[PATCH v5] app/testpmd: stop secondary process fwd_lcores during primary teardown

When the secondary process testpmd application running any fwd_engine and after that primary has exited will cause a crash. This patch forces secondary process forwarding lcores in fwd_engine to stop before the primary process exits. Fixes: a550baf24af90f ("app/testpmd: support multi-process") Cc

[PATCH v2] eal: fix DMA mask validation inconsistency in IOVA VA

When --iova-mode is explicitly specified in command line, DMA mask constraints were not being validated, leading to potential runtime failures when device DMA capabilities are exceeded. The issue occurred because rte_bus_get_iommu_class() was only called during IOVA mode auto-detection, but this f

Re: [PATCH] net/xsc: fix use after free in some RXQ cleanup

On Tue, 9 Sept 2025 at 09:05, David Marchand wrote: > > Debian 12 gcc complains about a use after free in this cleanup section. > > [7/11] Compiling C object drivers/libtmp_rte_net_xsc.a.p/net_xsc_xsc_rx.c.o > In function 'xsc_rss_qp_create', > inlined from 'xsc_rxq_rss_obj_new' at ../drivers/

RE: [PATCH v3 10/15] net/ice: remove unsupported Rx offload

> > On Mon, 18 Aug 2025 at 13:00, Ciara Loftus wrote: > > > > The offload RTE_ETH_RX_OFFLOAD_SCTP_CKSUM is not supported in the ice > > driver so remove the one erroneous use of it. > > > > Signed-off-by: Ciara Loftus > > Acked-by: Bruce Richardson > > I just noticed this fix in main. > Fixes:

Re: [PATCH v2] event/dlb2: add support for stop and restart dlb device

On Sun, Jul 6, 2025 at 12:27 AM Pravin Pathak wrote: > > This feature enables restarting a stopped eventdev with a call > to rte_event_dev_start(). For this, the DLB scheduling domain needs > to be stopped, all DLB ports disabled during eventdev stop and > re-enabled during start. Port configurati

[V11 15/18] 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 | 3 + drivers/net/hinic3/hinic3_rx.c | 285 +++ drivers/net/hinic3/hinic3_tx.c | 77

[PATCH 2/4] net/idpf: use the common Rx path selection infrastructure

Update the common rx path selection infrastructure to include the feature "single queue" which is relevant for the idpf and cpfl drivers. Replace the existing complicated logic in the idpf driver with the use of the common function. Signed-off-by: Ciara Loftus --- drivers/net/intel/common/rx.h

[V11 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 | 190 drivers/net/hinic3/base/hinic3_hw

Re: [PATCH v3 3/3] bbdev: fix build with MinGW 13

FYI The DTS failure for this series on patchwork for the MTU testsuite is coming from a different patch than this one. Once I have that resolved, I will put in a retest for this series which will clear up that MTU testsuite failure. On Mon, Sep 8, 2025 at 5:21 PM Thomas Monjalon wrote: > After a

[PATCH] net/mlx5: fix MTU initialization in device spawn

Currently with mlx5 PMD, rte_eth_dev_get_mtu() doesn't return the MTU the device was set with, but the default one. It happens because mlx5_dev_spawn() is not setting the eth_dev->data->mtu field after getting the actual MTU from the driver, so the default value is kept. This patch fixes the issue

Re: [PATCH v1 2/2] dts: update tests to use new API

Reviewed-by: Patrick Robb

Re: [PATCH v1 1/2] dts: move testpmd into API

Reviewed-by: Patrick Robb

[PATCH] sched: fix wrr parameter data type

wrr tokens getting truncated to uint8_t in wrr_store function() due to type mismatch. This patch changes the data type to uint16_t. Fixes: e16b06da0908 ("sched: remove WRR from strict priority TC queues") Signed-off-by: Megha Ajmera Acked-by: Jasvinder Singh --- lib/sched/rte_sched.c | 2 +- 1

[PATCH] test: support SVA copy for dmadev test

This commit supports SVA copy for dmadev test. Signed-off-by: Chengwen Feng --- app/test/test_dmadev.c | 79 ++ 1 file changed, 79 insertions(+) diff --git a/app/test/test_dmadev.c b/app/test/test_dmadev.c index 9cbb9a6552..dd4ace49ae 100644 --- a/app/tes

Re: [PATCH 9/9] gpu/cuda: support CUDA 13 building

15/09/2025 16:41, Gregory Etelson: > From: Bing Zhao > > The API name and prototype have been changed in the new CUDA, this > commit will ensure the compatibility with different versions. [...] > /* CUDA Driver functions loaded with cuGetProcAddress for versioning */ > +#if defined(CUDA_VERSION)

[PATCH v1 3/7] net/ntnic: migrate statistic thread to service

The statistic service is responsible for collecting statistics. Signed-off-by: Serhii Iliushyk --- drivers/net/ntnic/include/ntdrv_4ga.h | 1 - drivers/net/ntnic/ntnic_ethdev.c | 146 ++ drivers/net/ntnic/ntutil/nt_service.c | 6 ++ drivers/net/ntnic/rte_pmd_ntni

Re: [PATCH v1 0/7] migrate threads to DPDK service framework

From: Stephen Hemminger Sent: 08 September 2025 23:08 To: Serhii Iliushyk Cc: dev@dpdk.org ; Mykola Kostenok ; Christian Koue Muf Subject: Re: [PATCH v1 0/7] migrate threads to DPDK service framework On Mon, 8 Sep 2025 13:04:38 +0200 Serhii Iliushyk wrote: > This modification provides bette

[PATCH v2 1/5] net/intel: add AVX512DQ flag to AVX-512 checks

Add a check for the AVX512DQ cpu flag to the x86 vector capability function. This flag is required by the idpf and cpfl drivers which will soon use this function during their rx path selection process. Signed-off-by: Ciara Loftus --- drivers/net/intel/common/rx_vec_x86.h | 3 ++- 1 file changed,

[PATCH v1] net/mlx5: fix indirect action memory leak

There is a handle that is not freed when using indirect action list to manipulate legacy action. Fixes: e26f50adb ("net/mlx5: support indirect list meter mark action") Cc: getel...@nvidia.com Cc: sta...@dpdk.org Signed-off-by: Rongwei Liu Acked-by: Bing Zhao --- drivers/net/mlx5/mlx5_flow_hw.c

Re: [PATCH v1 0/7] migrate threads to DPDK service framework

On Mon, 8 Sep 2025 13:04:38 +0200 Serhii Iliushyk wrote: > This modification provides better resource (CPU) management for NTNIC PMD. > > The following threads are migrated: > * FLM update thread > * Statistic thread > * Port event thread > * Adapter monitoring t

[PATCH v4 1/4] hash: move table of hash compare functions out of header

Remove the definition of the compare jump table from the header file so the internal details are not exposed. Prevents future ABI breakage if new sizes are added. Make other macros local if possible, header should only contain exposed API. Signed-off-by: Stephen Hemminger Acked-by: Morten Brørup

[PATCH v2 0/5] idpf and cpfl rx path selection simplification

This series refactors the vector capability detection and Rx path selection code in the idpf and cpfl PMDs to use the common functions provided in drivers/net/intel/common/rx.h. v2: * Moved AVX512DQ check to common code. * Refactored rx function array definition for better readability. * Restored

[PATCH 4/4] net/cpfl: use the common Rx path selection infrastructure

Replace the existing complicated logic with the use of the common function. Signed-off-by: Ciara Loftus --- drivers/net/intel/cpfl/cpfl_rxtx.c | 105 ++-- drivers/net/intel/idpf/idpf_common_device.h | 1 - 2 files changed, 29 insertions(+), 77 deletions(-) diff --git

[PATCH v9 06/17] net/nbl: add Dispatch layer definitions and implementation

add Dispatch layer related definitions Signed-off-by: Dimon Zhao --- drivers/net/nbl/meson.build | 1 + drivers/net/nbl/nbl_core.c| 7 + drivers/net/nbl/nbl_core.h| 4 + drivers/net/nbl/nbl_dispatch.c| 546 ++

[V11 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:

[V11 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

[V9 11/17] 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

Re: [PATCH v4] app/testpmd: stop secondary process fwd_lcores during primary teardown

On Wed, 17 Sep 2025 04:36:01 -0700 Khadem Ullah <14pwcse1...@uetpeshawar.edu.pk> wrote: > When the secondary process testpmd application running any fwd_engine > and after that primary has exited will cause a crash. > > This patch forces secondary process forwarding lcores > in fwd_engine to stop

[PATCH v9 15/17] net/nbl: add nbl ethdev infos get

Implement NBL ethdev infos get functions Signed-off-by: Dimon Zhao --- drivers/net/nbl/nbl_dev/nbl_dev.c| 55 drivers/net/nbl/nbl_dev/nbl_dev.h| 4 ++ drivers/net/nbl/nbl_ethdev.c | 1 + drivers/net/nbl/nbl_ethdev.h |

Re: [PATCH v2] app/testpmd: stop secondary process fwd_lcores during primary teardown

Hi Thomas, On Thu, Sep 11, 2025, 22:53 Stephen Hemminger wrote: > On Thu, 11 Sep 2025 03:25:01 -0700 > Khadem Ullah <14pwcse1...@uetpeshawar.edu.pk> wrote: > > > When the secondary process testpmd application running any fwd_engine > > and after that primary has exited will cause a crash. > > >

[PATCH v1 1/7] net/ntnic: introduce service API for NTNIC PMD

This commit adds a common service API for the NTNIC PMD, which includes functions for service management: add or delete a service and retrieve information about a service. The API is designed to facilitate the interaction with services within the NTNIC driver, allowing for better control and monito

Re: [PATCH v10 1/1] ethdev: add support to provide link type

Hello, The title can be simply "ethdev: add link type". 08/09/2025 10:51, sk...@marvell.com: > +* **Added ethdev API in library.* Please be more specific, we don't need to group all ethdev changes together. Each new API feature deserves a separate bullet. > + > + * Added API to report type of

[PATCH v9 11/17] net/nbl: add nbl ethdev configuration

NBL device add ethdev configuration Signed-off-by: Dimon Zhao --- drivers/net/nbl/nbl_dev/nbl_dev.c | 38 +-- 1 file changed, 36 insertions(+), 2 deletions(-) diff --git a/drivers/net/nbl/nbl_dev/nbl_dev.c b/drivers/net/nbl/nbl_dev/nbl_dev.c index c415dcf795..12766b

Re: [PATCH v4] dts: enable port binding on the TG

Hi Andrew, thank you for this, just some minor comments. On Mon, Sep 08, 2025 at 01:36:18PM +, Andrew Bailey wrote: > diff --git a/dts/framework/testbed_model/port.py > b/dts/framework/testbed_model/port.py > index fc58e2b993..8f9b5c3931 100644 > --- a/dts/framework/testbed_model/port.py > +

[V8 08/17] 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 | 194 drivers/net/hinic3/base/hinic3_hw

Re: [EXTERNAL] [RFC] lib/cryptodev: update API documentation for aux_flags

On 12-Sep-25 3:56 PM, Akhil Goyal wrote: On 12-Sep-25 2:05 PM, Akhil Goyal wrote: Hi Radu, Update the API documentation description of rte_crypto_op field aux_flags as to allow PMDs to define driver-specific flags. Can you give examples of the flags that you want to add for driver specific

[PATCH v2 07/10] app/dma-perf: remove invalid or redundant field

Remove invalid or redundant fields to make code more clean. Signed-off-by: Chengwen Feng Acked-by: Vamsi Attunuru --- app/test-dma-perf/benchmark.c | 20 +--- app/test-dma-perf/main.c | 19 --- app/test-dma-perf/main.h | 12 ++-- 3 files changed

Re: [PATCH 1/1] ring: safe partial ordering for head/tail update

On Wed, 17 Sep 2025 08:47:53 +0100 Bruce Richardson wrote: > On Tue, Sep 16, 2025 at 06:19:41PM +, Ola Liljedahl wrote: > > (I am sending this from Outlook, I hope I have been able to fake a proper > > email client) > > > > > On 2025-09-16, 17:43, "Bruce Richardson" > > >

[PATCH v9 14/17] net/nbl: add nbl device Tx and Rx burst

Implement NBL device Tx and Rx burst Signed-off-by: Dimon Zhao --- drivers/net/nbl/nbl_core.c| 2 +- drivers/net/nbl/nbl_core.h| 2 +- drivers/net/nbl/nbl_dev/nbl_dev.c | 37 +- drivers/net/nbl/nbl_dev/nbl_dev.h | 4 + driver

[PATCH v3 3/3] dts: update tx_offload test from old dts

Currently, the RX/TX offload test in old DTS expects the TX ports to be initially configured to use mbuf fast free. This is no longer the case and must be updated to assume mbuf fast free is not initially utilized by capable NICs. Add updated test suite to test mbuf fast free configuration. Signed

[V11 04/18] net/hinic3: add support for cmdq mechanism

From: Xin Wang Microcode 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

Re: [PATCH v2 1/3] net/mlx5: fix ESP header match in strict mode

Hi, On 09/09/2025 9:28 AM, Maayan Kashani wrote: From: Viacheslav Ovsiienko The pattern like "eth / ipv6 / esp / end" matched on any IPv6 packet in strict mode, because there was no implicit match on the IP.proto forced. This patch adds the implicit match on IP.proto with value 50 (ESP) and

[V11 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 | 358 + drivers/net/hinic3/hinic3_ethdev.h | 6 + 2 files changed, 364 insertions(+)

[PATCH v1 0/2] Split DTS framework and public API

Split up framework and public API. All calls in the tests should go through the public API. This will allow us to change the framework internals without breaking the tests and also to provide a stable and smaller API for test writers. More importantly this will make it easier to non DTS developers

[V9 09/17] 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:

[V9 02/17] 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 --- MAINTAINERS | 1 + drivers/net/hinic3

Re: [PATCH v3 0/2] Add jump flow support and queue menegment with new snippets

25/08/2025 09:23, Shani Peretz: > v3: > add comma in the meson.build file to fix build error > > v2: > sent mistakely as RFC - remove RFC tag, no functional changes > > v1: > This patch series adds port affinity matching for bonded ports and > refactors queue management to support the new port af

[PATCH v3 2/3] dts: add TX offload capabilities to NIC capabilities

Currently, there is no support for tracking tx_offload capabilities and there is no separation between port capabilities and queue capabilities. This is an issue if a test case requires a tx_offload capability or if a test case requires that a card supports a capability on a queue. This causes test

DPDK LACP implemantation

Hi, At Cato Networks we are currently working on implementing LACP LAG (bonding device, mode 4) using the DPDK library. During our evaluation, we identified some shortcomings in the implementation — for example, the lack of support for short timeout and the absence of proper handling for partner

[PATCH v3 1/3] dts: allow mbuf_fast_free to be set with testpmd shell

Currently, there is no way in the testpmd shell class to set the mbuf fast free offload configuration for queues or ports. This prohibits any test suites to be written utilizing this offload configuration. Introduce methods that support calls to testpmd in order to allow the configuration of mbuf f

[PATCH v3 0/3] dts: add tx_offload support in dts

This patchset introduces the support for Tx offload configuration through DTS, allowing test cases to be written utilizing Tx offload capabilities. Along with configuring these capabilities, they are also added to the NIC capabilities class, in which they can be required by test suites. Finally, a

Re: [PATCH v2 2/4] net/mlx5: mark an operation in mbuf's history

On Tue, 16 Sep 2025 23:31:34 +0200 Thomas Monjalon wrote: > 16/09/2025 23:14, Stephen Hemminger: > > On Tue, 16 Sep 2025 18:12:05 +0300 > > Shani Peretz wrote: > > > > > record operations on mbufs when it is allocated > > > and released inside the mlx5 PMD. > > > > > > Signed-off-by: Shani P

Re: [RFC v2 7/9] vfio: stop including Linux kernel header in public and driver API

On 9/3/2025 5:17 PM, David Marchand wrote: The DPDK API is not dependent on the VFIO API itself. Remove inclusion in rte_vfio.h (and bus_fslmc_driver.h) and add explicit inclusion where needed. Signed-off-by: David Marchand Reviewed-by: Rosen Xu --- Acked-by: Anatoly Burakov -- Thanks, Ana

RE: [PATCH v2 1/4] mbuf: record mbuf operations history

> From: Shani Peretz [mailto:shper...@nvidia.com] > Sent: Tuesday, 16 September 2025 17.12 > > This feature is designed to monitor the lifecycle of mbufs > as they move between the applicationand the PMD. > > It will allow us to track the operations and transitions > of each mbuf throughout the

[PATCH v4] app/testpmd: stop secondary process fwd_lcores during primary teardown

When the secondary process testpmd application running any fwd_engine and after that primary has exited will cause a crash. This patch forces secondary process forwarding lcores in fwd_engine to stop before the primary process exits. Fixes: a550baf24af90f ("app/testpmd: support multi-process") Cc

Re: [PATCH 1/1] ring: safe partial ordering for head/tail update

(I am sending this from Outlook, I hope I have been able to fake a proper email client) > On 2025-09-16, 17:43, "Bruce Richardson" > > wrote: > > > On Mon, Sep 15, 2025 at 06:54:50PM +, Wathsala Vithanage wrote: > > The function __rte_ring_headtail_move_hea

[PATCH v9 02/17] net/nbl: add simple probe/remove and log module

Our driver architecture is relatively complex because the code is highly reusable and designed to support multiple features. For example, our driver can support open-source UIO/VFIO drivers while also coexisting with kernel drivers. Additionally, the codebase supports multiple chip variants, each w

[PATCH v9 13/17] net/nbl: add nbl device start and stop ops

Implement NBL device start and stop functions Signed-off-by: Dimon Zhao --- drivers/net/nbl/nbl_dev/nbl_dev.c | 172 +- drivers/net/nbl/nbl_dispatch.c| 121 +++- drivers/net/nbl/nbl_hw/nbl_txrx.c | 72 +++- drivers/net/nbl/nbl_

DPDK 22.11.10 released

Hi all, Here is a new stable release: https://fast.dpdk.org/rel/dpdk-22.11.10.tar.xz This is a security update to fix CVE-2025-23259. The git tree is at: https://dpdk.org/browse/dpdk-stable/?h=22.11 Luca Boccassi --- VERSION| 2 +- doc/guides/

[V11 14/18] net/hinic3: add device initialization

From: Xin Wang Add device initializationd function codes. Signed-off-by: Xin Wang Reviewed-by: Feifei Wang Reviewed-by: Yi Chen --- drivers/net/hinic3/hinic3_ethdev.c | 274 + 1 file changed, 274 insertions(+) diff --git a/drivers/net/hinic3/hinic3_ethdev.c b/dr

[V11 06/18] net/hinic3: add eq mechanism

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

[V11 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

[V11 17/18] net/hinic3: add flow control and FDIR 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 | 65 ++ drivers/net/hinic3/hinic3_ethdev.h

[PATCH v9 16/17] net/nbl: add nbl device xstats and stats

Implement NBL device xstats and stats functions Signed-off-by: Dimon Zhao --- drivers/net/nbl/nbl_dev/nbl_dev.c | 174 ++ drivers/net/nbl/nbl_dev/nbl_dev.h | 9 + drivers/net/nbl/nbl_dispatch.c| 113 drivers/net/nbl/nbl_ethde

[V11 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

[V11 18/18] drivers/net: add hinic3 PMD build and doc files

From: Yi Chen The hinic3.ini file and hinic3.rst file are added to this patch. Signed-off-by: Yi Chen Reviewed-by: Xin Wang Reviewed-by: Feifei Wang --- MAINTAINERS | 1 + doc/guides/nics/features/hinic3.ini | 60 + doc/guides/nics/hinic3.

[V11 12/18] net/hinic3: add futions for 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 | 255 + drivers/net/hinic3/hinic3_ethdev.h | 118 +

[V11 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

[V11 01/18] doc: add hinic3 driver

From: Yi Chen This patch adds document for hinic3 driver. Signed-off-by: Feifei Wang Signed-off-by: Yi Chen Reviewed-by: Xin Wang --- .mailmap | 4 +++- MAINTAINERS| 4 doc/guides/nics/index.rst | 1 + doc/guides/rel

[V11 00/18] add-hinic3-PMD-driver

The hinic3 PMD (**librte_net_hinic3**) provides poll mode driver support for 25Gbps/100Gbps/200Gbps Huawei SPx series Network Adapters. v11: -reorder code to avoid forward declarations -remove unused casts -use assignment instead of memcpy -change some LOG level to DEBUG level -remove unused funct

[V11 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 --- MAINTAINERS | 1 + drivers/net/hinic3

Re: [PATCH 7/9] gpu/cuda: extend NVIDIA GPU device ID list

15/09/2025 16:41, Gregory Etelson: > From: eagostini > > Add new NVIDIA GPU IDs taken from public driver list. > https://github.com/NVIDIA/open-gpu-kernel-modules/blob/e45d91de0224e17a6bf7c971d8f165090b3c07a6/src/nvidia/generated/g_nv_name_released.h It is not synchronized. For instance, there a

Re: [PATCH 0/2] net/idpf: enable AVX2 for split queue Rx/Tx

On Wed, Sep 17, 2025 at 10:56:56AM +0530, Shaiq Wani wrote: > In case some CPUs don't support AVX512. Enable AVX2 for them to > get better per-core performance. > > In the single queue model, the same descriptor queue is used by SW > to post descriptors to the device and used by device to report c

Re: [PATCH v2 1/5] net/intel: add AVX512DQ flag to AVX-512 checks

On Wed, Sep 17, 2025 at 09:17:27AM +, Ciara Loftus wrote: > Add a check for the AVX512DQ cpu flag to the x86 vector capability > function. This flag is required by the idpf and cpfl drivers which will > soon use this function during their rx path selection process. > > Signed-off-by: Ciara Lof

[PATCH v2 3/5] net/idpf: use the common Rx path selection infrastructure

Update the common rx path selection infrastructure to include the feature "single queue" which is relevant for the idpf and cpfl drivers. Replace the existing complicated logic in the idpf driver with the use of the common function. Signed-off-by: Ciara Loftus --- v2: * Restored rx function names

[PATCH v2 4/5] net/cpfl: use the new common vector capability function

Use the new function for determining the maximum simd bitwidth in the cpfl driver. Also, remove unused elements related to AVX capability from the idpf_vport structure, now that neither the idpf or cpfl drivers use them. Signed-off-by: Ciara Loftus --- v2: * Removed check for AVX512DQ in the driv

Re: [PATCH] config/arm: support crypto in cortex-a78ae mcpu

> > ARM cortex-a78ae configuration (part number 0xd42) is being built without > > the > > necessary crypto extensions. This results in infinite loops in the crypto > > performance tests applications because the hardware crypto features are not > > properly enabled. > > This fix enables the crypto

Re: [PATCH] eal: fix DMA mask validation inconsistency in IOVA VA

Recheck-request: rebase=main, iol-mellanox-Functional, iol-compile-amd64-testing, iol-compile-arm64-testing, iol-unit-amd64-testing, iol-unit-arm64-testing

[PATCH v9 01/17] net/nbl: add doc and minimum nbl build framework

add minimum PMD code, doc and build infrastructure for nbl driver. Signed-off-by: Dimon Zhao --- .mailmap | 4 + MAINTAINERS | 9 ++ doc/guides/nics/features/nbl.ini | 31 +++ doc/guides/nics/index.rst

[PATCH v9 00/17] NBL PMD for Nebulamatrix NICs

Features: - - MTU update - promisc mode set - xstats - Basic stats Support NICs: - - S1205CQ-A00CHT - S1105AS-A00CHT - S1055AS-A00CHT - S1052AS-A00CHT - S1051AS-A00CHT - S1045XS-A00CHT - S1205CQ-A00CSP - S1055AS-A00CSP - S1052AS-A00CSP Dimon Zhao (17): net/nbl: add doc and

[PATCH v9 10/17] net/nbl: add nbl coexistence mode for nbl

NBL device support coexistence mode Signed-off-by: Dimon Zhao --- drivers/net/nbl/nbl_common/nbl_userdev.c | 747 ++- drivers/net/nbl/nbl_common/nbl_userdev.h | 11 + drivers/net/nbl/nbl_core.c | 3 +- drivers/net/nbl/nbl_core.h |

[PATCH v9 08/17] net/nbl: add complete device init and uninit functionality

NBL device is a concept of low level device which used to manage hw resource and to interact with fw Signed-off-by: Dimon Zhao --- drivers/net/nbl/nbl_core.c| 4 +- drivers/net/nbl/nbl_core.h| 7 + drivers/net/nbl/nbl_dev/nbl_dev.c | 284 ++

[PATCH v9 07/17] net/nbl: add Dev layer definitions and implementation

add Dev layer related definitions Signed-off-by: Dimon Zhao --- drivers/net/nbl/meson.build | 3 + drivers/net/nbl/nbl_core.c| 14 +- drivers/net/nbl/nbl_core.h| 16 ++ drivers/net/nbl/nbl_dev/nbl_dev.c | 194 ++ drive

[PATCH v9 05/17] net/nbl: add Resource layer definitions and implementation

add Resource layer related definitions Signed-off-by: Dimon Zhao --- drivers/net/nbl/meson.build | 3 + drivers/net/nbl/nbl_core.c| 11 +- drivers/net/nbl/nbl_core.h| 4 + .../nbl/nbl_hw/nbl_hw_leonis/nbl_res_leonis.c | 137 +

[PATCH v9 03/17] net/nbl: add HW layer definitions and implementation

add HW layer related definitions and product ops Signed-off-by: Dimon Zhao --- drivers/net/nbl/meson.build | 2 + drivers/net/nbl/nbl_core.c| 49 +- drivers/net/nbl/nbl_core.h| 22 - drivers/net/nbl/nbl_hw/nbl_hw.h

RE: [PATCH 1/1] ring: safe partial ordering for head/tail update

To avoid information loss I combined reply to two Wathsala replies into one. > > > The function __rte_ring_headtail_move_head() assumes that the > > > barrier > > (fence) between the load of the head and the load-acquire of the > > > opposing tail guarantees the following: if a first thread reads

Re: [PATCH 1/1] ring: safe partial ordering for head/tail update

On Tue, Sep 16, 2025 at 06:19:41PM +, Ola Liljedahl wrote: > (I am sending this from Outlook, I hope I have been able to fake a proper > email client) > > > On 2025-09-16, 17:43, "Bruce Richardson" > > > wrote: > > > > > > On Mon, Sep 15, 2025 at 06:54:50PM