[dpdk-dev] [PATCH v5] doc: add GRO API limitations in prog_guide

This patch adds GRO API limitations in the programmer guide. Fixes: 2c900d09055e ("doc: add GRO guide") Cc: sta...@dpdk.org Signed-off-by: Jiayu Hu --- changes in v5: - remove fix commit 9e0b9d2ec0f4 changes in v4: - update MBUF->l2_len/... requirement changes in v3: - add MBUF limitation change

[dpdk-dev] [PATCH] net/mlx5: fix instruction hotspot on replenishing Rx buffer

On replenishing Rx buffers for vectorized Rx, mbuf->buf_addr isn't needed to be accessed as it is static and easily calculated from the mbuf address. Accessing the mbuf content causes unnecessary load stall and it is worsened on ARM. Fixes: 545b884b1da3 ("net/mlx5: fix buffer address posting in SS

Re: [dpdk-dev] [PATCH] maintainer: claim maintainership of Hashes

On Tue, Jan 08, 2019 at 07:08:34AM -0800, Yipeng Wang wrote: > Add Yipeng and Sameh as additional maintainers. > > Signed-off-by: Yipeng Wang > Signed-off-by: Sameh Gobriel > --- > MAINTAINERS | 2 ++ > 1 file changed, 2 insertions(+) > Acked-by: Bruce Richardson Thanks for stepping up.

[dpdk-dev] [PATCH] config: add Mellanox BlueField ARMv8 SoC

BlueField is Mellanox's new SoC based on ARMv8. BlueField integrates Mellanox ConnectX-5 interconnect and Cortex-A72 cores into a single device. http://www.mellanox.com/page/products_dyn?product_family=256&mtag=soc_overview Signed-off-by: Yongseok Koh --- This patch should be applied after

Re: [dpdk-dev] [PATCH 1/2] config: gather options for dlopen mlx dependency

On Wed, Jan 09, 2019 at 03:05:23AM +0100, Thomas Monjalon wrote: > Rename options CONFIG_RTE_LIBRTE_MLX4_DLOPEN_DEPS and > CONFIG_RTE_LIBRTE_MLX5_DLOPEN_DEPS to a single option > CONFIG_RTE_IBVERBS_LINK_DLOPEN. > Rename meson option enable_driver_mlx_glue to ibverbs_link. > > There was no good rea

Re: [dpdk-dev] [PATCH] net/mlx5: fix instruction hotspot on replenishing Rx buffer

On Wed, Jan 9, 2019 at 9:54 AM Yongseok Koh wrote: > On replenishing Rx buffers for vectorized Rx, mbuf->buf_addr isn't needed > to be accessed as it is static and easily calculated from the mbuf address. > Accessing the mbuf content causes unnecessary load stall and it is worsened > on ARM. > >

Re: [dpdk-dev] [PATCH 2/2] config: add static linkage of mlx dependency

On Wed, Jan 09, 2019 at 03:05:24AM +0100, Thomas Monjalon wrote: > The libraries provided by rdma-core may be statically linked > if enabling CONFIG_RTE_IBVERBS_LINK_STATIC in the make-based build. > If CONFIG_RTE_BUILD_SHARED_LIB is disabled, > the applications will embed the mlx PMDs with ibverbs

[dpdk-dev] [PATCH] config: change default cache line size for ARMv8 with meson

In config/arm64_armv8_linuxapp_gcc, maximum available cache line size (128B) in arm64 implementations is set by default for generic config. However, setting 64B is preferable for meson build in order to support majority of CPUs which don't have Implementor ID or Part Number programmed on chip. Sig

Re: [dpdk-dev] [PATCH] config: add Mellanox BlueField ARMv8 SoC

On Wed, 2019-01-09 at 01:32 -0800, Yongseok Koh wrote: > BlueField is Mellanox's new SoC based on ARMv8. BlueField integrates > Mellanox ConnectX-5 interconnect and Cortex-A72 cores into a single > device. > > http://www.mellanox.com/page/products_dyn?product_family=256&mtag=soc_overview > > Sign

Re: [dpdk-dev] [PATCH] net/mlx5: fix instruction hotspot on replenishing Rx buffer

On Wed, Jan 09, 2019 at 10:38:07AM +0100, David Marchand wrote: > On Wed, Jan 9, 2019 at 9:54 AM Yongseok Koh wrote: > > > On replenishing Rx buffers for vectorized Rx, mbuf->buf_addr isn't needed > > to be accessed as it is static and easily calculated from the mbuf address. > > Accessing the mb

Re: [dpdk-dev] [PATCH] config: add Mellanox BlueField ARMv8 SoC

> On Jan 9, 2019, at 1:43 AM, Jerin Jacob Kollanukkaran > wrote: > > On Wed, 2019-01-09 at 01:32 -0800, Yongseok Koh wrote: >> BlueField is Mellanox's new SoC based on ARMv8. BlueField integrates >> Mellanox ConnectX-5 interconnect and Cortex-A72 cores into a single >> device. >> >> http://w

Re: [dpdk-dev] [PATCH 1/2] config: gather options for dlopen mlx dependency

09/01/2019 10:33, Bruce Richardson: > On Wed, Jan 09, 2019 at 03:05:23AM +0100, Thomas Monjalon wrote: > > Rename options CONFIG_RTE_LIBRTE_MLX4_DLOPEN_DEPS and > > CONFIG_RTE_LIBRTE_MLX5_DLOPEN_DEPS to a single option > > CONFIG_RTE_IBVERBS_LINK_DLOPEN. > > Rename meson option enable_driver_mlx_gl

Re: [dpdk-dev] [PATCH] net/mlx5: fix instruction hotspot on replenishing Rx buffer

> On Jan 9, 2019, at 1:52 AM, Olivier Matz wrote: > > On Wed, Jan 09, 2019 at 10:38:07AM +0100, David Marchand wrote: >> On Wed, Jan 9, 2019 at 9:54 AM Yongseok Koh wrote: >> >>> On replenishing Rx buffers for vectorized Rx, mbuf->buf_addr isn't needed >>> to be accessed as it is static and e

Re: [dpdk-dev] [EXT] Re: [PATCH] config: add Mellanox BlueField ARMv8 SoC

On Wed, 2019-01-09 at 09:51 +, Yongseok Koh wrote: > External Email > > --- > --- > > > > On Jan 9, 2019, at 1:43 AM, Jerin Jacob Kollanukkaran < > > jer...@marvell.com> wrote: > > > > On Wed, 2019-01-09 at 01:32 -0800, Yongseo

Re: [dpdk-dev] [PATCH 2/2] config: add static linkage of mlx dependency

09/01/2019 10:37, Bruce Richardson: > On Wed, Jan 09, 2019 at 03:05:24AM +0100, Thomas Monjalon wrote: > > The libraries provided by rdma-core may be statically linked > > if enabling CONFIG_RTE_IBVERBS_LINK_STATIC in the make-based build. > > If CONFIG_RTE_BUILD_SHARED_LIB is disabled, > > the app

Re: [dpdk-dev] [PATCH] net/mlx5: fix instruction hotspot on replenishing Rx buffer

On Wed, Jan 9, 2019 at 10:56 AM Yongseok Koh wrote: > > > On Jan 9, 2019, at 1:52 AM, Olivier Matz wrote: > > > > On Wed, Jan 09, 2019 at 10:38:07AM +0100, David Marchand wrote: > >> On Wed, Jan 9, 2019 at 9:54 AM Yongseok Koh wrote: > >> > >>> On replenishing Rx buffers for vectorized Rx, mbuf

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

On Wed, 2019-01-09 at 01:39 -0800, Yongseok Koh wrote: > > --- > --- > In config/arm64_armv8_linuxapp_gcc, maximum available cache line size > (128B) in arm64 implementations is set by default for generic config. > However, setting 64

Re: [dpdk-dev] [PATCH] net/mlx5: fix instruction hotspot on replenishing Rx buffer

> On Jan 9, 2019, at 2:05 AM, David Marchand wrote: > > > > On Wed, Jan 9, 2019 at 10:56 AM Yongseok Koh wrote: > > > On Jan 9, 2019, at 1:52 AM, Olivier Matz wrote: > > > > On Wed, Jan 09, 2019 at 10:38:07AM +0100, David Marchand wrote: > >> On Wed, Jan 9, 2019 at 9:54 AM Yongseok Koh

[dpdk-dev] [PATCH v3 2/4] meson: add infra to support machine specific flags

From: Pavan Nikhilesh Currently, RTE_* flags are set based on the implementer ID but there might be some micro arch specific differences from the same vendor eg. CACHE_LINESIZE. Add support to set micro arch specific flags. Signed-off-by: Jerin Jacob Signed-off-by: Pavan Nikhilesh --- v2 Chan

[dpdk-dev] [PATCH v3 4/4] config: add octeontx2 machine config

From: Jerin Jacob Optimized configuration for Marvell octeontx2 SoC. Update meson build to support Marvell octeontx2 SoC. Signed-off-by: Jerin Jacob Signed-off-by: Pavan Nikhilesh --- config/arm/meson.build| 10 +- config/defconfig_arm64-octeontx2-linuxapp-gcc | 18

[dpdk-dev] [PATCH v3 3/4] config: add thunderx2 machine config

From: Jerin Jacob Optimized configuration for Marvell thunderx2 SoC. Update meson build to support Marvell thunderx2 SoC. Product details are here: https://www.marvell.com/server-processors/thunderx2-arm-processors/ Signed-off-by: Jerin Jacob Signed-off-by: Pavan Nikhilesh --- v3 Changes:

[dpdk-dev] [PATCH v3 1/4] mk: introduce helper to check valid compiler argument

From: Jerin Jacob Introduce rte_cc_has_argument() Makefile helper to check a given argument is support by the compiler. Example Usage: include $(RTE_SDK)/mk/rte.helper.mk MACHINE_CFLAGS += $(call rte_cc_has_argument, -mcpu=octeontx2) This would allow adding -mcpu=octeontx2 in MACHINE_CFLAGS if

[dpdk-dev] [PATCH v3 5/5] meson: add cross build targets for thunderx2 and octeontx2

From: Pavan Nikhilesh Add Thunderx2 and Octeontx2 SoC cross build targets. meson build --cross-file config/arm/arm64___ Signed-off-by: Jerin Jacob Signed-off-by: Pavan Nikhilesh --- config/arm/arm64_octeontx2_linuxapp_gcc | 14 ++ config/arm/arm64_thunderx2_linuxapp_gcc | 14 +

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

On Wed, 2019-01-09 at 10:09 +, Jerin Jacob Kollanukkaran wrote: > On Wed, 2019-01-09 at 01:39 -0800, Yongseok Koh wrote: > > > > --- > > --- > > In config/arm64_armv8_linuxapp_gcc, maximum available cache line > > size > > (128B)

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

> On Jan 9, 2019, at 2:09 AM, Jerin Jacob Kollanukkaran > wrote: > > On Wed, 2019-01-09 at 01:39 -0800, Yongseok Koh wrote: >> >> --- >> --- >> In config/arm64_armv8_linuxapp_gcc, maximum available cache line size >> (128B) in ar

[dpdk-dev] [PATCH v4 2/5] meson: add infra to support machine specific flags

From: Pavan Nikhilesh Currently, RTE_* flags are set based on the implementer ID but there might be some micro arch specific differences from the same vendor eg. CACHE_LINESIZE. Add support to set micro arch specific flags. Signed-off-by: Jerin Jacob Signed-off-by: Pavan Nikhilesh --- config/

[dpdk-dev] [PATCH v4 3/5] config: add thunderx2 machine config

From: Jerin Jacob Optimized configuration for Marvell thunderx2 SoC. Update meson build to support Marvell thunderx2 SoC. Product details are here: https://www.marvell.com/server-processors/thunderx2-arm-processors/ Signed-off-by: Jerin Jacob Signed-off-by: Pavan Nikhilesh --- config/arm/me

[dpdk-dev] [PATCH v4 1/5] mk: introduce helper to check valid compiler argument

From: Jerin Jacob Introduce rte_cc_has_argument() Makefile helper to check a given argument is support by the compiler. Example Usage: include $(RTE_SDK)/mk/rte.helper.mk MACHINE_CFLAGS += $(call rte_cc_has_argument, -mcpu=octeontx2) This would allow adding -mcpu=octeontx2 in MACHINE_CFLAGS if

[dpdk-dev] [PATCH v4 4/5] config: add octeontx2 machine config

From: Jerin Jacob Optimized configuration for Marvell octeontx2 SoC. Update meson build to support Marvell octeontx2 SoC. Signed-off-by: Jerin Jacob Signed-off-by: Pavan Nikhilesh --- config/arm/meson.build| 10 +- config/defconfig_arm64-octeontx2-linuxapp-gcc | 18

[dpdk-dev] [PATCH v4 5/5] meson: add cross build targets for thunderx2 and octeontx2

From: Pavan Nikhilesh Add Thunderx2 and Octeontx2 SoC cross build targets. meson build --cross-file config/arm/arm64___ Signed-off-by: Pavan Nikhilesh --- config/arm/arm64_octeontx2_linuxapp_gcc | 14 ++ config/arm/arm64_thunderx2_linuxapp_gcc | 14 ++ 2 files changed,

Re: [dpdk-dev] [PATCH v3 1/2] cryptodev: change queue pair configure structure

Hi, > -Original Message- > From: Zhang, Roy Fan > Sent: Friday, December 21, 2018 1:56 PM > To: dev@dpdk.org > Cc: akhil.go...@nxp.com; De Lara Guarch, Pablo > ; Trahe, Fiona > Subject: [PATCH v3 1/2] cryptodev: change queue pair configure structure > > This patch changes the cryptodev q

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

On Wed, 2019-01-09 at 10:22 +, Yongseok Koh wrote: > > On Jan 9, 2019, at 2:09 AM, Jerin Jacob Kollanukkaran < > > jer...@marvell.com> wrote: > > > > On Wed, 2019-01-09 at 01:39 -0800, Yongseok Koh wrote: > > > --- > > > > > > --

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

On Wed, 2019-01-09 at 10:19 +, Luca Boccassi wrote: > On Wed, 2019-01-09 at 10:09 +, Jerin Jacob Kollanukkaran wrote: > > On Wed, 2019-01-09 at 01:39 -0800, Yongseok Koh wrote: > > > --- > > > > > > --- > > > In config/arm64_a

Re: [dpdk-dev] [PATCH] net/nfp: add CPP bridge as service

On 1/3/2019 8:56 AM, Alejandro Lucero wrote: > The Netronome's Network Flow Processor chip is highly programmable > with the goal of processing packets at high speed. Processing units > and other chip components are available from the host through the > PCIe CPP(Command Push Pull bus) interface. Th

Re: [dpdk-dev] [PATCH v2] doc: fix a parameter name in testpmd guide

On 1/4/2019 9:57 AM, Iremonger, Bernard wrote: >> -Original Message- >> From: Rami Rosen [mailto:ramir...@gmail.com] >> Sent: Friday, January 4, 2019 9:11 AM >> To: dev@dpdk.org >> Cc: sta...@dpdk.org; Iremonger, Bernard ; >> Rami Rosen >> Subject: [PATCH v2] doc: fix a parameter name in t

Re: [dpdk-dev] [PATCH v3 2/2] cryptodev: change symmetric session structure

Hi Fan, > -Original Message- > From: Zhang, Roy Fan > Sent: Friday, December 21, 2018 1:56 PM > To: dev@dpdk.org > Cc: akhil.go...@nxp.com; De Lara Guarch, Pablo > ; Trahe, Fiona > Subject: [PATCH v3 2/2] cryptodev: change symmetric session structure > > This patch changes the symmetric

[dpdk-dev] [PATCH] net/sfc: add missing header guard to TSO header file

From: Ivan Malov Add missing header guard, including compiler directive for cplusplus. Fixes: f1f575be9b76 ("net/sfc: put generalised TSO declarations in a header") Cc: sta...@dpdk.org Signed-off-by: Ivan Malov Signed-off-by: Andrew Rybchenko --- drivers/net/sfc/sfc_tso.h | 13 +

[dpdk-dev] [PATCH] net/sfc: discard last seen VLAN TCI if Tx packet is dropped

From: Ivan Malov Early processing of a packet on transmit may change last seen VLAN TCI in the queue context. If such a packet is eventually dropped, last seen VLAN TCI must be set to its previous value. Fixes: 7fd636815a43 ("net/sfc: support VLAN offload on transmit path") Cc: sta...@dpdk.org

Re: [dpdk-dev] [PATCH v3 2/2] cryptodev: change symmetric session structure

Hi Pablo, Thanks for the review. Comments inline. Regards, Fan > -Original Message- > From: De Lara Guarch, Pablo > Sent: Wednesday, January 9, 2019 11:01 AM > To: Zhang, Roy Fan ; dev@dpdk.org > Cc: akhil.go...@nxp.com; Trahe, Fiona > Subject: RE: [PATCH v3 2/2] cryptodev: change symme

[dpdk-dev] [PATCH] net/sfc/base: fix Tx descriptor max number check

From: Igor Romanov Fix check of maximum descriptor number (compare with maximum Tx descriptor number instead of maximum EVQ events number). Fixes: f7dc06bf35f2 ("net/sfc/base: import 5xxx/6xxx family support") Cc: sta...@dpdk.org Signed-off-by: Igor Romanov Signed-off-by: Andrew Rybchenko ---

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

09/01/2019 11:49, Jerin Jacob Kollanukkaran: > On Wed, 2019-01-09 at 10:22 +, Yongseok Koh wrote: > > On Jan 9, 2019, at 2:09 AM, Jerin Jacob Kollanukkaran wrote: > > > I think, I way forward is to add config/arm/arm64_a72_linuxapp_gcc > > > for meson. This config can be used for all SoC with A

Re: [dpdk-dev] [PATCH v3 1/2] cryptodev: change queue pair configure structure

Hi Pablo, Thanks for the review. Comments inline. > -Original Message- > From: De Lara Guarch, Pablo > Sent: Tuesday, January 8, 2019 11:21 PM > To: Zhang, Roy Fan ; dev@dpdk.org > Cc: akhil.go...@nxp.com; Trahe, Fiona > Subject: RE: [PATCH v3 1/2] cryptodev: change queue pair configure

[dpdk-dev] [PATCH v6 0/3] ring test enhancement and new ring reset api and use it by hash

V6: Made upper case for the user name to comply with the convention. V5: 1. Commit message tweaking for ring test case enhancement patch 2. Upper to lower for mails to make match/grep more easily V4: 1. Include the ring perf test case enhancement patch in the series. 2. Replace ARRAY_SIZE with R

[dpdk-dev] [PATCH v6 3/3] hash: flush the rings instead of dequeuing one by one

From: Gavin Hu Within rte_hash_reset, calling a while loop to dequeue one by one from the ring, while not using them at all, is wasting cycles, The patch just flush the ring by resetting the indices can save cpu cycles. Fixes: b26473ff8f4a ("hash: add reset function") Fixes: 75706568a7eb ("hash:

[dpdk-dev] [PATCH v6 1/3] test/ring: ring perf test case enhancement

From: Joyce Kong Run ring perf test on all available cores to really verify MPMC operations. The old way of running on a pair of cores is not enough for MPMC rings. Suggested-by: Gavin Hu Signed-off-by: Joyce Kong Reviewed-by: Ruifeng Wang Reviewed-by: Honnappa Nagarahalli Reviewed-by: Dharm

[dpdk-dev] [PATCH v6 2/3] ring: add reset API to flush the ring when not in use

From: Gavin Hu Currently, the flush is done by dequeuing the ring in a while loop. It is much simpler to flush the queue by resetting the head and tail indices. Signed-off-by: Gavin Hu Reviewed-by: Ruifeng Wang Reviewed-by: Honnappa Nagarahalli --- lib/librte_ring/rte_ring.h | 20 +

[dpdk-dev] [PATCH v2] doc: fix MAC address rewrite actions documentation

This patch fixes a typo in SET_MAC_DST action description. It also adds restriction note for set MAC src/dst actions description. Fixes: 15dbcdaada77 ("ethdev: add generic MAC address rewrite actions") Cc: jack...@mellanox.com Signed-off-by: Dekel Peled --- doc/guides/prog_guide/rte_flow.rst |

[dpdk-dev] [PATCH v7 00/10] examples/ipsec-secgw: make app to use ipsec library

This patch series depends on the patch series: ipsec: new library for IPsec data-path processing http://patches.dpdk.org/patch/49410/ http://patches.dpdk.org/patch/49411/ http://patches.dpdk.org/patch/49412/ http://patches.dpdk.org/patch/49413/ http://patches.dpdk.org/patch/49414/ http://patches.d

[dpdk-dev] [PATCH v7 03/10] examples/ipsec-secgw: fix crypto-op might never get dequeued

In some cases crypto-ops could never be dequeued from the crypto-device. The easiest way to reproduce: start ipsec-secgw with crypto-dev and send to it less then 32 packets. none packets will be forwarded. Reason for that is that the application does dequeue() from crypto-queues only when new packe

[dpdk-dev] [PATCH v7 02/10] examples/ipsec-secgw: allow to specify neighbour mac address

In some cases it is useful to allow user to specify destination ether address for outgoing packets. This patch adds such ability by introducing new 'neigh' config file option. Signed-off-by: Konstantin Ananyev Acked-by: Radu Nicolau --- doc/guides/sample_app_ug/ipsec_secgw.rst | 42 ++-

[dpdk-dev] [PATCH v7 01/10] examples/ipsec-secgw: allow user to disable some RX/TX offloads

Right now ipsec-secgw always enables TX offloads (DEV_TX_OFFLOAD_MULTI_SEGS, DEV_TX_OFFLOAD_SECURITY), even when they are not requested by the config. That causes many PMD to choose full-featured TX function, which in many cases is much slower then one without offloads. That patch adds ability for

[dpdk-dev] [PATCH v7 06/10] examples/ipsec-secgw: fix inbound SA checking

In the inbound_sa_check() make sure that sa pointer stored inside mbuf private area is not NULL. Fixes: d299106e8e31 ("examples/ipsec-secgw: add IPsec sample application") Cc: sta...@dpdk.org Signed-off-by: Bernard Iremonger Acked-by: Radu Nicolau Signed-off-by: Konstantin Ananyev --- example

[dpdk-dev] [PATCH v7 04/10] examples/ipsec-secgw: fix outbound codepath for single SA

Looking at process_pkts_outbound_nosp() there seems few issues: - accessing mbuf after it was freed - invoking ipsec_outbound() for ipv4 packets only - copying number of packets, but not the mbuf pointers itself that patch provides fixes for that issues. Fixes: 906257e965b7 ("examples/ipsec-secgw

[dpdk-dev] [PATCH v7 05/10] examples/ipsec-secgw: make local variables static

in sp4.c and sp6.c there are few globals that used only locally. Define them as static ones. Cc: sta...@dpdk.org Signed-off-by: Konstantin Ananyev Acked-by: Radu Nicolau --- examples/ipsec-secgw/sp4.c | 10 +- examples/ipsec-secgw/sp6.c | 10 +- 2 files changed, 10 insertions(+

[dpdk-dev] [PATCH v7 08/10] examples/ipsec-secgw: make data-path to use ipsec library

Changes to make ipsec-secgw data-path code to utilize librte_ipsec library. Note that right now by default current (non-librte_ipsec) code-path will be used. User has to run application with new command-line option ('-l') to enable new codepath. Signed-off-by: Mohammad Abdul Awal Signed-off-by: B

[dpdk-dev] [PATCH v7 09/10] examples/ipsec-secgw: add scripts for functional test

The purpose of these scripts is to automate ipsec-secgw functional testing. The scripts require two machines (SUT and DUT) connected through at least 2 NICs and running linux (so far tested only on Ubuntu 18.04). Introduced test-cases for the following scenarios: - Transport/Tunnel modes - AES-CBC

[dpdk-dev] [PATCH v7 10/10] doc: update ipsec-secgw guide and relelase notes

Update ipsec-secgw guide and relelase notes to reflect latest changes. Signed-off-by: Bernard Iremonger Signed-off-by: Konstantin Ananyev --- doc/guides/rel_notes/release_19_02.rst | 14 +++ doc/guides/sample_app_ug/ipsec_secgw.rst | 105 ++- 2 files changed, 117 insertio

[dpdk-dev] [PATCH v7 07/10] examples/ipsec-secgw: make app to use ipsec library

Changes to make ipsec-secgw to utilize librte_ipsec library. That patch provides: - changes in the related data structures. - changes in the initialization code. - new command-line parameters to enable librte_ipsec codepath and related features. Note that right now by default current (non-li

[dpdk-dev] [PATCH v2] doc: fix aesni mb documentation.

This patch fixes the incorrect intel multi buffer library support version and missed limitation of GCM algorithm support. Fixes: 0e9f8507afcb ("crypto/aesni_mb: support AES-GCM algorithm") Cc: sta...@dpdk.org Signed-off-by: Fan Zhang --- v2: -fixed a typo doc/guides/cryptodevs/aesni_mb.rst | 8

Re: [dpdk-dev] [dpdk-stable] [PATCH v2] app/testpmd: fix quit to stop all ports before close

On 1/4/2019 1:47 PM, Iremonger, Bernard wrote: >> -Original Message- >> From: Dumitrescu, Cristian >> Sent: Friday, January 4, 2019 12:29 PM >> To: dev@dpdk.org >> Cc: Lu, Wenzhuo ; Wu, Jingjing >> ; Iremonger, Bernard ; >> sta...@dpdk.org >> Subject: [PATCH v2] app/testpmd: fix quit to sto

[dpdk-dev] [PATCH v2] config: add Mellanox BlueField ARMv8 SoC

BlueField is Mellanox's new SoC based on ARMv8. BlueField integrates Mellanox ConnectX-5 interconnect and Cortex-A72 cores into a single device. http://www.mellanox.com/page/products_dyn?product_family=256&mtag=soc_overview Signed-off-by: Yongseok Koh --- config/defconfig_arm64-bluefield-linuxa

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

On Wed, 2019-01-09 at 12:28 +0100, Thomas Monjalon wrote: > 09/01/2019 11:49, Jerin Jacob Kollanukkaran: > > On Wed, 2019-01-09 at 10:22 +, Yongseok Koh wrote: > > > On Jan 9, 2019, at 2:09 AM, Jerin Jacob Kollanukkaran wrote: > > > > I think, I way forward is to add > > > > config/arm/arm64_a7

Re: [dpdk-dev] [PATCH v2] config: add Mellanox BlueField ARMv8 SoC

On Wed, 2019-01-09 at 04:34 -0800, Yongseok Koh wrote: > BlueField is Mellanox's new SoC based on ARMv8. BlueField integrates > Mellanox ConnectX-5 interconnect and Cortex-A72 cores into a single > device. > > http://www.mellanox.com/page/products_dyn?product_family=256&mtag=soc_overview > > Sign

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

On Wed, 2019-01-09 at 10:52 +, Jerin Jacob Kollanukkaran wrote: > On Wed, 2019-01-09 at 10:19 +, Luca Boccassi wrote: > > On Wed, 2019-01-09 at 10:09 +, Jerin Jacob Kollanukkaran wrote: > > > On Wed, 2019-01-09 at 01:39 -0800, Yongseok Koh wrote: > > > >

[dpdk-dev] [PATCH v2 1/2] mbuf: add function returning default buffer address

This patch introduces two new functions - rte_mbuf_buf_addr_default() and rte_mbuf_data_baddr_default(). rte_mbuf_buf_addr_default() reutrns the default buffer address of given mbuf which comes after mbuf structure and private data. rte_mbuf_data_baddr_default() returns the default address of mbu

[dpdk-dev] [PATCH v2 2/2] net/mlx5: fix instruction hotspot on replenishing Rx buffer

On replenishing Rx buffers for vectorized Rx, mbuf->buf_addr isn't needed to be accessed as it is static and easily calculated from the mbuf address. Accessing the mbuf content causes unnecessary load stall and it is worsened on ARM. Fixes: 545b884b1da3 ("net/mlx5: fix buffer address posting in SS

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

09/01/2019 13:47, Jerin Jacob Kollanukkaran: > On Wed, 2019-01-09 at 12:28 +0100, Thomas Monjalon wrote: > > 09/01/2019 11:49, Jerin Jacob Kollanukkaran: > > > On Wed, 2019-01-09 at 10:22 +, Yongseok Koh wrote: > > > > On Jan 9, 2019, at 2:09 AM, Jerin Jacob Kollanukkaran wrote: > > > > > I thi

Re: [dpdk-dev] [PATCH v2 1/2] mbuf: add function returning default buffer address

On Wed, Jan 9, 2019 at 2:19 PM Yongseok Koh wrote: > This patch introduces two new functions - rte_mbuf_buf_addr_default() and > rte_mbuf_data_baddr_default(). > > rte_mbuf_buf_addr_default() reutrns the default buffer address of given > mbuf which comes after mbuf structure and private data. >

Re: [dpdk-dev] net/bonding: fix possible null pointer reference

On 1/8/2019 11:17 AM, Declan Doherty wrote: > In function check_for_bonded_ethdev the driver name is used without > validating the pointer references in the passed ethdev object. > > Fixes: 740feaf349b1 ("ethdev: remove driver name from device private data") > Cc: sta...@dpdk.org > > Signed-off-b

Re: [dpdk-dev] [PATCH] net/nfp: add CPP bridge as service

On Wed, Jan 9, 2019 at 10:54 AM Ferruh Yigit wrote: > On 1/3/2019 8:56 AM, Alejandro Lucero wrote: > > The Netronome's Network Flow Processor chip is highly programmable > > with the goal of processing packets at high speed. Processing units > > and other chip components are available from the ho

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

On Wed, 2019-01-09 at 14:30 +0100, Thomas Monjalon wrote: > 09/01/2019 13:47, Jerin Jacob Kollanukkaran: > > On Wed, 2019-01-09 at 12:28 +0100, Thomas Monjalon wrote: > > > 09/01/2019 11:49, Jerin Jacob Kollanukkaran: > > > > On Wed, 2019-01-09 at 10:22 +, Yongseok Koh wrote: > > > > > On Jan 9

[dpdk-dev] [PATCH v2 1/2] config: gather options for dlopen mlx dependency

Rename options CONFIG_RTE_LIBRTE_MLX4_DLOPEN_DEPS and CONFIG_RTE_LIBRTE_MLX5_DLOPEN_DEPS to a single option CONFIG_RTE_IBVERBS_LINK_DLOPEN. Rename meson option enable_driver_mlx_glue to ibverbs_link. There was no good reason for setting a different link option for mlx4 and mlx5. Having a single co

[dpdk-dev] [PATCH v2 2/2] config: add static linkage of mlx dependency

The libraries provided by rdma-core may be statically linked if enabling CONFIG_RTE_IBVERBS_LINK_STATIC in the make-based build. If CONFIG_RTE_BUILD_SHARED_LIB is disabled, the applications will embed the mlx PMDs with ibverbs and the mlx libraries. If CONFIG_RTE_BUILD_SHARED_LIB is enabled, the ml

Re: [dpdk-dev] [PATCH v2] net/virtio: add platform memory ordering feature support

On 27.12.2018 13:07, Shahaf Shuler wrote: > Hi Ilya, > > Wednesday, December 26, 2018 6:37 PM, Ilya Maximets: >> Subject: [dpdk-dev] [PATCH v2] net/virtio: add platform memory ordering >> feature support >> >> VIRTIO_F_ORDER_PLATFORM is required to use proper memory barriers in >> case of HW vhos

Re: [dpdk-dev] [PATCH] drivers: fix sprintf with snprintf

On 1/7/2019 4:16 PM, Pallantla Poornima wrote: > sprintf function is not secure as it doesn't check the length of string. > More secure function snprintf is used > > Fixes: 828d51d8fc ("bus/fslmc: refactor scan and probe functions") > Fixes: c22fab9a6c ("raw/dpaa2_qdma: support configuration APIs

[dpdk-dev] [PATCH v3 0/3] Missing barriers and VIRTIO_F_ORDER_PLATFORM.

Version 3: * Added 2 patches with fixes for current virtio driver. Not directly connected with the new feature. Version 2: * rebased on current master (packed rings). RFC --> Version 1: * Dropped vendor-specific hack to determine if we need real barriers. * Added VIRTIO_F_ORDER_PLATFO

[dpdk-dev] [PATCH v3 1/3] net/virtio: add missing barrier before reading the flags

Reading the used->flags could be reordered with avail->idx update. vhost in kernel disables notifications for the time of packets receiving, like this: 1. disable notify 2. process packets 3. enable notify 4. has more packets ? goto 1 In case of reordering, virtio driver could rea

[dpdk-dev] [PATCH v3 2/3] net/virtio: update memory ordering comment for vq notify

We're not using io ports in case of modern device even on IA. Also, this comment useless for other architectures. Signed-off-by: Ilya Maximets --- drivers/net/virtio/virtqueue.h | 9 - 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/virtio/virtqueue.h b/drivers/

[dpdk-dev] [PATCH v3 3/3] net/virtio: add platform memory ordering feature support

VIRTIO_F_ORDER_PLATFORM is required to use proper memory barriers in case of HW vhost implementations like vDPA. DMA barriers (rte_cio_*) are sufficent for that purpose. Previously known as VIRTIO_F_IO_BARRIER. Signed-off-by: Ilya Maximets --- drivers/net/virtio/virtio_ethdev.c | 2 ++ driver

Re: [dpdk-dev] [PATCH v3 0/3] Missing barriers and VIRTIO_F_ORDER_PLATFORM.

On Wed, Jan 09, 2019 at 05:50:12PM +0300, Ilya Maximets wrote: > Version 3: > * Added 2 patches with fixes for current virtio driver. > Not directly connected with the new feature. New version shouldn't be reply-to old one really :). But the patches are good I think. Acked-by: Michael S. Ts

[dpdk-dev] [PATCH] examples/vhost: remove unnecessary method and constant

This cleanup patch removes a method and a constant which are now unnecessary in the VHOST sample applicaiopn, namely the validate_num_devices() method and the MAX_DEVICES constant. Fixes: 56fe86f8dcaf ("examples/vhost: embed statistics into device structure") Cc: sta...@dpdk.org Signed-off-by: R

Re: [dpdk-dev] [EXT] [PATCH] config: change default cache line size for ARMv8 with meson

09/01/2019 15:23, Jerin Jacob Kollanukkaran: > On Wed, 2019-01-09 at 14:30 +0100, Thomas Monjalon wrote: > > 09/01/2019 13:47, Jerin Jacob Kollanukkaran: > > > On Wed, 2019-01-09 at 12:28 +0100, Thomas Monjalon wrote: > > > > 09/01/2019 11:49, Jerin Jacob Kollanukkaran: > > > > > On Wed, 2019-01-09

Re: [dpdk-dev] [PATCH v2 1/2] config: gather options for dlopen mlx dependency

Wednesday, January 9, 2019 4:23 PM, Thomas Monjalon: > Subject: [PATCH v2 1/2] config: gather options for dlopen mlx dependency > > Rename options CONFIG_RTE_LIBRTE_MLX4_DLOPEN_DEPS and > CONFIG_RTE_LIBRTE_MLX5_DLOPEN_DEPS to a single option > CONFIG_RTE_IBVERBS_LINK_DLOPEN. > Rename meson option

[dpdk-dev] [PATCH] crypto/dpaa_sec: support PDCP offload

From: Hemant Agrawal PDCP session configuration for lookaside protocol offload and data path is added. Signed-off-by: Hemant Agrawal Acked-by: Akhil Goyal --- drivers/crypto/dpaa_sec/dpaa_sec.c | 268 + drivers/crypto/dpaa_sec/dpaa_sec.h | 212 +

[dpdk-dev] [PATCH] crypto/dpaa_sec: support same session flows on multi cores

In dpaa_sec, each session should have a separate in-queue, and each in-queue should be mapped to an outq. So if multiple flows of same SA comes to different cores due to rss distribution of NIC, enqueue from any core will try to do re-assignment of inq - outq mapping which will fail. In this patch

[dpdk-dev] [PATCH] crypto/dpaa2_sec: fix FLC address for physical mode

Fixes: 547a4d40e7bf ("crypto/dpaa2_sec: support out of place protocol offload") Fixes: 0a23d4b6f4c2 ("crypto/dpaa2_sec: support protocol offload IPsec") Cc:sta...@dpdk.org Signed-off-by: Akhil Goyal --- drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 del

Re: [dpdk-dev] [PATCH v3 0/3] Missing barriers and VIRTIO_F_ORDER_PLATFORM.

On 09.01.2019 17:55, Michael S. Tsirkin wrote: > On Wed, Jan 09, 2019 at 05:50:12PM +0300, Ilya Maximets wrote: >> Version 3: >> * Added 2 patches with fixes for current virtio driver. >> Not directly connected with the new feature. > > New version shouldn't be reply-to old one really :). I

Re: [dpdk-dev] [PATCH] config: change default cache line size for ARMv8 with meson

> > Please check below thread and patch. > > > > http://mails.dpdk.org/archives/dev/2019-January/122676.html > > https://patches.dpdk.org/patch/49477/ > > > > Debian folks are building like this for the _generic_ image. > > What ever works for every distros, I am fine with that. > > > > meson c

Re: [dpdk-dev] [RFC] function to parse packet headers

Cutting in Olivier, requesting input as the maintainer of rte_net. > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of > long...@viettel.com.vn > > Hi Morten, > > What is the difference compare to rte_net_get_ptype(), which also > parses > packet types and reports on header length. > > In my

Re: [dpdk-dev] [PATCH] config: change default cache line size for ARMv8 with meson

On Wed, 2019-01-09 at 15:34 +, Jerin Jacob Kollanukkaran wrote: > > > Please check below thread and patch. > > > > > > http://mails.dpdk.org/archives/dev/2019-January/122676.html > > > https://patches.dpdk.org/patch/49477/ > > > > > > Debian folks are building like this for the _generic_ imag

Re: [dpdk-dev] [PATCH v2] net/virtio: add platform memory ordering feature support

On Wed, Jan 09, 2019 at 05:34:38PM +0300, Ilya Maximets wrote: > virtio_mb() is really heavy. I'd like to avoid it somehow, but I don't > know how to do this yet. Linux driver doesn't avoid it either. -- MST

Re: [dpdk-dev] [RFC] function to parse packet headers

From: Rami Rosen [mailto:roszenr...@gmail.com] >Hi Morten, >A good idea, thanks for volunteering!  >Several minor comments:  >I would consider calling it rte_mbuf_hdr_parse(), to make it more related to >the rte_mbuf* methods, and also I would consider having it in librte_mbuf and >not in librte

Re: [dpdk-dev] [dpdk-stable] [PATCH] net/sfc: add missing header guard to TSO header file

On 1/9/2019 11:05 AM, Andrew Rybchenko wrote: > From: Ivan Malov > > Add missing header guard, including compiler directive for cplusplus. > > Fixes: f1f575be9b76 ("net/sfc: put generalised TSO declarations in a header") > Cc: sta...@dpdk.org > > Signed-off-by: Ivan Malov > Signed-off-by: Andr

Re: [dpdk-dev] [PATCH] net/nfp: add CPP bridge as service

On 1/9/2019 2:20 PM, Alejandro Lucero wrote: > > > On Wed, Jan 9, 2019 at 10:54 AM Ferruh Yigit > wrote: > > On 1/3/2019 8:56 AM, Alejandro Lucero wrote: > > The Netronome's Network Flow Processor chip is highly programmable > > with the goal of proces

Re: [dpdk-dev] [EXT] Re: [PATCH] config: change default cache line size for ARMv8 with meson

On Wed, 2019-01-09 at 15:41 +, Luca Boccassi wrote: > External Email > > --- > --- > On Wed, 2019-01-09 at 15:34 +, Jerin Jacob Kollanukkaran wrote: > > > > Please check below thread and patch. > > > > > > > > http://mails.dp

Re: [dpdk-dev] [dpdk-stable] [PATCH] net/sfc: discard last seen VLAN TCI if Tx packet is dropped

On 1/9/2019 11:06 AM, Andrew Rybchenko wrote: > From: Ivan Malov > > Early processing of a packet on transmit may change last seen > VLAN TCI in the queue context. If such a packet is eventually > dropped, last seen VLAN TCI must be set to its previous value. > > Fixes: 7fd636815a43 ("net/sfc: s

Re: [dpdk-dev] [PATCH v2 1/2] test/compress: add out of space test

Hi Marko, > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Marko Kovacevic > Sent: Thursday, December 20, 2018 2:58 PM > To: dev@dpdk.org > Cc: akhil.go...@nxp.com; Daly, Lee ; Jozwiak, TomaszX > ; O'Hare, Cathal ; > Trahe, Fiona ; Kovacevic, Marko > > Subject:

[dpdk-dev] [PATCH] vhostuser: fix deadlock when vhost unregister

When rte_vhost_driver_unregister delete the connection fd, fdset_try_del will always try and donot release the vhostuser.mutex if the fd is busy, but the fdset_event_dispatch will set the fd to busy and call vhost_user_msg_handler to get vhostuser.mutex, which will cause deadlock. To fix i

[dpdk-dev] Seg fault with GRE in pktgen

Hi, Using pktgen 3.6.1, I'm getting a seg fault when enabling GRE. In app/pktgen.c, on line 556 l3_hdr is set to NULL, and then on line 567 it is send to a function that calls memset on it, triggering the seg fault I'm seeing. I suppose that l3_hdr argument (and the last argument on line 569 to

[dpdk-dev] Wrong constant being used

Hi, In pktgen 3.6.1, app/pktgen.c, line 219, the constant "IPPROTO_UDP" is used. Shouldn't that be "PG_IPPROTO_UDP" instead? Kind regards, DanielPharos

  1   2   >