RSS on L2TP, Teredo, PPPoE Tunnels

Hello DPDK Team, Hope you guys are doing great !! We are developing application with dpdk 22.03 & Mellanox Connectx-6 adapter, Want to use IP-Port tuples (Inner in case of tunnels) to RSS traffic to multiple queues. We need to handle L2TPv2/3, Teredo, PPPoE etc, but adapter have limited tunnel

[PATCH] mempool: fix rte_mempool_avail_count may segment fault when used in multiprocess

rte_mempool_create put tailq entry into rte_mempool_tailq list before populate, and pool_data set when populate. So in multi process, if process A create mempool, and process B can get mempool through rte_mempool_lookup before pool_data set, if B call rte_mempool_lookup, it will cause segment fault

[PATCH v6] ethdev: add special flags when creating async transfer table

In case flow rules match only one kind of traffic in a flow table, then optimization can be done via allocation of this table. Such optimization is possible only if the application gives a hint about its usage of the table during initial configuration. The transfer domain rules may process traffic

Re: [PATCH] app/testpmd: flush flow templates when port is removed

On 11/11/22 19:22, Singh, Aman Deep wrote: On 11/8/2022 3:00 PM, Dariusz Sosnowski wrote: From: Suanming Mou This patch adds explicit flushing of template tables, pattern and actions templates, when a port is closed or detached. Signed-off-by: Suanming Mou Acked-by: Aman Singh Applied t

Re: [PATCH v3] netdev-dpdk: add control plane protection support

Fixing To: to add back in OVS ML. +cc Ori, as mlx5 operation discussed below. On 11/11/2022 18:15, Kevin Traynor wrote: Hi Robin, On 21/10/2022 15:53, Robin Jarry wrote: Some control protocols are used to maintain link status between forwarding engines (e.g. LACP). When the system is not size

RE: [PATCH] mempool: fix rte_mempool_avail_count may segment fault when used in multiprocess

> From: changfengnan [mailto:changfeng...@bytedance.com] > Sent: Monday, 14 November 2022 08.15 > > rte_mempool_create put tailq entry into rte_mempool_tailq list before > populate, and pool_data set when populate. So in multi process, if > process A create mempool, and process B can get mempool t

Re: [dpdk-dev] [PATCH] lib: fix doxygen syntax issues

On Wed, Nov 9, 2022 at 3:54 PM wrote: > > From: Jerin Jacob > > Fix following syntax error reported by doxygen 1.9.5 version. > > lib/eal/include/rte_uuid.h:89: error: RTE_UUID_STRLEN > has @param documentation sections but no arguments > (warning treated as error, aborting now) > > lib/power/rte

Re: [PATCH] power: fix double free of opened files

On Mon, Nov 7, 2022 at 10:18 AM Pattan, Reshma wrote: > > Fix double free of f_min and f_max by reverting the flcose() for f_min and > > f_max. As f_min and f_max are stored for further use and closed in uncore > > deinitialization. > > > > Fixes: b127e74 ("power: fix open file descriptors leak")

Re: [PATCH] hash: fix memory leak of hash_rcu_cfg

On Fri, Nov 4, 2022 at 10:52 AM Jun Qiu wrote: > > The memory of h->hash_rcu_cfg which is allocated in > rte_hash_rcu_qsbr_add was leaked. > > Fixes: 769b2de ("hash: implement RCU resources reclamation") Please, use 12 chars format for commit hash, as documented. git config alias.fixline "log -1

Re: [PATCH v3 1/2] test/hash: fix coverity warning

On Thu, Nov 10, 2022 at 4:14 PM Vladimir Medvedkin wrote: > > Remove unnecessary variable assignment > > Coverity issue: 336800 > Fixes: 3f9aab961ed3 ("test/hash: check lock-free extendable bucket") > Cc: sta...@dpdk.org > > Signed-off-by: Vladimir Medvedkin > Reviewed-by: Ruifeng Wang Series a

Re: [PATCH v2] bus/auxiliary: prevent device from being probed again

On Wed, Nov 9, 2022 at 3:54 PM Bing Zhao wrote: > > The device on auxiliary bus doesn't support being probed again > without being removed firstly. The PMD will detect and return error > for this unsupported operation. Some of the resources would be > cleared wrongly. When quitting, there will be

RE: [PATCH v3] net/ice: fix ice_interrupt_handler panic when stop

> -Original Message- > From: Du, Frank > Sent: Monday, November 14, 2022 3:03 PM > To: dev@dpdk.org > Subject: [PATCH v3] net/ice: fix ice_interrupt_handler panic when stop > > rte_intr_callback_unregister may fail when irq cb is in handling, use sync > version to make sure unregister

RE: [dpdk-dev v2] app/test: fix of bitwise and operator in return

Hi Kai, > -Original Message- > From: Kai Ji > Sent: Friday 11 November 2022 16:27 > To: dev@dpdk.org > Cc: sta...@dpdk.org; gak...@marvell.com; Ji, Kai ; > Krakowiak, LukaszX > Subject: [dpdk-dev v2] app/test: fix of bitwise and operator in return > > This patch remove incorrect bitwise

Re: [PATCH] common/mlx5: use build configuration dictionary

On Tue, Nov 8, 2022 at 8:51 AM David Marchand wrote: > > On Mon, Nov 7, 2022 at 5:37 PM Thomas Monjalon wrote: > > > > A recent commit added an explicit dependency check on common/mlx5. > > For consistency, query dpdk_conf instead of the list of common drivers. > > The lists *_drivers should be u

Re: [PATCH] build: list selected applications

On Fri, Oct 28, 2022 at 6:30 PM Markus Theil wrote: > On 10/28/22 14:34, David Marchand wrote: > > With the addition of enable/disable_apps meson options, it is a bit > harder to figure out which application is built, and why. > > Display the list of applications in the same way we do for drivers

Re: [PATCH] maintainers: group service cores files

On Tue, Nov 8, 2022 at 9:48 AM Van Haaren, Harry wrote: > > From: Thomas Monjalon > > > > Move example with library files, all with the same maintainer. > > > > Signed-off-by: Thomas Monjalon > Acked-by: Harry van Haaren Applied, thanks. -- David Marchand

Re: [PATCH] maintainers: update for pmdinfo tool

On Tue, Nov 8, 2022 at 3:18 PM David Marchand wrote: > On Mon, Nov 7, 2022 at 6:14 PM Thomas Monjalon wrote: > > > > The original maintainer of pmdinfo/pmdinfogen > > did not send an email for 2 years. > > > > Signed-off-by: Thomas Monjalon > Acked-by: David Marchand Applied, thanks. -- Dav

[PATCH] net/idpf: need to stop device when closing device

From: Beilei Xing This patch stops device at the beginning of idpf_dev_close. Fixes: 14aa6ed8f2ec ("net/idpf: support device start and stop") Signed-off-by: Beilei Xing --- drivers/net/idpf/idpf_ethdev.c | 7 +++ drivers/net/idpf/idpf_ethdev.h | 2 ++ 2 files changed, 9 insertions(+) dif

Re: [PATCH 0/2] GitHub Actions configuration fixes

On Wed, Oct 12, 2022 at 6:30 PM David Marchand wrote: > > GitHub Actions started to deprecated some part of the workflow syntax > and dependencies of some core actions. > > This series (mostly) fix those warnings. > For reviewers/testers, this is still moving: I got new warnings while > I was test

[PATCH 1/2] common/cnxk: update IPsec completion codes

Update the IPsec completion codes as per UCODE version OCPT-04-IE-IPSEC-MC-30-01-28-00 Signed-off-by: Rahul Bhansali --- drivers/common/cnxk/hw/cpt.h | 2 ++ drivers/common/cnxk/roc_cpt.c | 2 +- drivers/common/cnxk/roc_ie_ot.h | 21 +++-- dri

[PATCH 2/2] net/cnxk: update IPsec completion code handling

Update IPsec handling with reference from UCODE version OCPT-04-IE-IPSEC-MC-30-01-28-00 Signed-off-by: Rahul Bhansali --- drivers/net/cnxk/cn10k_rx.h | 170 1 file changed, 95 insertions(+), 75 deletions(-) diff --git a/drivers/net/cnxk/cn10k_rx.h b/drivers/

Re: [PATCH v1] net/mlx5: fix action flag data type

01/11/2022 11:07, Shun Hao: > This patch fixes this by making all action flags definition as 64-bit > data type. No, it is defining as unsigned long long. [...] > /* Actions */ > -#define MLX5_FLOW_ACTION_DROP (1u << 0) > -#define MLX5_FLOW_ACTION_QUEUE (1u << 1) > -#define MLX5_FLOW_ACTION_RSS

[PATCH v7] ethdev: add special flags when creating async transfer table

In case flow rules match only one kind of traffic in a flow table, then optimization can be done via allocation of this table. Such optimization is possible only if the application gives a hint about its usage of the table during initial configuration. The transfer domain rules may process traffic

[dpdk-dev] [PATCH v1 00/12] mldev: introduce machine learning device library

From: Jerin Jacob Machine learning inference library == Definition of machine learning inference Inference in machine learning is the process of making an output prediction based on new input data using a pre-trained machin

[dpdk-dev] [PATCH v1 02/12] mldev: add PMD functions for ML device

From: Srikanth Yalavarthi Added PMD functions to handle ML devices. The rte_mldev_pmd.* files are for drivers only and should be private to DPDK, and are not installed for application use. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Jerin Jacob --- lib/mldev/meson.build | 9 +++

[dpdk-dev] [PATCH v1 03/12] mldev: support device handling functions

From: Srikanth Yalavarthi Added device handling APIs. These APIs are used to get device information, configure, start, stop and close ML devices. Added function prototypes to PMD layer which are used by the ML driver implementations in the poll mode driver. Signed-off-by: Srikanth Yalavarthi Si

[dpdk-dev] [PATCH v1 01/12] mldev: introduce machine learning device library

From: Jerin Jacob Add mldev API specification to standardize and use the machine learning device and inference operations in vendor neutral way. Following operations are abstracted through APIs - ML device capability probe - ML device configuration - ML device queue pair configuration - ML devi

[dpdk-dev] [PATCH v1 04/12] mldev: support device queue-pair setup

From: Srikanth Yalavarthi Added APIs to create a queue-pair attached to ML device. Queue pairs are created with a user specified ID. Added function prototypes to be used by ML drivers for queue pair create and destroy. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Jerin Jacob --- lib/mlde

[dpdk-dev] [PATCH v1 06/12] mldev: support input and output data handling

From: Srikanth Yalavarthi Added RTE library functions to handle model input and output data. The APIs can be used to get the size of I/O buffers, quantize input data and dequantize output data. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Jerin Jacob --- lib/mldev/rte_mldev.c | 94

[dpdk-dev] [PATCH v1 05/12] mldev: support handling ML models

From: Srikanth Yalavarthi Added RTE functions to handle ML models. These APIs can load, unload, start, and stop an ML model. Additional APIs to update model parameters and get model information are added. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Jerin Jacob --- lib/mldev/rte_mldev.c

[dpdk-dev] [PATCH v1 07/12] mldev: support op pool and its operations

From: Srikanth Yalavarthi Added RTE library functions to create and free ML op pool. Create function allocates new ML op pool and initializes ML ops to their defaults. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Jerin Jacob --- lib/mldev/rte_mldev.c | 69

[dpdk-dev] [PATCH v1 08/12] mldev: support inference enqueue and dequeue

From: Srikanth Yalavarthi Added implementations of fast-path functions to enqueue and dequeue ML requests from an ML device queue-pair. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Jerin Jacob --- lib/mldev/rte_mldev.c | 76 ++ lib/mldev/rte_mldev

[dpdk-dev] [PATCH v1 09/12] mldev: support device statistics

From: Srikanth Yalavarthi Added functions to get and reset device stats. Device stats include number of requests enqueued, dequeued and errors. Added function prototypes to used by driver implementations. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Jerin Jacob --- lib/mldev/rte_mldev.c

[dpdk-dev] [PATCH v1 10/12] mldev: support device extended statistics

From: Srikanth Yalavarthi Added functions to handle device extended stats. xstats supported are driver specific and can include stats specific to ML device or ML model and I/O. Added prototypes for functions to be called by the device drivers. Signed-off-by: Srikanth Yalavarthi Signed-off-by: J

[dpdk-dev] [PATCH v1 11/12] mldev: support to retrieve error information

From: Srikanth Yalavarthi Added functions to get error information for an ML op. This information can include both drive specific error message and error code. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Jerin Jacob --- lib/mldev/rte_mldev.c | 31 +++ li

[dpdk-dev] [PATCH v1 12/12] mldev: support to get debug info and test device

From: Srikanth Yalavarthi Added library functions for ML device debug APIs. The APIs are used to dump ML device debug information and to run selftest. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Jerin Jacob --- lib/mldev/rte_mldev.c | 39 ++ lib/

Re: [PATCH v3] netdev-dpdk: add control plane protection support

Hi Kevin, Kevin Traynor, Nov 11, 2022 at 19:15: > > +reta_conf_size = (dev->reta_size / RTE_ETH_RETA_GROUP_SIZE) > > +* sizeof(struct rte_eth_rss_reta_entry64); > > In dpdk_eth_dev_init, we get reta_size from driver, > > mlx5_ethdev.c > > 333├>info->reta_size = priv->reta_idx_n

RE: [PATCH v2 1/3] net/mlx5: fix log level on failed transfer proxy stop

> -Original Message- > From: Dariusz Sosnowski > Sent: Wednesday, November 9, 2022 21:07 > To: Matan Azrad ; Slava Ovsiienko > Cc: dev@dpdk.org > Subject: [PATCH v2 1/3] net/mlx5: fix log level on failed transfer proxy > stop > > This patches increases log level for error reporting when

RE: [PATCH v2 2/3] doc: document E-Switch limitations with HWS in mlx5 PMD

> -Original Message- > From: Dariusz Sosnowski > Sent: Wednesday, November 9, 2022 21:07 > To: Matan Azrad ; Slava Ovsiienko > Cc: dev@dpdk.org > Subject: [PATCH v2 2/3] doc: document E-Switch limitations with HWS in mlx5 > PMD > > This patch adds the following limitations to the mlx5 PM

Re: [PATCH v2 3/3] ethdev: document special cases of port start and stop

On 11/9/2022 7:06 PM, Dariusz Sosnowski wrote: This patch clarifies the handling of following cases in the ethdev API docs: - If rte_eth_dev_start() returns (-EAGAIN) for some port, it cannot be started until other port is started. - If rte_eth_dev_stop() returns (-EBUSY) for some port, it

[PATCH] devtools: catch empty symbol maps

version.map are now optional for drivers if no symbol is exported. Having no symbol exported from a library does not make sense. Catch all empty maps and warn about them. Example: $ ./devtools/check-symbol-maps.sh Found empty maps: drivers/crypto/uadk/version.map drivers/net/gve/version.map drive

Re: [PATCH v4 1/2] build: make version file optional for drivers

On Wed, Oct 12, 2022 at 1:33 PM Ferruh Yigit wrote: > On 10/12/2022 11:42 AM, Abdullah Ömer Yamaç wrote: > > In this patch, we removed the necessity of the version files and > > you don't need to update these files for each release, you can just > > remove them. > > > > Suggested-by: Ferruh Yigit

[PATCH] drivers: various typos found by Lintian

From: Luca Boccassi Signed-off-by: Luca Boccassi --- drivers/crypto/dpaa_sec/dpaa_sec.c | 4 ++-- drivers/net/bonding/rte_eth_bond_pmd.c | 2 +- drivers/net/hns3/hns3_ethdev.c | 2 +- drivers/net/qede/base/ecore_int.c | 4 ++-- 4 files changed, 6 insertions(+), 6 deletions(-)

[PATCH 2/2] docs: sort files lists in generator scripts

From: Luca Boccassi In order to build the documentation in a reproducible manner, sort the lists of files used as input, since walking the filesystem is not guaranteed to be done in a stable order. When converting the scripts from shell to python, sorting the input was lost. Fixes: 53bb9a073f4f

[PATCH 1/2] docs: add +x to generator scripts

From: Luca Boccassi These scripts have a shebang so they are meant to be runnable, so set +x bits Fixes: 53bb9a073f4f ("doc: rewrite shell scripts in Python") Signed-off-by: Luca Boccassi --- doc/api/generate_doxygen.py | 0 doc/api/generate_examples.py | 0 2 files changed, 0 insertions(+),

Re: [PATCH 2/2] docs: sort files lists in generator scripts

On Mon, Nov 14, 2022 at 02:22:25PM +, luca.bocca...@gmail.com wrote: > From: Luca Boccassi > > In order to build the documentation in a reproducible manner, sort the lists > of > files used as input, since walking the filesystem is not guaranteed to be done > in a stable order. > When conver

Re: [PATCH 1/2] docs: add +x to generator scripts

On Mon, Nov 14, 2022 at 02:22:24PM +, luca.bocca...@gmail.com wrote: > From: Luca Boccassi > > These scripts have a shebang so they are meant to be runnable, so set +x bits > > Fixes: 53bb9a073f4f ("doc: rewrite shell scripts in Python") > > Signed-off-by: Luca Boccassi > --- > doc/api/ge

Re: [PATCH] devtools: catch empty symbol maps

On Mon, Nov 14, 2022 at 03:16:51PM +0100, David Marchand wrote: > version.map are now optional for drivers if no symbol is exported. > Having no symbol exported from a library does not make sense. > > Catch all empty maps and warn about them. > > Example: > $ ./devtools/check-symbol-maps.sh > Fou

Re: [PATCH] devtools: catch empty symbol maps

On 11/14/2022 2:31 PM, Bruce Richardson wrote: On Mon, Nov 14, 2022 at 03:16:51PM +0100, David Marchand wrote: version.map are now optional for drivers if no symbol is exported. Having no symbol exported from a library does not make sense. Catch all empty maps and warn about them. Example: $ .

RE: [PATCH 4/4] examples: remove unnecessary null checks

Hi Stephen, Looks good for fips validation. > -Original Message- > From: Stephen Hemminger > Sent: Wednesday, November 9, 2022 11:47 PM > To: dev@dpdk.org > Cc: Stephen Hemminger ; Hunt, David > ; Dooley, Brian > Subject: [PATCH 4/4] examples: remove unnecessary null checks > > The fun

RE: [PATCH v2 3/3] ethdev: document special cases of port start and stop

Hi Ferruh, > -Original Message- > From: Ferruh Yigit > Sent: Monday, November 14, 2022 15:08 > To: Dariusz Sosnowski ; Aman Singh > ; Yuying Zhang ; > NBU-Contact-Thomas Monjalon (EXTERNAL) ; > Andrew Rybchenko > Cc: dev@dpdk.org > Subject: Re: [PATCH v2 3/3] ethdev: document special cas

[RFC PATCH v2 00/10] dts: add hello world testcase

Add code needed to run the HelloWorld testcase which just runs the hello world dpdk application. The patch first outlines the basic class architecture, covering Nodes (hosts that DTS connects to), RemoteSession, OS-specific code, test runner and Exceptions. The patchset currently heavily refactor

[RFC PATCH v2 01/10] dts: add node and os abstractions

The abstraction model in DTS is as follows: Node, defining and implementing methods common to and the base of SUT (system under test) Node and TG (traffic generator) Node. Remote Session, defining and implementing methods common to any remote session implementation, such as SSH Session. OSSession,

[RFC PATCH v2 02/10] dts: add ssh command verification

This is a basic capability needed to check whether the command execution was successful or not. If not, raise a RemoteCommandExecutionError. When a failure is expected, the caller is supposed to catch the exception. Signed-off-by: Juraj Linkeš --- dts/framework/exception.py|

[RFC PATCH v2 03/10] dts: add dpdk build on sut

Add the ability to build DPDK and apps, using a configured target. Signed-off-by: Juraj Linkeš --- dts/framework/exception.py| 17 +++ dts/framework/remote_session/os/os_session.py | 90 +++- .../remote_session/os/posix_session.py| 128 + ...

[RFC PATCH v2 04/10] dts: add dpdk execution handling

Add methods for setting up and shutting down DPDK apps and for constructing EAL parameters. Signed-off-by: Juraj Linkeš --- dts/conf.yaml | 4 + dts/framework/config/__init__.py | 85 - dts/framework/config/conf_yaml_schema.json| 22 ++

[RFC PATCH v2 05/10] dts: add node memory setup

Setup hugepages on nodes. This is useful not only on SUT nodes, but also on TG nodes which use TGs that utilize hugepages. Signed-off-by: Juraj Linkeš --- dts/framework/remote_session/__init__.py | 1 + dts/framework/remote_session/arch/__init__.py | 20 + dts/framework/remote_session/

[RFC PATCH v2 06/10] dts: add test results module

The module keeps track of test case results along with miscellaneous information, such as on which SUT's did a failure occur and during the testing of which build target. Signed-off-by: Juraj Linkeš --- dts/framework/dts.py | 5 + dts/framework/test_result.py | 217

[RFC PATCH v2 07/10] dts: add simple stats report

Provide a summary of testcase passed/failed/blocked counts. Signed-off-by: Juraj Linkeš --- dts/framework/dts.py| 3 ++ dts/framework/stats_reporter.py | 65 + 2 files changed, 68 insertions(+) create mode 100644 dts/framework/stats_reporter.py diff

[RFC PATCH v2 08/10] dts: add testsuite class

This is the base class that all test suites inherit from. The base class implements methods common to all test suites. The derived test suites implement tests and any particular setup needed for the suite or tests. Signed-off-by: Juraj Linkeš --- dts/conf.yaml | 4

[RFC PATCH v2 09/10] dts: add hello world testplan

The testplan describes the capabilities of the tested application along with the description of testcases to test it. Signed-off-by: Juraj Linkeš --- dts/test_plans/hello_world_test_plan.rst | 68 1 file changed, 68 insertions(+) create mode 100644 dts/test_plans/hello_

[RFC PATCH v2 10/10] dts: add hello world testsuite

The testsuite implements the testcases defined in the corresponding test plan. Signed-off-by: Juraj Linkeš --- dts/framework/remote_session/os/os_session.py | 16 +- dts/framework/testbed_model/__init__.py | 1 + dts/framework/testbed_model/node/sut_node.py | 11 dts/tests/TestS

[PATCH 1/2] test/crypto-perf: fix number of sessions for cores

Currently the performance application creates a device session per lcore. This was not reflected in how many session objects were available in the mempool, when using a scheduler device. The number of lcores is now taken into consideration when calculating how many sessions are needed for the sche

[PATCH 2/2] test/crypto-perf: replace slave with worker

Update the use of outdated language "slaves" with "workers". Signed-off-by: Ciara Power --- app/test-crypto-perf/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/app/test-crypto-perf/main.c b/app/test-crypto-perf/main.c index 22f6b2b3ba..af5bd0d23b 100644 --- a/app/

Re: [PATCH] net/mlx5: fix drop action validation

10/11/2022 13:18, Raslan Darawsheh: > From: Shun Hao > > Currently there's limitation for Drop action that can only co-exist with > > Count action. > > > > Sample and Age actions are also able to exist with Drop within the same > > flow, and this patch includes them in the Drop action validation.

Re: [PATCH v2 3/3] ethdev: document special cases of port start and stop

On 11/14/2022 4:12 PM, Dariusz Sosnowski wrote: Hi Ferruh, -Original Message- From: Ferruh Yigit Sent: Monday, November 14, 2022 15:08 To: Dariusz Sosnowski ; Aman Singh ; Yuying Zhang ; NBU-Contact-Thomas Monjalon (EXTERNAL) ; Andrew Rybchenko Cc: dev@dpdk.org Subject: Re: [PATCH v2

[PATCH v3 0/3] ethdev: document special cases of port start and stop

This patch series attempts to address the special failure cases of rte_eth_dev_stop() and rte_eth_dev_start(). In case of starting a port, If the port cannot be started and start operation must be retried, PMDs might return (-EAGAIN) to notify about such situation. In case of stopping a port, If

[PATCH v3 1/3] net/mlx5: fix log level on failed transfer proxy stop

This patches increases log level for error reporting when stopping the transfer proxy port failed. Stopping can fail with EBUSY when related representor ports are still running. Fixes: 483181f7b6dd ("net/mlx5: support device control of representor matching") Signed-off-by: Dariusz Sosnowski Acke

[PATCH v3 2/3] net/mlx5: document E-Switch limitations with HWS in mlx5 PMD

This patch adds the following limitations to the mlx5 PMD guide: - With HW Steering and E-Switch enabled, transfer proxy port must be started before any port representor. - With HW Steering and E-Switch enabled, all representors must be stopped before transfer proxy port is stopped. Documenta

[PATCH v3 3/3] ethdev: document special cases of port start and stop

This patch clarifies the handling of following cases in the ethdev API docs: - If rte_eth_dev_start() returns (-EAGAIN) for some port, it cannot be started right now and start operation must be retried. - If rte_eth_dev_stop() returns (-EBUSY) for some port, it cannot be stopped in the curre

RE: [PATCH v2 3/3] ethdev: document special cases of port start and stop

> -Original Message- > From: Ferruh Yigit > Sent: Monday, November 14, 2022 18:10 > To: Dariusz Sosnowski ; Aman Singh > ; Yuying Zhang ; > NBU-Contact-Thomas Monjalon (EXTERNAL) ; > Andrew Rybchenko > Cc: dev@dpdk.org > Subject: Re: [PATCH v2 3/3] ethdev: document special cases of port s

Re: [PATCH v3 3/3] ethdev: document special cases of port start and stop

On 11/14/2022 6:19 PM, Dariusz Sosnowski wrote: This patch clarifies the handling of following cases in the ethdev API docs: - If rte_eth_dev_start() returns (-EAGAIN) for some port, it cannot be started right now and start operation must be retried. - If rte_eth_dev_stop() returns (-EBUSY

Re: [PATCH] mempool: fix rte_mempool_avail_count may segment fault when used in multiprocess

On Mon, Nov 14, 2022 at 9:13 AM changfengnan wrote: > > rte_mempool_create put tailq entry into rte_mempool_tailq list before > populate, and pool_data set when populate. So in multi process, if > process A create mempool, and process B can get mempool through > rte_mempool_lookup before pool_data

Re: [PATCH 0/2] GitHub Actions configuration fixes

On Mon, Nov 14, 2022 at 11:44 AM David Marchand wrote: > > On Wed, Oct 12, 2022 at 6:30 PM David Marchand > wrote: > > > > GitHub Actions started to deprecated some part of the workflow syntax > > and dependencies of some core actions. > > > > This series (mostly) fix those warnings. > > For revi

[PATCH 1/3] examples/l3fwd: validate ptype only for type of traffic sent

The check_ptype function is not considering the ptype of the incoming traffic. --parse-ptype flag must be provided only when the NIC does not support parsing the ptype of the incoming traffic Suggested-by: Nathan Brown Signed-off-by: Kamalakshitha Aligeri Reviewed-by: Ruifeng Wang Reviewed-by:

[PATCH 2/3] examples/l3fwd: removed hash entry number

hash_entry_number in l3fwd is not being used by both lpm and em lookup method. Removed the global variable hash_entry_number and the function that parses the hash-entry-number flag. Signed-off-by: Kamalakshitha Aligeri Reviewed-by: Honnappa Nagarahalli --- examples/l3fwd/l3fwd.h | 1 - example

[PATCH 3/3] doc/l3fwd: lpm supports IPv4 and IPv6 forwarding

LPM based lookup supports both IPv4 and IPv6 forwarding. Fixes: 6a094e328598 ("examples/l3fwd: implement FIB lookup method") Cc: sta...@dpdk.org Signed-off-by: Kamalakshitha Aligeri Reviewed-by: Honnappa Nagarahalli --- doc/guides/sample_app_ug/l3_forward.rst | 3 +-- 1 file changed, 1 inserti

Re: [PATCH] mempool: fix rte_mempool_avail_count may segment fault when used in multiprocess

It seems that this modification ignores some certain cases, for example calling rte_mempool_create_empty directly, maybe add a new flag bit to indicate when to put tailq entry into rte_mempool_tailq list is a better way ? Looking forward to any suggestions. Thanks. Fengnan Chang. changfengnan 于

RE: [PATCH v4] doc: support IPsec Multi-buffer lib v1.3

Hi Akhil, I remember you have a comment in earlier version of this patch about to include this ipsec mb v1.3 release doc update into release notes. I have review the release_22_11.rst, but I'm not sure the best section to capture this info , any recommendations ? Best Kai > -Original

[PATCH] net/nfp: fix the problem of mask table free

The free process of mask table has problem, should use 'rte_has_free()' rather than 'rte_free()'. Fixes: ac09376096d8 ("net/nfp: add structures and functions for flow offload") Signed-off-by: Chaoyong He Reviewed-by: Niklas Söderlund --- drivers/net/nfp/nfp_flow.c | 2 +- 1 file changed, 1 ins

RE: [PATCH v2] net/mlx5: use just sufficient barrier for Arm platforms

> > > > > Hi, Honnappa > Hi Slava, thanks for the feedback. > > > > > We discussed the barrier here: > > http://patches.dpdk.org/project/dpdk/patch/20210606164948.35997-1- > > honnappa.nagaraha...@arm.com/ > Yes, I have changed the patch according to the discussion. i.e. barrier is > needed, bu

[PATCH] config/arm: make SoC-generic more generic

The non-generic soc has 1280 max-lcores and 32 max-numas, but the implementer-generic still has 256 max-lcores and 4 max-numas, which may result in restrictions on the use of binaries compiled by soc-generic in these systems. This patch changes the soc-generic max-lcores to 1280 and max-numas to 3

Re: [PATCH v3] mempool/cnxk: fix mempool destroy for empty pools

08/11/2022 07:55, Ashwin Sekhar T K: > In scenarios where rte_mempool_free() is called immediately > after rte_mempool_create_empty(), the NPA pool will not be > created. In such cases the free path should not call > roc_npa_pool_destroy(). > > Fixes: bbf19e89b87c ("mempool/cnxk: add generic opera

RE: [PATCH] net/idpf: need to stop device when closing device

> -Original Message- > From: Xing, Beilei > Sent: Monday, November 14, 2022 6:40 PM > To: Wu, Jingjing ; Zhang, Qi Z > Cc: dev@dpdk.org; Xing, Beilei > Subject: [PATCH] net/idpf: need to stop device when closing device > > From: Beilei Xing > > This patch stops device at the beginn

[Bug 1119] [dpdk-22.11]pvp_virtio_bonding/vhost_virtio_bonding_mode_from_0_to_6: start bonding device failed and core dumped when quit testpmd

https://bugs.dpdk.org/show_bug.cgi?id=1119 Yuan,Dukai (dukaix.y...@intel.com) changed: What|Removed |Added Resolution|--- |FIXED Status|CON

[Bug 1118] [dpdk-22.11.0rc1][meson test] driver-tests/link_bonding_autotest test failed core dumped

https://bugs.dpdk.org/show_bug.cgi?id=1118 liweiyuan (weiyuanx...@intel.com) changed: What|Removed |Added Resolution|--- |FIXED Status|CONF

Re: [PATCH] config/arm: make SoC-generic more generic

On Tue, Nov 15, 2022 at 7:46 AM Chengwen Feng wrote: > > The non-generic soc has 1280 max-lcores and 32 max-numas, but the > implementer-generic still has 256 max-lcores and 4 max-numas, which may > result in restrictions on the use of binaries compiled by soc-generic > in these systems. > > This

RE: [External] Re: [PATCH] mempool: fix rte_mempool_avail_count may segment fault when used in multiprocess

> From: Fengnan Chang [mailto:changfeng...@bytedance.com] > Sent: Tuesday, 15 November 2022 02.51 > > David Marchand 于2022年11月15日周二 > 04:44写道： > > > > On Mon, Nov 14, 2022 at 9:13 AM changfengnan > wrote: [...] > > > Signed-off-by: changfengnan > > > > Please use your real name. > > It's my

Re: [External] Re: [PATCH] mempool: fix rte_mempool_avail_count may segment fault when used in multiprocess

On Tue, Nov 15, 2022 at 2:51 AM Fengnan Chang wrote: > > David Marchand 于2022年11月15日周二 04:44写道： > > > > On Mon, Nov 14, 2022 at 9:13 AM changfengnan > > wrote: > > > > > > rte_mempool_create put tailq entry into rte_mempool_tailq list before > > > populate, and pool_data set when populate. So i

Re: [PATCH] config/arm: make SoC-generic more generic

Hi Jerin, On 2022/11/15 15:08, Jerin Jacob wrote: > On Tue, Nov 15, 2022 at 7:46 AM Chengwen Feng wrote: >> >> The non-generic soc has 1280 max-lcores and 32 max-numas, but the >> implementer-generic still has 256 max-lcores and 4 max-numas, which may >> result in restrictions on the use of binar