RE: [PATCH 1/2] net/txgbe: add vectorized functions for Rx/Tx

On Wed, Feb 7, 2024 11:13 AM, ferruh.yi...@amd.com wrote: > On 2/1/2024 3:00 AM, Jiawen Wu wrote: > > To optimize Rx/Tx burst process, add SSE/NEON vector instructions on > > x86/arm architecture. > > > > Do you have any performance improvement number with vector > implementation, if so can you pu

[RFC] net/gve: add IPv4 checksum offloading capability

Gvnic's DQO format allows offloading IPv4 checksum. Made changes to Tx and Rx path to translate DPDK flags to descriptor for offloading (and vice-versa). Added ptype adminq support to only add this flags for supported L3/L4 packet-types. --- drivers/net/gve/gve_ethdev.c | 29 ++

Re: [PATCH v4] vhost: enhance virtqueue access lock asserts

On Tue, Feb 27, 2024 at 11:39 AM David Marchand wrote: > > A simple comment in vhost_user_msg_handler() is not that robust. > > Add a lock_all_qps property to message handlers so that their > implementation can add a build check and assert a vq is locked. > > Signed-off-by: David Marchand > Revie

Re: [PATCH v2] vhost: fix VDUSE device destruction failure

On Mon, Mar 4, 2024 at 11:36 AM David Marchand wrote: > > From: Maxime Coquelin > > VDUSE_DESTROY_DEVICE ioctl can fail because the device's > chardev is not released despite close syscall having been > called. It happens because the events handler thread is > still polling the file descriptor. >

[PATCH] vhost: fix vring addr update with vDPA

For vDPA devices, vq are not locked once the device has been configured at runtime. On the other hand, we need to hold the vq lock to evaluate vq->access_ok, invalidate vring addresses and translate them. Move vring address update earlier and, when vDPA is configured, skip parts which expect lock

RE: [PATCH v2 22/71] raw/ifpga: replace use of fixed size rte_memcpy

Hi, > -Original Message- > From: Stephen Hemminger > Sent: Saturday, March 2, 2024 1:15 AM > To: dev@dpdk.org > Cc: Stephen Hemminger ; Xu, Rosen > > Subject: [PATCH v2 22/71] raw/ifpga: replace use of fixed size rte_memcpy > > Automatically generated by devtools/cocci/rte_memcpy.cocci

Re: [PATCH] hash: make gfni stubs inline

On Mon, Mar 4, 2024 at 7:45 PM Stephen Hemminger wrote: > > This reverts commit 07d836e5929d18ad6640ebae90dd2f81a2cafb71. > > Tyler found build issues with MSVC and the thash gfni stubs. > The problem would be link errors from missing symbols. Trying to understand this link error. Does it come fr

[PATCH] config/arm: add Marvell Odyssey

Add meson build configuration for Marvell Odyssey platform with 64-bit ARM Neoverse V2 cores. Signed-off-by: Anoob Joseph --- Depends-on: series-31141 ("config/arm: add Neoverse V2 part number") config/arm/arm64_odyssey_linux_gcc-marvell | 17 + config/arm/meson.build

[PATCH v7] net/i40e: add diagnostic support in Tx path

Implemented a Tx wrapper to perform a thorough check on mbufs, categorizing and counting invalid cases by type for diagnostic purposes. The count of invalid cases is accessible through xstats_get. Also, the devarg option "mbuf_check" was introduced to configure the diagnostic parameters to enable

[PATCH v4] net/ice: add diagnostic support in Tx path

Implemented a Tx wrapper to perform a thorough check on mbufs, categorizing and counting invalid cases by type for diagnostic purposes. The count of invalid cases is accessible through xstats_get. Also, the devarg option "mbuf_check" was introduced to configure the diagnostic parameters to enable

[PATCH] argparse: add version in symbols map

Fixes: e3e579f5bab5 ("argparse: introduce argparse library") Signed-off-by: David Marchand --- lib/argparse/version.map | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/argparse/version.map b/lib/argparse/version.map index 9b68464600..46da99a3e2 100644 --- a/lib/argparse/version.map +++ b

[PATCH] net/ice: add version in symbols map

Fixes: 0d8d7bd720ba ("net/ice: support DDP dump switch rule binary") Fixes: ab4eaf9a8a31 ("net/ice: dump Tx scheduling tree") Signed-off-by: David Marchand --- drivers/net/ice/version.map | 4 1 file changed, 4 insertions(+) diff --git a/drivers/net/ice/version.map b/drivers/net/ice/versio

Re: [PATCH] argparse: add version in symbols map

On Tue, Mar 05, 2024 at 11:36:40AM +0100, David Marchand wrote: > Fixes: e3e579f5bab5 ("argparse: introduce argparse library") > > Signed-off-by: David Marchand > --- Acked-by: Bruce Richardson

Re: [PATCH] net/ice: add version in symbols map

On Tue, Mar 05, 2024 at 11:36:51AM +0100, David Marchand wrote: > Fixes: 0d8d7bd720ba ("net/ice: support DDP dump switch rule binary") > Fixes: ab4eaf9a8a31 ("net/ice: dump Tx scheduling tree") > > Signed-off-by: David Marchand > --- Acked-by: Bruce Richardson

[PATCH v2] config/arm: add Marvell Odyssey

Add meson build configuration for Marvell Odyssey platform with 64-bit ARM Neoverse V2 cores. Signed-off-by: Anoob Joseph --- Depends-on: series-31141 ("config/arm: add Neoverse V2 part number") Changes in v2: - Renamed config file config/arm/arm64_odyssey_linux_gcc | 17 + co

[PATCH] test/crypto: fix non ASCII character

Fix non ASCII character in the comment. Revert to original text. Bugzilla ID: 1396 Fixes: f97c63f4f445 ("test/crypto: add AES-GCM external mbuf case") Signed-off-by: Anoob Joseph --- app/test/test_cryptodev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/app/test/test_cryp

Re: [PATCH] argparse: add version in symbols map

Acked-by: Chengwen Feng BTW: which tool detects this problem? On 2024/3/5 18:36, David Marchand wrote: > Fixes: e3e579f5bab5 ("argparse: introduce argparse library") > > Signed-off-by: David Marchand > --- > lib/argparse/version.map | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/li

Re: [PATCH] examples/dma: fix max-frame-size cannot be zero

Hi Thomas, This commit fix bug "Bug 1387 - [dpdk24.03] cbdma: Failed to launch dpdk-dma app" [1] Should I send v2 to add the following line in commit log? Bugzilla ID: 1387 [1] https://bugs.dpdk.org/show_bug.cgi?id=1387 Thanks On 2024/2/21 14:51, Jiang, YuX wrote: >> -Original Message

[PATCH] common/qat: fix undefined macro

When using RTE_ENABLE_ASSERT and debug mode, an undefined macro error appeared for ICP_QAT_FW_SYM_COMM_ADDR_SGL. This was not being defined, but is now added to the header file. Bugzilla ID: 1395 Fixes: e9271821e489 ("common/qat: support GEN LCE device") Signed-off-by: Ciara Power --- Cc: nishi

RE: [PATCH] common/qat: fix undefined macro

> -Original Message- > From: Power, Ciara > Sent: Tuesday, March 5, 2024 5:26 PM > To: dev@dpdk.org > Cc: gak...@marvell.com; Power, Ciara ; Nayak, > Nishikanta ; Ji, Kai > Subject: [PATCH] common/qat: fix undefined macro > > When using RTE_ENABLE_ASSERT and debug mode, an undefined m

RE: [PATCH] test/crypto: fix non ASCII character

> -Original Message- > From: Anoob Joseph > Sent: Tuesday, March 5, 2024 1:34 PM > To: Akhil Goyal ; David Marchand > > Cc: Aakash Sasidharan ; dev@dpdk.org > Subject: [PATCH] test/crypto: fix non ASCII character > > Fix non ASCII character in the comment. Revert to original text. > > B

Re: [PATCH] argparse: add version in symbols map

On Tue, Mar 5, 2024 at 12:35 PM fengchengwen wrote: > > Acked-by: Chengwen Feng > > BTW: which tool detects this problem? I found out about those issues while manually inspecting the changes on **/version.map since v23.11. At the moment, there is no tool enforcing that experimental symbols must

RE: [PATCH] common/qat: fix undefined macro

> -Original Message- > From: Ciara Power > Sent: Tuesday, March 5, 2024 1:56 PM > To: dev@dpdk.org > Cc: gak...@marvell.com; Ciara Power ; > nishikanta.na...@intel.com; Kai Ji > Subject: [PATCH] common/qat: fix undefined macro > > When using RTE_ENABLE_ASSERT and debug mode, an undefined

Re: [PATCH] examples/dma: fix max-frame-size cannot be zero

05/03/2024 12:42, fengchengwen: > Hi Thomas, > > This commit fix bug "Bug 1387 - [dpdk24.03] cbdma: Failed to launch dpdk-dma > app" [1] > > Should I send v2 to add the following line in commit log? > Bugzilla ID: 1387 I can add it while merging.

Re: [PATCH v7] net/i40e: add diagnostic support in Tx path

On Tue, Mar 05, 2024 at 10:17:47AM +, Mingjin Ye wrote: > Implemented a Tx wrapper to perform a thorough check on mbufs, > categorizing and counting invalid cases by type for diagnostic > purposes. The count of invalid cases is accessible through xstats_get. > > Also, the devarg option "mbuf_c

[PATCH 1/2] net/mlx5: update speed capabilities parsing on Linux

Ease maintenance of speed capabilities parsing from ethtool by using rte_eth_link_speed_g*(). Functions in ethdev library are simpler, more complete, and easier to maintain. Signed-off-by: Thomas Monjalon --- drivers/common/mlx5/linux/meson.build | 22 drivers/net/mlx5/linux/mlx5_ethdev_

[PATCH 2/2] net/mlx5: apply default tuning to future speeds

Some default parameters for number of queues and ring size are different starting with 100G speed capability. Instead of checking all speed above 100G, make sure it is applied for any speed capability newer than 100G (including 400G for instance). Signed-off-by: Thomas Monjalon --- drivers/net/

DPDK Release Status Meeting 2024-02-29

Release status meeting minutes 2024-02-29 = Agenda: * Release Dates * Subtrees * Roadmaps * LTS * Defects * Opens Participants: * AMD * ARM * Intel * Marvell * Nvidia * Red Hat Release Dates - The following are the current/updated working date

Re: [PATCH] common/qat: fix undefined macro

05/03/2024 13:15, Ali Alnubani: > > -Original Message- > > From: Ciara Power > > Sent: Tuesday, March 5, 2024 1:56 PM > > To: dev@dpdk.org > > Cc: gak...@marvell.com; Ciara Power ; > > nishikanta.na...@intel.com; Kai Ji > > Subject: [PATCH] common/qat: fix undefined macro > > > > When us

RE: [PATCH 00/21] Improvements and new test cases

> Subject: [PATCH 00/21] Improvements and new test cases > > Adding new test cases and improvements to test application. > > Aakash Sasidharan (7): > test/security: enable AES-GCM in combined mode TLS > test/security: add TLS 1.2 data walkthrough test > test/security: add DTLS 1.2 data walk

Re: [PATCH] test/crypto: fix non ASCII character

05/03/2024 13:14, Ali Alnubani: > > Subject: [PATCH] test/crypto: fix non ASCII character > > > > Fix non ASCII character in the comment. Revert to original text. > > > > Bugzilla ID: 1396 > > Fixes: f97c63f4f445 ("test/crypto: add AES-GCM external mbuf case") > > > > Signed-off-by: Anoob Joseph

Re: [PATCH] test/crypto: fix non ASCII character

On Tue, Mar 5, 2024 at 2:25 PM Thomas Monjalon wrote: > > 05/03/2024 13:14, Ali Alnubani: > > > Subject: [PATCH] test/crypto: fix non ASCII character > > > > > > Fix non ASCII character in the comment. Revert to original text. > > > > > > Bugzilla ID: 1396 > > > Fixes: f97c63f4f445 ("test/crypto:

Re: [PATCH] vhost: fix vring addr update with vDPA

On Tue, Mar 5, 2024 at 10:13 AM David Marchand wrote: > > For vDPA devices, vq are not locked once the device has been configured > at runtime. > > On the other hand, we need to hold the vq lock to evaluate vq->access_ok, > invalidate vring addresses and translate them. > > Move vring address upda

Re: [PATCH] test/crypto: fix non ASCII character

David Marchand, Mar 05, 2024 at 14:27: > The script buildtools/get-test-suites.py is not tolerant with Unicode. > We may be more flexible probably. > Bruce, Robin, what do you think about allowing Unicode characters in this script? Note: I could reproduce this issue with a Ubuntu 18.04 containe

[PATCH] tests: assume c source files are utf-8 encoded

Instead of relying on the default locale from the environment (LC_ALL), explicitly read the files as utf-8 encoded. Fixes: 0aeaf75df879 ("test: define unit tests suites based on test types") Signed-off-by: Robin Jarry --- buildtools/get-test-suites.py | 2 +- 1 file changed, 1 insertion(+), 1 d

Re: [PATCH v4] net/ice: add diagnostic support in Tx path

On Tue, Mar 05, 2024 at 10:18:42AM +, Mingjin Ye wrote: > Implemented a Tx wrapper to perform a thorough check on mbufs, > categorizing and counting invalid cases by type for diagnostic > purposes. The count of invalid cases is accessible through xstats_get. > > Also, the devarg option "mbuf_c

Re: [PATCH] tests: assume c source files are utf-8 encoded

On Tue, Mar 05, 2024 at 02:46:15PM +0100, Robin Jarry wrote: > Instead of relying on the default locale from the environment (LC_ALL), > explicitly read the files as utf-8 encoded. > > Fixes: 0aeaf75df879 ("test: define unit tests suites based on test types") > > Signed-off-by: Robin Jarry > ---

[PATCH] devtools: require version for experimental symbols

Add version to all symbols maps and a check so any experimental symbol is versioned. Signed-off-by: David Marchand --- buildtools/map-list-symbol.sh | 8 ++-- devtools/check-symbol-maps.sh | 15 +++ doc/guides/contributing/abi_policy.rst | 17 ++

RE: [PATCH] tests: assume c source files are utf-8 encoded

> From: Robin Jarry [mailto:rja...@redhat.com] > Sent: Tuesday, 5 March 2024 14.46 > > Instead of relying on the default locale from the environment (LC_ALL), > explicitly read the files as utf-8 encoded. > > Fixes: 0aeaf75df879 ("test: define unit tests suites based on test types") > > Signed-o

Re: [PATCH v7 08/39] mbuf: use C11 alignas

On Mon, Mar 4, 2024 at 6:54 PM Tyler Retzlaff wrote: > > The current location used for __rte_aligned(a) for alignment of types > and variables is not compatible with MSVC. There is only a single > location accepted by both toolchains. > > For variables standard C11 offers alignas(a) supported by c

RE: [EXT] [PATCH] app/test: don't count skipped tests as executed

> Subject: [EXT] [PATCH] app/test: don't count skipped tests as executed > The logic around skipped tests is a little confusing in the unit test > runner. > * Any explicitly disabled tests are counted as skipped but not > executed. > * Any tests that return TEST_SKIPPED are counted as both skippe

Re: [PATCH] argparse: add version in symbols map

On Tue, Mar 5, 2024 at 1:14 PM David Marchand wrote: > > On Tue, Mar 5, 2024 at 12:35 PM fengchengwen wrote: > > > > Acked-by: Chengwen Feng > > > > BTW: which tool detects this problem? > > I found out about those issues while manually inspecting the changes > on **/version.map since v23.11. >

RE: [PATCH v4 2/2] doc: remove outdated version details

> Subject: [PATCH v4 2/2] doc: remove outdated version details > > SW PMDs documentation is updated to remove details of unsupported IPsec > Multi-buffer versions.DPDK older than 20.11 is end of life. So, older DPDK > versions are removed from the Crypto library version table. > > Signed-off-by:

Re: [EXT] [PATCH] app/test: don't count skipped tests as executed

On Tue, Mar 05, 2024 at 02:36:27PM +, Akhil Goyal wrote: > > Subject: [EXT] [PATCH] app/test: don't count skipped tests as executed > > The logic around skipped tests is a little confusing in the unit test > > runner. > > * Any explicitly disabled tests are counted as skipped but not > > exec

RE: [PATCH v4 1/2] crypto/ipsec_mb: bump minimum IPsec Multi-buffer version

> Subject: [PATCH v4 1/2] crypto/ipsec_mb: bump minimum IPsec Multi-buffer > version > > SW PMDs increment IPsec Multi-buffer version to 1.4. > A minimum IPsec Multi-buffer version of 1.4 or greater is now required. > > Signed-off-by: Sivaramakrishnan Venkat > > Acked-by: Ciara Power > Acked-by

RE: [PATCH v2] crypto/ipsec_mb: use new ipad/opad calculation API

> Signed-off-by: Pablo de Lara > Signed-off-by: Brian Dooley > Acked-by: Ciara Power Acked-by: Wathsala Vithanage > > Depends-on: series-30989 ("crypto/ipsec_mb: bump minimum IPsec Multi- > buffer version") > > v2: > - Remove ipsec mb version checks > --- > drivers/crypto/ipsec_mb/pmd_aesn

RE: [PATCH v4] crypto/ipsec_mb: unified IPsec MB interface

> Subject: [PATCH v4] crypto/ipsec_mb: unified IPsec MB interface > > Currently IPsec MB provides both the JOB API and direct API. > AESNI_MB PMD is using the JOB API codepath while ZUC, KASUMI, SNOW3G > and CHACHA20_POLY1305 are using the direct API. > Instead of using the direct API for these PM

RE: [PATCH] app/test: don't count skipped tests as executed

Hi Bruce, > -Original Message- > From: Bruce Richardson > Sent: Monday, November 13, 2023 3:06 PM > To: dev@dpdk.org > Cc: Richardson, Bruce > Subject: [PATCH] app/test: don't count skipped tests as executed > > The logic around skipped tests is a little confusing in the unit test run

Re: [PATCH v5 4/4] hash: add SVE support for bulk key lookup

On 3/4/24 13:35, Konstantin Ananyev wrote: - Implemented SVE code for comparing signatures in bulk lookup. - Added Defines in code for SVE code support. - Optimise NEON code - New SVE code is ~5% slower than optimized NEON for N2 processor. Signed-off-by: Yoan Picchi Signed-off-by: Harjot Si

Re: [PATCH v7 10/39] eventdev: use C11 alignas

On Mon, Mar 4, 2024 at 6:54 PM Tyler Retzlaff wrote: > diff --git a/lib/eventdev/rte_eventdev.h b/lib/eventdev/rte_eventdev.h > index 3af4686..08e5f93 100644 > --- a/lib/eventdev/rte_eventdev.h > +++ b/lib/eventdev/rte_eventdev.h > @@ -1338,7 +1338,7 @@ int rte_event_dev_stop_flush_callback_regist

RE: [EXTERNAL] [PATCH] crypto/ipsec_mb: update Arm IPsec-MB library tag

> Subject: RE: [EXTERNAL] [PATCH] crypto/ipsec_mb: update Arm IPsec-MB library > tag > > > Updates the tag of Arm IPsec-MB library to SECLIB-IPSEC-2023.10.13 > > in snow3g and zuc documentation. Tag SECLIB-IPSEC-2023.10.13 updates > > IPSec-MB library version to 1.4. > > > > Signed-off-by: Wathsal

RE: RFC: Using and renaming 8-bit reserved field of rte_crypto_op for implementation specific

Hi Ganapati, Can you please explain the flow with a sequence of APIs to be used. Regards, Akhil From: Kundapura, Ganapati Sent: Tuesday, March 5, 2024 12:44 PM To: dpdk-dev ; Akhil Goyal ; fanzhang@gmail.com; Ji, Kai ; Power, Ciara ; Kusztal, ArkadiuszX ; Gujjar, Abhinandan S ; Jayatheer

RE: [PATCH 1/2] net/mlx5: update speed capabilities parsing on Linux

> -Original Message- > From: Thomas Monjalon > Sent: Tuesday, March 5, 2024 14:13 > To: dev@dpdk.org > Cc: Dariusz Sosnowski ; Slava Ovsiienko > ; Ori Kam ; Suanming Mou > ; Matan Azrad > Subject: [PATCH 1/2] net/mlx5: update speed capabilities parsing on Linux > > External email: Use ca

RE: [PATCH 2/2] net/mlx5: apply default tuning to future speeds

> -Original Message- > From: Thomas Monjalon > Sent: Tuesday, March 5, 2024 14:13 > To: dev@dpdk.org > Cc: Dariusz Sosnowski ; Slava Ovsiienko > ; Ori Kam ; Suanming Mou > ; Matan Azrad > Subject: [PATCH 2/2] net/mlx5: apply default tuning to future speeds > > External email: Use caution

RE: [PATCH v2 45/71] event/dlb2: replace use of fixed size rte_memcpy

Hi Stephen, Are all rte_memcpy functions now be replaced by memcpy and no more use of rte_memcpy?

RE: [PATCH v4] crypto/ipsec_mb: unified IPsec MB interface

> This is being worked on. We are in the process of creating a new tag. We will > update soon. > A new tag SECLIB-IPSEC-2024.03.05 has been created. We will be sending out a patch for the documentation soon.

RE: [EXT] Re: [PATCH v2 8/8] crypto/ipsec_mb: set and use session ID

> A new tag SECLIB-IPSEC-2023.10.13 has been created from the tip of arm > ipsec-mb git repo. > Please use this tag going forward, it has been tested and works as expected. Please use SECLIB-IPSEC-2024.03.05 that fixes issues caused by above tag. We will be updating the documentation soon.

Re: [PATCH v7 08/39] mbuf: use C11 alignas

On Tue, Mar 05, 2024 at 03:30:49PM +0100, David Marchand wrote: > On Mon, Mar 4, 2024 at 6:54 PM Tyler Retzlaff > wrote: > > > > The current location used for __rte_aligned(a) for alignment of types > > and variables is not compatible with MSVC. There is only a single > > location accepted by both

Re: [PATCH v7 10/39] eventdev: use C11 alignas

On Tue, Mar 05, 2024 at 04:47:05PM +0100, David Marchand wrote: > On Mon, Mar 4, 2024 at 6:54 PM Tyler Retzlaff > wrote: > > diff --git a/lib/eventdev/rte_eventdev.h b/lib/eventdev/rte_eventdev.h > > index 3af4686..08e5f93 100644 > > --- a/lib/eventdev/rte_eventdev.h > > +++ b/lib/eventdev/rte_eve

[PATCH v5 1/4] crypto/ipsec_mb: bump minimum IPsec Multi-buffer version

From: Sivaramakrishnan Venkat SW PMDs increment IPsec Multi-buffer version to 1.4. A minimum IPsec Multi-buffer version of 1.4 or greater is now required. Signed-off-by: Sivaramakrishnan Venkat Acked-by: Ciara Power Acked-by: Pablo de Lara Acked-by: Wathsala Vithanage --- v5: - Rebase

[PATCH v5 2/4] doc: remove outdated version details

From: Sivaramakrishnan Venkat SW PMDs documentation is updated to remove details of unsupported IPsec Multi-buffer versions.DPDK older than 20.11 is end of life. So, older DPDK versions are removed from the Crypto library version table. Signed-off-by: Sivaramakrishnan Venkat Acked-by: Pablo de

[PATCH v5 3/4] crypto/ipsec_mb: use new ipad/opad calculation API

IPSec Multi-buffer library v1.4 added a new API to calculate inner/outer padding for HMAC-SHAx/MD5. Signed-off-by: Pablo de Lara Signed-off-by: Brian Dooley Acked-by: Ciara Power Acked-by: Wathsala Vithanage --- v5: - Rebased and added to patchset v2: - Remove ipsec mb version checks --- dri

[PATCH v5 4/4] crypto/ipsec_mb: unified IPsec MB interface

Currently IPsec MB provides both the JOB API and direct API. AESNI_MB PMD is using the JOB API codepath while ZUC, KASUMI, SNOW3G and CHACHA20_POLY1305 are using the direct API. Instead of using the direct API for these PMDs, they should now make use of the JOB API codepath. This would remove all u

RE: [EXTERNAL] [PATCH] crypto/ipsec_mb: update Arm IPsec-MB library tag

> Hi Wathsala, > Any update on the updated tag and this patch? Hi Akhil, Tag SECLIB-IPSEC-2024.03.05 has been created.

Re: [PATCH] hash: make gfni stubs inline

On Tue, Mar 05, 2024 at 11:14:45AM +0100, David Marchand wrote: > On Mon, Mar 4, 2024 at 7:45 PM Stephen Hemminger > wrote: > > > > This reverts commit 07d836e5929d18ad6640ebae90dd2f81a2cafb71. > > > > Tyler found build issues with MSVC and the thash gfni stubs. > > The problem would be link error

Re: [RFC 1/7] eal: extend bit manipulation functions

On 2024-03-04 17:34, Tyler Retzlaff wrote: On Sun, Mar 03, 2024 at 07:26:36AM +0100, Mattias Rönnblom wrote: On 2024-03-02 18:05, Stephen Hemminger wrote: On Sat, 2 Mar 2024 14:53:22 +0100 Mattias Rönnblom wrote: diff --git a/lib/eal/include/rte_bitops.h b/lib/eal/include/rte_bitops.h index

Re: [**EXTERNAL**] [PATCH 03/30] net/ice/base: remove unnecessary control queue array

Hi @Qiming Yang, @Jacob Keller Good day! I am seeing a crash in ice/base running DPDK-2111-stable. We use VPP. While looking at DPDK-emails, I see some relevant changes here. Can you please take a look at the back-trace and suggest/p

Re: [RFC 1/7] eal: extend bit manipulation functions

On Tue, Mar 05, 2024 at 07:01:50PM +0100, Mattias Rönnblom wrote: > On 2024-03-04 17:34, Tyler Retzlaff wrote: > >On Sun, Mar 03, 2024 at 07:26:36AM +0100, Mattias Rönnblom wrote: > >>On 2024-03-02 18:05, Stephen Hemminger wrote: > >>>On Sat, 2 Mar 2024 14:53:22 +0100 > >>>Mattias Rönnblom wrote:

[PATCH] net/mlx5: fix async flow create error handling

Whenever processing of asynchronous flow rule create operation failed, but after some dynamic flow actions had already been allocated, these actions were not freed during error handling flow. That behavior lead to leaks e.g., RSS/QUEUE action objects were leaked which triggered assertions during de

Re: [RFC 2/7] eal: add generic bit manipulation macros

On 2024-03-04 17:42, Tyler Retzlaff wrote: On Sat, Mar 02, 2024 at 02:53:23PM +0100, Mattias Rönnblom wrote: Add bit-level test/set/clear/assign macros operating on both 32-bit and 64-bit words by means of C11 generic selection. Signed-off-by: Mattias Rönnblom --- _Generic is nice here. shou

Re: [PATCH] app/test: don't count skipped tests as executed

On Mon, Nov 13, 2023 at 03:05:33PM +, Bruce Richardson wrote: > The logic around skipped tests is a little confusing in the unit test > runner. > * Any explicitly disabled tests are counted as skipped but not > executed. > * Any tests that return TEST_SKIPPED are counted as both skipped and >

Re: [RFC 2/7] eal: add generic bit manipulation macros

On Tue, Mar 05, 2024 at 07:08:36PM +0100, Mattias Rönnblom wrote: > On 2024-03-04 17:42, Tyler Retzlaff wrote: > >On Sat, Mar 02, 2024 at 02:53:23PM +0100, Mattias Rönnblom wrote: > >>Add bit-level test/set/clear/assign macros operating on both 32-bit > >>and 64-bit words by means of C11 generic se

Re: [PATCH] tests: assume c source files are utf-8 encoded

On Tue, Mar 05, 2024 at 02:46:15PM +0100, Robin Jarry wrote: > Instead of relying on the default locale from the environment (LC_ALL), > explicitly read the files as utf-8 encoded. > > Fixes: 0aeaf75df879 ("test: define unit tests suites based on test types") > > Signed-off-by: Robin Jarry > ---

Re: [PATCH v2 45/71] event/dlb2: replace use of fixed size rte_memcpy

On Tue, 5 Mar 2024 17:07:02 + "Sevincer, Abdullah" wrote: > Hi Stephen, > > Are all rte_memcpy functions now be replaced by memcpy and no more use of > rte_memcpy? > Long term yes. There is no reason for rte_memcpy to exist, it only exists because the DPDK team at Intel was able to get a

Re: reg. https://patches.dpdk.org/project/dpdk/list/?series=31200 - patch result

"Power, Ciara" writes: > + Patrick > > > > From: Power, Ciara > Sent: Tuesday, March 5, 2024 10:05 AM > To: Sivaramakrishnan, VenkatX ; Akhil > Goyal > Cc: Ji, Kai ; Aaron Conole > Subject: RE: reg. https://patches.dpdk.org/project/dpdk/list/?series=31200 - > patch result > > > > Hi folk

Re: [PATCH] hash: make gfni stubs inline

On Tue, 5 Mar 2024 09:53:00 -0800 Tyler Retzlaff wrote: > On Tue, Mar 05, 2024 at 11:14:45AM +0100, David Marchand wrote: > > On Mon, Mar 4, 2024 at 7:45 PM Stephen Hemminger > > wrote: > > > > > > This reverts commit 07d836e5929d18ad6640ebae90dd2f81a2cafb71. > > > > > > Tyler found build issu

RE: [EXTERNAL] [PATCH v5 1/4] crypto/ipsec_mb: bump minimum IPsec Multi-buffer version

> Subject: [EXTERNAL] [PATCH v5 1/4] crypto/ipsec_mb: bump minimum IPsec > Multi-buffer version > > From: Sivaramakrishnan Venkat > > SW PMDs increment IPsec Multi-buffer version to 1.4. > A minimum IPsec Multi-buffer version of 1.4 or greater is now required. > > Signed-off-by: Sivaramakrishna

Re: [EXTERNAL] [PATCH v5 1/4] crypto/ipsec_mb: bump minimum IPsec Multi-buffer version

On Tue, Mar 5, 2024 at 2:11 PM Akhil Goyal wrote: > > > Subject: [EXTERNAL] [PATCH v5 1/4] crypto/ipsec_mb: bump minimum IPsec > > Multi-buffer version > > > > From: Sivaramakrishnan Venkat > > > > SW PMDs increment IPsec Multi-buffer version to 1.4. > > A minimum IPsec Multi-buffer version of 1.

Re: [PATCH v7 08/39] mbuf: use C11 alignas

On Tue, Mar 5, 2024 at 6:37 PM Tyler Retzlaff wrote: > > > diff --git a/lib/mbuf/rte_mbuf_core.h b/lib/mbuf/rte_mbuf_core.h > > > index 5688683..917a811 100644 > > > --- a/lib/mbuf/rte_mbuf_core.h > > > +++ b/lib/mbuf/rte_mbuf_core.h > > > @@ -463,7 +463,7 @@ enum { > > > /** > > > * The generi

Re: [RFC 2/7] eal: add generic bit manipulation macros

On 2024-03-05 19:22, Tyler Retzlaff wrote: On Tue, Mar 05, 2024 at 07:08:36PM +0100, Mattias Rönnblom wrote: On 2024-03-04 17:42, Tyler Retzlaff wrote: On Sat, Mar 02, 2024 at 02:53:23PM +0100, Mattias Rönnblom wrote: Add bit-level test/set/clear/assign macros operating on both 32-bit and 64-b

Re: [PATCH v7 00/39] use C11 alignas

On Mon, Mar 4, 2024 at 6:53 PM Tyler Retzlaff wrote: > > The current location used for __rte_aligned(a) for alignment of types > and variables is not compatible with MSVC. There is only a single > location accepted by both toolchains. > > For variables standard C11 offers alignas(a) supported by c

RTE lock

Shouldn't we have a DPDK-native mutex API, rather than using direct POSIX mutex lock calls? There are two reasons for this, as I see it 1) more cleanly support non-POSIX operating system (i.e., Microsoft Windows). 2) to discourage mechanical use of spinlocks in places where a regular mutex loc

Re: [RFC 2/7] eal: add generic bit manipulation macros

On Tue, Mar 05, 2024 at 09:02:34PM +0100, Mattias Rönnblom wrote: > On 2024-03-05 19:22, Tyler Retzlaff wrote: > >On Tue, Mar 05, 2024 at 07:08:36PM +0100, Mattias Rönnblom wrote: > >>On 2024-03-04 17:42, Tyler Retzlaff wrote: > >>>On Sat, Mar 02, 2024 at 02:53:23PM +0100, Mattias Rönnblom wrote: >

Re: RTE lock

On Tue, Mar 05, 2024 at 09:18:20PM +0100, Mattias Rönnblom wrote: > Shouldn't we have a DPDK-native mutex API, rather than using direct > POSIX mutex lock calls? David raised this a while back and the consensus is yes. I admit it's been on my radar for a long time for the obvious reasons you list

Re: [EXTERNAL] [PATCH v5 1/4] crypto/ipsec_mb: bump minimum IPsec Multi-buffer version

Recheck-request: iol-unit-arm64-testing

Re: [PATCH v2] config/arm: add Marvell Odyssey

On 2024/3/5 7:13 PM, Anoob Joseph wrote: Add meson build configuration for Marvell Odyssey platform with 64-bit ARM Neoverse V2 cores. Signed-off-by: Anoob Joseph --- Depends-on: series-31141 ("config/arm: add Neoverse V2 part number") Changes in v2: - Renamed config file config/arm/arm

Re: [PATCH v2] config/arm: add Marvell Odyssey

> On Mar 5, 2024, at 5:13 AM, Anoob Joseph wrote: > > Add meson build configuration for Marvell Odyssey platform with 64-bit > ARM Neoverse V2 cores. > > Signed-off-by: Anoob Joseph > --- > > Depends-on: series-31141 ("config/arm: add Neoverse V2 part number") > > Changes in v2: > - Renamed

Re: [EXTERNAL] [PATCH v5 1/4] crypto/ipsec_mb: bump minimum IPsec Multi-buffer version

On Tue, Mar 5, 2024 at 6:30 PM Patrick Robb wrote: > > Recheck-request: iol-unit-arm64-testing https://mails.dpdk.org/archives/test-report/2024-March/601582.html Hello. I wanted to flag this as still failing on arm after running the testing using the new tag Wathsala published today. We did it v

RE: [PATCH v2] config/arm: add Marvell Odyssey

Hi Honnappa, Thanks for the review. Please see inline. Thanks, Anoob > -Original Message- > From: Honnappa Nagarahalli > Sent: Wednesday, March 6, 2024 8:50 AM > To: Anoob Joseph > Cc: Juraj Linkeš ; tho...@monjalon.net; David > Marchand ; Jerin Jacob ; nd > ; Pavan Nikhilesh Bhagavatu

Reminder - DPDK Tech Board Call - Tomorrow, Wed. Mar 6 , 2024 - 7am Pacific/10am Eastern/1500h UTC

Good evening Dpdk Community, Tomorrow morning is the biweekly meeting - as always please put your agenda items here in advance: https://annuel.framapad.org/p/r.0c3cc4d1e011214183872a98f6b5c7db

RE: RFC: Using and renaming 8-bit reserved field of rte_crypto_op for implementation specific

Hi Akhil, No changes in sequence of API's by adding 'uint8_t impl_opaque' to 'struct rte_crypto_op'. It's required in case application/event dispatcher passes some implementation specific value in rte_event::impl_opaque, to restore the value back on to rte_event::impl_opaque after enqueue to

Re: [PATCH v2] config/arm: add Marvell Odyssey

> On Mar 5, 2024, at 10:41 PM, Anoob Joseph wrote: > > Hi Honnappa, > > Thanks for the review. Please see inline. > > Thanks, > Anoob > >> -Original Message- >> From: Honnappa Nagarahalli >> Sent: Wednesday, March 6, 2024 8:50 AM >> To: Anoob Joseph >> Cc: Juraj Linkeš ; tho...@mon

Re: [PATCH v2] config/arm: add Marvell Odyssey

> On Mar 5, 2024, at 5:13 AM, Anoob Joseph wrote: > > Add meson build configuration for Marvell Odyssey platform with 64-bit > ARM Neoverse V2 cores. > > Signed-off-by: Anoob Joseph Reviewed-by: Honnappa Nagarahalli > --- > > Depends-on: series-31141 ("config/arm: add Neoverse V2 part numb

[PATCH v3] config/arm: add Marvell Odyssey

Add meson build configuration for Marvell Odyssey platform with 64-bit ARM Neoverse V2 cores. Signed-off-by: Anoob Joseph Reviewed-by: Honnappa Nagarahalli Reviewed-by: Ruifeng Wang --- Depends-on: series-31141 ("config/arm: add Neoverse V2 part number") Changes in v3: - Added string for Odys

[PATCH] net/mlx5: fix mlx5dr context release ordering

Creating rules on group >0, creates a jump action on the group table. Non template code releases the group data under shared mlx5dr free code, And the mlx5dr context was already closed in HWS code. Remove mlx5dr context release from hws resource release function. Fixes: b401400db24e ("net/mlx5: a

Re: [PATCH] doc: update size parameter details

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding. For configuration parameters `mem_size` and `buf_size` are represented as megabytes and bytes respectively in application. Update the documentation to represe

Re: [PATCH v4 2/7] ethdev: add telemetry cmd for registers

Hi, Chengwen, Thanks for your review, all will be modified in next version. Best Regards, Jie Hai On 2024/2/26 17:09, fengchengwen wrote: Hi Jie, On 2024/2/26 11:07, Jie Hai wrote: This patch adds a telemetry command for registers dump, and supports get registers with specified names. The leng

Re: [PATCH v4 1/7] ethdev: support report register names and filter

Hi, fengchengwen, On 2024/2/26 16:01, fengchengwen wrote: Hi Jie, On 2024/2/26 11:07, Jie Hai wrote: This patch adds "filter" and "names" fields to "rte_dev_reg_info" structure. Names of registers in data fields can be reported and the registers can be filtered by their names. The new API rte_

Symmetric RSS Hashing support in DPDK

Hello, Our application needs symmetric hashing to handle the reverse traffic on the same core, also to Improve performance by distributing the traffic across core. Tried using rss config as below . action_rss_tcp.types = ETH_RSS_NONFRAG_IPV4_TCP | ETH_RSS_L3_SRC_ONLY| ETH_RSS_L3_DST_ONLY | ET

[PATCH] net/mlx5: fix pattern template size validation

PMD running in HWS FDB mode can be configured to steer group 0 to FW. In that case PMD activates legacy DV pattern processing. There are control flows that require HWS pattern processing in group 0. Pattern template validation tried to create a matcher both in group 0 and HWS group. As the result,

  1   2   >