An additional output port is now implicitly created for every pipeline
to serve as the packet drop port. Up to now, the drop port had to be
explicitly created for each pipeline.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Yogesh Jangra
---
examples/pipeline/cli.c | 15 ++
Move the table type registration for the well known table types from
the application to the pipeline library.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Yogesh Jangra
---
examples/pipeline/obj.c | 16
lib/pipeline/rte_swx_pipeline.c | 29 +
The output port to be used as the drop port is now determined when the
drop instruction is executed as opposed to being statically determined
at instruction translation time and hardcoded in the opcode.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Yogesh Jangra :
---
lib/pipeline/rte_swx_pi
Move the port type registration for the well known port types from the
application to the pipeline library.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Yogesh Jangra
---
examples/pipeline/obj.c | 54 ---
lib/pipeline/rte_swx_pipeline.c | 159 --
An additional output port is now implicitly created for every pipeline
to seve as the packet drop port. Up to now, the drop port had to be
explicitly created for each pipeline.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Yogesh Jangra
---
examples/pipeline/cli.c | 15 +++
Move the table type registration for the well known table types from
the application to the pipeline library.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Yogesh Jangra
---
examples/pipeline/obj.c | 16
lib/pipeline/rte_swx_pipeline.c | 29 +
Move the port type registration for the well known port types from the
application to the pipeline library.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Yogesh Jangra
---
examples/pipeline/obj.c | 54 ---
lib/pipeline/rte_swx_pipeline.c | 159 --
The output port to be used as the drop port is now determined when the
drop instruction is executed as opposed to being statically determined
at instruction translation time and hardcoded in the opcode.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Yogesh Jangra :
---
lib/pipeline/rte_swx_pi
A new major release is available:
https://fast.dpdk.org/rel/dpdk-21.11.tar.xz
This is a big DPDK release.
1875 commits from 204 authors
2413 files changed, 259559 insertions(+), 87876 deletions(-)
The branch 21.11 should be supported for at least two years,
making it recommended for s
https://bugs.dpdk.org/show_bug.cgi?id=238
Thomas Monjalon (tho...@monjalon.net) changed:
What|Removed |Added
Resolution|--- |FIXED
Status|C
https://bugs.dpdk.org/show_bug.cgi?id=646
Thomas Monjalon (tho...@monjalon.net) changed:
What|Removed |Added
Resolution|--- |FIXED
Status|U
https://bugs.dpdk.org/show_bug.cgi?id=755
Thomas Monjalon (tho...@monjalon.net) changed:
What|Removed |Added
Status|CONFIRMED |RESOLVED
Resolutio
https://bugs.dpdk.org/show_bug.cgi?id=760
Thomas Monjalon (tho...@monjalon.net) changed:
What|Removed |Added
Resolution|--- |FIXED
Status|U
https://bugs.dpdk.org/show_bug.cgi?id=853
Thomas Monjalon (tho...@monjalon.net) changed:
What|Removed |Added
Status|CONFIRMED |RESOLVED
Resolutio
https://bugs.dpdk.org/show_bug.cgi?id=888
Thomas Monjalon (tho...@monjalon.net) changed:
What|Removed |Added
Status|IN_PROGRESS |RESOLVED
Resolutio
> > Replacing myself with Fan as compressdev API maintainer.
> >
> > Signed-off-by: Fiona Trahe
> > ---
> > Compression API - EXPERIMENTAL
> > -M: Fiona Trahe
> > +M: Fan Zhang
> > M: Ashish Gupta
Acked-by: Fan Zhang
> Acked-by: Ashish Gupta
Applied, thanks all.
23/10/2021 12:29, David Marchand:
> __reserved is a reserved keyword in Windows system headers.
>
> Signed-off-by: David Marchand
[...]
> + # refrain from using __reserved which is a reserved keyword in Windows
> + # system headers
Reworded as "forbid"
Applied, thanks.
26/11/2021 15:52, Olivier Matz:
> On Fri, Nov 26, 2021 at 02:06:23PM +0100, Thomas Monjalon wrote:
> > 26/11/2021 13:53, Ferruh Yigit:
> > > On 11/26/2021 9:51 AM, Viacheslav Ovsiienko wrote:
> > > > The generic RTE_FLOW_ACTION_TYPE_MODIFY_FIELD action was
> > > > introduced by [1]. This action pro
26/11/2021 17:37, Ferruh Yigit:
> On 11/25/2021 6:41 PM, Ferruh Yigit wrote:
> > On 11/23/2021 8:47 AM, Aman Singh wrote:
> >> The cocci script is to help add prefix 'RTE_ETH' namespace to enum
> >> & macro of ethdev library. It helps in automating these changes for
> >> applications. The script wo
> >The testing guide is now updated to include details about using
> >sub-testsuites.
> >Some example code is given to demonstrate how they can be used.
> >
> >A note is also added to highlight the need for using vdev EAL args when
> >running cryptodev tests.
> >
> >Signed-off-by: Ciara Power
> >
On 11/25/2021 6:41 PM, Ferruh Yigit wrote:
On 11/23/2021 8:47 AM, Aman Singh wrote:
The cocci script is to help add prefix 'RTE_ETH' namespace to enum
& macro of ethdev library. It helps in automating these changes for
applications. The script won't make changes in the code comment part.
Usage:
15/10/2021 19:06, Aaron Conole:
> The DPDK testing infrastructure includes a comprehensive set of
> libraries, utilities, and CI integrations for developers to test
> their code changes. This isn't well documented, however.
>
> Document the basics for adding a test suite to the infrastructure
> a
24/11/2021 14:03, sk...@marvell.com:
> From: Sunil Kumar Kori
>
> Patch adds feature matrices for event dev, Rx/Tx, Crypto
> and Timer adapters.
>
> Along with, .ini files are added for all supported PMDs.
>
> Signed-off-by: Sunil Kumar Kori
Applied, thanks.
I hope we can merge the script to
On Fri, Nov 26, 2021 at 02:06:23PM +0100, Thomas Monjalon wrote:
> 26/11/2021 13:53, Ferruh Yigit:
> > On 11/26/2021 9:51 AM, Viacheslav Ovsiienko wrote:
> > > The generic RTE_FLOW_ACTION_TYPE_MODIFY_FIELD action was
> > > introduced by [1]. This action provides an unified way
> > > to perform vari
> -Original Message-
> From: Fiona Trahe
> Sent: Wednesday, October 6, 2021 9:56 PM
> To: dev@dpdk.org
> Cc: fiona.tr...@intel.com; roy.fan.zh...@intel.com; Ashish Gupta
>
> Subject: [EXT] [PATCH] MAINTAINERS: update entry for compressdev
>
> External Email
>
> -
On Tue, Nov 9, 2021 at 12:33 PM Walsh, Conor wrote:
>
> > From: dev On Behalf Of Vladimir Medvedkin
> > Sent: Monday 8 November 2021 17:37
> > To: dev@dpdk.org
> > Subject: [dpdk-dev] [PATCH 2/2] doc: add programmer's guide for the FIB
> > library
> >
> > Currently, programmer's guide for the FIB
> -Original Message-
> From: Thomas Monjalon
> Sent: Friday, November 26, 2021 2:54 PM
> To: Juraj Linkeš
> Cc: david.march...@redhat.com; bruce.richard...@intel.com;
> honnappa.nagaraha...@arm.com; ruifeng.w...@arm.com;
> ferruh.yi...@intel.com; dev@dpdk.org
> Subject: Re: [PATCH v1] d
> -Original Message-
> From: Thomas Monjalon
> Sent: Friday, November 26, 2021 2:41 PM
> To: Juraj Linkeš
> Cc: david.march...@redhat.com; bruce.richard...@intel.com; dev@dpdk.org;
> honnappa.nagaraha...@arm.com; Ruifeng Wang
> Subject: Re: [dpdk-dev] [PATCH v2] doc: update machine mes
On Mon, Nov 8, 2021 at 12:32 PM Pavan Nikhilesh Bhagavatula
wrote:
> We need to further split Rx/Tx functions in both net/cnxk and event/cnxk to
> enable more parallelism.
> This is planned for the next release.
Looking fwd to this change.
--
David Marchand
18/11/2021 11:00, Juraj Linkeš:
> Numactl cross compilation doesn't work with clang, remove it and fix the
> gcc cross compiler executable name.
>
> Remove CFLAGS and LDFLAGS since Meson doesn't support them well enough.
> Add alternatives.
>
> The names of the downloaded gcc binaries differ from
On Mon, Oct 18, 2021 at 4:30 PM Kefu Chai wrote:
>
> change from "how many segments each segment can have" to
> "how many segments each segment list can have".
>
> Signed-off-by: Kefu Chai
Applied, thanks.
--
David Marchand
On Mon, Aug 9, 2021 at 10:37 AM Dumitrescu, Cristian
wrote:
> > Added a diagram to document meter library components
> > and added text for steps performed by the application to
> > configure the traffic meter and policing library.
> >
> > Signed-off-by: Jerin Jacob
> Acked-by: Cristian Dumitresc
On Fri, Nov 26, 2021 at 2:38 PM Kinsella, Ray wrote:
> On 26/11/2021 13:34, David Marchand wrote:
> > On Fri, Nov 26, 2021 at 2:18 PM David Marchand
> > wrote:
> >>
> >> On Tue, Aug 10, 2021 at 4:36 PM Ray Kinsella wrote:
> >>>
> >>> Fix documentation typos that are generating spurious CI warnin
11/10/2021 15:42, Juraj Linkeš:
> Update the docs to reflect the two new variables, cpu_instruction_set
> for non-arm builds and platform for arm builds.
>
> Fixes: bf66003b51ec ("build: use platform for generic and native builds")
>
> Signed-off-by: Juraj Linkeš
> ---
> --- a/doc/guides/prog_gu
On 26/11/2021 13:34, David Marchand wrote:
On Fri, Nov 26, 2021 at 2:18 PM David Marchand
wrote:
On Tue, Aug 10, 2021 at 4:36 PM Ray Kinsella wrote:
Fix documentation typos that are generating spurious CI warnings.
Cc: sta...@dpdk.org
^^^
Actually, no, dropped Cc.
This patch o
On Fri, Nov 26, 2021 at 2:18 PM David Marchand
wrote:
>
> On Tue, Aug 10, 2021 at 4:36 PM Ray Kinsella wrote:
> >
> > Fix documentation typos that are generating spurious CI warnings.
>
> Cc: sta...@dpdk.org
^^^
Actually, no, dropped Cc.
This patch only fixes:
Fixes: 9a212dc06c7a ("doc: use
24/11/2021 17:53, David Hunt:
> When using PMD Power Management, scale mode reacts slower than
> monitor mode and pause mode. Add note in user guide to this
> effect.
>
> Signed-off-by: David Hunt
> ---
> This power saving scheme will use ``librte_power`` library functionality
> to
> - sca
On Tue, Aug 10, 2021 at 4:36 PM Ray Kinsella wrote:
>
> Fix documentation typos that are generating spurious CI warnings.
Cc: sta...@dpdk.org
>
> Signed-off-by: Ray Kinsella
Acked-by: Aaron Conole
Reviewed-by: Conor Walsh
Applied, thanks.
--
David Marchand
On Fri, Nov 26, 2021 at 12:47 PM Jiang, YuX wrote:
> > You may share some release validation results by replying to this message at
> > dev@dpdk.org.
>
> Update the test status for Intel part. Till now dpdk21.11-rc4 validation test
> is almost finished. No critical issue and no new issue is found
The MAC addresses fields are 48 bit wide and are processed
by mlx5 PMD as two words. There the bug was introduced for
the offset, causing malfunction of MODIFY_FIELD action
with MAC address fields as source or destination and
with non zero field offset.
Fixes: 40c8fb1fd3b3 ("net/mlx5: update modif
26/11/2021 13:53, Ferruh Yigit:
> On 11/26/2021 9:51 AM, Viacheslav Ovsiienko wrote:
> > The generic RTE_FLOW_ACTION_TYPE_MODIFY_FIELD action was
> > introduced by [1]. This action provides an unified way
> > to perform various arithmetic and transfer operations over
> > packet network header field
On Fri, Nov 26, 2021 at 1:17 PM Raslan Darawsheh wrote:
>
> Add tested platforms with Mellanox NICs to the 21.11 release notes.
>
> Signed-off-by: Raslan Darawsheh
Applied.
--
David Marchand
On 11/26/2021 9:51 AM, Viacheslav Ovsiienko wrote:
The generic RTE_FLOW_ACTION_TYPE_MODIFY_FIELD action was
introduced by [1]. This action provides an unified way
to perform various arithmetic and transfer operations over
packet network header fields and packet metadata.
[1] commit 641dbe4fb053
On Fri, Nov 26, 2021 at 10:41 AM Apeksha Gupta wrote:
>
> Add tested NXP platform to v21.11 release note for NXP enetfec
> PMD.
>
> Signed-off-by: Apeksha Gupta
> ---
> doc/guides/rel_notes/release_21_11.rst | 11 +++
> 1 file changed, 11 insertions(+)
>
> diff --git a/doc/guides/rel_not
https://bugs.dpdk.org/show_bug.cgi?id=891
Bug ID: 891
Summary: bnxt PMD: multicast filtering fails
Product: DPDK
Version: 20.11
Hardware: x86
OS: Linux
Status: UNCONFIRMED
Severity: normal
Priori
25/11/2021 11:38, Matan Azrad:
> From: Thomas Monjalon
> > 25/11/2021 07:16, michae...@nvidia.com:
> > > From: Michael Baum
> > >
> > > The mlx5_args function reads the devargs and checks if they are valid
> > > for this driver and if not it returns an error.
> > >
> > > This was normal behavior a
> > Memory region (MR) was being looked up incorrectly for the data address of
> > an externally-attached mbuf.
> > A search was attempted for the mempool of the mbuf, while mbuf data
> > address does not belong to this mempool in case of externally-attached mbuf.
> > Only attempt the search:
> > 1
26/11/2021 00:03, eagost...@nvidia.com:
> From: Elena Agostini
>
> Remove all memory leaks in case of errors in
> test-gpudev application.
>
> Fixes: e818c4e2bf50 ("gpudev: add memory API")
> Fixes: c7ebd65c1372 ("gpudev: add communication list")
>
> Signed-off-by: Elena Agostini
Applied, tha
Add tested platforms with Mellanox NICs to the 21.11 release notes.
Signed-off-by: Raslan Darawsheh
---
doc/guides/rel_notes/release_21_11.rst | 147 +
1 file changed, 147 insertions(+)
diff --git a/doc/guides/rel_notes/release_21_11.rst
b/doc/guides/rel_notes/release_2
https://bugs.dpdk.org/show_bug.cgi?id=890
Bug ID: 890
Summary: lib/ip_frag: IPv4 options without copied bit set are
present in all fragments
Product: DPDK
Version: 21.11
Hardware: All
OS: All
Sta
The MAC addresses fields are 48 bit wide and are processed
by mlx5 PMD as two words. There the bug was introduced for
the offset, causing wrong action translation if action
field offset was not zero.
Fixes: 40c8fb1fd3b3 ("net/mlx5: update modify field action")
Signed-off-by: Viacheslav Ovsiienko
> -Original Message-
> From: David Marchand
> Sent: Thursday, November 25, 2021 2:38 AM
> To: annou...@dpdk.org
> Cc: Thomas Monjalon
> Subject: release candidate 21.11-rc4
>
> Hi all,
>
> A new DPDK release candidate is ready for testing:
> https://git.dpdk.org/dpdk/tag/?id=v21
25/11/2021 23:40, eagost...@nvidia.com:
> From: Elena Agostini
>
> Remove unnecessary rte_gpu_wmb from rte_gpu_comm_populate_list_pkts.
> It causes a performance degradation in case of NVIDIA GPU V100.
>
> This change doesn't affect any functionality as the status resides
> in CPU registered mem
25/11/2021 11:07, Zhang, Roy Fan:
> > -Original Message-
> > From: Trahe, Fiona
> > Sent: Wednesday, October 6, 2021 5:26 PM
> > To: dev@dpdk.org
> > Cc: Trahe, Fiona ; Zhang, Roy Fan
> > ; ashish.gu...@marvell.com
> >
> > Replacing myself with Fan as compressdev API maintainer.
> >
> >
26/11/2021 11:04, Thomas Monjalon:
> From: Aman Singh
>
> Add Aman Singh as co-maintainer of testpmd.
>
> Make the title description more accurate for this tool.
>
> Signed-off-by: Aman Singh
> Acked-by: Ferruh Yigit
> Signed-off-by: Thomas Monjalon
Applied
Thanks Aman for volunteering.
[Public]
Hi Arsalan,
I have submitted new patch to community review and looped you in. Please share
your comments.
https://patches.dpdk.org/project/dpdk/list/?series=20788
Regards,
Chandu
-Original Message-
From: Awan, Arsalan
Sent: Thursday, November 25, 2021 2:37 PM
To: Namburu, Ch
"bus/pci: optimize bus scan" broke axgbe on V1000/R1000.
RV root complex pci device does not have any kernel driver assigned
so it is removed from pci scan list which is used in
"net/axgbe: add a HW quirk for register definitions"
Get root complex device id directly from pci sysfs instead of
pci s
On Mon, Nov 1, 2021 at 3:54 PM Bruce Richardson
wrote:
>
> On Fri, Oct 29, 2021 at 04:19:02PM +0300, Dariusz Sosnowski wrote:
> > This patch fixes a typo in DPDK Coding Style, in Return Values section,
> > i.e. replaces "indicated may" with "indicated by".
> >
> > Fixes: 36032e46be40 ("doc: add co
16/11/2021 00:26, Stephen Hemminger:
> Current version of Linux kernel checkpatch now complains about
> usages of strlcpy because the Linux kernel prefers strcspy.
>
> WARNING:STRLCPY: Prefer strscpy over strlcpy
>
> But DPDK project allows strlcpy, therefore suppress the warning.
>
> Signed-off
20/10/2021 11:14, David Marchand:
> The convention in DPDK is to directly use library names as prefix,
> without a lib/.
>
> Signed-off-by: David Marchand
Applied, thanks.
On Mon, Nov 22, 2021 at 11:52 AM Sean Morrissey
wrote:
>
> This patchset cleans up the use of the phrase PMD
> throughout dpdk by capitalising pmd and also
> removing the use of the word driver following PMD.
>
> This patchset also removes some unnecessary
> duplication of the word "the" in commen
On Fri, Nov 26, 2021 at 10:57 AM Apeksha Gupta wrote:
> > You may share some release validation results by replying to this
> > message at dev@dpdk.org.
> [Apeksha]
> Hi David,
>
> The testing with DPDK 21.11-rc4 from ENETFEC driver looks good. We don't see
> any issues with the following tests:
Hi Ian,
On Thu, Nov 25, 2021 at 5:08 PM Stokes, Ian wrote:
> Intel has completed the following validation with OVS and DPDK 21.11-rc4, no
> issues seen.
>
> Ixgbe Performance Tests
> phy2phy_tput
> pvp_tput
> pvp_cont
> pvvp_tput
> pvpv_cont
>
> Ixgbe Functional Tests
> RSS Multiqueue
> Dynamic
From: Aman Singh
Add Aman Singh as co-maintainer of testpmd.
Make the title description more accurate for this tool.
Signed-off-by: Aman Singh
Acked-by: Ferruh Yigit
Signed-off-by: Thomas Monjalon
---
v2: update the section title
v3: update the section title
---
MAINTAINERS | 3 ++-
1 file
On 11/22/2021 10:50 AM, Sean Morrissey wrote:
This patchset cleans up the use of the phrase PMD
throughout dpdk by capitalising pmd and also
removing the use of the word driver following PMD.
This patchset also removes some unnecessary
duplication of the word "the" in comments and
docs.
Sean Mo
The generic RTE_FLOW_ACTION_TYPE_MODIFY_FIELD action was
introduced by [1]. This action provides an unified way
to perform various arithmetic and transfer operations over
packet network header fields and packet metadata.
[1] commit 641dbe4fb053 ("net/mlx5: support modify field flow action")
On ot
Add tested NXP platform to v21.11 release note for NXP enetfec
PMD.
Signed-off-by: Apeksha Gupta
---
doc/guides/rel_notes/release_21_11.rst | 11 +++
1 file changed, 11 insertions(+)
diff --git a/doc/guides/rel_notes/release_21_11.rst
b/doc/guides/rel_notes/release_21_11.rst
index f31d
Hi,
Is it possible that you can provide more info about this isuee. I mean: qemu
cmdline/libvirt xml, ovs cmdline, guest driver version and etc… Or it’s hard to
reproduce the issue.
Thanks,
Chenbo
From: Bendror, Eran (Nokia - US)
Sent: Wednesday, November 17, 2021 10:42 PM
To: ktray...@redhat
Please find below Red Hat roadmap for v22.03 release:
* Improve Vhost library logging by providing device identification
* Add stats/xstats support to DPDK Vhost library
* Add support to hash report feature to Virtio PMD
Last item is less urgent and may be postponed to a later release.
Regards,
A leading '0' was missed of the hexadecimal value.
Fixes: 3ceeed9f7855 ("doc: update flow mark action in mlx5 guide")
Cc: viachesl...@nvidia.com
Cc: sta...@dpdk.org
Signed-off-by: Bing Zhao
Acked-by: Viacheslav Ovsiienko
---
doc/guides/nics/mlx5.rst | 2 +-
1 file changed, 1 insertion(+), 1 de
> -Original Message-
> From: Dmitry Kozlyuk
> Sent: Thursday, November 25, 2021 22:21
> To: dev@dpdk.org
> Cc: NBU-Contact-Thomas Monjalon (EXTERNAL) ;
> Raslan Darawsheh ; Slava Ovsiienko
> ; Matan Azrad
> Subject: [PATCH] common/mlx5: fix MR lookup on slow path
>
> Memory region (MR) w
> -Original Message-
> From: Sean Morrissey
> Sent: Monday, November 22, 2021 10:51 AM
> Cc: dev@dpdk.org; Morrissey, Sean
> Subject: [PATCH v2 0/3] Fix typo's and capitalise PMD
>
> This patchset cleans up the use of the phrase PMD throughout dpdk by
> capitalising pmd and also removi
72 matches
Mail list logo
