[PATCH v2 1/1] doc: fix cnxk platform HW accelerator blocks list

Add ML to the list of platform hardware accelerator blocks, and added reference to ML device driver. Fixes: fe83ffd9ec2e ("ml/cnxk: add skeleton") Signed-off-by: Srikanth Yalavarthi Acked-by: Jerin Jacob --- v2: * Updated fixes and commit message * Updated device table index doc/guides/plat

Re: [PATCH 1/1] usertools/devbind: add ml device class

On Mon, Mar 13, 2023 at 10:53 PM Srikanth Yalavarthi wrote: > > Added new ML device class and support for cnxk ML device. > > Signed-off-by: Srikanth Yalavarthi Acked-by: Jerin Jacob > --- > usertools/dpdk-devbind.py | 11 ++- > 1 file changed, 10 insertions(+), 1 deletion(-) > > dif

Re: [PATCH 1/1] doc: add ML to list of cnxk platform blocks

On Mon, Mar 13, 2023 at 11:10 PM Srikanth Yalavarthi wrote: > > Add ML to the list of platform hardware accelerator blocks. > > Signed-off-by: Srikanth Yalavarthi > --- > doc/guides/platform/cnxk.rst | 5 + > 1 file changed, 5 insertions(+) > > diff --git a/doc/guides/platform/cnxk.rst b/doc

回复: [PATCH v3 2/3] net/i40e: enable direct rearm with separate API

> -邮件原件- > 发件人: Konstantin Ananyev > 发送时间: Tuesday, March 7, 2023 7:01 PM > 收件人: Feifei Wang ; Konstantin Ananyev > ; Yuying Zhang > ; Beilei Xing ; Ruifeng > Wang > 抄送: dev@dpdk.org; nd ; Honnappa Nagarahalli > ; nd ; nd > 主题: RE: [PATCH v3 2/3] net/i40e: enable direct rearm with sepa

RE: [PATCH v1] common/cnxk: fix initialization of timer LF count

> -Original Message- > From: Shijith Thotton > Sent: Tuesday, March 14, 2023 9:17 AM > To: Jerin Jacob Kollanukkaran > Cc: Shijith Thotton ; dev@dpdk.org; Pavan > Nikhilesh Bhagavatula > Subject: [PATCH v1] common/cnxk: fix initialization of timer LF count > > Assignment of nb_lfs var

[Bug 1181] [DPDK-23.03]loopback_virtio_user_server_mode_cbdma: testpmd can't loop packets after start dpdk-pdump app Immediately

https://bugs.dpdk.org/show_bug.cgi?id=1181 Bug ID: 1181 Summary: [DPDK-23.03]loopback_virtio_user_server_mode_cbdma: testpmd can't loop packets after start dpdk-pdump app Immediately Product: DPDK Version: 22.03

[PATCH v1] common/cnxk: fix initialization of timer LF count

Assignment of nb_lfs variable with the available number of timer LFs was not happening in the success case after the addition of the new label "done". This patch fixes the same by moving the assignment under the label. Fixes: 44a9307c0908 ("common/cnxk: support mailbox locking") Signed-off-by: Sh

[PATCH v2] net/i40e: fix MAC loopback on X722

If enabling MAC loopback mode on X722 NIC, transmitted packets are not seen in the receive queue. The root cause is using wrong loopback mode bits. Correct it according to the X722 datasheet. Fixes: 3a838ab649df ("net/i40e: support MAC loopback") Fixes: 5712e6407089 ("net/i40e: revert enhancing lo

[PATCH] net/i4oe: fix MAC loopback on X722

If enabling MAC loopback mode on X722 NIC, transmitted packets are not seen in the receive queue. The root cause is using wrong loopback mode bits. Correct it according to the X722 datasheet. Fixes: 3a838ab649df ("net/i40e: support MAC loopback") Fixes: 5712e6407089 ("net/i40e: revert enhancing lo

Re: [PATCH v4] lib/bpf: Rename bpf function names to avoid potential conflict with libpcap

Ok, that was my mistake. I’ll send the new patch later :) Sent from my iPhone > On Mar 14, 2023, at 01:22, Stephen Hemminger > wrote: > > On Mon, 13 Mar 2023 17:07:29 + > Konstantin Ananyev wrote: > >>> I've read the libbpf code again and I found some other functions with >>> pure 'bpf_

[dpdk-dev v1 2/2] app/test: add ecdh test cases

From: Arkadiusz Kusztal Added Elliptic-Curve Diffie Hellman test cases. Signed-off-by: Arkadiusz Kusztal Signed-off-by: Kai Ji --- app/test/test_cryptodev_asym.c | 356 app/test/test_cryptodev_ecdh_test_vectors.h | 144 2 files changed, 500 insertion

[dpdk-dev v1 1/2] app/test: add diffie-hellman test cases

From: Arkadiusz Kusztal Added Diffie-Hellman tests. This tests adding possibility to check correctness of particular DH phases, which is not possible with current tests cases. Signed-off-by: Arkadiusz Kusztal Signed-off-by: Kai Ji --- app/test/test_cryptodev_asym.c| 262 ++

Re: [PATCH 23.07 2/2] build: explicitly track file paths in current directory

On Fri, Mar 10, 2023 at 11:11:38AM +, Bruce Richardson wrote: > To ensure proper path tracking for files being used by the build, the > "files()" function should always be used. While meson currently assumes > that bare filenames passed to commands refer to paths in the current > directory, oth

Re: [PATCH 23.07 1/2] build: fix case of project language name

On Fri, Mar 10, 2023 at 11:11:37AM +, Bruce Richardson wrote: > According to the meson manual [1], the project language should be given > as 'c', rather than 'C' in the initial "project" function call. While > meson itself does not complain about this, the "muon" project, which > attempts to re

[PATCH v2 1/2] eal: make cpusetp to rte thread set affinity const

const qualify rte_cpuset_t *cpusetp parameter in the rte_thread_set_affinity API. Signed-off-by: Tyler Retzlaff --- lib/eal/common/eal_common_thread.c | 6 +++--- lib/eal/include/rte_thread.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/lib/eal/common/eal_common_t

[PATCH v2 2/2] eal: fix failure path race setting new thread affinity

In rte_thread_create setting affinity after pthread_create may fail. Such a failure should result in the entire rte_thread_create failing but doesn't. Additionally if there is a failure to set affinity a race exists where the creating thread will free ctx and depending on scheduling of the new thr

[PATCH v2 0/2] fix race in rte_thread_create failure path

v2: * new approach over v1 of the patch to avoid using pthread np API that is not available on Alpine Linux. * to conform to rte_thread_create parameter const qualification include an additional patch to const qualify rte_thread_set_affinity cpusetp parameter. Tyler Retzlaff (2):

[RFT v2] test-pmd: go back to using cmdline_interact

The cmdline library poll function is broken on Windows and was never tested, don't use it. Instead, use sigaction() to cancel read character on Unix OS's and a new helper to cancel I/O on Windows. Signed-off-by: Stephen Hemminger --- v2 - make cmdline_cancel an exposed API app/test-pmd/cmdline

[PATCH] net/bnxt: limit max_vnics for CoS classification

When using CoS classification the number of vnics is capped to avoid unnecessary memzone allocations. Signed-off-by: Dave Johnson --- .mailmap | 1 + drivers/net/bnxt/bnxt.h | 1 + drivers/net/bnxt/bnxt_hwrm.c | 10 -- 3 files changed, 10 insertions(+), 2 delet

Re: [PATCH] mldev: remove variable self assignment in dev init

On Sat, Mar 11, 2023 at 06:57:04AM -0800, Srikanth Yalavarthi wrote: > Fix variable self assignment in rte_ml_devinit. > Issue reported by coverity scan. > > Coverity issue: 383652 > Fixes: ea80eafbd4d8 ("mldev: add PMD functions") > > Signed-off-by: Srikanth Yalavarthi > --- Reviewed-by: Tyler

[PATCH] net/mlx5: relax hws meter validation

The policies array is not required for the new METER_MARK action. It is only required for the old METER action implementation. Furthermore, the profiles array is optional for the METER_MARK action since a profile can be found using the rte_mtr_meter_profile_get(). Do not enforce the preallocation o

RE: [EXT] Re: [PATCH 1/1] usertools/devbind: add ml device class

> -Original Message- > From: Jerin Jacob > Sent: 13 March 2023 23:01 > To: Srikanth Yalavarthi > Cc: dev@dpdk.org; Shivah Shankar Shankar Narayan Rao > ; Jerin Jacob Kollanukkaran > > Subject: [EXT] Re: [PATCH 1/1] usertools/devbind: add ml device class > > External Email > > -

[PATCH 1/1] doc: add ML to list of cnxk platform blocks

Add ML to the list of platform hardware accelerator blocks. Signed-off-by: Srikanth Yalavarthi --- doc/guides/platform/cnxk.rst | 5 + 1 file changed, 5 insertions(+) diff --git a/doc/guides/platform/cnxk.rst b/doc/guides/platform/cnxk.rst index aadd60b5d4..1956cc31d8 100644 --- a/doc/guide

Re: [PATCH 1/1] usertools/devbind: add ml device class

On Mon, Mar 13, 2023 at 10:53 PM Srikanth Yalavarthi wrote: > > Added new ML device class and support for cnxk ML device. Please also add missing documentation connection at https://doc.dpdk.org/guides/platform/cnxk.html > > Signed-off-by: Srikanth Yalavarthi > --- > usertools/dpdk-devbind.py

RE: [EXT] Re: [PATCH] reorder: fix registration of dynamic field in mbuf

> -Original Message- > From: Stephen Hemminger > Sent: Monday, March 13, 2023 4:51 PM > To: Volodymyr Fialko > Cc: dev@dpdk.org; Reshma Pattan ; David Marchand > ; Andrew Rybchenko > ; Jerin Jacob > Kollanukkaran ; Anoob Joseph > Subject: [EXT] Re: [PATCH] reorder: fix registration o

[PATCH 1/1] usertools/devbind: add ml device class

Added new ML device class and support for cnxk ML device. Signed-off-by: Srikanth Yalavarthi --- usertools/dpdk-devbind.py | 11 ++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/usertools/dpdk-devbind.py b/usertools/dpdk-devbind.py index 4d9c1be666..a278f5e7f3 100755 ---

Re: [PATCH v4] lib/bpf: Rename bpf function names to avoid potential conflict with libpcap

On Mon, 13 Mar 2023 17:07:29 + Konstantin Ananyev wrote: > > I've read the libbpf code again and I found some other functions with > > pure 'bpf_' prefix. Should we rename all the functions whose names > > start with pure 'bpf_'? > > I thought you already prefixed all non-static functions

[RFT] test-pmd: go back to using cmdline_interact

The cmdline library poll function is broken on Windows and was never tested, don't use it. Instead, use sigaction() to cancel read character on Unix OS's and a new helper to cancel I/O on Windows. Fixes: 0fd1386c30c3 ("app/testpmd: cleanup cleanly from signal") Bugzilla ID: 1180 Signed-off-by: St

RE: [PATCH v4] lib/bpf: Rename bpf function names to avoid potential conflict with libpcap

> I've read the libbpf code again and I found some other functions with > pure 'bpf_' prefix. Should we rename all the functions whose names > start with pure 'bpf_'? I thought you already prefixed all non-static functions in the lib... Or do I miss something? > Konstantin Ananyev 于2023年3月12日

[PATCH] app: fix mbuf_autotest in case of defined RTE_LIBRTE_MBUF_DEBUG

How to reproduce: 1. Define RTE_LIBRTE_MBUF_DEBUG 2. MALLOC_PERTURB_=178 DPDK_TEST=mbuf_autotest gdb --args obj-x86_64-linux-gnu/app/test/dpdk-test --file-prefix=mbuf_autotest PANIC in rte_mbuf_sanity_check(): bad pkt_len ... #6 0x77d3d4cc in rte_mbuf_sanity_check (m=m@entr

RE: Dpdk packet reception

Hi Rajasekhar, Power Management API can “put the CPU into optimized power state and monitor the Ethernet PMD RX descriptor address, waking the CPU up whenever there’s new traffic”. Please take a look at the rte_power_monitor() and dpdk-l3fwd-power application example to see if it works for you.

Re: [PATCH v4] lib/bpf: Rename bpf function names to avoid potential conflict with libpcap

On Mon, 13 Mar 2023 22:55:34 +0800 "J.J. Martzki" wrote: > I've read the libbpf code again and I found some other functions with > pure 'bpf_' prefix. Should we rename all the functions whose names > start with pure 'bpf_'? Yes, all visible (ie non-static) functions should use a DPDK style prefi

Re: [PATCH v11 0/3] Fix cmdline_poll and testpmd signal handling

On Mon, 13 Mar 2023 10:34:55 + "Ling, WeiX" wrote: > > -Original Message- > > From: Tal Shnaiderman > > Sent: Monday, March 13, 2023 1:18 AM > > To: NBU-Contact-Thomas Monjalon (EXTERNAL) ; > > Stephen Hemminger ; Pier Damouny > > > > Cc: dev@dpdk.org; sta...@dpdk.org; ferruh.yi...@

Re: [PATCH v2 1/2] build: clarify configuration without IOVA field in mbuf

09/03/2023 14:10, Bruce Richardson: > On Thu, Mar 09, 2023 at 01:12:51PM +0100, Thomas Monjalon wrote: > > 09/03/2023 12:23, fengchengwen: > > > On 2023/3/9 15:29, Thomas Monjalon wrote: > > > > 09/03/2023 02:43, fengchengwen: > > > >> On 2023/3/7 0:13, Thomas Monjalon wrote: > > > >>> --- a/doc/gu

Re: [PATCH] lib/hash: new feature adding existing key

On Mon, 13 Mar 2023 07:35:48 + Abdullah Ömer Yamaç wrote: > diff --git a/lib/hash/rte_cuckoo_hash.h b/lib/hash/rte_cuckoo_hash.h > index eb2644f74b..e8b7283ec2 100644 > --- a/lib/hash/rte_cuckoo_hash.h > +++ b/lib/hash/rte_cuckoo_hash.h > @@ -193,6 +193,8 @@ struct rte_hash { > /**< If

Re: [PATCH v4] lib/bpf: Rename bpf function names to avoid potential conflict with libpcap

I've read the libbpf code again and I found some other functions with pure 'bpf_' prefix. Should we rename all the functions whose names start with pure 'bpf_'? Konstantin Ananyev 于2023年3月12日周日 22:02写道： > > 12/03/2023 06:20, J.J. Martzki пишет: > > The library libpcap has their function 'bpf_vali

[PATCH v3 2/2] crypto/qat: add cipher-crc offload support

This patch adds support to the QAT symmetric crypto PMD for combined cipher-crc offload feature, primarily for DOCSIS, on gen2/gen3/gen4 QAT devices. A new parameter called qat_sym_cipher_crc_enable has been added to the PMD, which can be set on process start as follows: -a ,qat_sym_cipher_crc_en

[PATCH v3 1/2] crypto/qat: add cipher-crc offload support to fw interface

This patch adds support to the QAT firmware interface header files for the combined cipher-crc offload feature for DOCSIS on gen2/gen3/ gen4 QAT devices. The main change is that new structures have been added for the crc content descriptor for the various generations. Signed-off-by: Kevin O'Sulliv

[PATCH v3 0/2] crypto/qat: add cipher-crc offload feature

This patchset adds support to the QAT PMD for combined cipher-crc processing for DOCSIS on the QAT device. The current QAT PMD implementation of cipher-crc calculates CRC in software and uses QAT for encryption/decryption offload. Note: The previous code-path is still retained for QAT firmware ver

RE: [EXT] Re: [PATCH] reorder: fix registration of dynamic field in mbuf

> All rte_reorder_buffer objects need to go through rte_reorder_init(). > You can check rte_reorder_init() return code. Hi David, I agree with all comments, however there is one catch with locks. Both reorder lib and mbuf dynamic field are using `rte_mcfg_tailq` read/write lock for synchronization

[PATCH v2] reorder: fix registration of dynamic field in mbuf

It's possible to initialize reorder buffer with user allocated memory via rte_reorder_init() function. In such case rte_reorder_create() is not required and reorder dynamic field in rte_mbuf will not be registered. Both reorder lib and mbuf dynamic field are using `rte_mcfg_tailq` read/write lock

[PATCH v2] reorder: fix registration of dynamic field in mbuf

It's possible to initialize reorder buffer with user allocated memory via rte_reorder_init() function. In such case rte_reorder_create() is not required and reorder dynamic field in rte_mbuf will not be registered. Both reorder lib and mbuf dynamic field are using `rte_mcfg_tailq` read/write lock

[PATCH 2/2] net/iavf: use static capabilities to set IV size

If iavf_crypto_capabilities contains the required capability then use the IV size defined there, otherwise use relaxed IV size constrains Signed-off-by: Radu Nicolau --- drivers/net/iavf/iavf_ipsec_crypto.c | 54 ++-- 1 file changed, 43 insertions(+), 11 deletions(-) dif

[PATCH 1/2] examples/ipsec-secgw: allow single xform SA

Update check capabilities before session create to allow single xform SA i.e. auth or cipher only Fixes: a8781df86c14 ("examples/ipsec-secgw: check capabilities before session create") Cc: gak...@marvell.com,kai...@intel.com Signed-off-by: Radu Nicolau --- examples/ipsec-secgw/ipsec.c | 6 ++--

[PATCH v2 1/1] mldev: split bfloat16 routines to separate files

Since bfloat16 intrinsics are not supported on all ARM platforms that support NEON, bfloat16 routines are moved to separate files. This would enable using scalar implementation for bfloat16 on unsupported ARM platforms. Bugzilla ID: 1179 Fixes: fc54766b1612 ("mldev: add Arm NEON type conversion")

[PATCH v2] crypto/ipsec_mb: expect ENOTSUP

Commit b35848bc01f6 ("crypto/ipsec_mb: add multi-process IPC request handler") is part of DPDK 22.11 release and it enforces usage of shared config and multiprocess mode. DPDK is not required to be run with more than one process in general, so instead of erroring out, catch the error and proceed w

[PATCH 1/1] mldev: split bfloat16 routines to separate files

Since bfloat16 intrinsics are not supported on all ARM platforms that support NEON, bfloat16 routines are moved to separate files. This would enable using scalar implementation for bfloat16 on unsupported ARM platforms. Bugzilla ID: 1179 Fixes: fc54766b1612 ("mldev: add Arm NEON type conversion")

RE: [EXT] Re: [PATCH] mldev: remove weak symbols use in type conversions

> -Original Message- > From: David Marchand > Sent: 13 March 2023 16:22 > To: Srikanth Yalavarthi > Cc: dev@dpdk.org; Shivah Shankar Shankar Narayan Rao > > Subject: [EXT] Re: [PATCH] mldev: remove weak symbols use in type > conversions > > External Email > > --

RE: [EXT] Re: [PATCH] MAINTAINERS: update maintainers list for qede

> -Original Message- > From: Thomas Monjalon > Sent: 10 March 2023 22:18 > To: Alok Prasad > Cc: dev@dpdk.org; Jerin Jacob Kollanukkaran ; > ferruh.yi...@intel.com; Manish Chopra > ; Devendra Singh Rawat > Subject: [EXT] Re: [PATCH] MAINTAINERS: update maintainers list for qede > > Ext

[PATCH v2 1/1] mldev: remove weak symbols use in type conversions

Drop use of weak symbols to select the type conversion functions. Select NEON implementation only on Aarch64 builds. Enable windows build. Fixes: 9637de38a2e3 ("mldev: add scalar type conversion") Signed-off-by: Srikanth Yalavarthi Reviewed-by: David Marchand --- v2: * Updated Fixes reference

Re: [PATCH] mldev: remove variable self assignment in dev init

On Sat, Mar 11, 2023 at 3:57 PM Srikanth Yalavarthi wrote: > > Fix variable self assignment in rte_ml_devinit. > Issue reported by coverity scan. > > Coverity issue: 383652 > Fixes: ea80eafbd4d8 ("mldev: add PMD functions") > > Signed-off-by: Srikanth Yalavarthi Reviewed-by: David Marchand --

Re: [PATCH] mldev: fix identical code in conditional branches

On Sat, Mar 11, 2023 at 3:56 PM Srikanth Yalavarthi wrote: > > Fix identical code in different conditional branches in float32 > to float16 conversion function. Issue reported in coverity scan. > > Coverity issue: 383651 > Fixes: 9637de38a2e3 ("mldev: add scalar type conversion") > > Signed-off-by

Re: [PATCH] mldev: remove weak symbols use in type conversions

Hello, On Sat, Mar 11, 2023 at 3:51 PM Srikanth Yalavarthi wrote: > > Drop use of weak symbols to select the type conversion > functions. Select NEON implementation only on Aarch64 > builds. Enable windows build. > > Fixes: 3c54f91ad8c9 ("mldev: disable build on Windows") Strictly speaking we ar

RE: [PATCH v11 0/3] Fix cmdline_poll and testpmd signal handling

> -Original Message- > From: Tal Shnaiderman > Sent: Monday, March 13, 2023 1:18 AM > To: NBU-Contact-Thomas Monjalon (EXTERNAL) ; > Stephen Hemminger ; Pier Damouny > > Cc: dev@dpdk.org; sta...@dpdk.org; ferruh.yi...@amd.com; Singh, Aman > Deep ; Zhang, Yuying > ; Raslan Darawsheh > Sub

Re: [PATCH] net/sfc: invalidate switch port entry on representor unplug

On 3/12/2023 7:28 AM, Andrew Rybchenko wrote: > On 3/10/23 20:07, Ivan Malov wrote: >> Once allocated, a switch port list entry always stays there, >> even after unplugging the ethdev that created it. Currently, >> the entry's ethdev ID is not cleared on unplug. Referencing >> the ethdev ID of a de

RE: [PATCH] app/crypto-perf: fix test file memory leak

Acked-by: Kai Ji > -Original Message- > From: Power, Ciara > Sent: Friday, March 10, 2023 1:20 PM > To: dev@dpdk.org > Cc: Ji, Kai ; Power, Ciara ; > sta...@dpdk.org > Subject: [PATCH] app/crypto-perf: fix test file memory leak > > A memory leak was detected using the AddressSanitizer t

Re: [PATCH] reorder: fix registration of dynamic field in mbuf

Hello, On Mon, Mar 13, 2023 at 10:35 AM Volodymyr Fialko wrote: > > It's possible to initialize reorder buffer with user allocated memory via > rte_reorder_init() function. In such case rte_reorder_create() not required > and reorder dynamic field in rte_mbuf will be not registered. Good catch.

Re: [PATCH v2 0/2] write link speed to control BAR

On 3/10/2023 6:25 AM, Chaoyong He wrote: > Due to changes in the firmware for NFPs, firmware will no longer write > the link speed of a port to the control BAR. In line with the behaviour > of the kernel NFP driver, this is now handled by the PMD by reading the > value provided by the NSP in the nf

Re: [PATCH] telemetry: fix autotest failures on Alpine

On Fri, Mar 10, 2023 at 11:08:32AM -0800, Stephen Hemminger wrote: > On Fri, 10 Mar 2023 18:18:36 + > Bruce Richardson wrote: > > > On Alpine linux, the telemetry_data_autotest was failing for the > > test where we had dictionaries embedded in other dictionaries up > > to three levels deep. I

[PATCH] reorder: fix registration of dynamic field in mbuf

It's possible to initialize reorder buffer with user allocated memory via rte_reorder_init() function. In such case rte_reorder_create() not required and reorder dynamic field in rte_mbuf will be not registered. Fixes: 01f3496695b5 ("reorder: switch sequence number to dynamic mbuf field") Signed-

Re: [PATCH v2 2/2] net/nfp: write link speed to control BAR

On 3/13/2023 3:03 AM, Chaoyong He wrote: >> On 3/10/2023 6:25 AM, Chaoyong He wrote: >>> + /** >>> +* Shift and mask nn_link_status so that it is effectively the value >>> +* at offset NFP_NET_CFG_STS_NSP_LINK_RATE. >>> +*/ >>> + nn_link_status = (nn_link_status >> >> NFP_NET_CFG_ST

RE: [PATCH] net/e1000: fix saving of stripped VLAN TCI

> -Original Message- > From: Wu, Wenjun1 > Sent: Monday, March 13, 2023 9:39 AM > To: Visa Hankala ; dev@dpdk.org > Cc: Su, Simei > Subject: RE: [PATCH] net/e1000: fix saving of stripped VLAN TCI > > Hi, > > > -Original Message- > > From: Visa Hankala > > Sent: Sunday, March

[PATCH] lib/hash: new feature adding existing key

In some use cases inserting data with the same key shouldn't be overwritten. We use a new flag in this patch to disable overwriting data for the same key. Signed-off-by: Abdullah Ömer Yamaç --- Cc: Yipeng Wang --- lib/hash/rte_cuckoo_hash.c | 10 +- lib/hash/rte_cuckoo_hash.h | 2 ++

[PATCH] lib/hash: new feature adding existing key

In some use cases inserting data with the same key shouldn't be overwritten. We use a new flag in this patch to disable overwriting data for the same key. Signed-off-by: Abdullah Ömer Yamaç --- Cc: Yipeng Wang --- lib/hash/rte_cuckoo_hash.c | 10 +- lib/hash/rte_cuckoo_hash.h | 2 ++

RE: [EXT] Re: [PATCH v4] bus: add platform bus

>-Original Message- >From: Thomas Monjalon >Sent: Friday, March 10, 2023 5:45 PM >To: Tomasz Duszynski >Cc: dev@dpdk.org; chenbo@intel.com; Jerin Jacob Kollanukkaran >; >step...@networkplumber.org; david.march...@redhat.com >Subject: [EXT] Re: [PATCH v4] bus: add platform bus > >E

[PATCH] bus/platform: probe devices without resources

Platform device does not necessarily need to have any resources defined. That means device is only capable of doing DMA transfers and platform bus should not hinder a valid use-case. Signed-off-by: Tomasz Duszynski --- drivers/bus/platform/platform.c | 4 +++- 1 file changed, 3 insertions(+), 1

RE: [EXT] [PATCH 04/16] drivers/event: use previous value atomic fetch operations

> -Original Message- > From: Tyler Retzlaff > Sent: Saturday, March 11, 2023 3:45 AM > To: dev@dpdk.org > Cc: honnappa.nagaraha...@arm.com; ruifeng.w...@arm.com; > tho...@monjalon.net; Tyler Retzlaff > Subject: [EXT] [PATCH 04/16] drivers/event: use previous value atomic fetch > operat

RE: [EXT] [PATCH v2 13/17] drivers/event: use previous value atomic fetch operations

> Use __atomic_fetch_{add,and,or,sub,xor} instead of > __atomic_{add,and,or,sub,xor}_fetch when we have no interest in the > result of the operation. > > Reduces unnecessary codegen that provided the result of the atomic > operation that was not used. > > Change brings closer alignment with atomi