Re: [dpdk-dev] [RFC 0/3] Vectorize packed ring RX path with NEON

Hi Maxime, > -Original Message- > From: Maxime Coquelin > Sent: Monday, October 5, 2020 3:34 PM > To: Joyce Kong > Cc: jer...@marvell.com; dev@dpdk.org; nd ; Honnappa > Nagarahalli ; Ruifeng Wang > ; Phil Yang > Subject: Re: [RFC 0/3] Vectorize packed ring RX path with NEON > > Hi Joyc

Re: [dpdk-dev] [PATCH 0/4] Add Marvell OCTEON TX2 regex driver

Kind reminder to all maintainers, please review and ack/comment. > -Original Message- > From: g...@marvell.com > Sent: Tuesday, September 1, 2020 3:25 PM > To: Jerin Jacob Kollanukkaran ; Nithin Kumar > Dabilpuram ; tho...@monjalon.net; > m...@ashroe.eu; nhor...@tuxdriver.com; bruce.richa

Re: [dpdk-dev] [PATCH v2 0/5] vhost add vectorized data path

> -Original Message- > From: Maxime Coquelin > Sent: Tuesday, October 6, 2020 9:34 PM > To: Liu, Yong ; Xia, Chenbo ; > Wang, Zhihong > Cc: dev@dpdk.org > Subject: Re: [PATCH v2 0/5] vhost add vectorized data path > > Hi, > > On 9/21/20 8:48 AM, Marvin Liu wrote: > > Packed ring forma

[dpdk-dev] [PATCH v3 2/3] event/octeontx2: add crypto adapter framework

The crypto adapter callback functions and associated data structures are added. Signed-off-by: Ankur Dwivedi --- drivers/crypto/octeontx2/meson.build | 1 + .../octeontx2/otx2_cryptodev_hw_access.h | 12 +++ .../crypto/octeontx2/otx2_cryptodev_mbox.h| 2 + drivers/crypto/octe

[dpdk-dev] [PATCH v3 3/3] event/octeontx2: add crypto adapter datapath

In the op new mode of crypto adapter, the completed crypto operation is submitted to the event device by the OCTEON TX2 crypto PMD. During event device dequeue the result of crypto operation is checked. Signed-off-by: Ankur Dwivedi --- drivers/common/cpt/cpt_common.h | 1 + driver

[dpdk-dev] [PATCH v3 1/3] crypto/octeontx2: move functions to helper file

Some functions are common across cryptodev pmd and the event crypto adapter. This patch moves them into a helper file. Signed-off-by: Ankur Dwivedi --- drivers/crypto/octeontx2/otx2_cryptodev_ops.c | 65 +--- .../octeontx2/otx2_cryptodev_ops_helper.h | 74 +++ 2 f

[dpdk-dev] [PATCH v3 0/3] event/octeontx2: add support for event crypto adapter

This patch series adds support for event crypto adapter in op new mode in the OCTEON TX2 event PMD. The functionality has been verified with event crypto adapter test application. Build with meson and ninja is supported. v3: * In the "event/octeontx2: add crypto adapter framework" patch, the fol

[dpdk-dev] [PATCH v5 15/15] distributor: fix clearing returns buffer

The patch clears distributors returns buffer in clear_returns() by setting start and count to 0. Fixes: 775003ad2f96 ("distributor: add new burst-capable library") Cc: david.h...@intel.com Cc: sta...@dpdk.org Signed-off-by: Lukasz Wojciechowski --- lib/librte_distributor/rte_distributor.c | 2 +

[dpdk-dev] [PATCH v5 13/15] test/distributor: add test with packets marking

All of the former tests analyzed only statistics of packets processed by all workers. The new test verifies also if packets are processed on workers as expected. Every packets processed by the worker is marked and analyzed after it is returned to distributor. This test allows finding issues in mat

[dpdk-dev] [PATCH v5 12/15] distributor: fix scalar matching

Fix improper indexes while comparing tags. In the find_match_scalar() function: * j iterates over flow tags of following packets; * w iterates over backlog or in flight tags positions. Fixes: 775003ad2f96 ("distributor: add new burst-capable library") Cc: david.h...@intel.com Cc: sta...@dpdk.org

[dpdk-dev] [PATCH v5 14/15] distributor: fix flushing in flight packets

rte_distributor_flush() is using total_outstanding() function to calculate if it should still wait for processing packets. However in burst mode only backlog packets were counted. This patch fixes that issue by counting also in flight packets. There are also sum fixes to properly keep count of in

[dpdk-dev] [PATCH v5 10/15] distributor: align API documentation with code

After introducing burst API there were some artefacts in the API documentation from legacy single API. Also the rte_distributor_poll_pkt() function return values mismatched the implementation. Fixes: c0de0eb82e40 ("distributor: switch over to new API") Cc: david.h...@intel.com Cc: sta...@dpdk.org

[dpdk-dev] [PATCH v5 11/15] test/distributor: replace delays with spin locks

Instead of making delays in test code and waiting for worker hopefully to reach proper states, synchronize worker shutdown test cases with spin lock on atomic variable. Fixes: c0de0eb82e40 ("distributor: switch over to new API") Cc: david.h...@intel.com Cc: sta...@dpdk.org Signed-off-by: Lukasz W

[dpdk-dev] [PATCH v5 08/15] test/distributor: fix freeing mbufs

Sanity tests with mbuf alloc and shutdown tests assume that mbufs passed to worker cores are freed in handlers. Such packets should not be returned to the distributor's main core. The only packets that should be returned are the packets send after completion of the tests in quit_workers function.

[dpdk-dev] [PATCH v5 09/15] test/distributor: collect return mbufs

During quit_workers function distributor's main core processes some packets to wake up pending worker cores so they can quit. As quit_workers acts also as a cleanup procedure for next test case it should also collect these packages returned by workers' handlers, so the cyclic buffer with returned p

[dpdk-dev] [PATCH v5 06/15] test/distributor: synchronize lcores statistics

Statistics of handled packets are cleared and read on main lcore, while they are increased in workers handlers on different lcores. Without synchronization occasionally showed invalid values. This patch uses atomic acquire/release mechanisms to synchronize. Fixes: c3eabff124e6 ("distributor: add

[dpdk-dev] [PATCH v5 05/15] test/distributor: fix shutdown of busy worker

The sanity test with worker shutdown delegates all bufs to be processed by a single lcore worker, then it freezes one of the lcore workers and continues to send more bufs. The freezed core shuts down first by calling rte_distributor_return_pkt(). The test intention is to verify if packets assigned

[dpdk-dev] [PATCH v5 07/15] distributor: fix return pkt calls in single mode

In the single legacy version of the distributor synchronization requires continues exchange of buffers between distributor and workers. Empty buffers are sent if only handshake synchronization is required. However calls to the rte_distributor_return_pkt() with 0 buffers in single mode were ignored

[dpdk-dev] [PATCH v5 03/15] distributor: do not use oldpkt when not needed

rte_distributor_request_pkt and rte_distributor_get_pkt dereferenced oldpkt parameter when in RTE_DIST_ALG_SINGLE even if number of returned buffers from worker to distributor was 0. This patch passes NULL to the legacy API when number of returned buffers is 0. This allows passing NULL as oldpkt p

[dpdk-dev] [PATCH v5 02/15] distributor: fix handshake deadlock

Synchronization of data exchange between distributor and worker cores is based on 2 handshakes: retptr64 for returning mbufs from workers to distributor and bufptr64 for passing mbufs to workers. Without proper order of verifying those 2 handshakes a deadlock may occur. This can happen when worker

[dpdk-dev] [PATCH v5 04/15] distributor: handle worker shutdown in burst mode

The burst version of distributor implementation was missing proper handling of worker shutdown. A worker processing packets received from distributor can call rte_distributor_return_pkt() function informing distributor that it want no more packets. Further calls to rte_distributor_request_pkt() or

[dpdk-dev] [PATCH v5 00/15] fix distributor synchronization issues

During review and verification of the patch created by Sarosh Arif: "test_distributor: prevent memory leakages from the pool" I found out that running distributor unit tests multiple times in a row causes fails. So I investigated all the issues I found. There are few synchronization issues that mi

[dpdk-dev] [PATCH v5 01/15] distributor: fix missing handshake synchronization

rte_distributor_return_pkt function which is run on worker cores must wait for distributor core to clear handshake on retptr64 before using those buffers. While the handshake is set distributor core controls buffers and any operations on worker side might overwrite buffers which are unread yet. Sam

Re: [dpdk-dev] [PATCH] net/fm10k: fix memory leak when Tx thresh check fails

> -Original Message- > From: Wang, Xiao W > Sent: Thursday, October 8, 2020 9:39 AM > To: wangyunjian ; dev@dpdk.org > Cc: Zhang, Qi Z ; jerry.lili...@huawei.com; > xudin...@huawei.com; sta...@dpdk.org > Subject: RE: [dpdk-dev] [PATCH] net/fm10k: fix memory leak when Tx thresh > check f

[dpdk-dev] [PATCH v1] doc: fix dpaa2 guide

From: Sachin Saxena The diagram to show dpaa2 drivers brief was missing in dpaa2.html file. fix a typo in encoding for a literal block to make it visible in generated doc file. Fixes: 846a8305f277 ("add DPAA2 NIC details") Cc: sta...@dpdk.org Signed-off-by: Sachin Saxena --- doc/guides/nics/

Re: [dpdk-dev] [PATCH v3 2/2] ethdev: make rte_flow API thread safe

> -Original Message- > From: Matan Azrad > Sent: Thursday, October 8, 2020 4:11 AM > To: Suanming Mou ; Ori Kam ; > NBU-Contact-Thomas Monjalon ; Ferruh Yigit > ; Andrew Rybchenko > Cc: dev@dpdk.org > Subject: RE: [dpdk-dev] [PATCH v3 2/2] ethdev: make rte_flow API thread safe > > >

Re: [dpdk-dev] [PATCH v3 1/2] eal/windows: add pthread mutex lock

Hi Dmitry, Thank you very much. I also got some messages that they wish the PTHREAD_MUTEX_INITIALIZER macro can also be supported. Refer to [1], we found that with critical section solution, maybe the macro can be defined as this: #define PTHREAD_MUTEX_INITIALIZER {(void*)-1,-1,0,0,0,0} We hav

Re: [dpdk-dev] [PATCH v3] net/dpaa2: fix build error about timesync functions

Following change should also be handled as suggested by Ferruh in earlier. diff --git a/drivers/net/dpaa2/dpaa2_ptp.c b/drivers/net/dpaa2/dpaa2_ptp.c index 9f755e84bf..0e44d4c6bf 100644 --- a/drivers/net/dpaa2/dpaa2_ptp.c +++ b/drivers/net/dpaa2/dpaa2_ptp.c @@ -178,4 +178,6 @@ s

Re: [dpdk-dev] [PATCH] net/fm10k: fix memory leak when Tx thresh check fails

Hi, Thanks for the patch. > -Original Message- > From: wangyunjian > Sent: Wednesday, October 7, 2020 3:37 PM > To: dev@dpdk.org > Cc: Zhang, Qi Z ; Wang, Xiao W > ; jerry.lili...@huawei.com; > xudin...@huawei.com; Yunjian Wang ; > sta...@dpdk.org > Subject: [dpdk-dev] [PATCH] net/fm10k:

Re: [dpdk-dev] [PATCH v5 1/2] ethdev: add flow shared action API

Please see inline.. On Wed, Oct 7, 2020 at 5:56 AM Andrey Vesnovaty wrote: > > This commit introduces extension of DPDK flow action API enabling > sharing of single rte_flow_action in multiple flows. The API intended for > PMDs, where multiple HW offloaded flows can reuse the same HW > essence/ob

Re: [dpdk-dev] [PATCH v6 2/2] app/testpmd: support shared action

On Wed, Oct 7, 2020 at 11:36 AM Andrey Vesnovaty wrote: > > This patch adds shared action support to testpmd CLI. > > All shared actions created via testpmd CLI assigned ID for further > reference in other CLI commands. Shared action ID supplied as CLI > argument or assigned by testpmd is similar

Re: [dpdk-dev] [PATCH] baseband/turbo_sw: fix memory leak in error path

Hi wangyunjian, > -Original Message- > From: wangyunjian > Sent: Wednesday, October 7, 2020 2:04 AM > To: dev@dpdk.org > Cc: Chautru, Nicolas ; jerry.lili...@huawei.com; > xudin...@huawei.com; Yunjian Wang ; > sta...@dpdk.org > Subject: [dpdk-dev] [PATCH] baseband/turbo_sw: fix memory lea

Re: [dpdk-dev] [PATCH V15 3/3] app/testpmd: add FEC command

HI，Ferry, thank you very much. this is good news to me. I promise the new version will be sent in these two days. thanks again. -- 胡敏 Hu Min Mobile: +86-13528728164 Email: humi...@huawei.com 发件人：Ferruh Yigit

Re: [dpdk-dev] [RFC PATCH v4 3/3] app/testpmd: handle device recovery event

On Wed, Oct 7, 2020 at 2:37 AM Ferruh Yigit wrote: > > On 10/7/2020 5:46 AM, Kalesh Anakkur Purayil wrote: > > Hi Ophir, > > > > Thank you for the comments. I will address them in the next version. > > > > I will push these changes as Patches next time and not as an RFC. Hope that > > is OK. > > >

Re: [dpdk-dev] [PATCH 22/22] doc: add new DLB2 eventdev driver to relnotes

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > To: Mcnamara, John ; Kovacevic, Marko > > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 22/22] doc: add new DLB2 eventdev driver

Re: [dpdk-dev] [PATCH 21/22] event/dlb2: add timeout ticks entry point

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 21/22] event/dlb2: add timeout ticks entry point > > Adds the timeout ticks convers

Re: [dpdk-dev] [PATCH 20/22] event/dlb2: add queue and port release

> static void > +dlb2_eventdev_queue_release(struct rte_eventdev *dev, uint8_t id) > +{ > + RTE_SET_USED(dev); > + RTE_SET_USED(id); > + > + /* This function intentionally left blank. dlb2 does not support > + * reconfiguring individual queues or ports -- the entire device > +

[dpdk-dev] [PATCH] ethdev: fix xstat name of basic stats per queue

As described in doc/guides/prog_guide/poll_mode_drv.rst, the naming scheme for the xstats is parts separated with underscore: * direction * detail 1 * detail 2 * detail n * unit where detail 1 can be "q" followed with a queue number. It means the name of the

Re: [dpdk-dev] [PATCH 19/22] event/dlb2: add PMD self-tests

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > To: Jerin Jacob > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry > Subject: [PATCH 19/22] event/dlb2: add PMD self-tests > > Add a variety of self-tests for both ldb and

Re: [dpdk-dev] [PATCH 18/22] event/dlb2: add PMD's token pop public interface

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > To: Ray Kinsella ; Neil Horman > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 18/22] event/dlb2: add PMD's token pop public inte

[dpdk-dev] [PATCH v5 8/8] crypto/bcmfs: add crypto pmd into cryptodev test

Add global test suite for bcmfs crypto pmd Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- app/test/test_cryptodev.c | 17 + app/test/test_cryptodev.h | 1 + doc/guides/cryptodevs/bcmfs.rst | 11 +++ 3 files cha

[dpdk-dev] [PATCH v5 6/8] crypto/bcmfs: add session handling and capabilities

Add session handling and capabilities supported by crypto HW accelerator Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- doc/guides/cryptodevs/bcmfs.rst | 47 ++ doc/guides/cryptodevs/features/bcmfs.ini | 56 ++ drivers/crypto/

[dpdk-dev] [PATCH v5 7/8] crypto/bcmfs: add crypto HW module

Add crypto h/w module to process crypto op. Crypto op is processed via sym_engine module before submitting the crypto request to HW queues. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- drivers/crypto/bcmfs/bcmfs_sym.c| 289 ++ drive

[dpdk-dev] [PATCH v5 4/8] crypto/bcmfs: add HW queue pair operations

Add queue pair operations exported by supported devices. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- drivers/crypto/bcmfs/bcmfs_dev_msg.h | 29 + drivers/crypto/bcmfs/bcmfs_device.c | 51 ++ drivers/crypto/bcmfs/bcmfs_device.h

[dpdk-dev] [PATCH v5 5/8] crypto/bcmfs: create a symmetric cryptodev

Create a symmetric crypto device and add supported cryptodev ops. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- drivers/crypto/bcmfs/bcmfs_device.c | 15 ++ drivers/crypto/bcmfs/bcmfs_device.h | 6 + drivers/crypto/bcmfs/bcmfs_qp.c | 3

Re: [dpdk-dev] [PATCH 17/22] event/dlb2: add eventdev stop and close

> +static void > +dlb2_eventdev_stop(struct rte_eventdev *dev) > +{ > + /* FIXME: Handle the case that app threads are waiting in > + * rte_event_dequeue_burst() (either blocked on interrupt or in umwait, > + * or waiting with a timeout). Looking into proposing a new function to > +

[dpdk-dev] [PATCH v5 3/8] crypto/bcmfs: add queue pair management API

Add queue pair management APIs which will be used by Crypto device to manage h/w queues. A bcmfs device structure owns multiple queue-pairs based on the mapped address allocated to it. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- drivers/crypto/

[dpdk-dev] [PATCH v5 2/8] crypto/bcmfs: add vfio support

Add VFIO support for BCMFS PMD. The BCMFS PMD functionality is dependent on the VFIO_PRESENT flag, which gets enabled in the rte_vfio.h. If this flag is not enabled in the compiling platform driver will silently return with error, when executed. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra

[dpdk-dev] [PATCH v5 1/8] crypto/bcmfs: add BCMFS driver

Add Broadcom FlexSparc(FS) device creation driver which registers to a vdev and create a device. Add APIs for logs, supportive documentation and maintainers file. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- MAINTAINERS

[dpdk-dev] [PATCH v5 0/8] Add Crypto PMD for Broadcom`s FlexSparc devices

Hi, This patchset contains support for Crypto offload on Broadcom’s Stingray/Stingray2 SoCs having FlexSparc unit. BCMFS is an acronym for Broadcom FlexSparc device used in the patchest. The patchset progressively adds major modules as below. a) Detection of platform-device based on the known reg

Re: [dpdk-dev] [PATCH 16/22] event/dlb2: add dequeue and its burst variants

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 16/22] event/dlb2: add dequeue and its burst variants > > Add support for dequeue,

Re: [dpdk-dev] [PATCH 15/22] event/dlb2: add enqueue and its burst variants

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 15/22] event/dlb2: add enqueue and its burst variants > > Add support for enqueue a

Re: [dpdk-dev] [PATCH 14/22] event/dlb2: add eventdev start

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 14/22] event/dlb2: add eventdev start > > Add support for the eventdev start entry

[dpdk-dev] [PATCH v4 7/8] crypto/bcmfs: add crypto HW module

Add crypto h/w module to process crypto op. Crypto op is processed via sym_engine module before submitting the crypto request to h/w queues. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- drivers/crypto/bcmfs/bcmfs_sym.c| 289 ++ driv

[dpdk-dev] [PATCH v4 8/8] crypto/bcmfs: add crypto pmd into cryptodev test

Add global test suite for bcmfs crypto pmd Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- app/test/test_cryptodev.c | 17 + app/test/test_cryptodev.h | 1 + doc/guides/cryptodevs/bcmfs.rst | 11 +++ 3 files cha

[dpdk-dev] [PATCH v4 5/8] crypto/bcmfs: create a symmetric cryptodev

Create a symmetric crypto device and add supported cryptodev ops. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- drivers/crypto/bcmfs/bcmfs_device.c | 15 ++ drivers/crypto/bcmfs/bcmfs_device.h | 6 + drivers/crypto/bcmfs/bcmfs_qp.c | 3

[dpdk-dev] [PATCH v4 6/8] crypto/bcmfs: add session handling and capabilities

Add session handling and capabilities supported by crypto h/w accelerator Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- doc/guides/cryptodevs/bcmfs.rst | 47 ++ doc/guides/cryptodevs/features/bcmfs.ini | 56 ++ drivers/crypto

[dpdk-dev] [PATCH v4 3/8] crypto/bcmfs: add queue pair management API

Add queue pair management APIs which will be used by Crypto device to manage h/w queues. A bcmfs device structure owns multiple queue-pairs based on the mapped address allocated to it. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- drivers/crypto/

[dpdk-dev] [PATCH v4 4/8] crypto/bcmfs: add HW queue pair operations

Add queue pair operations exported by supported devices. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- drivers/crypto/bcmfs/bcmfs_dev_msg.h | 29 + drivers/crypto/bcmfs/bcmfs_device.c | 51 ++ drivers/crypto/bcmfs/bcmfs_device.h

[dpdk-dev] [PATCH v4 1/8] crypto/bcmfs: add BCMFS driver

Add Broadcom FlexSparc(FS) device creation driver which registers to a vdev and create a device. Add APIs for logs, supportive documentation and maintainers file. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra Padasalagi Reviewed-by: Ajit Khaparde --- MAINTAINERS

[dpdk-dev] [PATCH v4 2/8] crypto/bcmfs: add vfio support

Add VFIO support for BCMFS PMD. The BCMFS PMD functionality is dependent on the VFIO_PRESENT flag, which gets enabled in the rte_vfio.h. If this flag is not enabled in the compiling platform driver will silently return with error, when executed. Signed-off-by: Vikas Gupta Signed-off-by: Raveendra

[dpdk-dev] [PATCH v4 0/8] Add Crypto PMD for Broadcom`s FlexSparc devices

Hi, This patchset contains support for Crypto offload on Broadcom’s Stingray/Stingray2 SoCs having FlexSparc unit. BCMFS is an acronym for Broadcom FlexSparc device used in the patchest. The patchset progressively adds major modules as below. a) Detection of platform-device based on the known reg

Re: [dpdk-dev] [PATCH 13/22] event/dlb2: add port unlink and port unlinks in progress

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 13/22] event/dlb2: add port unlink and port unlinks in > progress > > Add supports

Re: [dpdk-dev] [PATCH 12/22] event/dlb2: add port link

> +static int > +dlb2_event_queue_join_ldb(struct dlb2_eventdev *dlb2, > + struct dlb2_eventdev_port *ev_port, > + struct dlb2_eventdev_queue *ev_queue, > + uint8_t priority) > +{ > + int first_avail = -1; > + int ret, i; > +

Re: [dpdk-dev] [PATCH 11/22] event/dlb2: add port setup

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 11/22] event/dlb2: add port setup > > Configure the load balanded (ldb) or directed

Re: [dpdk-dev] [PATCH v3 2/2] ethdev: make rte_flow API thread safe

From: Suanming Mou > Currently, the rte_flow functions are not defined as thread safe. > DPDK applications either call the functions in single thread or add locks > around the functions for the critical section. > Better to write here "or protect any concurrent calling for the rte_flow operat

Re: [dpdk-dev] [PATCH 10/22] event/dlb2: add queue setup

> +static int > +dlb2_eventdev_ldb_queue_setup(struct rte_eventdev *dev, > + struct dlb2_eventdev_queue *ev_queue, > + const struct rte_event_queue_conf *queue_conf) > +{ > + struct dlb2_eventdev *dlb2 = dlb2_pmd_priv(dev); > + int32_t qm_

Re: [dpdk-dev] [PATCH 08/22] event/dlb2: add infos get and configure

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 08/22] event/dlb2: add infos get and configure > > Add support for configuring the

Re: [dpdk-dev] [PATCH 09/22] event/dlb2: add queue and port default conf

> -Original Message- > From: McDaniel, Timothy > Sent: Friday, September 11, 2020 3:26 PM > Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage > ; Van Haaren, Harry ; > jer...@marvell.com > Subject: [PATCH 09/22] event/dlb2: add queue and port default conf > > Add support for getting the

Re: [dpdk-dev] [PATCH 07/22] event/dlb2: add xstats

> diff --git a/drivers/event/dlb2/dlb2_xstats.c > b/drivers/event/dlb2/dlb2_xstats.c > new file mode 100644 > index 000..9a69d78 > --- /dev/null > +++ b/drivers/event/dlb2/dlb2_xstats.c > @@ -0,0 +1,1269 @@ > +/* SPDX-License-Identifier: BSD-3-Clause > + * Copyright(c) 2016-2020 Intel Corporat

Re: [dpdk-dev] [PATCH v3 2/2] ethdev: make rte_flow API thread safe

On Wed, Oct 7, 2020 at 7:18 AM Suanming Mou wrote: > > Currently, the rte_flow functions are not defined as thread safe. > DPDK applications either call the functions in single thread or add > locks around the functions for the critical section. > > For PMDs support the flow operations thread safe

[dpdk-dev] [PATCH v6 2/2] app/testpmd: support shared action

This patch adds shared action support to testpmd CLI. All shared actions created via testpmd CLI assigned ID for further reference in other CLI commands. Shared action ID supplied as CLI argument or assigned by testpmd is similar to flow ID & limited to scope of testpdm CLI. Create shared action

[dpdk-dev] [PATCH v6 1/2] ethdev: add flow shared action API

This commit introduces extension of DPDK flow action API enabling sharing of single rte_flow_action in multiple flows. The API intended for PMDs, where multiple HW offloaded flows can reuse the same HW essence/object representing flow action and modification of such an essence/object affects all th

[dpdk-dev] [PATCH v6 0/2] RTE flow shared action

This patchset introduces shared action API for RTE flow. v6 changes: * fix build warning in testpmd Andrey Vesnovaty (2): ethdev: add flow shared action API app/testpmd: support shared action app/test-pmd/cmdline_flow.c | 262 +++- app/test-pmd/config.c

[dpdk-dev] [PATCH v3] ethdev: add VLAN attributes to ETH and VLAN items

This patch implements the change proposes in RFC [1], adding dedicated fields to ETH and VLAN items structs, to clearly define the required characteristic of a packet, and enable precise match criteria. Documentation is updated accordingly. [1] https://mails.dpdk.org/archives/dev/2020-August/17753

Re: [dpdk-dev] [PATCH v3 1/1] vfio: modify spapr iommu support to use static window sizing

On 9/17/20 4:13 AM, Burakov, Anatoly wrote: On 10-Aug-20 10:07 PM, David Christensen wrote: The SPAPR IOMMU requires that a DMA window size be defined before memory can be mapped for DMA. Current code dynamically modifies the DMA window size in response to every new memory allocation which is

Re: [dpdk-dev] [PATCH RESEND 2/2] raw/octeontx2_dma: Add support in case of multiple DPI blocks

-Original Message- From: Radha Mohan Chintakuntla Sent: Tuesday, October 6, 2020 11:00 AM To: dev@dpdk.org; Satha Koteswara Rao Kottidi Cc: Jerin Jacob Kollanukkaran ; Radha Chintakuntla ; Satananda Burla Subject: [PATCH RESEND 2/2] raw/octeontx2_dma: Add support in case of multiple

Re: [dpdk-dev] [PATCH RESEND 1/2] raw/octeontx2_dma: Assign pem_id as lport for non-internal DMA

-Original Message- From: Radha Mohan Chintakuntla Sent: Tuesday, October 6, 2020 11:00 AM To: dev@dpdk.org; Satha Koteswara Rao Kottidi Cc: Jerin Jacob Kollanukkaran ; Radha Chintakuntla ; Satananda Burla Subject: [PATCH RESEND 1/2] raw/octeontx2_dma: Assign pem_id as lport for non

[dpdk-dev] [PATCH v5 06/25] raw/ioat: split header for readability

Rather than having a single long complicated header file for general use we can split things so that there is one header with all the publicly needed information - data structs and function prototypes - while the rest of the internal details are put separately. This makes it easier to read, underst

Re: [dpdk-dev] [PATCH v2 1/8] net/memif: do not update local copy of tail in tx function

Hi Jakub, Appreciate if you could review this series and provide any comments you might have. Thank you, Honnappa > -Original Message- > From: Honnappa Nagarahalli > Sent: Monday, September 28, 2020 2:03 PM > To: dev@dpdk.org; Honnappa Nagarahalli ; > Phil Yang ; jgraj...@cisco.

[dpdk-dev] [PATCH v5 10/25] usertools/dpdk-devbind.py: add support for DSA HW

From: Kevin Laatz Intel Data Streaming Accelerator (Intel DSA) is a high-performance data copy and transformation accelerator which will be integrated in future Intel processors [1]. Add DSA device support to dpdk-devbind.py script. [1] https://01.org/blogs/2019/introducing-intel-data-streaming

Re: [dpdk-dev] [PATCH 06/22] event/dlb2: add probe

> diff --git a/drivers/event/dlb2/dlb2.c b/drivers/event/dlb2/dlb2.c > new file mode 100644 > index 000..7ff7dac > --- /dev/null > +++ b/drivers/event/dlb2/dlb2.c > @@ -0,0 +1,557 @@ > +/* SPDX-License-Identifier: BSD-3-Clause > + * Copyright(c) 2016-2020 Intel Corporation > + */ > + > +#includ

Re: [dpdk-dev] [PATCH v3 1/2] eal/windows: add pthread mutex lock

On Wed, 7 Oct 2020 22:17:28 +0800, Suanming Mou wrote: > Add pthread mutex lock as it is needed for the thread safe rte_flow > functions. > > Signed-off-by: Suanming Mou Acked-by: Dmitry Kozlyuk

[dpdk-dev] [PATCH v5 05/25] raw/ioat: add a flag to control copying handle parameters

From: Cheng Jiang Add a flag which controls whether rte_ioat_enqueue_copy and rte_ioat_completed_copies function should process handle parameters. Not doing so can improve the performance when handle parameters are not necessary. Signed-off-by: Cheng Jiang Signed-off-by: Bruce Richardson Revie

[dpdk-dev] [PATCH v5 19/25] raw/ioat: add data path for idxd devices

Add support for doing copies using DSA hardware. This is implemented by just switching on the device type field at the start of the inline functions. Since there is no hardware which will have both device types present this branch will always be predictable after the first call, meaning it has litt

[dpdk-dev] [PATCH v5 07/25] raw/ioat: rename functions to be operation-agnostic

Since the hardware supported by the ioat driver is capable of operations other than just copies, we can rename the doorbell and completion-return functions to not have "copies" in their names. These functions are not copy-specific, and so would apply for other operations which may be added later to

[dpdk-dev] [PATCH v5 09/25] raw/ioat: make the HW register spec private

Only a few definitions from the hardware spec are actually used in the driver runtime, so we can copy over those few and make the rest of the spec a private header in the driver. Signed-off-by: Bruce Richardson Reviewed-by: Kevin Laatz Acked-by: Radu Nicolau --- drivers/raw/ioat/ioat_rawdev.c

[dpdk-dev] [PATCH v5 04/25] raw/ioat: include extra info in error messages

In case of any failures, include the function name and the line number of the error message in the message, to make tracking down the failure easier. Signed-off-by: Bruce Richardson Reviewed-by: Kevin Laatz Acked-by: Radu Nicolau --- drivers/raw/ioat/ioat_rawdev_test.c | 53 +++

[dpdk-dev] [PATCH v5 14/25] raw/ioat: create rawdev instances on idxd PCI probe

When a matching device is found via PCI probe create a rawdev instance for each queue on the hardware. Use empty self-test function for these devices so that the overall rawdev_autotest does not report failures. Signed-off-by: Bruce Richardson Reviewed-by: Kevin Laatz Acked-by: Radu Nicolau ---

[dpdk-dev] [PATCH v5 13/25] raw/ioat: include example configuration script

Devices managed by the idxd kernel driver must be configured for DPDK use before it can be used by the ioat driver. This example script serves both as a quick way to get the driver set up with a simple configuration, and as the basis for users to modify it and create their own configuration scripts

[dpdk-dev] [PATCH v5 11/25] raw/ioat: add skeleton for VFIO/UIO based DSA device

Add in the basic probe/remove skeleton code for DSA devices which are bound directly to vfio or uio driver. The kernel module for supporting these uses the "idxd" name, so that name is used as function and file prefix to avoid conflict with existing "ioat" prefixed functions. Since we are adding n

[dpdk-dev] [PATCH v5 12/25] raw/ioat: add vdev probe for DSA/idxd devices

From: Kevin Laatz The Intel DSA devices can be exposed to userspace via kernel driver, so can be used without having to bind them to vfio/uio. Therefore we add support for using those kernel-configured devices as vdevs, taking as parameter the individual HW work queue to be used by the vdev. Sig

[dpdk-dev] [PATCH v5 01/25] doc/api: add ioat driver to index

Add the ioat driver to the doxygen documentation. Signed-off-by: Bruce Richardson Reviewed-by: Kevin Laatz Acked-by: Radu Nicolau --- doc/api/doxy-api-index.md | 1 + doc/api/doxy-api.conf.in | 1 + 2 files changed, 2 insertions(+) diff --git a/doc/api/doxy-api-index.md b/doc/api/doxy-api-in

[dpdk-dev] [PATCH v5 08/25] raw/ioat: add separate API for fence call

Rather than having the fence signalled via a flag on a descriptor - which requires reading the docs to find out whether the flag needs to go on the last descriptor before, or the first descriptor after the fence - we can instead add a separate fence API call. This becomes unambiguous to use, since

[dpdk-dev] [PATCH v5 21/25] raw/ioat: create separate statistics structure

Rather than having the xstats as fields inside the main driver structure, create a separate structure type for them. As part of the change, when updating the stats functions referring to the stats by the old path, we can simplify them to use the id to directly index into the stats structure, makin

[dpdk-dev] [PATCH v5 24/25] raw/ioat: clean up use of common test function

Now that all devices can pass the same set of unit tests, eliminate the temporary idxd_rawdev_test function and move the prototype for ioat_rawdev_test to the proper internal header file, to be used by all device instances. Signed-off-by: Bruce Richardson Reviewed-by: Kevin Laatz Acked-by: Radu

[dpdk-dev] [PATCH v5 25/25] raw/ioat: add fill operation

From: Kevin Laatz Add fill operation enqueue support for IOAT and IDXD. The fill enqueue is similar to the copy enqueue, but takes a 'pattern' rather than a source address to transfer to the destination address. This patch also includes an additional test case for the new operation type. Signed-

Re: [dpdk-dev] [PATCH v3 2/2] ethdev: make rte_flow API thread safe

Hi Suanming, > -Original Message- > From: dev On Behalf Of Ajit Khaparde > Sent: Wednesday, October 7, 2020 5:43 PM > Subject: Re: [dpdk-dev] [PATCH v3 2/2] ethdev: make rte_flow API thread safe > > On Wed, Oct 7, 2020 at 7:18 AM Suanming Mou > wrote: > > > > Currently, the rte_flow fu

[dpdk-dev] [PATCH v5 23/25] raw/ioat: add xstats tracking for idxd devices

Add update of the relevant stats for the data path functions and point the overall device struct xstats function pointers to the existing ioat functions. At this point, all necessary hooks for supporting the existing unit tests are in place so call them for each device. Signed-off-by: Bruce Richa

[dpdk-dev] [PATCH v5 02/25] raw/ioat: fix missing close function

From: Kevin Laatz When rte_rawdev_pmd_release() is called, rte_rawdev_close() looks for a dev_close function for the device causing a segmentation fault when no close() function is implemented for a driver. This patch resolves the issue by adding a stub function ioat_dev_close(). Fixes: f687e84

  1   2   3   >