[dpdk-dev] [PATCH] net/netvsc: ignore NVS_TYPE_TXTBL_NOTE while executing a sync command

From: Long Li On netvsc initialization, the host VSP may send a NVS_TYPE_TXTBL_NOTE packet while executing a VSP command synchronously. Ignore this packet as we don't use it for DPDK. Cc: sta...@dpdk.org Signed-off-by: Long Li --- drivers/net/netvsc/hn_nvs.c | 7 ++- 1 file changed, 6 ins

Re: [dpdk-dev] [PATCH v1 00/12] fix rx packets dropped issue

Hi, steve What I saw is that you replace of frame size checking to mtu checking, but you still use "18" as overhead number to configure max_rx_pkt_len? uint32_t frame_size = mtu + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN; dev->data->dev_conf.rxmode.max_rx_pkt_len = frame_size; > -Original Me

Re: [dpdk-dev] [PATCH] net/i40e: issue with ADD VLAN from Guest

hi, souvik From: Souvik Dey Sent: Thursday, December 10, 2020 1:55 AM To: Xing, Beilei ; Guo, Jia ; Zhang, Qi Z Cc: dev@dpdk.org; Souvik Dey Subject: [PATCH] net/i40e: issue with ADD VLAN from Guest In case of i40evf pmd, when ADD_VLAN is sent down the linux i40e driver, along with add the vl

[dpdk-dev] [PATCH 2/2] vhost: enhance async enqueue for small packets

Async enqueue offloads large copies to DMA devices, and small copies are still performed by the CPU. However, it requires users to get enqueue completed packets by rte_vhost_poll_enqueue_completed(), even if they are completed by the CPU when rte_vhost_submit_enqueue_burst() returns. This design in

[dpdk-dev] [PATCH 1/2] vhost: cleanup async enqueue

This patch removes unncessary check and function calls, and it changes appropriate types for internal variables and fixes typos. Signed-off-by: Jiayu Hu --- lib/librte_vhost/rte_vhost_async.h | 6 +++--- lib/librte_vhost/virtio_net.c | 16 2 files changed, 11 insertions(+)

[dpdk-dev] [PATCH 0/2] Enhance Async Enqueue for Small Packets

Async enqueue offloads large copies to DMA devices, and small copies are still performed by the CPU. However, it requires users to get enqueue completed packets by rte_vhost_poll_enqueue_completed(), even if they are completed by the CPU when rte_vhost_submit_enqueue_burst() returns. This design in

Re: [dpdk-dev] [PATCH v3 00/17] fixes and refactoring changes for bnxt

On Wed, Dec 9, 2020 at 3:53 PM Ajit Khaparde wrote: > > Some fixes and refactoring changes for bnxt PMD. > > v1->v2: Resend without the legal signature/footer. > v2->v3: Fix index calculation in patch 17/17. Patchset applied to dpdk-next-net-brcm. Thanks > > > Ajit Khaparde (9): > net/bnxt: re

Re: [dpdk-dev] [PATCH] net/ixgbe: check the result of setting VF MTU

> -Original Message- > From: dev On Behalf Of Wang, Haiyue > Sent: Wednesday, December 2, 2020 6:55 PM > To: Zhang, AlvinX ; Guo, Jia > Cc: dev@dpdk.org; Zhang, AlvinX ; sta...@dpdk.org > Subject: Re: [dpdk-dev] [PATCH] net/ixgbe: check the result of setting VF MTU > > > -Original

Re: [dpdk-dev] [PATCH v2] net/i40e: fix global register recovery

> -Original Message- > From: dev On Behalf Of Guo, Jia > Sent: Tuesday, November 24, 2020 1:56 PM > To: Xing, Beilei ; dev@dpdk.org > Cc: sta...@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v2] net/i40e: fix global register recovery > > Acked-by: Jeff Guo > > > -Original Message

Re: [dpdk-dev] [PATCH v2] net/i40e: fix incorrect checksum flag of L4 checksum

> -Original Message- > From: dev On Behalf Of Guo, Jia > Sent: Friday, December 4, 2020 10:19 AM > To: Yang, MurphyX ; dev@dpdk.org > Cc: Yang, Qiming ; Yang, SteveX > ; Xing, Beilei ; Yang, MurphyX > > Subject: Re: [dpdk-dev] [PATCH v2] net/i40e: fix incorrect checksum flag of L4 > ch

Re: [dpdk-dev] [PATCH] net/ice: fix outer UDP Tx offload checksum error

> -Original Message- > From: Xie, WeiX > Sent: Monday, November 23, 2020 4:31 PM > To: Yang, MurphyX ; dev@dpdk.org > Cc: Yang, Qiming ; Zhang, Qi Z ; > Yang, SteveX ; Yang, MurphyX > > Subject: RE: [dpdk-dev] [PATCH] net/ice: fix outer UDP Tx offload checksum > error > > Tested-by:

Re: [dpdk-dev] [PATCH] net/virtio-user: fix error run close(0)

Hi Jiawei, >From: 17826875952 <17826875...@163.com> >Sent: Friday, December 11, 2020 1:31 AM >To: Xia, Chenbo >Cc: maxime.coque...@redhat.com >Subject: Re:RE: [PATCH] net/virtio-user: fix error run close(0) > > >Hi Chenbo, >Thanks for you comment！ > >At 2020-12-09 19:31:19, "Xia, Chenbo"

Re: [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON vector

> -Original Message- > From: dev On Behalf Of Feifei Wang > Sent: Wednesday, November 18, 2020 2:29 PM > Cc: dev@dpdk.org; n...@arm.com; Feifei Wang > Subject: [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON > vector > > This patch series are mainly to enable checksum of

Re: [dpdk-dev] [PATCH V2 0/2] hns3 fixes

在 2020/12/11 0:30, Ferruh Yigit 写道: On 12/10/2020 12:48 PM, Lijun Ou wrote: Here series are fixes for hns3 PMD driver. Change from V1: 1. fix the comments given by Ferruh Yigit for 4/4 Lijun Ou (1): net/hns3: adjust printing MAC addresses in log Min Hu (Connor) (1): net/hns3: fix FEC

[dpdk-dev] [PATCH] net/ixgbe: fix fdirctrl register setting

From: YU DAPENG The function ixgbe_fdir_set_flexbytes_offset is used when create FDir rule for flexbytes. It set a register: FDIRCTRL.FLEX_OFFSET, which cause that even if the FDir flexbytes rule is destroyed, the rule still direct the packet and transfer it to the wrong place. It is because Sett

[dpdk-dev] [PATCH] eal/windows: add interrupt functions stub

Add some missing interrupt implementations on Windows. Also add respestive functions to export file. Signed-off-by: Tal Shnaiderman Signed-off-by: Pallavi Kadam Reviewed-by: Ranjit Menon --- lib/librte_eal/rte_eal_exports.def | 11 lib/librte_eal/windows/eal_interrupts.c | 76 +++

Re: [dpdk-dev] [EXTERNAL] Re: Windows DPDK real-time priority threads causing thread starvation

There is a configuration in Windows similar to Linux isolcpus where scheduler tries not to run anything on such cores, and implementation is being enhanced for the next Windows release with User-mode vmswitch feedback. I'll dig out the details. Dmitry -Original Message- From: Stephen H

Re: [dpdk-dev] [EXTERNAL] 19.11.6 patches review and test

Thank you! On Thu, 2020-12-10 at 16:58 +, Abhishek Marathe wrote: > Hi Luca, > > No new issues found for 19.11.6 testing. All testcases failed below are due > to known issues. > > Regards, > Abhishek > > > Test Results: > > Test case description: > > * VERIFY-DPDK-COMPLIANCE - verifies

Re: [dpdk-dev] rte_pktmbuf_pool_create returns EINVAL

Hello All, We could observe the issue with rte_mempool_populate_default() API. Does this lead to fetching contiguous memorywhen allocating it ? BTW we are using the "legacy mem" option to initialize it. Please share if you have more info on this issue. On Tue, Dec 8, 2020 at 12:59 PM Kamaraj P

Re: [dpdk-dev] ipv6 rte_flow supported on intel ixgbe/i40e dpdk 18.11.2

On 09/12/2020 12:00, 万乐冰 wrote: > Hi Team: > recently I am using ipv6 rte_flow on intel ixgbe/i40e with dpdk > 18.11.2，but it doesn't works. > Hi, it is better to ask ixgbe and i40e maintainers, but just to note that there are many further 18.11 releases that you can test to see if any issues

Re: [dpdk-dev] [PATCH V2 0/2] hns3 fixes

On 12/10/2020 12:48 PM, Lijun Ou wrote: Here series are fixes for hns3 PMD driver. Change from V1: 1. fix the comments given by Ferruh Yigit for 4/4 Lijun Ou (1): net/hns3: adjust printing MAC addresses in log Min Hu (Connor) (1): net/hns3: fix FEC state query Series applied to dpdk-n

[dpdk-dev] ipv6 rte_flow supported on intel ixgbe/i40e dpdk 18.11.2

Hi Team: recently I am using ipv6 rte_flow on intel ixgbe/i40e with dpdk 18.11.2，but it doesn't works. i40e: testpmd cmd: ./x86_64-native-linuxapp-gcc/app/testpmd -l 0,1-7,15,25-31 -n 4 -- -i --pkt-filter-mode=perfect --rxq=8 --txq=8 --nb-cores=8 --pkt-filter-size= *128K* ​ test flows: -

Re: [dpdk-dev] [PATCH] Remove printf from signal handler.

Hi Agree. What is the way out? The printfs you mentioned look like important messages and may have been called outside signal handler routines. Shall they be removed as well or converted to "write" function call? Or we live with the possiblity of deadlock howsoever unlikely. Regards Prateek Aga

[dpdk-dev] [PATCH v1 2/2] linux/kni: Added support for KNI multiple fifos

In order to improve performance, the KNI is made to support multiple fifos, So that multiple threads pinned to multiple cores can process packets in parallel. Signed-off-by: dheemanth --- app/test/test_kni.c | 4 +- drivers/net/kni/rte_eth_kni.c | 5 +- examples/kni/main.c

Re: [dpdk-dev] [PATCH v3 16/17] net/bnxt: add missing comments

On Wed, Dec 9, 2020 at 6:59 PM Ajit Khaparde wrote: > > Add and update some missing comments in the code. > > Signed-off-by: Ajit Khaparde > --- > drivers/net/bnxt/bnxt.h | 6 ++ > drivers/net/bnxt/tf_ulp/ulp_template_db_act.c | 5 + > drivers/net/bnxt/tf_ulp/ul

Re: [dpdk-dev] [PATCH v3 15/17] net/bnxt: changes to indentation and coding style

On Wed, Dec 9, 2020 at 6:59 PM Ajit Khaparde wrote: > > Indentation and coding style fixes. > > Signed-off-by: Ajit Khaparde > --- > drivers/net/bnxt/bnxt.h| 4 ++-- > drivers/net/bnxt/bnxt_ethdev.c | 9 - > drivers/net/bnxt/bnxt_reps.c | 2 +- > drivers/net/bnxt/bnxt_ring.c

Re: [dpdk-dev] [PATCH v3 12/17] net/bnxt: remove function declaration

On Wed, Dec 9, 2020 at 6:58 PM Ajit Khaparde wrote: > > Remove an orphan function declaration. > It has not been defined yet and hence not used anywhere. > > Signed-off-by: Ajit Khaparde > --- > drivers/net/bnxt/bnxt_hwrm.h | 2 -- > 1 file changed, 2 deletions(-) > > diff --git a/drivers/net/bn

Re: [dpdk-dev] [PATCH v3 11/17] net/bnxt: use the right function to free mbuf

On Wed, Dec 9, 2020 at 6:57 PM Ajit Khaparde wrote: > > mbufs are being allocated using rte_mbuf_raw_alloc(). > Use corresponding rte_mbuf_raw_free() to free mbuf. > > Signed-off-by: Somnath Kotur > > Signed-off-by: Ajit Khaparde > --- > drivers/net/bnxt/bnxt_reps.c | 2 +- > 1 file changed, 1

Re: [dpdk-dev] [PATCH v3 08/17] net/bnxt: fix format specifier for unsigned int

On Wed, Dec 9, 2020 at 6:56 PM Ajit Khaparde wrote: > > &device requires the %u format specifer not the %d specifier, as > &device is unsigned. > > Fixes: a46bbb57605b ("net/bnxt: update multi device design") > Cc: sta...@dpdk.org > > Signed-off-by: Ajit Khaparde > --- > drivers/net/bnxt/tf_core

Re: [dpdk-dev] [PATCH v3 07/17] net/bnxt: fix cleanup on mutex init failure

On Wed, Dec 9, 2020 at 6:56 PM Ajit Khaparde wrote: > > In case mutex init fails during initialization, start cleanup and > fail the initialization process. > > Fixes: a73b8e939f10 ("net/bnxt: fix race between start and interrupt handler") > Cc: sta...@dpdk.org > > Signed-off-by: Ajit Khaparde >

Re: [dpdk-dev] [PATCH v3 05/17] net/bnxt: remove references to Thor

On Wed, Dec 9, 2020 at 6:55 PM Ajit Khaparde wrote: > > Refactor code to remove references to Thor. > Instead use P5 as in phase 5 of development cycle since it is applicable > to boards other than Thor as well. > > Signed-off-by: Ajit Khaparde > --- > drivers/net/bnxt/bnxt.h| 20 +++

Re: [dpdk-dev] [PATCH v3 03/17] net/bnxt: remove unused field

On Wed, Dec 9, 2020 at 6:55 PM Ajit Khaparde wrote: > > Remove flow_xstat from bnxt structure. > > Signed-off-by: Ajit Khaparde > --- > drivers/net/bnxt/bnxt.h | 1 - > 1 file changed, 1 deletion(-) > > diff --git a/drivers/net/bnxt/bnxt.h b/drivers/net/bnxt/bnxt.h > index 9bd4f1da9..f13d586d4 1

[dpdk-dev] [PATCH] net/mlx5: fix mbufs double free in vectorized MPRQ

Wrong index is used to find mbufs belonging to an application in the rxq_free_elts_sprq() function in the case of vectorized MPRQ. elts_ci points to the last allocated mbuf in this case, not rq_ci. Use this field to avoid double free of mbuf and segmentation fault. Fixes: 0f20acbf5ed ("net/mlx5: i

[dpdk-dev] [PATCH v2 33/33] net/mlx5: refactor eth dev ops for Windows

From: Ophir Munk There are two types of eth_dev_ops used under Windows: primary and isolate mode. Their function calls initialization is added to the OS specific file mlx5_os.c. Secondary process eth_dev_ops is nullified. Signed-off-by: Ophir Munk Acked-by: Matan Azrad --- drivers/net/mlx5/wi

[dpdk-dev] [PATCH v2 30/33] net/mlx5/windows: implement device attribute getter

From: Ophir Munk This commit is the Windows implementation of mlx5_os_get_dev_attr() API. It follows the commit in [1]. A new file named mlx5_os.c is added under windows directory as its Linux counterpart file: linux/mlx5_os.c. [1]. commit e85f623e13ea ("net/mlx5: remove attributes dependency on

[dpdk-dev] [PATCH v2 32/33] net/mlx5/windows: implement mlx5 mac addr add

Get the list of MAC addresses and verify if the input mac parameter already exists. If not - return -ENOTSUP (as Windows does not support adding new MAC addresses). If the MAC address exists (EEXIST) return 0 (the equivalent of Linux implementation of this API). Signed-off-by: Tal Shnaiderman Ack

[dpdk-dev] [PATCH v2 20/33] mlx5/windows: add mlx5 meson file

File drivers/common/mlx5/windows/meson.build is added to enable mlx5 source files compilation under common windows directory. A Devx SDK tool must be installed to export two external H files: mlx5devx.h and mlx5_ifc_devx.h. The installation is based on environment variable DEVX_INC_PATH. In additio

[dpdk-dev] [PATCH v2 21/33] mlx5/windows: add initialization routine for external lib

From: Ophir Munk Add function mlx5_glue_constructor() as an initialization routine for run-time dependency on external lib. Currently the routine has an empty body. It is used for compatibility with Linux. Signed-off-by: Ophir Munk Acked-by: Matan Azrad --- drivers/common/mlx5/windows/meson.

[dpdk-dev] [PATCH v2 29/33] drivers/common: enable Windows common mlx5 compilation

From: Ophir Munk Prior to this commit meson did not progress beyond directory drivers/common for Windows compilations. This commit enables drivers compilation under this directory. Signed-off-by: Ophir Munk Acked-by: Matan Azrad --- drivers/common/meson.build | 8 +++- 1 file changed, 3

[dpdk-dev] [PATCH v2 31/33] net/mlx5/windows: add mlx5_os.c stubs

From: Ophir Munk mlx5_os_set_nonblock_channel_fd mlx5_os_dev_shared_handler_install mlx5_os_dev_shared_handler_uninstall mlx5_os_read_dev_stat mlx5_os_mac_addr_flush mlx5_os_mac_addr_remove mlx5_os_vf_mac_addr_modify mlx5_os_set_promisc mlx5_os_set_allmulti Set struct mlx5_flow_driver_ops mlx5_f

[dpdk-dev] [PATCH v2 27/33] net/mlx5: update MR prototypes for DevX

From: Ophir Munk Currently MR operations are Verbs based. This commit updates MR operations prototypes such that DevX MR operations callbacks can be used as well. Rename 'struct mlx5_verbs_ops' as 'struct mlx5_mr_ops' and move it to shared file mlx5.h. Signed-off-by: Ophir Munk Acked-by: Matan

[dpdk-dev] [PATCH v2 22/33] mlx5/windows: generate file mlx5_autoconf.h

From: Ophir Munk File mlx5_autoconf.h is generated under Windows to maintain compatibility with the Linux build system. This file is included in Linux/Windows shared source files therefore it is required. Currently the file is created empty. Signed-off-by: Ophir Munk Acked-by: Matan Azrad ---

[dpdk-dev] [PATCH v2 26/33] common/mlx5/windows: add OS umem reg/dereg API

Implement Windows API mlx5_os_umem_reg() and mlx5_os_umem_dereg(). They are equivalent to the Linux implementation. Signed-off-by: Tal Shnaiderman Acked-by: Matan Azrad --- drivers/common/mlx5/rte_common_mlx5_exports.def | 2 + drivers/common/mlx5/windows/mlx5_common_os.c| 60 +

[dpdk-dev] [PATCH v2 25/33] common/mlx5/windows: add OS alloc/dealloc pd

Implement Windows API mlx5_os_alloc_pd() and mlx5_os_dealloc_pd(). They are equivalent to the Linux implementation in [1]. [1] ("net/mlx5: wrap glue alloc/dealloc PD with OS calls") Signed-off-by: Tal Shnaiderman Acked-by: Matan Azrad --- drivers/common/mlx5/rte_common_mlx5_exports.def | 3 +-

[dpdk-dev] [PATCH v2 23/33] common/mlx5/windows: extend PRM match_param_bits struct

Add reserved size to PRM 'struct mlx5_ifc_fte_match_param_bits' for non Linux OS. Windows drivers require this extension since their expected size should match the actual struct size. Linux drivers do not require this extension and already use calculations based on the shorter size. Use a static a

[dpdk-dev] [PATCH v2 28/33] common/mlx5/windows: add OS reg/dereg MR

From: Ophir Munk This commits implements Windows API for MR registration and deregistration. It is based on DevX. Is support the relaxed ordering flow in Windows by checking the capabilities and machine type. Signed-off-by: Ophir Munk Signed-off-by: Tal Shnaiderman Acked-by: Matan Azrad ---

[dpdk-dev] [PATCH v2 24/33] common/mlx5/windows: add getter functions

From: Ophir Munk Add file mlx5/windows/mlx5_common_os.h the equivalent of Linux file mlx5/linux/mlx5_common_os.h. It contains getters functions mlx5_os_get_dev_device_name, mlx5_os_get_ctx_device_name, mlx5_os_get_ctx_device_path, mlx5_os_get_umem_id, mlx5_os_get_devx_channel_fd. Signed-off-by:

[dpdk-dev] [PATCH v2 18/33] common/mlx5: add DevX alloc PD command

Add a new DevX API mlx5_devx_cmd_alloc_pd() that creates a new protection domain (PD). Signed-off-by: Tal Shnaiderman Acked-by: Matan Azrad --- drivers/common/mlx5/mlx5_devx_cmds.c| 35 drivers/common/mlx5/mlx5_devx_cmds.h| 2 ++ drivers/common/

[dpdk-dev] [PATCH v2 19/33] common/mlx5/windows: add glue functions APIs

Windows glue functions are added to file mlx5/windows/mlx5_glue.c. The following APIs are supported: get_device_list, free_device_list, open_device, close_device, query_device, query_hca_iseg, devx_obj_create, devx_obj_destroy, devx_obj_query, devx_obj_modify, devx_general_cmd, devx_umem_reg, devx_

[dpdk-dev] [PATCH v2 17/33] common/mlx5: extend DevX query hca attributes command

Extend DevX API mlx5_devx_cmd_query_hca_attr() to report on max number of available objects including: CQ, QP, PD, SRQ. Signed-off-by: Tal Shnaiderman Acked-by: Matan Azrad --- drivers/common/mlx5/mlx5_devx_cmds.c | 11 +++ drivers/common/mlx5/mlx5_devx_cmds.h | 10 +- drivers/c

[dpdk-dev] [PATCH v2 04/33] net/mlx5: fix freeing packet pacing

From: Ophir Munk Packet pacing is allocated under condition #ifdef HAVE_MLX5DV_PP_ALLOC. In a similar way - free packet pacing index under the same condition. This update is required to successfully compile under operating systems which do not support packet pacing. Fixes: aef1e20ebeb2 ("net/mlx

[dpdk-dev] [PATCH v2 16/33] common/mlx5: add Windows exports file

File drivers/common/mlx5/rte_common_mlx5_exports.def contains mlx5 Windows exported symbols under common/mlx5 directory (DLL file name librte_common_mlx5*.dll). It is the equivalent of Linux map file rte_common_mlx5_version.map but the list of symbols may be different between the two operating syst

[dpdk-dev] [PATCH v2 15/33] common/mlx5/linux: wrap event channel APIs with OS calls

Wrap the API to create/destroy event channel and to subscribe an event with OS calls. In Linux those calls are implemented by glue functions while in Windows they are not supported. Signed-off-by: Tal Shnaiderman Acked-by: Matan Azrad --- drivers/common/mlx5/linux/mlx5_common_os.h | 22

[dpdk-dev] [PATCH v2 06/33] net/mlx5: define mprq functions as static inline

From: Ophir Munk Functions mlx5_check_mprq_support(), mlx5_rxq_mprq_enabled(), mlx5_mprq_enabled() are moved from source file mlx5_rxq.c to header file mlx5_rxtx.h and their type is updated to 'static __rte_always_inline'. Previously the functions were declared as 'inline' in the source file whic

[dpdk-dev] [PATCH v2 13/33] common/mlx5/linux: handle memory allocations with alignment

From: Ophir Munk mlx5_malloc() API has an alignment parameter for system memory allocations. malloc() is called for non-aligned allocations and posix_memalign() is called for aligned allocations. When calling mlx5_free() there is no distinction whether the memory was originally allocated with or

[dpdk-dev] [PATCH v2 14/33] common/mlx5/windows: handle memory allocations with alignment

From: Ophir Munk This commit is the Windows equivalent of the Linux implementation. The APIs included in this commit: mlx5_os_malloc(), mlx5_os_free(). For memory allocations (with or without alignment) we always call _aligned_malloc(). Even if zero alignment was requested in the first place - w

[dpdk-dev] [PATCH v2 05/33] net/mlx5: replace Linux sleep with rte sleep

From: Ophir Munk Replace Linux API usleep() and nanosleep() with rte_delay_us_sleep(). The replacement occurs in shared files compiled under different operating systems. Signed-off-by: Ophir Munk Acked-by: Matan Azrad --- drivers/net/mlx5/mlx5.c | 5 +++-- drivers/net/mlx5/mlx5_trigge

[dpdk-dev] [PATCH v2 09/33] net/mlx5: wrap glue alloc/dealloc PD with OS calls

From: Ophir Munk Wrap glue calls alloc_pd() and dealloc_pd() with generic OS calls. In Linux - protection domain allocations are implemented by Verbs glue API while in Windows it is by DevX API. Signed-off-by: Ophir Munk Acked-by: Matan Azrad --- drivers/common/mlx5/linux/mlx5_common_os.h |

[dpdk-dev] [PATCH v2 00/33] mlx5 Windows support - part #5

This patch series is part of preparing mlx5 PMD to compile and run under Windows OS. Part #5 v1: initial version v2: Fixes after CR and rebase, also patchset was split and part of the commits sent in v1 will be sent later on. Ophir Munk (21): net/mlx5/linux: extend device attributes getter

[dpdk-dev] [PATCH v2 12/33] common/mlx5: add definition HAVE_INFINIBAND_VERBS_H

From: Ophir Munk Add a Verbs file presence indication. Under Linux it is required that file infiniband/verbs.h is installed for building DPDK. Other operating systems (e.g. Windows) ignore Verbs completely. This commit adds definition HAVE_INFINIBAND_VERBS_H (file mlx5_autoconf.h) to indicate w

[dpdk-dev] [PATCH v2 08/33] net/mlx5: move static_assert calls to global scope

From: Ophir Munk Some Windows compilers consider static_assert() as calls to another function rather than a compiler directive which allows checking type information at compile time. This only occurs if the static_assert call appears inside another function scope. To solve it move the static_ass

[dpdk-dev] [PATCH v2 03/33] net/mlx5: remove Linux files from Windows compilation

From: Ophir Munk This commit removes Linux files flow_verbs.c and mlx5_rxtx_vec.c from Windows compilation. Signed-off-by: Ophir Munk Acked-by: Matan Azrad --- drivers/net/mlx5/meson.build | 16 +++- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/net/mlx5/m

[dpdk-dev] [PATCH v2 11/33] net/mlx5: fix adding destroy flow action wrapper

From: Ophir Munk Glue function destroy_flow_action() was wrapped by OS specific operation mlx5_flow_os_destroy_flow_action(). It was skipped in file mlx5.c. Fixes: b293fbf9672b ("net/mlx5: add OS specific flow actions operations") Cc: sta...@dpdk.org Signed-off-by: Ophir Munk Acked-by: Matan A

[dpdk-dev] [PATCH v2 10/33] net/mlx5: wrap glue reg/dereg UMEM with OS calls

Wrap glue calls for UMEM registration and deregistration with generic OS calls since each OS (Linux or Windows) has a different glue API parameters. Signed-off-by: Tal Shnaiderman Signed-off-by: Ophir Munk Acked-by: Matan Azrad --- drivers/common/mlx5/linux/mlx5_common_os.h | 12

[dpdk-dev] [PATCH v2 07/33] net/mlx5: do not define static_assert in Windows

From: Ophir Munk In Linux 'static_assert' is defined in file mlx5_defs.h: #ifndef HAVE_STATIC_ASSERT #define static_assert _Static_assert #endif The same definition can originate from Linux file /usr/include/assert.h. In Windows static_assert is used while _Static_assert is unknown. Ther

[dpdk-dev] [PATCH v2 01/33] net/mlx5: fix folding constant array error

Before this commit the PMD used: const int elt_n = 8 const int *stack[elt_n]; In Windows clang compiler complains: net/mlx5/mlx5_flow.c:215:19: error: variable length array folded to constant array as an extension [-Werror,-Wgnu-folding-constant] Fix it by using a constant macro definition

[dpdk-dev] [PATCH v2 02/33] net/mlx5/linux: extend device attributes getter

From: Ophir Munk This commit adds device attributes parameters to be reported by mlx5_os_get_dev_attr(): max_cqe, max_mr, max_pd, max_srq, max_srq_wr Signed-off-by: Ophir Munk Acked-by: Matan Azrad --- drivers/net/mlx5/linux/mlx5_os.c | 5 + drivers/net/mlx5/mlx5.h | 5 + 2 f

Re: [dpdk-dev] Patchworks Re: [PATCH v5 0/9] net/ionic: minor updates and documentation

On 12/10/2020 2:44 PM, Andrew Boyer wrote: Ferruh, 'After sending a new version of a patch, developers should set the previous patch as “Superseded”.' Did this happen automatically for v4 & friends or did you do it? (I did not). I will do it in future if it is not automatic. 'When a patch i

[dpdk-dev] Patchworks Re: [PATCH v5 0/9] net/ionic: minor updates and documentation

Ferruh, 'After sending a new version of a patch, developers should set the previous patch as “Superseded”.' Did this happen automatically for v4 & friends or did you do it? (I did not). I will do it in future if it is not automatic. 'When a patch is applied, it is set to “Accepted”.' Does that

Re: [dpdk-dev] [PATCH v3 17/17] net/bnxt: modify ring index logic

On Wed, Dec 9, 2020 at 6:59 PM Ajit Khaparde wrote: > > Change the ring logic so that the index increments > unbounded and mask it only when needed. > > Modify the existing macros so that the index is not masked. > Add a new macro RING_IDX() to mask it only when needed. > - > v2->v3: Updated the i

[dpdk-dev] [PATCH 6/6] net/ionic: stop queues when LIF is stopped

Otherwise they can not be restarted. Signed-off-by: Andrew Boyer --- drivers/net/ionic/ionic_lif.c | 14 ++ 1 file changed, 14 insertions(+) diff --git a/drivers/net/ionic/ionic_lif.c b/drivers/net/ionic/ionic_lif.c index 2452451be..98797b22b 100644 --- a/drivers/net/ionic/ionic_lif

[dpdk-dev] [PATCH 5/6] net/ionic: improve queue state handling

Skip ionic_lif_[rxq|txq]_init() in queue start if it's already done. Move ionic_lif_[rxq|txq]_deinit() from queue stop to queue release. This allows the queues to be restarted. Signed-off-by: Andrew Boyer --- drivers/net/ionic/ionic_rxtx.c | 62 +++--- 1 file changed

[dpdk-dev] [PATCH 4/6] net/ionic: improve link state handling

Add UP and FW_RESET state flags. Update the stack info when the link state changes. Convert set_link_up/set_link_down to lif_start/lif_stop. Condition reported link state on UP flag. Change lif_stop to return void. Signed-off-by: Andrew Boyer --- drivers/net/ionic/ionic_ethdev.c | 49 ++-

[dpdk-dev] [PATCH 3/6] net/ionic: fully implement remove-on-close

This is now required behavior for a PMD. Remove the UNMAINTAINED flag. Signed-off-by: Andrew Boyer --- MAINTAINERS | 2 +- drivers/net/ionic/ionic_ethdev.c | 41 drivers/net/ionic/ionic_lif.c| 15 drivers/net/ionic/ionic_lif

[dpdk-dev] [PATCH 2/6] net/ionic: preserve RX mode across LIF stop/start

Otherwise, non-default settings (like PROMISC) get reset. Signed-off-by: Andrew Boyer --- drivers/net/ionic/ionic_lif.c | 18 +- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/ionic/ionic_lif.c b/drivers/net/ionic/ionic_lif.c index 646c921b2..875c7e585

[dpdk-dev] [PATCH 1/6] net/ionic: preserve RSS state unless RETA size changes

This preserves settings across a stop/start. Signed-off-by: Andrew Boyer --- drivers/net/ionic/ionic_lif.c | 44 --- drivers/net/ionic/ionic_lif.h | 1 + 2 files changed, 21 insertions(+), 24 deletions(-) diff --git a/drivers/net/ionic/ionic_lif.c b/drivers/net/

[dpdk-dev] [PATCH 0/6] net/ionic: fixes for stop and start

These patches address issues found when testing port stop and start, link up and down, and queue stop and start. The UNMAINTAINED flag is removed in patch 3. Signed-off-by: Andrew Boyer Andrew Boyer (6): net/ionic: preserve RSS state unless RETA size changes net/ionic: preserve RX mode acro

[dpdk-dev] [PATCH V2 1/2] net/hns3: adjust printing MAC addresses in log

Here the printing of MAC addresses is adjusted. After the modification, only some bytes of the MAC address are displayed. Signed-off-by: Chengchang Tang Signed-off-by: Lijun Ou --- drivers/net/hns3/hns3_ethdev.c| 53 +++ drivers/net/hns3/hns3_ethdev.h

[dpdk-dev] [PATCH V2 0/2] hns3 fixes

Here series are fixes for hns3 PMD driver. Change from V1: 1. fix the comments given by Ferruh Yigit for 4/4 Lijun Ou (1): net/hns3: adjust printing MAC addresses in log Min Hu (Connor) (1): net/hns3: fix FEC state query drivers/net/hns3/hns3_ethdev.c| 93 --

[dpdk-dev] [PATCH V2 2/2] net/hns3: fix FEC state query

From: "Min Hu (Connor)" As FEC is not supported below 10 Gbps, CMD(HNS3_OPC_CONFIG_FEC_MODE) offered from Firmware read will return fail in 10 Gbps device. This patch will prevent read this CMD when below 10 Gbps, as this is non-sense. Fixes: 9bf2ea8dbc65 ("net/hns3: support FEC") Cc: sta...@dp

Re: [dpdk-dev] [PATCH v5 0/9] net/ionic: minor updates and documentation

On 12/10/2020 2:57 AM, Andrew Boyer wrote: These patches make some minor changes to the ionic PMD. Signed-off-by: Andrew Boyer --- v5: * Fix syntax error in .rst file v4: * Address additional reviewer comments v3: * Fixed up false-positives from codespell and gcc 8.3/9.3 v2: * Address Ferru

Re: [dpdk-dev] [PATCH v5 3/9] net/ionic: update documentation and MAINTAINERS

On 12/10/2020 2:57 AM, Andrew Boyer wrote: The UNMAINTAINED flag will be removed in a future patch. Signed-off-by: Andrew Boyer --- MAINTAINERS| 2 +- doc/guides/nics/features/ionic.ini | 1 + doc/guides/nics/ionic.rst | 13 +++-- 3 files changed,

Re: [dpdk-dev] [PATCH v2] net/axgbe: enabling VLAN support in axgbe

On 12/1/2020 2:18 PM, Somalapuram, Amaranath wrote: [AMD Official Use Only - Internal Distribution Only] -Original Message- From: Nandibasappa, Girish Sent: Tuesday, December 1, 2020 5:27 PM To: dev@dpdk.org Cc: Somalapuram, Amaranath Subject: [PATCH v2] net/axgbe: enabling VLAN suppor

Re: [dpdk-dev] [PATCH 3/4] net/hns3: adjust printing MAC addresses in log

在 2020/12/7 22:52, oulijun 写道: 在 2020/11/20 22:25, Ferruh Yigit 写道: On 11/20/2020 11:27 AM, Lijun Ou wrote: Here the printing of MAC addresses is adjusted. After the modification, only some bytes of the MAC address are displayed. Why logging only some bytes of the MAC address? I underst

[dpdk-dev] DPDK Release Status Meeting 10/12/2020

Meeting minutes of 10 December 2020 --- Agenda: * Release Dates * Subtrees * LTS * OvS * Opens Participants: * Arm * Broadcom * Debian/Microsoft * Intel * Nvidia * Red Hat Release Dates - * v21.02 dates * Proposal/V1:Sunday, 20 December 2020

Re: [dpdk-dev] 19.11.6 patches review and test

On Thu, 2020-12-10 at 10:07 +, Chen, BoX C wrote: > Hi Luca, > Update LTS 19.11.6 test result for Intel part. All passed except the known > issues. One new minor CVL bug was found which affected two test cases. Thank you! > * Intel(R) Testing > > # Basic Intel(R) NIC testing > * PF(i40e

Re: [dpdk-dev] 19.11.6 patches review and test

Hi Luca, Update LTS 19.11.6 test result for Intel part. All passed except the known issues. One new minor CVL bug was found which affected two test cases. * Intel(R) Testing # Basic Intel(R) NIC testing * PF(i40e):Passed known issue: create rule for set hash key, but rule create failed.

Re: [dpdk-dev] [PATCH v3 9/9] net/ionic: minor logging fixups

On 12/9/2020 7:26 PM, Andrew Boyer wrote: On Dec 9, 2020, at 10:42 AM, Ferruh Yigit wrote: On 12/9/2020 2:45 PM, Andrew Boyer wrote: On Dec 9, 2020, at 8:47 AM, Ferruh Yigit mailto:ferruh.yi...@intel.com>> wrote: On 12/4/2020 8:16 PM, Andrew Boyer wrote: Expose ionic_opcode_to_str() so it

Re: [dpdk-dev] [PATCH] Remove printf from signal handler.

> Hi > I don't have a good solution here. > Removing doesn't seem a good idea because there are many important alerts or > reminders in all of those function calls and they may be > called in other places too. > I think replacing with "write" can't solve the problem too. Because behavior > like

Re: [dpdk-dev] [PATCH v3 3/9] net/ionic: update documentation and MAINTAINERS

On 12/9/2020 7:05 PM, Andrew Boyer wrote: On Dec 9, 2020, at 12:15 PM, Ferruh Yigit wrote: On 12/9/2020 4:24 PM, Andrew Boyer wrote: On Dec 9, 2020, at 10:24 AM, Ferruh Yigit mailto:ferruh.yi...@intel.com>> wrote: On 12/9/2020 2:36 PM, Andrew Boyer wrote: Please respond to my questions th