RE: Does rte_net_get_ptype() support processing packets with two 0x8100 VLAN tags?

> From: huangdengdui [mailto:huangdeng...@huawei.com] > Sent: Wednesday, 2 July 2025 04.38 > > Hi everyone, > > The current rte_net_get_ptype() only supports parsing packets with a > single 0x8100 VLAN tag and two 0x88a8 VLAN tags, > but does not support processing packets with two 0x8100 VLAN t

[PATCH v3 5/5] dts: add performance test functions to test suite API

From: Nicholas Pratte Provide functional performance method to run performance tests using a user-supplied performance traffic generator. The single core performance test is included, with some basic statistics checks verifying TG packet transmission rates. Bugzilla ID: 1697 Signed-off-by: Nicho

[PATCH v3 4/5] dts: add trex traffic generator to dts framework

From: Nicholas Pratte Implement the TREX traffic generator for use in the DTS framework. The provided implementation leverages TREX's stateless API automation library, via use of a Python shell. As such, limitation to specific TREX versions may be needed. The DTS context has been modified to incl

[PATCH v3 3/5] dts: add timeout override option to interactive shells

From: Nicholas Pratte Add an extra parameter to the interactive shell send command to handle function to allow for a 1 time override of the send command timeout. Bugzilla ID: 1697 Signed-off-by: Nicholas Pratte Signed-off-by: Patrick Robb Reviewed-by: Dean Marx --- dts/framework/remote_sessi

[PATCH v3 2/5] dts: rework traffic generator inheritance structure

From: Nicholas Pratte Rework TG class hierarchy to include performance traffic generators. As such, methods specific to capturing traffic have been moved to the CapturingTrafficGenerator subclass. Bugzilla ID: 1697 Signed-off-by: Nicholas Pratte Signed-off-by: Patrick Robb Reviewed-by: Dean Ma

[PATCH v3 1/5] dts: rework config module to support perf TGs

From: Nicholas Pratte Rework test run configuration file for TGs to support both application directory location and any necessary configuration files; an example TREX configuration file is provided. Configuration files have been moved to a configurations directory, requiring a slight modification

[V5 16/18] net/hinic3: add RSS promiscuous ops

From: Xin Wang Add RSS and promiscuous ops related function codes. Signed-off-by: Xin Wang Reviewed-by: Feifei Wang Reviewed-by: Yi Chen --- drivers/net/hinic3/hinic3_ethdev.c | 370 + drivers/net/hinic3/hinic3_ethdev.h | 31 +++ 2 files changed, 401 insertions(+

[V5 17/18] net/hinic3: add FDIR flow control module

From: Yi Chen Added support for rte_flow, including ethertype, IPv4, IPv6, and tunnel VXLAN. In addition, user can add or delete filters. Signed-off-by: Yi Chen Reviewed-by: Xin Wang Reviewed-by: Feifei Wang --- drivers/net/hinic3/hinic3_ethdev.c | 82 ++ drivers/net/hinic3/hinic3_ethdev.h

[V5 07/18] net/hinic3: add mgmt module function code

From: Yi Chen Mgmt module is a kind of administration module for the chip. It is responsible for handling administration command from host. It mainly uses aeq to implement. This patch adds related data structures, packaged interfaces and function codes. Signed-off-by: Yi Chen Reviewed-by: Xin W

[V5 14/18] net/hinic3: add Rx/Tx functions

From: Feifei Wang This patch add package sending and receiving function codes. Signed-off-by: Feifei Wang Signed-off-by: Yi Chen Reviewed-by: Xin Wang --- drivers/net/hinic3/hinic3_ethdev.c | 15 +- drivers/net/hinic3/hinic3_rx.c | 305 +++- drivers/net/hinic3/hinic3_tx.c |

[V5 05/18] net/hinic3: add NIC event module

From: Xin Wang Currently, there are two types of events: pf/vf connection status and port information printing. This patch contains related data structures and function codes. Signed-off-by: Xin Wang Reviewed-by: Yi Chen Reviewed-by: Feifei Wang --- drivers/net/hinic3/base/hinic3_nic_event.c

Re: [EXTERNAL] [PATCH v3 0/2] uadk: realize async mode

On Mon, 30 Jun 2025 at 18:15, Akhil Goyal wrote: > > > Hi, Akhil > > > > On Mon, 30 Jun 2025 at 17:04, Akhil Goyal wrote: > > > > > > > > > make[2]: Entering directory '/home/gakhil/up/uadk' > > > > > > depbase=`echo wd_alg.lo | sed 's|[^/]*$|.deps/&|;s|\.lo$||'`;\ > > > > > > /bin/bash ./libtool

[PATCH v4 1/2] compress/uadk: use async mode to replace sync mode

To get better performance, using async mode to replace sync mode Signed-off-by: Zhangfei Gao --- doc/guides/compressdevs/uadk.rst | 15 +++ drivers/compress/uadk/meson.build | 4 +- drivers/compress/uadk/uadk_compress_pmd.c | 94 ++- .../compress/uad

[V5 02/18] net/hinic3: add basic header files

From: Xin Wang Add HW registers definition header file for SP series NIC. Add some headers that define commands and basic defines for use in the code. Signed-off-by: Xin Wang Reviewed-by: Yi Chen Reviewed-by: Feifei Wang --- drivers/net/hinic3/base/hinic3_cmd.h| 231

[PATCH v4 2/2] crypto/uadk: use async mode to replace sync mode

To get better performance, using async mode to replace sync mode However, case UADK_CHAIN_CIPHER_AUTH and UADK_CHAIN_AUTH_CIPHER still use sync mode for the first operation and async mode for the second operation since the dependence. Also RTE_CRYPTO_AUTH_OP_VERIFY will hold the generated auth in

[PATCH v4 0/2] uadk: realize async mode

Realize async mode to replace sync mode for better performance v4: Akril pointed uadk build issue on x86 uadk 2.9.1 has fixed the issue https://github.com/Linaro/uadk/releases/tag/v2.9.1 Update doc accordingly v3: uadk 2.9 is released use different label name to fix build warning: "duplic

Does rte_net_get_ptype() support processing packets with two 0x8100 VLAN tags?

Hi everyone, The current rte_net_get_ptype() only supports parsing packets with a single 0x8100 VLAN tag and two 0x88a8 VLAN tags, but does not support processing packets with two 0x8100 VLAN tags. Some network cards (e.g., hns3) do support parsing packets with two 0x8100 VLAN tags. Can this A

[V5 08/18] net/hinic3: add module about hardware operation

From: Yi Chen Add code and data structure for hardware operation, including configuration, query, initialization and release. Signed-off-by: Yi Chen Signed-off-by: Xin Wang Reviewed-by: Feifei Wang --- drivers/net/hinic3/base/hinic3_hw_cfg.c | 240 ++ drivers/net/hinic3/base/hinic3_

[V5 01/18] doc: add some basic files to describe the hinic3 driver.

From: Yi Chen This patch adds some basic files to describe the hinic3 driver. Signed-off-by: Feifei Wang Signed-off-by: Yi Chen Reviewed-by: Xin Wang --- .mailmap | 4 +- MAINTAINERS| 6 +++ doc/guides/nics/hinic3.rst |

[V5 18/18] drivers/net: add hinic3 PMD build and doc files

From: Yi Chen The meson.build file is added to this patch to enable the hinic3 compilation function. Signed-off-by: Yi Chen Reviewed-by: Xin Wang Reviewed-by: Feifei Wang --- doc/guides/nics/features/hinic3.ini | 61 + drivers/net/hinic3/base/meson.build | 50

[V5 03/18] net/hinic3: add hardware interfaces of BAR operation

From: Yi Chen This patch adds some HW interfaces for bar operatioin interfaces, including: mapped bar address geeting, HW attributes getting, msi-x reg operation, function type getting and so on. Signed-off-by: Yi Chen Reviewed-by: Xin Wang Reviewed-by: Feifei Wang --- drivers/net/hinic3/bas

[V5 10/18] net/hinic3: add context and work queue support

From: Xin Wang Work queue is used for cmdq and tx/rx buff description. Nic business needs to configure cmdq context and txq/rxq context. This patch adds data structures and function codes for work queue and context. Signed-off-by: Xin Wang Reviewed-by: Feifei Wang Reviewed-by: Yi Chen --- dr

[V5 15/18] net/hinic3: add MML and EEPROM access feature

From: Xin Wang Add man-machine language support and implements the get eeprom method. Signed-off-by: Xin Wang Reviewed-by: Feifei Wang Reviewed-by: Yi Chen --- drivers/net/hinic3/hinic3_ethdev.c| 13 + drivers/net/hinic3/mml/hinic3_dbg.c | 171 + drivers/net/hinic3/mml/hin

[V5 12/18] net/hinic3: add device initialization

From: Xin Wang This patch contains data structures and function codes related to device initialization. Signed-off-by: Xin Wang Reviewed-by: Feifei Wang Reviewed-by: Yi Chen --- drivers/net/hinic3/hinic3_ethdev.c | 514 + drivers/net/hinic3/hinic3_ethdev.h | 119 +

[V5 11/18] net/hinic3: add a mailbox communication module

From: Yi Chen This patch adds support for mailbox of hinic3 PMD driver, mailbox is used for communication between PF/VF driver and MPU. This patch provides mailbox-related data structures and functional code. Signed-off-by: Yi Chen Reviewed-by: Xin Wang Reviewed-by: Feifei Wang --- drivers/n

[V5 09/18] net/hinic3: add a NIC business configuration module

From: Yi Chen The items of configurations and queries for NIC business include MAC, VLAN, MTU, RSS and so on. These configurations and queries are handled by mgmt module. This patch introduces related data structures and function codes. Signed-off-by: Yi Chen Reviewed-by: Xin Wang Reviewed-by:

[V5 06/18] net/hinic3: add eq mechanism function code

From: Yi Chen Eqs include aeq and ceq. Aeq is a kind of queue for mgmt asynchronous message and mgmt command response message. This patch introduces data structures, initialization, and related interfaces about aeq. Signed-off-by: Yi Chen Reviewed-by: Xin Wang Reviewed-by: Feifei Wang --- dr

[V5 04/18] net/hinic3: add support for cmdq mechanism

From: Xin Wang Micocode is named ucode in SP series NIC. Its main responsibility is data transmission and reception. But it can also handle some administration works. It uses cmdq mechanism. This patch introduces data structures, initialization, interfaces, and commands sending functions of cmdq.

[V5 00/18] add hinic3 pmd driver

From: Yi Chen The hinic3 PMD (**librte_net_hinic3**) provides poll mode driver support for 25Gbps/100Gbps/200Gbps Huawei SPx series Network Adapters. v5: - solve hinic3.ini unknown feature issue V4: - solve patch application conflict issue V3: - Fix checkpatchs error issue v2: - modify CI com

RE: [PATCH v3 01/17] net/txgbe: support flow filter for VF

> -Original Message- > From: Stephen Hemminger > Sent: Tuesday, July 1, 2025 10:39 PM > To: Jiawen Wu > Cc: dev@dpdk.org; zaiyuw...@trustnetic.com > Subject: Re: [PATCH v3 01/17] net/txgbe: support flow filter for VF > > On Fri, 13 Jun 2025 16:41:43 +0800 > Jiawen Wu wrote: > > > +b

[DPDK/testpmd Bug 1735] [dpdk-25.07-rc2] vf_pf_reset/test_vlan_rx_restore_vf_reset_all_ports: Unable to receive VLAN packets

https://bugs.dpdk.org/show_bug.cgi?id=1735 Bug ID: 1735 Summary: [dpdk-25.07-rc2] vf_pf_reset/test_vlan_rx_restore_vf_reset_all_ports: Unable to receive VLAN packets Product: DPDK Version: 25.03 Hardware

Reminder to get your CFP submissions in by this Sunday night - DPDK Bay Area Summit

Dear DPDK Community and Boards, A reminder that our CFP deadline for the 2025 Bay Area Summit at Intel in Santa Clara, Sep. 17-18, 2025, terms this Sunday, July 6 at 11:59pm Pacific Time. You can reach the CFP page here . We are also very much i

RE: [PATCH v1] event/dlb2: add dequeue interrupt mode support

> -Original Message- > From: Mattias Rönnblom > Sent: Tuesday, July 1, 2025 4:16 AM > To: Pathak, Pravin ; Jerin Jacob > > Cc: dev@dpdk.org; jer...@marvell.com; Chen, Mike Ximing > ; Richardson, Bruce > ; tho...@monjalon.net; Marchand, David > ; nipun.gu...@amd.com; > chen...@nvidia.com

[PATCH v2 2/5] eal/riscv/spinlock: add rte_cpuflag.h

From: Sun Yuechi Same as the x86 style, include "rte_cpuflags.h" in rte_spinlock.h so that files like lib/fib/dir24_8.c don’t need to include it. Signed-off-by: Sun Yuechi --- lib/eal/riscv/include/rte_spinlock.h | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/eal/riscv/include/rte_spi

[PATCH v2 5/5] riscv: override machine_args only when default

From: Sun Yuechi Support using -Dcpu_instruction_set=rv64gcv to enable V extension. Signed-off-by: Sun Yuechi --- config/riscv/meson.build | 16 +--- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/config/riscv/meson.build b/config/riscv/meson.build index e3694cf2e6..

[PATCH v2 4/5] lib/fib: R-V V rte_fib_lookup_bulk

From: Sun Yuechi Implement rte_fib_lookup_bulk function for RISC-V architecture using RISC-V Vector Extension instruction set Signed-off-by: Sun Yuechi --- lib/fib/dir24_8.c | 20 ++ lib/fib/dir24_8_rvv.c | 64 +++ lib/fib/dir24_8_rvv.h |

[PATCH v2 3/5] lib/lpm: R-V V rte_lpm_lookupx4

From: Sun Yuechi Implement LPM lookupx4 function for RISC-V architecture using RISC-V Vector Extension instruction set Signed-off-by: Sun Yuechi --- MAINTAINERS | 2 ++ lib/lpm/meson.build | 1 + lib/lpm/rte_lpm.h | 2 ++ lib/lpm/rte_lpm_rvv.h | 59 ++

[PATCH v2 1/5] config/riscv: detect V extension

From: Sun Yuechi This patch is derived from "config/riscv: detect presence of Zbc extension with modifications". The RISC-V C api defines architecture extension test macros These let us detect whether the V extension is supported on the compiler and -march we're building with. The C api also def

[PATCH v2 0/5] Add RISC-V V extension detection and LPM, FIB optimization

From: Sun Yuechi This patch series adds support for the RISC-V Vector (V) extension and provides an optimized implementation of `rte_lpm_lookupx4` using RVV. The initialization of lpm/vtbl_entry is not fully vectorized here because doing so would require __riscv_vluxei32_v_u32m1, which is slower

Re: [PATCH] test/event: disable vector adapter test

01/07/2025 15:44, Bruce Richardson: > On Tue, Jul 01, 2025 at 03:15:24PM +0200, Thomas Monjalon wrote: > > This test triggers failures in the CI: > > > > event_vector_adapter_autotest FAIL > > 3.39s (exit status 255 or signal 127 SIGinvalid) > > > > Disable it until we have a fix. > >

Re: [PATCH v3] test/argparse: change initialization to workaround LTO

On Tue, Jul 01, 2025 at 08:41:46AM -0700, Stephen Hemminger wrote: > When compiled with Link Time Optimization, the existing code > generated an error, because the compiler was unable to intuit > that there was space in the flexible array. > > In function ‘test_argparse_copy’, > inlined from ‘

[PATCH v3] test/argparse: change initialization to workaround LTO

When compiled with Link Time Optimization, the existing code generated an error, because the compiler was unable to intuit that there was space in the flexible array. In function ‘test_argparse_copy’, inlined from ‘test_argparse_init_obj’ at ../app/test/test_argparse.c:108:2, inlined from

[PATCH 5/5] riscv: override machine_args only when default

From: Sun Yuechi Support using -Dcpu_instruction_set=rv64gcv to enable V extension. Signed-off-by: Sun Yuechi --- config/riscv/meson.build | 16 +--- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/config/riscv/meson.build b/config/riscv/meson.build index e3694cf2e6..

[PATCH 3/5] lib/lpm: R-V V rte_lpm_lookupx4

From: Sun Yuechi Implement LPM lookupx4 function for RISC-V architecture using RISC-V Vector Extension instruction set Signed-off-by: Sun Yuechi --- MAINTAINERS | 2 ++ lib/lpm/meson.build | 1 + lib/lpm/rte_lpm.h | 2 ++ lib/lpm/rte_lpm_rvv.h | 59 ++

[PATCH 4/5] lib/fib: R-V V rte_fib_lookup_bulk

From: Sun Yuechi Implement rte_fib_lookup_bulk function for RISC-V architecture using RISC-V Vector Extension instruction set Signed-off-by: Sun Yuechi --- lib/fib/dir24_8.c | 20 +++ lib/fib/dir24_8_rvv.c | 60 +++ lib/fib/dir24_8_rvv.h

[PATCH 2/5] eal/riscv/spinlock: add rte_cpuflag.h

From: Sun Yuechi Same as the x86 style, include "rte_cpuflags.h" in rte_spinlock.h so that files like lib/fib/dir24_8.c don’t need to include it. Signed-off-by: Sun Yuechi --- lib/eal/riscv/include/rte_spinlock.h | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/eal/riscv/include/rte_spi

[PATCH 1/5] config/riscv: detect V extension

From: Sun Yuechi This patch is derived from "config/riscv: detect presence of Zbc extension with modifications". The RISC-V C api defines architecture extension test macros These let us detect whether the V extension is supported on the compiler and -march we're building with. The C api also def

[PATCH 0/5] *** Add RISC-V V extension detection and LPM, FIB optimization ***

From: Sun Yuechi This patch series adds support for the RISC-V Vector (V) extension and provides an optimized implementation of `rte_lpm_lookupx4` using RVV. The initialization of lpm/vtbl_entry is not fully vectorized here because doing so would require __riscv_vluxei32_v_u32m1, which is slower

Re: [PATCH 0/6] net/hns3: VF support multi-TCs

On Wed, 11 Jun 2025 16:18:54 +0800 Dengdui Huang wrote: > This patchset adds the VF multi-TCs feature. > > Chengwen Feng (6): > net/hns3: fix VF fail to config queue TC > net/hns3: remove duplicate struct field > net/hns3: refactor DCB module code > net/hns3: VF support parse max TC numb

Re: [PATCH v3 00/17] Fixes and supports for Wangxun NICs

On Fri, 13 Jun 2025 16:41:42 +0800 Jiawen Wu wrote: > Fix some bugs and improve flow filters. > > v2 -> v3: > - Split the patch 2/12 for various changes > > v1 -> v2: > - Add new flow feature geneve and gre into txgbe.ini > > Jiawen Wu (17): > net/txgbe: support flow filter for VF > net/tx

Re: [PATCH] node: fix C++ compatibility errors (option 2)

On Mon, Jun 30, 2025 at 4:27 PM Bruce Richardson wrote: > > C++ does not allow zero-sized unions - they end up being of size 1-byte, > which leads to C/C++ compatibility issues, flagged by the compiler. > > lib/node/rte_node_mbuf_dynfield.h:78:2: error: union has size 0 in C, > size 1 in C++ [-W

Re: [PATCH v3 01/17] net/txgbe: support flow filter for VF

On Fri, 13 Jun 2025 16:41:43 +0800 Jiawen Wu wrote: > +bool txgbe_is_pf(struct txgbe_hw *hw) > +{ > + switch (hw->mac.type) { > + case txgbe_mac_raptor: > + return true; > + default: > + return false; > + } > +} > + This is ok as is, but you could make it

Re: [PATCH 2/2] dts: rework test results

Reviewed-by: Dean Marx

Re: [PATCH 1/2] dts: change test suite name property

Reviewed-by: Dean Marx

Re: [PATCH] rcu: add deprecation notice about limit on defer queue element size

23/05/2025 01:37, Andre Muezerie: > The functions rte_rcu_qsbr_dq_create and rte_rcu_qsbr_dq_reclaim establish > no limit on the size of each element in the defer queue. Very good, we need more unlimited API in DPDK. > With DPDK 25.11 a hard limit will be set (``RTE_QSBR_ESIZE_MAX``). I think it

Re: [PATCH v7 3/6] bus/fslmc: add DPBP APIs for setting depletion thresholds

On Tue, 1 Jul 2025 09:59:14 +0530 Gagandeep Singh wrote: > @@ -62,6 +72,8 @@ rte_dpaa2_mbuf_from_buf_addr(struct rte_mempool *mp, void > *buf_addr); > __rte_internal > int rte_dpaa2_bpid_info_init(struct rte_mempool *mp); > > +int rte_dpaa2_dpbp_set_notifications(struct rte_mempool *mp, str

Re: [v3 01/10] bus/dpaa: avoid using same structure and variable name

On Tue, 10 Jun 2025 14:44:02 +0530 vanshika.shu...@nxp.com wrote: > From: Hemant Agrawal > > rte_dpaa_bus was being used as structure and variable name both. > > Signed-off-by: Jun Yang > Signed-off-by: Hemant Agrawal > --- NAK Since rte_bus_pci has same type and name, there is no point in c

Re: [v5 6/9] net/dpaa: add Tx rate limiting DPAA PMD API

On Tue, 1 Jul 2025 17:07:04 +0530 vanshika.shu...@nxp.com wrote: > +/** > + * Set TX rate limit > + * > + * @param port_id > + *The port identifier of the Ethernet device. > + * @param burst > + *Max burst size(KBytes) of the Ethernet device. > + *0 - Disable TX rate limit. > + * @par

Re: [v5 6/9] net/dpaa: add Tx rate limiting DPAA PMD API

On Tue, 1 Jul 2025 17:07:04 +0530 vanshika.shu...@nxp.com wrote: > +/** > + * Set TX rate limit > + * > + * @param port_id > + *The port identifier of the Ethernet device. > + * @param burst > + *Max burst size(KBytes) of the Ethernet device. > + *0 - Disable TX rate limit. > + * @par

Re: [PATCH] test/event: disable vector adapter test

On Tue, Jul 01, 2025 at 03:15:24PM +0200, Thomas Monjalon wrote: > This test triggers failures in the CI: > > event_vector_adapter_autotest FAIL > 3.39s (exit status 255 or signal 127 SIGinvalid) > > Disable it until we have a fix. > > Bugzilla ID: 1720 > Fixes: 2eca0f4cd5da ("tes

Re: [PATCH v7 7/8] trace: add PMU

On Fri, Jun 27, 2025 at 5:41 PM Tomasz Duszynski wrote: > > In order to profile app, one needs to store significant amount of samples > somewhere for an analysis later on. > Since trace library supports storing data in a CTF format, > lets take advantage of that and add a dedicated PMU tracepoint.

Re: [EXT] Re: [v4 07/10] net/dpaa: add Tx rate limiting DPAA PMD API

01/07/2025 13:42, Vanshika Shukla: > From: Stephen Hemminger > > On Wed, 11 Jun 2025 12:40:36 +0530 > > vanshika.shu...@nxp.com wrote: > > > > > From: Vinod Pullabhatla > > > > > > Add support to set Tx rate on DPAA platform through PMD APIs > > > > > > Signed-off-by: Vinod Pullabhatla > > > Si

[PATCH] test/event: disable vector adapter test

This test triggers failures in the CI: event_vector_adapter_autotest FAIL 3.39s (exit status 255 or signal 127 SIGinvalid) Disable it until we have a fix. Bugzilla ID: 1720 Fixes: 2eca0f4cd5da ("test/event: fix event vector adapter timeouts") Signed-off-by: Thomas Monjalon -

Re: [PATCH] node: fix C++ compatibility errors (option 2)

30/06/2025 12:50, Bruce Richardson: > C++ does not allow zero-sized unions - they end up being of size 1-byte, > which leads to C/C++ compatibility issues, flagged by the compiler. > > lib/node/rte_node_mbuf_dynfield.h:78:2: error: union has size 0 in C, > size 1 in C++ [-Werror,-Wextern-c-compa

Re: [PATCH] net/ice: fix inconsistency in Rx queue VLAN tag placement

On Fri, Jun 27, 2025 at 04:31:20PM +0200, Burakov, Anatoly wrote: > On 6/27/2025 3:52 PM, Bruce Richardson wrote: > > When VLAN or QinQ stripping is enabled in the ice driver, an > > inconsistency was observed between the placement of the VLAN tag in the > > descriptors of the final Rx queue (irres

RE: [EXT] Re: [v4 07/10] net/dpaa: add Tx rate limiting DPAA PMD API

Hi Stephen, We have exported the API and are currently testing it using our internal application. This feature is specific to our platform. The existing ethdev queue rate_limit API supports per-queue rate limiting. However, our use case requires per-port rate limiting, so we have implemented a

Re: [PATCH] ci: check C++ headers with clang

On Tue, Jul 1, 2025 at 1:33 PM David Marchand wrote: > > If not passing an explicit compiler for C++, meson uses c++ which > defaults to /usr/bin/g++ on a Ubuntu system. > Explicitly choose which compiler to use for C++. > > Signed-off-by: David Marchand > --- > Depends-on: series-35592 ("node: f

RE: [EXT] Re: [v4 01/10] bus/dpaa: avoid using same structure and variable name

Hi Stephen, I have removed this patch from the patchlist. Regards, Vanshika > -Original Message- > From: Stephen Hemminger > Sent: 29 June 2025 22:01 > To: Vanshika Shukla > Cc: dev@dpdk.org; Hemant Agrawal ; Sachin > Saxena ; Jun Yang > Subject: [EXT] Re: [v4 01/10] bus/dpaa: avoid u

[v5 9/9] bus/dpaa: optimize qman enqueue check

From: Hemant Agrawal This patch improves data access during qman enequeue ring check. Signed-off-by: Jun Yang Signed-off-by: Hemant Agrawal --- drivers/bus/dpaa/base/fman/fman.c | 3 ++- drivers/bus/dpaa/base/qbman/bman.c | 6 ++--- drivers/bus/dpaa/base/qbman/qman.c | 41 ++

[v5 5/9] mempool/dpaa: adjust pool element for LS1043A errata

From: Jun Yang Adjust every element of pool by populate callback. 1) Make sure start DMA address is aligned with 16B. 2) For buffer across 4KB boundary, make sure start DMA address is aligned with 256B. Signed-off-by: Jun Yang --- drivers/mempool/dpaa/dpaa_mempool.c | 144 ++

[v5 8/9] bus/dpaa: improve DPAA cleanup

From: Gagandeep Singh This patch addresses DPAA driver issues with the introduction of rte_eal_cleanup, which caused driver-specific destructors to fail due to memory cleanup. To resolve this, we remove the driver destructor and relocate the code to the bus cleanup function. So, this patch also

[v5 7/9] net/dpaa: add devargs for enabling err packets on main queue

From: Vanshika Shukla Currently, error queue is mapped to the Rx queue and enabled by default. This patch adds the devargs to control the err packets on main queue. Also, in VSP mode the error queue should be disabled because the error packets from kernel are diverted to the Rx queue/err queue ca

[v5 6/9] net/dpaa: add Tx rate limiting DPAA PMD API

From: Vinod Pullabhatla Add support to set Tx rate on DPAA platform through PMD APIs Signed-off-by: Vinod Pullabhatla Signed-off-by: Vanshika Shukla --- .mailmap | 1 + drivers/net/dpaa/dpaa_flow.c | 89 +++- drivers/net/dpaa/fmlib/

[v5 3/9] bus/dpaa: optimize bman acquire/release

From: Jun Yang 1) Reduce byte swap between big endian and little endian. 2) Reduce ci(cache invalid) access by 128bit R/W instructions. These methods improve ~10% buffer acquire/release performance. Signed-off-by: Jun Yang --- drivers/bus/dpaa/base/qbman/bman.c | 147 -

[v5 2/9] bus/dpaa: enhance DPAA SoC version

From: Jun Yang Provide internal API to identify DPAA1 SoC version instead of accessing global variable directly. Signed-off-by: Jun Yang --- drivers/bus/dpaa/base/qbman/qman.c | 9 +++--- drivers/bus/dpaa/bus_dpaa_driver.h | 9 +++--- drivers/bus/dpaa/dpaa_bus.c| 48 +

[v5 4/9] mempool/dpaa: fast acquire and release

From: Jun Yang Use new BMan APIs to improve performance and support burst release. Improve release performance ~90% by burst release. Signed-off-by: Jun Yang --- drivers/mempool/dpaa/dpaa_mempool.c | 85 - drivers/mempool/dpaa/dpaa_mempool.h | 2 +- 2 files changed

[v5 1/9] bus/dpaa: add FMan node

From: Jun Yang Add FMan node(s) and associate FMan to its interface (port). This method describes FMan attributes and avoids accessing FMan from port directly. Logically, something like IEEE 1588 is an FMan global resource, which is in range of 0xF_E000–0xF_EFFF. Port specific resource is in rang

[v5 0/9] DPAA specific fixes

From: Vanshika Shukla This series includes fixes for NXP DPAA drivers. V5: Fixed comments by the reviewer. V4: Fixed compilation errors in the "bus/dpaa: optimize qman enqueue check" patch on Ubuntu 22.04. - Ensured buffer bounds are respected and added validation for buffer count extracted fro

[PATCH v3 3/6] net/hns3: refactor DCB module code

From: Chengwen Feng The DCB-related fields span in multiple structures, this patch moves them into struct hns3_dcb_info. Signed-off-by: Chengwen Feng Signed-off-by: Dengdui Huang --- drivers/net/hns3/hns3_dcb.c | 13 +-- drivers/net/hns3/hns3_ethdev.c| 38 +++

[PATCH v3 6/6] net/hns3: VF support multi-TCs configure

From: Chengwen Feng If VF has the multi-TCs capability, then application could configure the multi-TCs feature through the DCB interface. Because VF does not have its own ETS and PFC components, the constraints are as follows: 1. The DCB configuration (struct rte_eth_dcb_rx_conf and rte_eth_d

[PATCH] ci: check C++ headers with clang

If not passing an explicit compiler for C++, meson uses c++ which defaults to /usr/bin/g++ on a Ubuntu system. Explicitly choose which compiler to use for C++. Signed-off-by: David Marchand --- Depends-on: series-35592 ("node: fix C++ compatibility errors (option 2)") --- .ci/linux-build.sh | 6

Re: [PATCH v1 0/4] net/ntnic: implement start, stop and deferred start for Rx/Tx queues

Thanks for noticing it. We will take it into account and address the issue. From: Stephen Hemminger Sent: 29 June 2025 01:20 To: Oleksandr Kolomeiets Cc: dev@dpdk.org ; Mykola Kostenok ; Serhii Iliushyk ; Christian Koue Muf Subject: Re: [PATCH v1 0/4] net/ntnic:

[PATCH] net/mlx5: fix masked indirect age action validation

Masked indirect age flow action is not supported in actions templates. Up to this patch, this case was checked only through debug assertion. As a side effect, in a build without assertions, this lead to a segfault on the attempt to create a table using actions template with masked indirect age acti

[PATCH v2 3/3] net/ntnic: unmap DMA during queue release

From: Oleksandr Kolomeiets Perform unmapping in a default container, which is used by queues. Handle multiple mappings when IOMMU is unoptimized. Fixes: c1c139535591 ("net/ntnic: add VFIO module") Signed-off-by: Oleksandr Kolomeiets --- drivers/net/ntnic/include/ntos_drv.h | 1 + drivers/net

[PATCH v2 2/3] net/ntnic: implement deferred start for Rx/Tx queues

From: Oleksandr Kolomeiets Handle rx_deferred_start and tx_deferred_start flags during configuration done in rx_queue_setup and tx_queue_setup, so that marked queues do not start with dev_start. Signed-off-by: Oleksandr Kolomeiets --- drivers/net/ntnic/dbsconfig/ntnic_dbsconfig.c | 46

[PATCH v2 1/3] net/ntnic: implement start/stop for Rx/Tx queues

From: Oleksandr Kolomeiets The following functions exported by the driver were stubs which merely changed the status flags: * rx_queue_start * rx_queue_stop * tx_queue_start * tx_queue_stop Proper implementation was added to control queues's state. Signed-off-by: Oleksan

[PATCH v2 0/3] net/ntnic: implement start, stop and deferred start for Rx/Tx queues

This patchset includes: * feature start/stop queues on HW layer. * feature deferred start for queues. * Improvement for memory mappings when IOMMU is unoptimized. v2 removes unnecessary log and adds fixed tag to the commit message. Oleksandr Kolomeiets (3): net/ntnic: implement start/stop

[PATCH v3 4/6] net/hns3: VF support parse max TC number

From: Chengwen Feng The mailbox message HNS3_MBX_GET_BASIC_INFO can obtain the maximum number of TCs of the device. The VF does not support multiple TCs, therefore, this field is not saved. Now the VF needs to support multiple TCs, therefore, this field needs to be saved. This commit also suppo

RE: [PATCH] net/ixgbe: fix sctp mask in flow director

Hi Bruce, This patch attempts to resolve the SCTP mismatching on 82599ES. A sample flow rule is as follows: flow create 0 ingress pattern eth / ipv4 dst is 245.194.135.241 src is 215.201.218.98 / sctp / end actions drop / end NIC will pass the packet to host , however we expect the packet to

[PATCH v2 0/6] net/hns3: VF support multi-TCs

This patchset adds the VF multi-TCs feature. --- v2: Use the macros __rte_packed_begin and __rte_packed_end instead of #pragma pack(). Chengwen Feng (6): net/hns3: fix VF fail to config queue TC net/hns3: remove duplicate struct field net/hns3: refactor DCB module code net/hns3: VF suppo

[PATCH v3 5/6] net/hns3: VF support discover multi-TCs capability

From: Chengwen Feng The VF multi-TCs feature depends on firmware and PF driver, the capability was set when: 1) Firmware report VF multi-TCs flag. 2) PF driver report VF multi-TCs flag. 3) PF driver support query multi-TCs info mailbox message. Signed-off-by: Chengwen Feng Signed-off-by: Dengdu

[PATCH v3 1/6] net/hns3: fix VF fail to config queue TC

From: Chengwen Feng The VF cannot configure the mapping of queue to TC by directly writing the register. Instead, the mapping must be modified by using firmware command. Fixes: bba636698316 ("net/hns3: support Rx/Tx and related operations") Cc: sta...@dpdk.org Signed-off-by: Chengwen Feng Sign

[PATCH v3 2/6] net/hns3: remove duplicate struct field

From: Chengwen Feng The struct hns3_hw and hns3_hw.dcb_info both has num_tc field, their meanings are the same, to ensure code readability, remove the num_tc field of struct hns3_hw. Signed-off-by: Chengwen Feng Signed-off-by: Dengdui Huang --- drivers/net/hns3/hns3_dcb.c | 44 +

[PATCH v3 0/6] net/hns3: VF support multi-TCs

This patchset adds the VF multi-TCs feature. --- v2: Use the macros __rte_packed_begin and __rte_packed_end instead of #pragma pack(). v3: Fix checkpatch warnings: line length of 102 exceeds 100 columns. Chengwen Feng (6): net/hns3: fix VF fail to config queue TC net/hns3: remove duplicate

RE: [PATCH] net/i40e: Fast release optimizations

> From: Konstantin Ananyev [mailto:konstantin.anan...@huawei.com] > Sent: Tuesday, 1 July 2025 10.16 [...] > I am talking about different thing: > I think with some extra effort driver can use (in some cases) > rte_mbuf_raw_free_bulk() even when RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE > is not spec

Re: [PATCH 6/6] net/hns3: VF support multi-TCs configure

On 2025/6/30 1:40, Stephen Hemminger wrote: > On Wed, 11 Jun 2025 16:19:00 +0800 > Dengdui Huang wrote: > >> +#pragma pack(1) >> +#define HNS3_MBX_PRIO_SHIFT 4 >> +#define HNS3_MBX_PRIO_MASK 0xFu >> +struct hns3_mbx_tc_config { >> +/* >> + * Each four bits correspond to one priority's

RE: [PATCH v2 08/10] hash: fix unaligned access in predictable RSS

> Caught by UBSan: > > ../lib/hash/rte_thash.c:421:8: runtime error: load of misaligned address > 0x0001816c2da3 for type 'uint32_t' (aka 'unsigned int'), > which requires 4 byte alignment > > Fixes: 28ebff11c2dc ("hash: add predictable RSS") > Cc: sta...@dpdk.org > > Signed-off-b

Re: [PATCH v2] eal: deprecate old coremask-based EAL parameters

On Mon, Jun 30, 2025 at 5:38 PM Bruce Richardson wrote: > > As the number of cores/cpus on platforms has increased over the years, > the use of coremasks rather than core-lists for identifying DPDK cores > has become more and more unwieldy. At this point, let's deprecate the > coremask-based EAL p

RE: [PATCH] net/i40e: Fast release optimizations

> > > > When fast releasing mbufs, the mbufs are not accessed, so do not > > prefetch > > > > them. > > > > This saves a mbuf load operation for each fast released TX mbuf. > > > > > > > > When fast release of mbufs is enabled for a TX queue, cache the mbuf > > > > mempool pointer in the TX queue

Re: [PATCH v1] event/dlb2: add dequeue interrupt mode support

On 2025-06-30 19:34, Pathak, Pravin wrote: -Original Message- From: Mattias Rönnblom Sent: Monday, June 30, 2025 12:51 PM To: Pathak, Pravin ; Jerin Jacob Cc: dev@dpdk.org; jer...@marvell.com; Chen, Mike Ximing ; Richardson, Bruce ; tho...@monjalon.net; Marchand, David ; nipun.gu...@

  1   2   >