation. High-order 32 bits of esn will be removed from packet
length in crypto post processing.
Signed-off-b
On 6/1/2019 5:13 PM, Ye Xiaolong wrote:
> On 05/31, William Tu wrote:
>> When users call rte_eth_dev_close() and rte_dev_remove(), the af_xdp
>> pmd return -1 (EPERM) due to eth_dev == NULL.
>>
>> Since the af_xdp pmd driver advertises RTE_ETH_DEV_CLOSE_REMOVE, all
>> the resources are freed on rte
On 5/27/2019 6:02 PM, Allain Legacy wrote:
> The rte_eth_dev_close() function now handles freeing resources for
> devices (e.g., mac_addrs). To conform with the new close() behaviour we
> are asserting the RTE_ETH_DEV_CLOSE_REMOVE flag so that
> rte_eth_dev_close() releases all device level dynami
> -Original Message-
> From: Jerin Jacob Kollanukkaran
> Sent: Wednesday, April 10, 2019 8:10 PM
> To: dev@dpdk.org; acon...@redhat.com
> Cc: gavin...@arm.com; konstantin.anan...@intel.com
> Subject: Re: [EXT] [PATCH 1/3] acl: fix arm argument types
>
> On Mon, 2019-04-08 at 14:24 -0400, A
Meeting notes for the DPDK technical board meeting held on 2018-05-22
Attendees:
- Bruce Richardson
- Ferruh Yigit
- Hemant Agrawal
- Konstantin Ananyev
- Maxime Coquelin
- Olivier Matz
- Stephen Hemminger
- Thomas Monjalon
1) DPDK
On Wed, 5 Jun 2019 11:59:52 +0300
Andrew Rybchenko wrote:
> On 6/5/19 4:08 AM, Stephen Hemminger wrote:
> > Use rte_eth_unformat_addr, so that ethdev can be built and work
> > without the cmdline library. The dependency on cmdline was
> > an arrangement of convenience anyway.
> >
> > Signed-off-b
10/04/2019 15:45, Bruce Richardson:
> Weak functions don't work well with static library builds as the linker
> always picks the first version of a function irrespective of whether it is
> weak or not. The solution to this is to use the "whole-archive" flag when
> linking, but this has the nasty si
1 - 100 of 215 matches
Mail list logo
