[dpdk-dev] [PATCH v4 0/7] add eCPRI support in mlx5 driver

This patch set is to add the eCPRI support of flow rules in mlx5 PMD driver. Right now, only eCPRI over Ethernet layer (including VLAN) is supported. eCPRI over UDP will be supported in the future. If the flow rule to be inserted is not supported, PMD driver will return error to indicate the reason

[dpdk-dev] [PATCH v4 1/7] net/mlx5: add flow validation of eCPRI header

When creating a flow with eCPRI header item, the validation of it is mandatory. The detailed limitations are listed below: 1. Over Ether / VLAN, ethertype must be 0xAEFE. 2. No tunnel support is described in the specification now. 3. L3 layer is only supported when L4 is UDP, see #4. 4. Ove

[dpdk-dev] [PATCH v4 3/7] common/mlx5: add flex parser DevX structures

The structures and other definitions will be used for the dynamic flex parser creation via Devx command interface. These structures will be used as some some intermediate variables and input parameters for the parser creation API. It is better to keep all members consistent with the PRM definition

[dpdk-dev] [PATCH v4 5/7] net/mlx5: create and destroy eCPRI flex parser

eCPRI protocol has unified format layout for the variants, over ETH layer (including .1Q) and UDP layer. The common header of the message has 4 bytes fixed length, and the message payload layers are different based on the type field. Now only type #0, #2 and #5 will be supported, and 2 bytes are n

[dpdk-dev] [PATCH v4 4/7] common/mlx5: adding DevX command for flex parsers

In order to use dynamic flex parser to parse protocols that is not supported natively, two steps are needed. Firstly, creating the parse graph node. There are three parts of the flex parser: node, arc and sample. Node is the whole structure of a flex parser, when creating, the length of the protoc

[dpdk-dev] [PATCH v4 2/7] net/mlx5: add flow translation of eCPRI header

In the translation stage, the eCPRI item should be translated into the format that lower layer driver could use. All the fields that need to match must be in network byte order after translation, as well as the mask. Since the header in the item belongs to the network layers stack, and the input pa

[dpdk-dev] [PATCH v4 6/7] net/mlx5: add eCPRI flex parser capacity check

If the NIC or the FW does not support the dynamic flex parser, it will return error when trying to create the parser for eCRPI. Then it is hard to know the detail error reason of the failure. Before creating the parser node and the following usage of the parser, the capacity bit saved in the HCA_CA

[dpdk-dev] [PATCH v4 7/7] doc: update release notes and guides for eCPRI

Update the release notes of mlx5 PMD part by adding the support of eCPRI. Update the firmware configuration in the mlx5 NIC guide to support the usage of eCPRI. Signed-off-by: Bing Zhao Acked-by: Viacheslav Ovsiienko --- doc/guides/nics/mlx5.rst | 5 + doc/guides/rel_notes/rel

Re: [dpdk-dev] [PATCH] app/testpmd: fix the default RSS key configuration

> >> Subject: [dpdk-dev] [PATCH] app/testpmd: fix the default RSS key > >> configuration > >> > >> When an user runs a flow create cmd to configure an RSS rule > >> without specifying the empty rss actions in testpmd, this mean > >> that the flow gets the default RSS functions. However, the > >>

Re: [dpdk-dev] [PATCH] net/i40e: fix missed i40e filter pctype

Reviewed-by: Wei Zhao > -Original Message- > From: dev On Behalf Of Shougang Wang > Sent: Wednesday, July 15, 2020 4:08 PM > To: dev@dpdk.org > Cc: Xing, Beilei ; Guo, Jia ; Wang, > ShougangX ; sta...@dpdk.org > Subject: [dpdk-dev] [PATCH] net/i40e: fix missed i40e filter pctype > > The

Re: [dpdk-dev] [PATCH v2] vhost: fix missing null dev pointer check

> -Original Message- > From: Fu, Patrick > Sent: Thursday, July 16, 2020 11:38 PM > To: dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo > > Cc: Fu, Patrick > Subject: [PATCH v2] vhost: fix missing null dev pointer check > > From: Patrick Fu > > This patch adds the check of dev

Re: [dpdk-dev] [PATCH v1] vhost: add vq status check in async enqueue poll

> -Original Message- > From: Fu, Patrick > Sent: Thursday, July 16, 2020 11:30 PM > To: dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo > > Cc: Fu, Patrick > Subject: [PATCH v1] vhost: add vq status check in async enqueue poll > > From: Patrick Fu > > Vring should not be touch

[dpdk-dev] [PATCH v5 0/4] i40e FDIR update rate optimization

From: Chenmin Sun [PATCH v5 1/4] net/i40e: introducing the fdir guaranteed/shared space tracking [PATCH v5 2/4] net/i40e: FDIR flow memory management optimization [PATCH v5 2/4] net/i40e: move the i40e_get_outer_vlan to where it real needed [PATCH v5 2/4] net/i40e: FDIR update rate optimization

[dpdk-dev] [PATCH v5 1/4] net/i40e: introducing the fdir space tracking

From: Chenmin Sun This patch introduces a fdir flow management for guaranteed/shared space tracking. The fdir space is reported by the i40e_hw_capabilities.fd_filters_guaranteed and fd_filters_best_effort. The fdir space is managed by hardware and now is tracking in software. The management algor

[dpdk-dev] [PATCH v5 4/4] net/i40e: FDIR update rate optimization

From: Chenmin Sun This patch optimized the fdir update rate for i40e PF, by tracking whether the fdir rule being inserted into the guaranteed space or shared space. For the flows that are inserted to the guaranteed space, we assume that the insertion will always succeed as the hardware only repor

[dpdk-dev] [PATCH v5 3/4] net/i40e: move the i40e_get_outer_vlan to where it real needed

From: Chenmin Sun This patch moves the fetching the device tpid to where it really needs, rather than fetching it every time when entered the functions. This is because this operation costs too many cycles and it is used only when matching the ethernet header. Signed-off-by: Chenmin Sun --- dr

[dpdk-dev] [PATCH v5 2/4] net/i40e: FDIR flow memory management optimization

From: Chenmin Sun This patch allocated some memory pool for flow management to avoid calling rte_zmalloc/rte_free every time. This patch also improves the hash table operation. When adding/removing a flow, the software will directly add/delete it from the hash table. If any error occurs, it then

Re: [dpdk-dev] [PATCH V4 4/4] net/i40e: FDIR update rate optimization

Best Regards, Sun, Chenmin > -Original Message- > From: Wu, Jingjing > Sent: Thursday, July 16, 2020 9:57 PM > To: Sun, Chenmin ; Zhang, Qi Z > ; Xing, Beilei ; Wang, Haiyue > > Cc: dev@dpdk.org > Subject: RE: [PATCH V4 4/4] net/i40e: FDIR update rate optimization > > > [...] > > >

Re: [dpdk-dev] [PATCH v9 2/3] devtools: prevent use of rte atomic APIs in future patches

17/07/2020 07:08, Phil Yang: > In order to deprecate the rte_atomic and rte_smp barrier APIs, prevent > the patches from using these APIs and __sync builtins in new code. > > On x86 the __atomic_thread_fence(__ATOMIC_SEQ_CST) is quite expensive > for SMP case. Flag the new code which use __atomic_

[dpdk-dev] [PATCH v6 0/4] i40e FDIR update rate optimization

From: Chenmin Sun [PATCH v6 1/4] net/i40e: introducing the fdir guaranteed/shared space tracking [PATCH v6 2/4] net/i40e: FDIR flow memory management optimization [PATCH v6 2/4] net/i40e: move the i40e_get_outer_vlan to where it real needed [PATCH v6 2/4] net/i40e: FDIR update rate optimization

[dpdk-dev] [PATCH v6 4/4] net/i40e: FDIR update rate optimization

From: Chenmin Sun This patch optimized the fdir update rate for i40e PF, by tracking whether the fdir rule being inserted into the guaranteed space or shared space. For the flows that are inserted to the guaranteed space, we assume that the insertion will always succeed as the hardware only repor

[dpdk-dev] [PATCH v6 3/4] net/i40e: move the i40e_get_outer_vlan to where it real needed

From: Chenmin Sun This patch moves the fetching the device tpid to where it really needs, rather than fetching it every time when entered the functions. This is because this operation costs too many cycles and it is used only when matching the ethernet header. Signed-off-by: Chenmin Sun --- dr

[dpdk-dev] [PATCH v6 2/4] net/i40e: FDIR flow memory management optimization

From: Chenmin Sun This patch allocated some memory pool for flow management to avoid calling rte_zmalloc/rte_free every time. This patch also improves the hash table operation. When adding/removing a flow, the software will directly add/delete it from the hash table. If any error occurs, it then

[dpdk-dev] [PATCH v6 1/4] net/i40e: introducing the fdir space tracking

From: Chenmin Sun This patch introduces a fdir flow management for guaranteed/shared space tracking. The fdir space is reported by the i40e_hw_capabilities.fd_filters_guaranteed and fd_filters_best_effort. The fdir space is managed by hardware and now is tracking in software. The management algor

Re: [dpdk-dev] [PATCH v9 3/3] eal/atomic: add wrapper for C11 atomic thread fence

17/07/2020 07:08, Phil Yang: > Provide a wrapper for __atomic_thread_fence builtins to support > optimized code for __ATOMIC_SEQ_CST memory order for x86 platforms. Logically, it should be the patch 2. So you can recommend using this wrapper in the explanation of the actual patch 2.

Re: [dpdk-dev] [PATCH v9 3/3] eal/atomic: add wrapper for C11 atomic thread fence

Thomas Monjalon writes: > > Provide a wrapper for __atomic_thread_fence builtins to support > > optimized code for __ATOMIC_SEQ_CST memory order for x86 platforms. > > Logically, it should be the patch 2. > So you can recommend using this wrapper in the explanation > of the actual patch 2. Inde

Re: [dpdk-dev] [PATCH v2] eal: change the log level for test assert macro

On Thu, Jul 16, 2020 at 8:39 PM Honnappa Nagarahalli wrote: > > Change the log level for RTE_TEST_ASSERT macro to error to help > log errors while running test cases. > > Suggested-by: David Marchand > Signed-off-by: Honnappa Nagarahalli > Acked-by: Aaron Conole > Acked-by: Lukasz Wojciechowski

Re: [dpdk-dev] Random failure in service_autotest

On Wed, Jul 15, 2020 at 12:41 PM Ferruh Yigit wrote: > > On 7/15/2020 11:14 AM, David Marchand wrote: > > Hello Harry and guys who touched the service code recently :-) > > > > I spotted a failure for the service UT in Travis: > > https://travis-ci.com/github/ovsrobot/dpdk/jobs/361097992#L18697 >

[dpdk-dev] [Bug 509] [dpdk-20.08] make failed with cflags -O1

https://bugs.dpdk.org/show_bug.cgi?id=509 Bug ID: 509 Summary: [dpdk-20.08] make failed with cflags -O1 Product: DPDK Version: 20.08 Hardware: x86 OS: Linux Status: UNCONFIRMED Severity: normal P

Re: [dpdk-dev] [PATCH 1/1] bus/fslmc: fix memory leak in secondary process

On Thu, Jul 9, 2020 at 12:40 PM wangyunjian wrote: > > From: Yunjian Wang > > In fslmc_process_mcp(), we allocate memory for 'dev_name' but not released > before return in secondary process. dev_name is not used anymore since a69f79300262 ("bus/fslmc: support multi VFIO group") We can remove it

[dpdk-dev] [RFC PATCH] ethdev: add a new flow action of queue range

From: Chengwen Feng This patch adds a new flow action of queue range, which was used to assign packets to a continuous queue range. Current FD (flow director) provide a useful means to assign packets to a target queue. But it has the following shortage: it can only route to one queue, and there

Re: [dpdk-dev] [dpdk-stable] [PATCH] metrics: fix installation of metrics header

On Wed, Jul 15, 2020 at 1:32 PM David Marchand wrote: > On Tue, Jul 14, 2020 at 2:43 PM Ciara Power wrote: > > > > If Jansson was found, the headers list is overwritten when including > > rte_metrics_telemetry.h, which prevents rte_metrics.h from being > > installed. This is now fixed to add to h

Re: [dpdk-dev] [PATCH 1/1] bus/fslmc: fix memory leak in secondary process

> -Original Message- > From: David Marchand [mailto:david.march...@redhat.com] > Sent: Friday, July 17, 2020 5:21 PM > To: wangyunjian ; Hemant Agrawal > > Cc: dev ; Sachin Saxena ; Lilijun > (Jerry) ; xudingke ; dpdk > stable > Subject: Re: [dpdk-dev] [PATCH 1/1] bus/fslmc: fix memory le

Re: [dpdk-dev] [PATCH v9 2/3] devtools: prevent use of rte atomic APIs in future patches

Thomas Monjalon wrties: > > In order to deprecate the rte_atomic and rte_smp barrier APIs, prevent > > the patches from using these APIs and __sync builtins in new code. > > > > On x86 the __atomic_thread_fence(__ATOMIC_SEQ_CST) is quite > expensive > > for SMP case. Flag the new code which use

Re: [dpdk-dev] small error in rte_eth_bond_api.c

Hello! I've found a small error in .../drivers/net/bonding/rte_eth_bond_api.c : Func rte_eth_bond_create: ret = rte_vdev_init(name, devargs); if (ret) return -ENOMEM; So, we get ENOMEM error regardless of the actual error code. This code would be more applicable. ret = rte_vdev_init(name, de

[dpdk-dev] [PATCH v10 1/3] doc: add optimizations using C11 atomic builtins

Add information about possible optimizations using C11 atomic builtins. Signed-off-by: Phil Yang Signed-off-by: Honnappa Nagarahalli Reviewed-by: Honnappa Nagarahalli --- doc/guides/prog_guide/writing_efficient_code.rst | 59 +++- 1 file changed, 58 insertions(+), 1 deletio

[dpdk-dev] [PATCH v10 0/3] generic rte atomic APIs deprecate proposal

DPDK provides generic rte_atomic APIs to do several atomic operations. These APIs are using the deprecated __sync builtins and enforce full memory barriers on aarch64. However, full barriers are not necessary in many use cases. In order to address such use cases, C language offers C11 atomic APIs.

[dpdk-dev] [PATCH v10 3/3] devtools: prevent use of rte atomic APIs in future patches

In order to deprecate the rte_atomic and rte_smp barrier APIs[1], prevent the patches from using these APIs and __sync builtins in new code. Please use __atomic builtins instead of __sync builtins, rte_atomicNN_xxx and rte_smp_[r/w]mb APIs. On x86 the __atomic_thread_fence(__ATOMIC_SEQ_CST) is qui

[dpdk-dev] [PATCH v10 2/3] eal/atomic: add wrapper for C11 atomic thread fence

Provide a wrapper for __atomic_thread_fence builtins to support optimized code for __ATOMIC_SEQ_CST memory order for x86 platforms. Suggested-by: Honnappa Nagarahalli Signed-off-by: Phil Yang Reviewed-by: Ola Liljedahl Acked-by: Konstantin Ananyev --- lib/librte_eal/arm/include/rte_atomic_32.

[dpdk-dev] [PATCH v3 01/13] regex/mlx5: add RegEx PMD layer and mlx5 driver

From: Yuval Avnery This commit introduce the RegEx poll mode drivers class, and adds Mellanox RegEx PMD. Signed-off-by: Yuval Avnery Signed-off-by: Ori Kam --- v3: * Address ML comments. v2: * Add docs. --- .gitignore| 1 + MAINTAINERS

[dpdk-dev] [PATCH v3 00/13] add Mellanox RegEx PMD

This patch series introduce the Mellanox BF2 RegEx PMD. Mellanox BF2 RegEx PMD implement the API defined in the regexdev lib [1]. This PMD allows a DPDK application to offload the RegEx functionality to Mellanox BF2 RegEx engine. [1] https://patches.dpdk.org/cover/72792/ v3: * Reorder and merg

[dpdk-dev] [PATCH v3 02/13] regex/mlx5: add log utils

From: Yuval Avnery Add the MLX5_REGEX_LOG macro which should be used for logs. Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/mlx5_regex.c | 5 + drivers/regex/mlx5/mlx5_regex_utils.h | 19 +++ 3 fi

[dpdk-dev] [PATCH v3 06/13] regex/mlx5: add configure function

This commit implements the configure function. This function is responsible to configure the RegEx engine. Signed-off-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.c | 2 + drivers/regex/mlx5/mlx5_regex.h | 15 +++ drivers/regex/mlx5/mlx5_rxp.c | 235 +++-

[dpdk-dev] [PATCH v3 05/13] regex/mlx5: add engine status check

This commit checks the engine status. Signed-off-by: Ori Kam --- drivers/common/mlx5/mlx5_prm.h | 91 ++ drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/meson.build | 1 + drivers/regex/mlx5/mlx5_regex.c | 28 +++ drivers/regex/mlx5/mlx5_regex.h

[dpdk-dev] [PATCH v3 03/13] regex/mlx5: add probe function

This commit adds the probe function to the RegEx PMD. Signed-off-by: Parav Pandit Signed-off-by: Ori Kam --- drivers/common/mlx5/mlx5_devx_cmds.c | 3 + drivers/common/mlx5/mlx5_devx_cmds.h | 2 + drivers/common/mlx5/mlx5_prm.h | 9 +- drivers/regex/mlx5/Makefile | 3 + d

[dpdk-dev] [PATCH v3 04/13] regex/mlx5: add get info function

This commit adds the get info function. Signed-off-by: Ori Kam --- drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/meson.build | 1 + drivers/regex/mlx5/mlx5_regex.c | 4 +++- drivers/regex/mlx5/mlx5_regex.h | 5 + drivers/regex/mlx5/mlx5_rxp.c | 29 +

[dpdk-dev] [PATCH v3 07/13] regex/mlx5: add program rules support

From: Francis Kelly This commit introduce the ability to program rules to the RegEx engine. Signed-off-by: Francis Kelly Acked-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.c | 34 ++ drivers/regex/mlx5/mlx5_regex.h | 54 ++- drivers/regex/mlx5/mlx5_regex_devx.c | 67 +++ drivers

[dpdk-dev] [PATCH v3 09/13] regex/mlx5: add send queue support

This commit introduce the SQ creation. The SQ is used for enqueuing a job. In order to support out of order matches, we create number of SQ per one applicaiton QP. Signed-off-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.h | 2 + drivers/regex/mlx5/mlx5_regex_control.c | 168 +

[dpdk-dev] [PATCH v3 12/13] regex/mlx5: implement dequeue function

From: Yuval Avnery Implement dequeue function for the regex API. Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/common/mlx5/mlx5_prm.h | 10 +++ drivers/regex/mlx5/mlx5_regex.c | 1 + drivers/regex/mlx5/mlx5_regex.h | 4 ++ drivers/regex/mlx5/mlx5_r

[dpdk-dev] [PATCH v3 11/13] regex/mlx5: add enqueue implementation

From: Yuval Avnery Will look for a free SQ to send the job on. doorbell will be given when sq is full, or no more jobs on the burst. Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.c | 1 + drivers/regex/mlx5/mlx5_regex.h | 6 ++ drivers/r

[dpdk-dev] [PATCH v3 10/13] regex/mlx5: fastpath setup

From: Yuval Avnery Allocate and register input/output buffers and metadata. Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/common/mlx5/mlx5_prm.h | 36 ++ drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/meson.build | 1 + drivers/rege

[dpdk-dev] [PATCH v3 08/13] regex/mlx5: add completion queue creation

This commit adds the creation of CQ Signed-off-by: Ori Kam --- drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/meson.build | 1 + drivers/regex/mlx5/mlx5_regex.c | 1 + drivers/regex/mlx5/mlx5_regex.h | 4 +- drivers/regex/mlx5/mlx5_regex_contro

[dpdk-dev] [PATCH v3 13/13] regex/mlx5: add start stop functions

Add the start, stop and close functions. In current implementation they are empty functions and are only exists in order that when called from rte level, the function will return with success code. Signed-off-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.c | 21 + drivers/reg

[dpdk-dev] [PATCH v8 0/4] eal: add WC store functions

Implement 2 new functions that will enable write combining stores depending on architecture. The functions are provided as a generic stub and a x86 specific implementation. The reason to implement these functions is to improve performance by reducing the overhead associated with regular mmio write

[dpdk-dev] [PATCH v8 1/4] eal: add WC store functions

Add rte_write32_wc and rte_write32_wc_relaxed functions that implement 32bit stores using write combining memory protocol. Provided generic stubs and x86 implementation. Signed-off-by: Radu Nicolau Acked-by: Bruce Richardson --- lib/librte_eal/arm/include/rte_io_64.h | 12 +++ lib/librte_e

[dpdk-dev] [PATCH v8 4/4] net/ixgbe: use WC store to update queue tail registers

Performance improvement: use a write combining store instead of a regular mmio write to update queue tail registers. Signed-off-by: Radu Nicolau --- drivers/net/ixgbe/base/ixgbe_osdep.h | 6 ++ drivers/net/ixgbe/ixgbe_rxtx.c | 12 ++-- drivers/net/ixgbe/ixgbe_rxtx_vec_sse.

[dpdk-dev] [PATCH v8 3/4] common/qat: use WC store to update queue tail registers

Performance improvement: use a write combining store instead of a regular mmio write to update queue tail registers. Signed-off-by: Radu Nicolau --- drivers/common/qat/qat_adf/adf_transport_access_macros.h | 6 -- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/common/q

[dpdk-dev] [PATCH v8 2/4] net/i40e: use WC store to update queue tail registers

Performance improvement: use a write combining store instead of a regular mmio write to update queue tail registers. Signed-off-by: Radu Nicolau Acked-by: Bruce Richardson --- drivers/net/i40e/base/i40e_osdep.h| 5 + drivers/net/i40e/i40e_rxtx.c | 8 drivers/net/i40e/i

[dpdk-dev] [PATCH v2] bus/fslmc: fix memory leak in secondary process

From: Yunjian Wang In fslmc_process_mcp(), we allocate memory for 'dev_name' but not released before return in secondary process. And it is not used since commit a69f79300262 ("bus/fslmc: support multi VFIO group"), so it can be removed. Fixes: e55d0494ab98 ("bus/fslmc: support secondary process

[dpdk-dev] [PATCH v4 03/13] regex/mlx5: add probe function

This commit adds the probe function to the RegEx PMD. Signed-off-by: Parav Pandit Signed-off-by: Ori Kam --- drivers/common/mlx5/mlx5_devx_cmds.c | 3 + drivers/common/mlx5/mlx5_devx_cmds.h | 2 + drivers/common/mlx5/mlx5_prm.h | 9 +- drivers/regex/mlx5/Makefile | 3 + d

[dpdk-dev] [PATCH v4 01/13] regex/mlx5: add RegEx PMD layer and mlx5 driver

From: Yuval Avnery This commit introduce the RegEx pull mode drivers class, and adds Mellanox RegEx PMD. Signed-off-by: Yuval Avnery Signed-off-by: Ori Kam --- v3: * Address ML comments. v2: * Add docs. --- .gitignore| 1 + MAINTAINERS

[dpdk-dev] [PATCH v4 02/13] regex/mlx5: add log utils

From: Yuval Avnery Add the MLX5_REGEX_LOG macro which should be used for error prints. Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/mlx5_regex.c | 5 + drivers/regex/mlx5/mlx5_regex_utils.h | 19 +

[dpdk-dev] [PATCH v4 00/13] add Mellanox RegEx PMD

This patch series introduce the Mellanox BF2 RegEx PMD. Mellanox BF2 RegEx PMD implement the API defined in the regexdev lib [1]. This PMD allows a DPDK application to offload the RegEx functionality to Mellanox BF2 RegEx engine. [1] https://patches.dpdk.org/cover/72792/ v4: * Typo fix in comm

[dpdk-dev] [PATCH v4 04/13] regex/mlx5: add get info function

This commit adds the get info function. Signed-off-by: Ori Kam --- drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/meson.build | 1 + drivers/regex/mlx5/mlx5_regex.c | 4 +++- drivers/regex/mlx5/mlx5_regex.h | 5 + drivers/regex/mlx5/mlx5_rxp.c | 29 +

[dpdk-dev] [PATCH v4 05/13] regex/mlx5: add engine status check

This commit checks the engine status. Signed-off-by: Ori Kam --- drivers/common/mlx5/mlx5_prm.h | 91 ++ drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/meson.build | 1 + drivers/regex/mlx5/mlx5_regex.c | 28 +++ drivers/regex/mlx5/mlx5_regex.h

[dpdk-dev] [PATCH v4 09/13] regex/mlx5: add send queue support

This commit introduce the SQ creation. The SQ is used for enqueuing a job. In order to support out of order matches, we create number os SQ per one application QP. Signed-off-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.h | 2 + drivers/regex/mlx5/mlx5_regex_control.c | 168 +

[dpdk-dev] [PATCH v4 08/13] regex/mlx5: add completion queue creation

This commit adds the creation of CQ Signed-off-by: Ori Kam --- drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/meson.build | 1 + drivers/regex/mlx5/mlx5_regex.c | 1 + drivers/regex/mlx5/mlx5_regex.h | 4 +- drivers/regex/mlx5/mlx5_regex_contro

[dpdk-dev] [PATCH v4 07/13] regex/mlx5: add program rules support

From: Francis Kelly This commit introduce the ability to program rules to the RegEx engine. Signed-off-by: Francis Kelly Acked-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.c | 34 ++ drivers/regex/mlx5/mlx5_regex.h | 52 ++- drivers/regex/mlx5/mlx5_regex_devx.c | 67 +++ drivers

[dpdk-dev] [PATCH v4 06/13] regex/mlx5: add configure function

This commit implements the configure function. This function is responsible to configure the RegEx engine. Signed-off-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.c | 2 + drivers/regex/mlx5/mlx5_regex.h | 15 +++ drivers/regex/mlx5/mlx5_rxp.c | 235 +++-

[dpdk-dev] [PATCH v4 11/13] regex/mlx5: add enqueue implementation

From: Yuval Avnery Will look for a free SQ to send the job on. doorbell will be given when sq is full, or no more jobs on the burst. Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.c | 1 + drivers/regex/mlx5/mlx5_regex.h | 6 ++ drivers/r

[dpdk-dev] [PATCH v4 12/13] regex/mlx5: implement dequeue function

From: Yuval Avnery Implement dequeue function for the regex API. Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/common/mlx5/mlx5_prm.h | 10 +++ drivers/regex/mlx5/mlx5_regex.c | 1 + drivers/regex/mlx5/mlx5_regex.h | 4 ++ drivers/regex/mlx5/mlx5_r

[dpdk-dev] [PATCH v4 13/13] regex/mlx5: add start stop functions

Add the start, stop and close functions. In current implementation they are empty functions and are only exists in order that when called from rte level, the function will return with success code. Signed-off-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex.c | 21 + drivers/reg

[dpdk-dev] [PATCH v4 10/13] regex/mlx5: fastpath setup

From: Yuval Avnery Allocated and register input/output buffers and metadata. Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/common/mlx5/mlx5_prm.h | 36 ++ drivers/regex/mlx5/Makefile | 1 + drivers/regex/mlx5/meson.build | 1 + drivers/reg

[dpdk-dev] [PATCH] net/qede: remove dead code

From: Yunjian Wang This patch fixes (Logically dead code) coverity issue. Coverity issue: 261777, 261778 Fixes: dd28bc8c6ef4 ("net/qede: fix VF port creation sequence") Cc: sta...@dpdk.org Signed-off-by: Yunjian Wang --- drivers/net/qede/qede_rxtx.c | 4 1 file changed, 4 deletions(-) d

Re: [dpdk-dev] [PATCH v8 4/4] net/ixgbe: use WC store to update queue tail registers

> Performance improvement: use a write combining store > instead of a regular mmio write to update queue tail > registers. > > Signed-off-by: Radu Nicolau > --- > drivers/net/ixgbe/base/ixgbe_osdep.h | 6 ++ > drivers/net/ixgbe/ixgbe_rxtx.c | 12 ++-- > drivers/net/ixgbe

Re: [dpdk-dev] [PATCH V2] net/bonding: delete redundant code

Reviewed-by: Wei Hu (Xavier) On 2020/7/4 9:22, Wei Hu (Xavier) wrote: On 2020/7/4 9:15, 197020...@qq.com wrote: From: pandongyang <197020...@qq.com> The function valid_bonded_port_id() has already contains function rte_eth_dev_is_valid_port(), so delete redundant check. Fixes: 588ae95e798

[dpdk-dev] [PATCH] event/dpaa: remove dead code

From: Yunjian Wang This patch fixes (Logically dead code) coverity issue. Coverity issue: 323495 Fixes: 77b5311d0ece ("event/dpaa: support select based event") Cc: sta...@dpdk.org Signed-off-by: Yunjian Wang --- drivers/event/dpaa/dpaa_eventdev.c | 4 +--- 1 file changed, 1 insertion(+), 3 de

Re: [dpdk-dev] [PATCH v3 1/8] net/dpaa: add support for fmlib in dpdk

On 7/11/2020 9:17 AM, Hemant Agrawal wrote: > DPAA platorm MAC interface is known as FMAN i.e. Frame Manager. > There are two ways to control it. > 1. Statically configure the queues and classification rules before the > start of the application using FMC tool. > 2. Dynamically configure it within

Re: [dpdk-dev] [PATCH] pmd_bond: fix mac address update for ACTIVE_BACKUP, TLB and ALB modes

Hi, Sergey Lvov Thanks for you reporting issues, The identical modification had been applied to dpdk-next-net. http://patches.dpdk.org/patch/68742/ repo: http://dpdk.org/git/next/dpdk-next-net f109ce2c5c6b114f533ffcb69460385ac04db215 net/bonding: fix MAC address whe

Re: [dpdk-dev] [PATCH] eal: fix memory leak in uevent parse and process

Is there any ideas on this bug? Ping for review, please. Yunjian > -Original Message- > From: wangyunjian > Sent: Saturday, May 23, 2020 6:52 PM > To: dev@dpdk.org > Cc: Lilijun (Jerry) ; xudingke > ; wangyunjian ; > sta...@dpdk.org > Subject: [dpdk-dev] [PATCH] eal: fix memory leak in ue

Re: [dpdk-dev] [PATCH v5 2/2] doc: announce deprecation of refcnt atomic member

On Fri, Jul 17, 2020 at 12:36:51PM +0800, Phil Yang wrote: > refcnt_atomic member in structures rte_mbuf and rte_mbuf_ext_shared_info > will be deprecated in 20.11 release. > > Suggested-by: Honnappa Nagarahalli > Signed-off-by: Phil Yang > Acked-by: Konstantin Ananyev Acked-by: Olivier Matz

Re: [dpdk-dev] [PATCH v2] vhost: support async copy free segmentations

On 7/17/2020 4:21 AM, Xia, Chenbo wrote: > >> -Original Message- >> From: Fu, Patrick >> Sent: Wednesday, July 15, 2020 7:15 PM >> To: dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo >> >> Cc: Fu, Patrick ; Wang, Yinan >> Subject: [PATCH v2] vhost: support async copy free segmenta

Re: [dpdk-dev] [PATCH v5 2/3] test/test_telemetry_data: add unit tests for data to JSON

On Wed, Jul 15, 2020 at 01:29:34PM +0100, Ciara Power wrote: > From: Louise Kilheeney > > This patch adds tests for verifying telemetry data structures are > converted to JSON as expected. Both flat and recursive data structures > are tested, for all possible value types. > > Signed-off-by: Loui

[dpdk-dev] [PATCH] lib/librte_eal: support SVE flag on ARM64

From: Chengwen Feng SVE is the next-generation SIMD extension of the ARMv8-A AArch64 instruction set. The related marco definition can be found in linux kernel: arch/arm64/include/uapi/asm/hwcap.h This patch supports getting cpu SVE feature on ARM64 platform. Signed-off-by: Chengwen Feng Sig

Re: [dpdk-dev] [PATCH] event/dpaa: remove dead code

Acked-by: Hemant Agrawal -Original Message- From: dev On Behalf Of wangyunjian Sent: Friday, July 17, 2020 5:02 PM To: dev@dpdk.org Cc: Hemant Agrawal ; Nipun Gupta ; jerry.lili...@huawei.com; xudin...@huawei.com; Yunjian Wang ; sta...@dpdk.org Subject: [dpdk-dev] [PATCH] event/dpaa: r

[dpdk-dev] [PATCH v3] examples/ipsec-secgw: enable rte_flow based packet distribution

From: Anoob Joseph RTE_FLOW API allows hardware parsing and steering of packets to specific queues which helps in distributing ingress traffic across various cores. Adding 'flow' rules allows user to specify the distribution required. Signed-off-by: Anoob Joseph Acked-by: Akhil Goyal --- v3: *

Re: [dpdk-dev] [v4 3/3] doc: update vm_power_manager cmdline options in doc

14/07/2020 18:02, Rory Sexton: > Updating the vm_power_manager docs to reflect changes made in > previous patches in set. For info, the doc must be updated atomically with the code.

Re: [dpdk-dev] [PATCH v1] vhost: set zmbufs to NULL when freed

On 7/17/2020 4:19 AM, Xia, Chenbo wrote: > >> -Original Message- >> From: Fu, Patrick >> Sent: Wednesday, July 15, 2020 11:59 PM >> To: dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo >> >> Cc: Wang, Yinan ; Fu, Patrick >> Subject: [PATCH v1] vhost: set zmbufs to NULL when freed >

Re: [dpdk-dev] [v4 1/3] examples/vm_power_manager: Make branch ratio threshold per core

15/07/2020 17:08, Pattan, Reshma: > From: Rory Sexton > > > > This modification allows for the branch ratio threshold to be set per core > > rather > > than system wide. This gives greater flexibility to the branch ration > > monitoring > > Small typo ration ->ratio > > > Signed-off-by: Rory S

Re: [dpdk-dev] [PATCH 0/9] python2 deprecation notice

On Thu, Jul 16, 2020 at 02:01:21PM -0700, Stephen Hemminger wrote: > On Thu, 16 Jul 2020 16:44:29 +0200 > Robin Jarry wrote: > > > 2020-07-13, Bruce Richardson: > > > In the absense of a "proper" solution, is the simplest option to > > > change the shebangs to all be python3, but leave the python

Re: [dpdk-dev] [dpdk-stable] [PATCH V2] net/bonding: delete redundant code

On 7/17/2020 12:22 PM, Wei Hu (Xavier) wrote: > Reviewed-by: Wei Hu (Xavier) > > > On 2020/7/4 9:22, Wei Hu (Xavier) wrote: >> >> >> On 2020/7/4 9:15, 197020...@qq.com wrote: >>> From: pandongyang <197020...@qq.com> >>> >>> The function valid_bonded_port_id() has already contains function >>> rt

Re: [dpdk-dev] [PATCH 20.11 v2] raw/ioat: add a flag to control copying handle parameters

On Wed, Jul 15, 2020 at 02:16:15AM +, Cheng Jiang wrote: > Add a flag which controls whether rte_ioat_enqueue_copy > and rte_ioat_completed_copies function should process > handle parameters to improve the performance when handle > parameters are not necessary to use. This is targeting > 20.11

Re: [dpdk-dev] [PATCH v6 0/4] i40e FDIR update rate optimization

> -Original Message- > From: Sun, Chenmin > Sent: Saturday, July 18, 2020 1:37 AM > To: Zhang, Qi Z ; Xing, Beilei ; > Wu, Jingjing ; Wang, Haiyue > Cc: dev@dpdk.org; Sun, Chenmin > Subject: [PATCH v6 0/4] i40e FDIR update rate optimization > > From: Chenmin Sun > > [PATCH v6 1/4]

Re: [dpdk-dev] [PATCH v3 1/2] power: fix power management env detection

On Tue, Jul 14, 2020 at 11:30:01AM +0100, Anatoly Burakov wrote: > Anything coming from sysfs has a newline at the end. Cut it off before > comparing the strings. > > Fixes: 20ab67608a39 ("power: add environment capability probing") > > Signed-off-by: Anatoly Burakov > Acked-by: David Hunt > --

Re: [dpdk-dev] [PATCH v4 0/7] add eCPRI support in mlx5 driver

Hi, > -Original Message- > From: Bing Zhao > Sent: Friday, July 17, 2020 10:12 AM > To: Ori Kam ; Slava Ovsiienko > > Cc: Raslan Darawsheh ; Matan Azrad > ; dev@dpdk.org; Netanel Gonen > > Subject: [PATCH v4 0/7] add eCPRI support in mlx5 driver > > This patch set is to add the eCPRI s

Re: [dpdk-dev] [PATCH v4 24/27] app/test-XXX: replace reference to master/slave

On 01-Jul-20 9:23 PM, Stephen Hemminger wrote: Use new terminology for lcore's Signed-off-by: Stephen Hemminger --- Acked-by: Anatoly Burakov -- Thanks, Anatoly

Re: [dpdk-dev] [PATCH v4 26/27] memif: replace master/slave with server/client

On 01-Jul-20 9:23 PM, Stephen Hemminger wrote: The names master and slave have no place inside this driver. It is really a traditional client server model, so use those names. Signed-off-by: Stephen Hemminger --- Isn't this an externally visible change? Or do we not provide any guarantees fo

Re: [dpdk-dev] [PATCH 3/3] doc: add missing SPDX license tags

On Tue, Jul 14, 2020 at 04:50:11PM -0700, Stephen Hemminger wrote: > A few files in doc directory were missing license tag info. > > Signed-off-by: Stephen Hemminger > --- For Intel copyright parts: Acked-by: Bruce Richardson > doc/guides/custom.css| 1 + > doc/gui

Re: [dpdk-dev] [PATCH v1] vhost: add vq status check in async enqueue poll

On 7/17/2020 9:09 AM, Xia, Chenbo wrote: > >> -Original Message- >> From: Fu, Patrick >> Sent: Thursday, July 16, 2020 11:30 PM >> To: dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo >> >> Cc: Fu, Patrick >> Subject: [PATCH v1] vhost: add vq status check in async enqueue poll >> >

Re: [dpdk-dev] [PATCH v2] vhost: fix missing null dev pointer check

On 7/17/2020 9:08 AM, Xia, Chenbo wrote: > >> -Original Message- >> From: Fu, Patrick >> Sent: Thursday, July 16, 2020 11:38 PM >> To: dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo >> >> Cc: Fu, Patrick >> Subject: [PATCH v2] vhost: fix missing null dev pointer check >> >> From:

  1   2   3   >