[dpdk-dev] [PATCH v2 2/2] net/mlx5: remove redundant checks

Signed-off-by: Yongseok Koh Acked-by: Xueming Li --- v2: * add missing 'Acked-by' tag. drivers/net/mlx5/mlx5_rxtx.c | 6 ++ drivers/net/mlx5/mlx5_rxtx.h | 14 +++--- 2 files changed, 9 insertions(+), 11 deletions(-) diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx

[dpdk-dev] [PATCH v2 1/2] net/mlx5: fix setting offsets for SW parser

Since ConnectX-5, SW parser just complements HW parser. SW parser starts to engage only if HW parser can't reach a header. For the older devices, HW parser will not kick in if any of SWP offsets is set. Therefore, all of the L3 offsets should be set regardless of HW offload. As IPv6 doesn't have he

[dpdk-dev] [PATCH 2/4] crypto/qat: add libcrypto detection to Makefile

This patch adds detection of libcrypto in qat/Makefile. Crypto QAT PMD is build, but only when this library is installed. Signed-off-by: Tomasz Jozwiak Acked-by: Fiona Trahe --- config/common_base | 5 +++-- drivers/crypto/qat/Makefile | 32

[dpdk-dev] [PATCH 4/4] doc/qat: document libcrypto detection

Signed-off-by: Tomasz Jozwiak Acked-by: Fiona Trahe --- doc/guides/cryptodevs/qat.rst | 9 +++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/doc/guides/cryptodevs/qat.rst b/doc/guides/cryptodevs/qat.rst index 77f8362..fa23a56 100644 --- a/doc/guides/cryptodevs/qat.rst +++ b

[dpdk-dev] [PATCH 0/4] crypto/qat: move files to drivers/common directory

This patchset depends on QAT dynamic logging patchset and should be targetig on 18.08. Patchset refactors the PMD in order that files are split into several places: common, crypto. New drivers/common/qat and drivers/common/qat/qat were added and files split between locations. Also added libcrypto d

[dpdk-dev] [PATCH 1/4] crypto/qat: add weak functions

This patch adds following weak functions to facilitate conditional compilation of code for those services: - qat_sym_dev_create - qat_asym_dev_create - qat_comp_dev_create - qat_sym_dev_destroy - qat_asym_dev_destroy - qat_comp_dev_destroy and removes unused files with empty defin

[dpdk-dev] [PATCH 3/4] crypto/qat: move common qat files to common dir

- moved common qat files to common/qat dir. - changed common/qat/Makefile, common/qat/meson.build, drivers/meson.build, drivers/Makefile, crypto/Makefile to add possibility of using new files locations - added common/qat/qat dir for meson build - added README file into crypto/

[dpdk-dev] [PATCH 1/2] net/mlx5: fix setting offsets for SW parser

Since ConnectX-5, SW parser just complements HW parser. SW parser starts to engage only if HW parser can't reach a header. For the older devices, HW parser will not kick in if any of SWP offsets is set. Therefore, all of the L3 offsets should be set regardless of HW offload. As IPv6 doesn't have he

[dpdk-dev] [PATCH 2/2] net/mlx5: remove redundant checks

Signed-off-by: Yongseok Koh --- drivers/net/mlx5/mlx5_rxtx.c | 6 ++ drivers/net/mlx5/mlx5_rxtx.h | 14 +++--- 2 files changed, 9 insertions(+), 11 deletions(-) diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c index cdd373e3e..527859461 100644 --- a/drivers/n

Re: [dpdk-dev] [PATCH v2] net/tap: perform proto field update for tun only

Hi Ophir, Thanks for the suggestion, once these are merged to dpdk or dpdk-net mainline, I can start the modifications. Thanks Vipin Varghese > -Original Message- > From: Ophir Munk [mailto:ophi...@mellanox.com] > Sent: Wednesday, May 16, 2018 3:59 AM > To: Varghese, Vipin ; dev@dpdk.or

Re: [dpdk-dev] [PATCH v5 6/6] cryptodev: rename get session size API

>-Original Message- >From: Pablo de Lara [mailto:pablo.de.lara.gua...@intel.com] >Sent: 21 May 2018 18:39 >To: declan.dohe...@intel.com; akhil.go...@nxp.com; Verma, Shally > >Cc: dev@dpdk.org; Pablo de Lara >Subject: [PATCH v5 6/6] cryptodev: rename get session size API > >rte_cryptodev_g

Re: [dpdk-dev] [PATCH] net/i40e: remove dependency on old rxmode flags

> -Original Message- > From: Zhang, Qi Z > Sent: Tuesday, May 22, 2018 9:01 AM > To: Yigit, Ferruh > Cc: dev@dpdk.org; Xing, Beilei ; Zhang, Qi Z > > Subject: [PATCH] net/i40e: remove dependency on old rxmode flags > > Cleanup remain dependency on old rxmode flags since we move to new

Re: [dpdk-dev] [PATCH] net/e1000 igb: fix compile issue with log register

> -Original Message- > From: Varghese, Vipin > Sent: Monday, May 21, 2018 6:10 PM > To: Van Haaren, Harry; dev@dpdk.org > Cc: Lu, Wenzhuo; Zhang, Helin > Subject: RE: [PATCH] net/e1000 igb: fix compile issue with log register > > > > -Original Message- > > From: Van Haaren, Harr

Re: [dpdk-dev] [PATCH] net/i40e: fix shifts of signed values

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ferruh Yigit > Sent: Monday, May 21, 2018 10:46 PM > To: Xing, Beilei; Zhang, Qi Z > Cc: dev@dpdk.org; Yigit, Ferruh > Subject: [dpdk-dev] [PATCH] net/i40e: fix shifts of signed values > > Fix following error rep

Re: [dpdk-dev] [PATCH v6 5/8] rte_mbuf.h: avoid implicit demotion in 64-bit arith

On 05/21/2018 08:27 PM, Bruce Richardson wrote: On Mon, May 21, 2018 at 10:01:18AM +0800, Andy Green wrote: /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: In function 'rte_validate_tx_offload': /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: 2112:19: warning: conversion to 'uint64_t

[dpdk-dev] [PATCH v7 6/8] rte_mbuf.h: choose correct type for temp

/projects/lagopus/src/dpdk/build/include/rte_mbuf.h: In function 'rte_pktmbuf_linearize': /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: 1873:32: warning: conversion to 'int' from 'uint32_t' {aka 'unsigned int'} may change the sign of the result [-Wsign-conversion] #define rte_pktmbuf_pkt_len

Re: [dpdk-dev] [PATCH v6 8/8] rte_ethdev.h: align sign and scope of temp var

On 05/21/2018 09:30 PM, Bruce Richardson wrote: On Mon, May 21, 2018 at 10:01:33AM +0800, Andy Green wrote: /projects/lagopus/src/dpdk/build/include/rte_ethdev.h: In function 'rte_eth_rx_burst': /projects/lagopus/src/dpdk/build/include/rte_ethdev.h: 3836:18: warning: conversion to 'int16_t' {a

[dpdk-dev] [PATCH v7 7/8] rte_mbuf.h: add and subtract explicitly to avoid promotion

/projects/lagopus/src/dpdk/build/include/rte_mbuf.h: In function 'rte_pktmbuf_prepend': /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: 1908:17: warning: conversion from 'int' to 'uint16_t' {aka 'short unsigned int'} may change value [-Wconversion] m->data_off -= len;

[dpdk-dev] [PATCH v7 8/8] rte_ethdev.h: align sign and scope of temp var

/projects/lagopus/src/dpdk/build/include/rte_ethdev.h: In function 'rte_eth_rx_burst': /projects/lagopus/src/dpdk/build/include/rte_ethdev.h: 3836:18: warning: conversion to 'int16_t' {aka 'short int'} from 'uint16_t' {aka 'short unsigned int'} may change the sign of the result [-Wsign-conversion]

[dpdk-dev] [PATCH v7 0/8] Fixes for GCC8 against lagopus

The following series fixes build problems in dpdk master headers, found when using it as the dpdk subproject in lagopus. These errors are coming when you try to use the dpdk headers, not when you build dpdk itself. 6/8 are acked by Bruce Richardson... the other two have had the pending comment ap

[dpdk-dev] [PATCH v7 2/8] rte_rwlock.h: gcc8 sign conversion warnings

In file included from /projects/lagopus/src/dpdk/ build/include/rte_rwlock.h:12, from ./mgr/lock.h:24, from ./mgr/sock_io.c:54: /projects/lagopus/src/dpdk/build/include/generic/ rte_rwlock.h: In function 'rte_rwlock_read_lock': /projects/lagopus/src/dpdk/build/incl

[dpdk-dev] [PATCH v7 4/8] rte_mbuf.h: reduce temp to match uint16 types

/projects/lagopus/src/dpdk/build/include/rte_mbuf.h: In function 'rte_pktmbuf_detach': /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: 1583:17: warning: conversion from 'uint32_t' {aka 'unsigned int'} to 'uint16_t' {aka 'short unsigned int'} may change value [-Wconversi

[dpdk-dev] [PATCH v7 1/8] lib/librte_eal: change type of tmp

/projects/lagopus/src/dpdk/build/include/rte_memcpy.h: 793:2: note: in expansion of macro 'MOVEUNALIGNED_LEFT47' MOVEUNALIGNED_LEFT47(dst, src, n, srcofs); ^~~~ /projects/lagopus/src/dpdk/build/include/rte_memcpy.h: 649:51: warning: conversion from 'size_t' {aka 'long unsigned i

[dpdk-dev] [PATCH v7 3/8] rte_ip.h: cast type decided by sizeof to uint32

/projects/lagopus/src/dpdk/build/include/rte_ip.h: In function 'rte_ipv4_udptcp_cksum': /projects/lagopus/src/dpdk/build/include/rte_byteorder.h: 51:24: warning: conversion from 'long unsigned int' to 'uint32_t' {aka 'unsigned int'} may change value [-Wconversion] #define rte_bswap16(x) ((uint16_t

[dpdk-dev] [PATCH v7 5/8] rte_mbuf.h: avoid implicit demotion in 64-bit arith

/projects/lagopus/src/dpdk/build/include/rte_mbuf.h: In function 'rte_validate_tx_offload': /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: 2112:19: warning: conversion to 'uint64_t' {aka 'long unsigned int'} from 'int' may change the sign of the result [-Wsign-conversion] inner_l3_offset +=

Re: [dpdk-dev] [PATCH] net/i40e: fix shifts of signed values

> -Original Message- > From: Yigit, Ferruh > Sent: Monday, May 21, 2018 10:46 PM > To: Xing, Beilei ; Zhang, Qi Z > Cc: dev@dpdk.org; Yigit, Ferruh > Subject: [PATCH] net/i40e: fix shifts of signed values > > Fix following error reported by cppcheck: > (error) Shifting signed 32-bit valu

[dpdk-dev] [PATCH] net/i40e: remove dependency on old rxmode flags

Cleanup remain dependency on old rxmode flags since we move to new offload APIs. Fixes: c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API") Fixes: e0cb96204b71 ("net/i40e: add support for representor ports") Signed-off-by: Qi Zhang --- drivers/net/i40e/i40e_rxtx_vec_common.h | 4 ++-- dri

[dpdk-dev] [PATCH] kni: fix build on Centos 7.4 when Ethtool enabled

Fix compilation errors on Centos 7.4 when CONFIG_RTE_KNI_KMOD_ETHTOOL is set to 'y'. Centos 7.4 needs HAVE_NDO_BRIDGE_GETLINK_FILTER_MASK_VLAN_FILL: igb_main.c: In function ‘igb_ndo_bridge_getlink’: igb_main.c:2289:2: error: too few arguments to function ‘ndo_dflt_bridge_getlin

[dpdk-dev] [PATCH] eventdev: fix resetting software timer

Fix the call to rte_timer_reset_sync() in sw_event_timer_cb(). The second parameter is the number of ticks, the third is the timer type. Fixes: 6750b21bd6af ("eventdev: add default software timer adapter") Cc: erik.g.carri...@intel.com Signed-off-by: Dan Gora --- lib/librte_eventdev/rte_event_

[dpdk-dev] [PATCH] compressdev: remove unused driver id

Driver id field is not set/used anywhere, so it should be removed from rte_compressdev structure. Fixes: ed7dd94f7f66 ("compressdev: add basic device management") Signed-off-by: Pablo de Lara --- lib/librte_compressdev/rte_compressdev_internal.h | 3 --- 1 file changed, 3 deletions(-) diff --g

Re: [dpdk-dev] [PATCH] compressdev: clarify buffer size limitation

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Verma, Shally > Sent: Thursday, May 17, 2018 7:10 AM > To: Trahe, Fiona ; dev@dpdk.org > Cc: De Lara Guarch, Pablo ; Gupta, Ashish > ; Sahu, Sunila > Subject: Re: [dpdk-dev] [PATCH] compressdev: clarify buffer si

Re: [dpdk-dev] [PATCH] doc/crypto: add clarification about chained mbuf feature

> -Original Message- > From: Jain, Deepak K > Sent: Thursday, May 10, 2018 1:29 PM > To: Trahe, Fiona ; dev@dpdk.org > Cc: De Lara Guarch, Pablo ; Trahe, Fiona > ; hemant.agra...@nxp.com; shreyansh.j...@nxp.com > Subject: RE: [dpdk-dev] [PATCH] doc/crypto: add clarification about chained

Re: [dpdk-dev] [PATCH] cryptodev: add missing feature string

> -Original Message- > From: Varghese, Vipin > Sent: Friday, May 18, 2018 3:01 PM > To: De Lara Guarch, Pablo ; Doherty, Declan > > Cc: dev@dpdk.org; De Lara Guarch, Pablo ; > sta...@dpdk.org > Subject: RE: [dpdk-dev] [PATCH] cryptodev: add missing feature string > > Thanks Pablo for th

Re: [dpdk-dev] [PATCH v2] cryptodev: extend feature flags description

> -Original Message- > From: Akhil Goyal [mailto:akhil.go...@nxp.com] > Sent: Monday, May 21, 2018 12:36 PM > To: De Lara Guarch, Pablo ; Varghese, Vipin > ; Doherty, Declan > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v2] cryptodev: extend feature flags description > > On 5/18/2

Re: [dpdk-dev] [PATCH] net/ark: Add missing call to probe_finish for first device

21/05/2018 21:42, john miller: > > > On May 21, 2018, at 3:29 PM, Ed Czeck wrote: > > > > Fix on commit fbe90cdd776c ("ethdev: add probing finish function") Fixes: fbe90cdd776c ("ethdev: add probing finish function") > > Signed-off-by: Ed Czeck > > Acked-by: John Miller

Re: [dpdk-dev] [PATCH] net/ark: Add missing call to probe_finish for first device

21/05/2018 21:18, Ed Czeck: > Fix on: fbe90cdd776c3ac99c4c56d1b5318a90fcf01602 Fixes: fbe90cdd776c ("ethdev: add probing finish function") My bad, sorry for the miss. > --- > drivers/net/ark/ark_ethdev.c | 1 + > 1 file changed, 1 insertion(+) Your Signed-off-by is missing. Signed-off-by: Ed

Re: [dpdk-dev] mellanox connectx-2 support

You can use rdma over Ethernet, AKA ROCE Mellanox PMDs don't need vfio I am not sure what you are trying to achieve, you want to run DPDK on Infiniband? -Original Message- From: Vasiliy Tolstov [mailto:v.tols...@selfip.ru] Sent: Tuesday, May 22, 2018 12:10 AM To: Adrien Mazarguil

Re: [dpdk-dev] mellanox connectx-2 support

пн, 21 мая 2018 г. в 12:15, Adrien Mazarguil : > On Sun, May 20, 2018 at 10:25:01PM +0300, Vasiliy Tolstov wrote: > > чт, 17 мая 2018 г. в 9:02, Olga Shern : > > > > > Vasily, > > > > > > ConnectX-2 is very, very old card. > > > We don't support it. > > > You can run DPDK on ConnectX-3 Pro, Connec

[dpdk-dev] [PATCH v2 2/2] net/failsafe: fix duplicate event registration

When the fail-safe device is reconfigured, it attempts to register again for the sub-devices LSC and RMV events. Prevent an event registration if it is already done. Fixes: 598fb8aec6f6 ("net/failsafe: support device removal") Cc: sta...@dpdk.org Signed-off-by: Matan Azrad --- drivers/net/fail

[dpdk-dev] [PATCH v2 1/2] net/failsafe: fix removed sub-device cleanup

The fail-safe PMD registers to RMV event for each removable sub-device port in order to cleanup the sub-device resources and switch the Tx sub-device directly when it is plugged-out. During removal time, the fail-safe PMD stops and closes the sub-device but it doesn't unregister the LSC and RMV ca

Re: [dpdk-dev] [PATCH] net/ark: Add missing call to probe_finish for first device

> On May 21, 2018, at 3:29 PM, Ed Czeck wrote: > > Fix on commit fbe90cdd776c ("ethdev: add probing finish function") > > Signed-off-by: Ed Czeck > --- > drivers/net/ark/ark_ethdev.c | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/drivers/net/ark/ark_ethdev.c b/drivers/net/ark/ark_et

[dpdk-dev] [PATCH] net/ark: Add missing call to probe_finish for first device

Fix on commit fbe90cdd776c ("ethdev: add probing finish function") Signed-off-by: Ed Czeck --- drivers/net/ark/ark_ethdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ark/ark_ethdev.c b/drivers/net/ark/ark_ethdev.c index 62e4fd3..834d8a9 100644 --- a/drivers/net/ark/ark_ethd

[dpdk-dev] [PATCH] net/ark: Add missing call to probe_finish for first device

Fix on: fbe90cdd776c3ac99c4c56d1b5318a90fcf01602 --- drivers/net/ark/ark_ethdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ark/ark_ethdev.c b/drivers/net/ark/ark_ethdev.c index 62e4fd3..834d8a9 100644 --- a/drivers/net/ark/ark_ethdev.c +++ b/drivers/net/ark/ark_ethdev.c @@ -

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix pmd_test_exit function for vdevs

21/05/2018 18:44, Ferruh Yigit: > On 5/21/2018 5:40 PM, Thomas Monjalon wrote: > > 21/05/2018 18:37, Ferruh Yigit: > >> On 5/19/2018 3:19 PM, Thomas Monjalon wrote: > >>> 18/05/2018 18:29, Ferruh Yigit: > On 5/18/2018 4:55 PM, Matan Azrad wrote: > > Hi all > > > > While this patch

Re: [dpdk-dev] [PATCH v1] net/mlx4: add an RSS hash update callback

For 18.05 this path can be withdrawn. It has already been suppressed a few days ago. Thanks, Ophir > -Original Message- > From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com] > Sent: Monday, May 21, 2018 7:08 PM > To: Ophir Munk > Cc: dev@dpdk.org; Thomas Monjalon ; Olga Shern > ;

Re: [dpdk-dev] [PATCH 1/2] net/failsafe: fix removed sub-device cleanup

Hi, Please find comments inline. > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Matan Azrad > Sent: Thursday, May 17, 2018 9:52 PM > To: Gaetan Rivet > Cc: dev@dpdk.org; sta...@dpdk.org > Subject: [dpdk-dev] [PATCH 1/2] net/failsafe: fix removed sub-device cle

Re: [dpdk-dev] [PATCH v2] bus/vdev: fix scope of device list lock

From: Thomas Monjalon > The lock vdev_device_list_lock was taken before calling "remove" function for > the device. > So it prevents to remove sub-devices (as in failsafe) inside its own "remove" > function, because of a deadlock. > > The lock is now only protecting the device list inside the bu

Re: [dpdk-dev] [PATCH v5 5/6] doc: announce deprecation in crypto feature flags

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara > Sent: Monday, May 21, 2018 2:09 PM > To: Doherty, Declan ; akhil.go...@nxp.com; > shally.ve...@cavium.com > Cc: dev@dpdk.org; De Lara Guarch, Pablo > Subject: [dpdk-dev] [PATCH v5 5/6] doc: annou

Re: [dpdk-dev] [PATCH] net/vdev_netvsc: fix automatic probing

From: Stephen Hemminger > On Mon, 21 May 2018 16:23:30 + > Matan Azrad wrote: > > > The vdev_netvsc driver allows an automatic probe in Hyper-V VM systems > > unless it was already specified by the EAL command line. > > > > The detection of a specified NetVSC device is wrongly done by > > c

Re: [dpdk-dev] [PATCH] net/vdev_netvsc: fix automatic probing

On Mon, 21 May 2018 16:23:30 + Matan Azrad wrote: > The vdev_netvsc driver allows an automatic probe in Hyper-V VM systems > unless it was already specified by the EAL command line. > > The detection of a specified NetVSC device is wrongly done by comparing > the vdev_netvsc driver name to a

[dpdk-dev] [PATCH v2] bus/vdev: fix scope of device list lock

The lock vdev_device_list_lock was taken before calling "remove" function for the device. So it prevents to remove sub-devices (as in failsafe) inside its own "remove" function, because of a deadlock. The lock is now only protecting the device list inside the bus driver. Fixes: 35f462839b69 ("bus

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix pmd_test_exit function for vdevs

On 5/21/2018 5:40 PM, Thomas Monjalon wrote: > 21/05/2018 18:37, Ferruh Yigit: >> On 5/19/2018 3:19 PM, Thomas Monjalon wrote: >>> 18/05/2018 18:29, Ferruh Yigit: On 5/18/2018 4:55 PM, Matan Azrad wrote: > Hi all > > While this patch also applied I don't understand it. > Is it

[dpdk-dev] [PATCH 2/2] pci: remove unused function prototype

Prototype for pci_unbind_kernel_driver exists but no code. Signed-off-by: Stephen Hemminger --- drivers/bus/pci/private.h | 10 -- 1 file changed, 10 deletions(-) diff --git a/drivers/bus/pci/private.h b/drivers/bus/pci/private.h index 02e2fb44367f..680879ed35a2 100644 --- a/drivers/bus

[dpdk-dev] [PATCH 1/2] pci: make rte_pci_remove_device static

Only used in one file, and therefore can be made static. Signed-off-by: Stephen Hemminger --- drivers/bus/pci/pci_common.c | 5 - drivers/bus/pci/private.h| 10 -- 2 files changed, 4 insertions(+), 11 deletions(-) diff --git a/drivers/bus/pci/pci_common.c b/drivers/bus/pci/pci_

[dpdk-dev] [PATCH 0/2] pci: a couple more cleanups

This is follow on to earlier PCI patches to remove unused functions Stephen Hemminger (2): pci: make rte_pci_remove_device static pci: remove unused function prototype drivers/bus/pci/pci_common.c | 5 - drivers/bus/pci/private.h| 20 2 files changed, 4 insertio

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix pmd_test_exit function for vdevs

21/05/2018 18:37, Ferruh Yigit: > On 5/19/2018 3:19 PM, Thomas Monjalon wrote: > > 18/05/2018 18:29, Ferruh Yigit: > >> On 5/18/2018 4:55 PM, Matan Azrad wrote: > >>> Hi all > >>> > >>> While this patch also applied I don't understand it. > >>> Is it mandatory for each PMD to free all its resources

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix pmd_test_exit function for vdevs

21/05/2018 18:32, Ferruh Yigit: > On 5/21/2018 11:54 AM, Thomas Monjalon wrote: > > 19/05/2018 16:19, Thomas Monjalon: > >> 18/05/2018 18:29, Ferruh Yigit: > >>> On 5/18/2018 4:55 PM, Matan Azrad wrote: > Hi all > > While this patch also applied I don't understand it. > Is it ma

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix pmd_test_exit function for vdevs

On 5/19/2018 3:19 PM, Thomas Monjalon wrote: > 18/05/2018 18:29, Ferruh Yigit: >> On 5/18/2018 4:55 PM, Matan Azrad wrote: >>> Hi all >>> >>> While this patch also applied I don't understand it. >>> Is it mandatory for each PMD to free all its resources in dev_close()? >>> Or it should be done by t

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix pmd_test_exit function for vdevs

On 5/21/2018 11:54 AM, Thomas Monjalon wrote: > 19/05/2018 16:19, Thomas Monjalon: >> 18/05/2018 18:29, Ferruh Yigit: >>> On 5/18/2018 4:55 PM, Matan Azrad wrote: Hi all While this patch also applied I don't understand it. Is it mandatory for each PMD to free all its resources i

[dpdk-dev] [PATCH] net/vdev_netvsc: fix automatic probing

The vdev_netvsc driver allows an automatic probe in Hyper-V VM systems unless it was already specified by the EAL command line. The detection of a specified NetVSC device is wrongly done by comparing the vdev_netvsc driver name to all the vdev devices names, including the suffix device index. Thus

Re: [dpdk-dev] [PATCH] test: fix hang on FreeBSD

On Mon, 21 May 2018 13:58:39 +0100 Radu Nicolau wrote: > On 5/21/2018 1:30 PM, Thomas Monjalon wrote: > > 21/05/2018 13:35, Radu Nicolau: > >> Fixes: af75078fece3 ("first public release") > >> Cc: sta...@dpdk.org > >> > >> Signed-off-by: Radu Nicolau > >> --- > >> @@ -34,7 +34,8 @@ test_panic(

[dpdk-dev] [PATCH] bus/vdev: reduce scope of device list lock

The lock vdev_device_list_lock was taken before calling "remove" function for the device. So it prevents to remove sub-devices (as in failsafe) inside its own "remove" function, because of a deadlock. The lock is now only protecting the device list inside the bus driver. Fixes: 35f462839b69 ("bus

Re: [dpdk-dev] [PATCH v1] net/mlx4: add an RSS hash update callback

On Thu, May 17, 2018 at 11:04:40AM +, Ophir Munk wrote: > Add an RSS hash update callback to eth_dev_ops. > > Signed-off-by: Ophir Munk This patch allows applications to configure legacy RSS past initial port configuration, but doesn't take input parameters into account. Its purpose is to si

[dpdk-dev] [PATCH v2 2/2] net/mlx4: refactor RSS conversion functions

Since commit 97b2217ae5bc ("net/mlx4: advertise supported RSS hash functions"), this PMD includes two similar-looking functions that convert RSS hash fields between Verbs and DPDK formats. This patch refactors them as a single two-way function and gets rid of redundant helper macros. Note the los

[dpdk-dev] [PATCH v2 1/2] net/mlx4: fix inadequate default in RSS converter

Below commit documents 0 as a value standing for a default set of RSS hash types, however the mlx4 PMD doesn't interpret it correctly and still uses its own internal special value for that (-1). Also, its function prototype was not updated. Fixes: ac8d22de2394 ("ethdev: flatten RSS configuration

Re: [dpdk-dev] [PATCH v2] ethdev: update description for functions

On 5/21/2018 4:15 PM, Ferruh Yigit wrote: > On 5/18/2018 6:12 AM, Vipin Varghese wrote: >> Change adds extra information on name parameter for API >> rte_eth_dev_get_name_by_port and rte_eth_dev_get_port_by_name. >> >> Signed-off-by: Vipin Varghese > > Reviewed-by: Ferruh Yigit Applied to dpdk-

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix burst stat reporting

> > When RTE_TEST_PMD_RECORD_BURST_STATS is enabled, testpmd collects > > burst statistics and includes them in the port stats report. The summary > > should include top 2 most frequent burst sizes, but there is a bug in > > finding > > the top-2. During the scan of burst size counts, the > > to

Re: [dpdk-dev] [PATCH v2] ethdev: update description for functions

On 5/18/2018 6:12 AM, Vipin Varghese wrote: > Change adds extra information on name parameter for API > rte_eth_dev_get_name_by_port and rte_eth_dev_get_port_by_name. > > Signed-off-by: Vipin Varghese Reviewed-by: Ferruh Yigit

Re: [dpdk-dev] [dpdk-stable] [PATCH v4] net/tap: fix device removal when no queues exist

On 5/21/2018 1:52 PM, Wiles, Keith wrote: > > >> On May 21, 2018, at 2:54 AM, Ophir Munk wrote: >> >> TAP device is created following its first queue creation. Multiple >> queues can be added or removed over time. In Linux terminology those >> are file descriptors which are opened or closed over

[dpdk-dev] [PATCH] net/i40e: fix shifts of signed values

Fix following error reported by cppcheck: (error) Shifting signed 32-bit value by 31 bits is undefined behaviour Signed-off-by: Ferruh Yigit --- I am aware this is an base driver issue, sending patch to keep record. Please take required action to fix these in base driver. --- drivers/net/i40e/ba

Re: [dpdk-dev] Remaining old offloading API usage in PMDs

On 5/21/2018 3:16 PM, Alejandro Lucero wrote: > I completely missed this last bit in the NFP driver. > > I will send a patch today. > > By the way, will it go into 18.05? I ask because I have another patch fixing a > problem which would be good to have in 18.05 as well. Release is still open for

Re: [dpdk-dev] [dpdk-stable] [PATCH] drivers/raw/ifpga_rawdev: fix coverity issue

16/05/2018 15:53, Rosen Xu: > Fix coverity issue: 279449 > > Signed-off-by: Rosen Xu > > Fixes: ef1e8ede3da5 ("raw/ifpga: add Intel FPGA bus rawdev driver") > Coverity issue: 279449 > Cc: sta...@dpdk.org Not for stable > --- a/drivers/raw/ifpga_rawdev/ifpga_rawdev.c > +++ b/drivers/raw/ifpga_r

Re: [dpdk-dev] Remaining old offloading API usage in PMDs

I completely missed this last bit in the NFP driver. I will send a patch today. By the way, will it go into 18.05? I ask because I have another patch fixing a problem which would be good to have in 18.05 as well. On Mon, May 21, 2018 at 1:38 PM, Ferruh Yigit wrote: > On 5/11/2018 11:45 AM, Fer

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix log of start command

On 5/21/2018 2:28 PM, Bernard Iremonger wrote: > Call the rte_eth_rxq_info_get() and rte_eth_txq_info_get() functions > to update the number of rx and tx descriptors in the rte_port > variable. > > Fixes: ce8d561418d4 ("app/testpmd: add port configuration settings") > Signed-off-by: Bernard Iremon

Re: [dpdk-dev] [dpdk-stable] [PATCH] raw/ifpga/base: fix a return error value in ifpga_fme_pr

16/05/2018 10:49, Xu, Rosen: > From: "Zhang, Tianfei" > > fix a return error value by DPDK Coverity static code analysis > > Fixes: 56bb54ea1bdf ("raw/ifpga/base: add Intel FPGA OPAE share code") > Coverity issue: 279448 > Cc: sta...@dpdk.org Not for stable, ifpga was introduced in 18.05. > Si

Re: [dpdk-dev] [dpdk-stable] [PATCH] drivers/bus/ifpga/: fix Coverity issue

16/05/2018 15:48, Rosen Xu: > Fix Coverity issue: 279455, 279459 and 279454 > > Signed-off-by: Rosen Xu > > Fixes: 05fa3d4a6539 ("bus/ifpga: add Intel FPGA bus library") > Coverity issue: 279455, 279459 and 279454 > Cc: sta...@dpdk.org The commit message should explain what was the issue. FYI,

Re: [dpdk-dev] [PATCH] test/eventdev: add multi port test to suite

Thanks, send v3 with the suggested changes. From: Rao, Nikhil Sent: Monday, May 21, 2018 5:09 PM To: Varghese, Vipin ; dev@dpdk.org; Jain, Deepak K Cc: Rao, Nikhil Subject: Re: [PATCH] test/eventdev: add multi port test to suite Hi Vipin, Thanks for posting V2. On 5/21/2018 4:30 PM, Varghes

[dpdk-dev] [PATCH v3] test/eventdev: add multi port test to suite

Add a new test to enhance the test suite, to allow multiple eth ports rx queue to be added to rx bridge adapter. Update the test function to reflect change of port index from 8 to 16 bit Signed-off-by: Vipin Varghese Acked-by: Nikhil Rao --- Changes in V3: - removed residue code for capabilitie

Re: [dpdk-dev] [PATCH v2] log: fix pattern matching

16/05/2018 16:09, Ferruh Yigit: > loglevel set wrong when ":" is used as separator, like > --log-type="user:debug" > > This is because fnmatch returns zero on success. Fixed fnmatch return > value check. > > Fixes: 7f0bb634a140 ("log: add ability to match log type with globbing") > Cc: step...@ne

Re: [dpdk-dev] [PATCH] test: fix hang on FreeBSD

On 5/21/2018 2:28 PM, Burakov, Anatoly wrote: On 21-May-18 12:35 PM, Radu Nicolau wrote: Fixes: af75078fece3 ("first public release") Cc: sta...@dpdk.org Signed-off-by: Radu Nicolau ---   test/test/test_debug.c | 3 ++-   1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/test/test/

Re: [dpdk-dev] [PATCH v6 8/8] rte_ethdev.h: align sign and scope of temp var

On Mon, May 21, 2018 at 10:01:33AM +0800, Andy Green wrote: > /projects/lagopus/src/dpdk/build/include/rte_ethdev.h: > In function 'rte_eth_rx_burst': > /projects/lagopus/src/dpdk/build/include/rte_ethdev.h: > 3836:18: warning: conversion to 'int16_t' {aka 'short > int'} from 'uint16_t' {aka 'short

[dpdk-dev] [PATCH v2] app/testpmd: fix log of start command

Call the rte_eth_rxq_info_get() and rte_eth_txq_info_get() functions to update the number of rx and tx descriptors in the rte_port variable. Fixes: ce8d561418d4 ("app/testpmd: add port configuration settings") Signed-off-by: Bernard Iremonger --- app/test-pmd/testpmd.c | 16 +++- 1 f

Re: [dpdk-dev] [PATCH] test: fix hang on FreeBSD

On 21-May-18 12:35 PM, Radu Nicolau wrote: Fixes: af75078fece3 ("first public release") Cc: sta...@dpdk.org Signed-off-by: Radu Nicolau --- test/test/test_debug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/test/test/test_debug.c b/test/test/test_debug.c index faf2c

Re: [dpdk-dev] [PATCH] test: fix hang on FreeBSD

21/05/2018 14:58, Radu Nicolau: > > On 5/21/2018 1:30 PM, Thomas Monjalon wrote: > > 21/05/2018 13:35, Radu Nicolau: > >> Fixes: af75078fece3 ("first public release") > >> Cc: sta...@dpdk.org > >> > >> Signed-off-by: Radu Nicolau > >> --- > >> @@ -34,7 +34,8 @@ test_panic(void) > >>pr

Re: [dpdk-dev] [PATCH] net/i40e: add a specific API to control the LLDP agent

Hi Zijie: > -Original Message- > From: Zijie Pan [mailto:zijie@6wind.com] > Sent: Friday, May 18, 2018 6:14 PM > To: dev@dpdk.org > Cc: Xing, Beilei ; Zhang, Qi Z ; > Laurent Hardy > Subject: [PATCH] net/i40e: add a specific API to control the LLDP agent > > Add a new API rte_pmd_i40

Re: [dpdk-dev] [PATCH v6 7/8] rte_mbuf.h: add and subtract explicitly to avoid promotion

On Mon, May 21, 2018 at 10:01:28AM +0800, Andy Green wrote: >/projects/lagopus/src/dpdk/build/include/rte_mbuf.h: > In function 'rte_pktmbuf_prepend': > /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: > 1908:17: warning: conversion from 'int' to 'uint16_t' > {aka 'short uns

[dpdk-dev] [PATCH v5 6/6] cryptodev: rename get session size API

rte_cryptodev_get_header_session_size() and rte_cryptodev_get_private_session_size() functions are targeting symmetric sessions. With the future addition of asymmetric operations, these functions need to be renamed from *cryptodev_*_session_* to *cryptodev_sym_*_session_* to be symmetric specific.

Re: [dpdk-dev] [PATCH v6 6/8] rte_mbuf.h: choose correct type for temp

On Mon, May 21, 2018 at 10:01:23AM +0800, Andy Green wrote: > /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: > In function 'rte_pktmbuf_linearize': > /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: > 1873:32: warning: conversion to 'int' from 'uint32_t' > {aka 'unsigned int'} may change

[dpdk-dev] [PATCH v5 5/6] doc: announce deprecation in crypto feature flags

Some feature flags, such as RTE_CRYPTODEV_FF_MBUF_SCATTER_GATHER are ambiguous. In this case, it is not clear if Scatter Gather lists are supported in the input buffer and/or output buffer. Signed-off-by: Pablo de Lara --- doc/guides/rel_notes/deprecation.rst | 2 ++ 1 file changed, 2 insertions

[dpdk-dev] [PATCH v5 4/6] doc: announce deprecation in crypto queue pair start/stop

Functions rte_cryptodev_queue_pair_start/stop are not really used in any of the crypto drivers (they all just return 0 or -ENOTSUP). Therefore, this API can be deprecated from 18.05 and removed in 18.08. Signed-off-by: Pablo de Lara Acked-by: Akhil Goyal Acked-by: Fiona Trahe --- doc/guides/re

[dpdk-dev] [PATCH v5 2/6] doc: announce ABI change for crypto info struct

Cryptodev info structure currently contains a pointer to an rte_pci_device structure. This field depends on a specific bus type (PCI), which is not following a bus independent design. Following the same approach taken in ethdev, the field will be replaced with a pointer to an rte_device structure.

[dpdk-dev] [PATCH v5 3/6] doc: announce deprecation for attach/detach crypto session

Functions rte_cryptodev_queue_pair_attach_sym_session and rte_cryptodev_queue_pair_detach_sym_sessions are not really used in any of the crypto drivers (only one driver implements it and it just return 0). Therefore, this API can be deprecated from 18.05 and removed in 18.08. Signed-off-by: Pablo

[dpdk-dev] [PATCH v5 0/6] Cryptodev API/ABI deprecation notices

v5: - Renamed rte_cryptodev_get_header_session_size with rte_cryptodev_sym_get_header_session_size, and rte_cryptodev_get_private_session_size with rte_cryptodev_sym_get_private_session_size. v4: - Fixed DPDK versions called out to deprecate/remove API. - Removed rte_cryptodev_queue_pair_att

[dpdk-dev] [PATCH v5 1/6] doc: announce ABI change for crypto sym info struct

Since the API changes made in 17.08, the session mempool is not created anymore in each crypto device. Therefore, there is no need to have, in the cryptodev info structure, the maximum number of sessions supported per device and per queue pair. Signed-off-by: Pablo de Lara Acked-by: Fiona Trahe

[dpdk-dev] [PATCH] net/liquidio:Fix Unable to update lio_dev->linfo.link var

When I was using VPP +dpdk-18.02+liqudio CN23xx, I encountered such a bug. \n When VPP called dpdk_device_start to initialize DPDK liqudio drive, I found that initialization failed. \n The reason for the failure is that VF MTU > PF MTU, but PF MTU has been modified to 9600 (> VF MTU). \n Finally,

Re: [dpdk-dev] [PATCH] test: fix hang on FreeBSD

On 5/21/2018 1:30 PM, Thomas Monjalon wrote: 21/05/2018 13:35, Radu Nicolau: Fixes: af75078fece3 ("first public release") Cc: sta...@dpdk.org Signed-off-by: Radu Nicolau --- @@ -34,7 +34,8 @@ test_panic(void) printf("Fork Failed\n"); return -1; } -

Re: [dpdk-dev] [PATCH v4] net/tap: fix device removal when no queues exist

> On May 21, 2018, at 2:54 AM, Ophir Munk wrote: > > TAP device is created following its first queue creation. Multiple > queues can be added or removed over time. In Linux terminology those > are file descriptors which are opened or closed over time. As long as > the number of opened file desc

Re: [dpdk-dev] [PATCH v2 1/2] app/testpmd: fix copy of raw flow item (revisited)

On 5/21/2018 12:44 PM, Adrien Mazarguil wrote: > While previous fix with the same title does address the main issue, root > cause is that proper handling of spec/last/mask was overlooked in the > original patch. > > Mask and last fields must be taken into account at all times. > > Fixes: d0ad8648

Re: [dpdk-dev] Remaining old offloading API usage in PMDs

On 5/11/2018 11:45 AM, Ferruh Yigit wrote: > Some PMDs are still using old offloading API related variables, thanks to > Andrew > for reporting it. > > Maintainers of related PMDs are cc'ed. > Please check following list and provide a fix ASAP for it, thanks. > > > # git grep header_split drive

Re: [dpdk-dev] [PATCH] test: fix hang on FreeBSD

21/05/2018 13:35, Radu Nicolau: > Fixes: af75078fece3 ("first public release") > Cc: sta...@dpdk.org > > Signed-off-by: Radu Nicolau > --- > @@ -34,7 +34,8 @@ test_panic(void) > printf("Fork Failed\n"); > return -1; > } > - wait(&status); > + sleep(1); >

  1   2   >