Re: [dpdk-dev] [PATCH v5 11/12] net/failsafe: support link status change event

This patch need to be rebased with this change: --- a/drivers/net/failsafe/failsafe_ether.c +++ b/drivers/net/failsafe/failsafe_ether.c @@ -417,7 +417,7 @@ failsafe_eth_rmv_event_callback(uint8_t port_id __rte_unused, void failsafe_eth_lsc_event_callback(uint8_t port_id __rte_unused,

Re: [dpdk-dev] [PATCH v5 10/12] net/failsafe: support device removal

This patch needs to be rebased with this change: --- a/drivers/net/failsafe/failsafe_ether.c +++ b/drivers/net/failsafe/failsafe_ether.c @@ -399,7 +399,7 @@ failsafe_eth_dev_state_sync(struct rte_eth_dev *dev) void failsafe_eth_rmv_event_callback(uint8_t port_id __rte_unused,

Re: [dpdk-dev] [PATCH 1/4] mempool: get the external mempool capability

Hi Olivier, On Monday 03 July 2017 10:07 PM, Olivier Matz wrote: > Hi Santosh, > > On Wed, 21 Jun 2017 17:32:45 +, Santosh Shukla > wrote: >> Allow external mempool to advertise its capability. >> A handler been introduced called rte_mempool_ops_get_hw_cap. >> - Upon ->get_hw_cap call, memp

Re: [dpdk-dev] [PATCH v2 00/40] Introduce NXP DPAA Bus, Mempool and PMD

05/07/2017 06:38, Shreyansh Jain: > Hello Thomas, > > On Wednesday 05 July 2017 05:43 AM, Thomas Monjalon wrote: > > Hi Shreyansh, > > > > 04/07/2017 16:43, Shreyansh Jain: > >> This patchset introduces the following: > >> 1. DPAA Bus (drivers/bus/dpaa) > >> The core of DPAA bus is implemented u

Re: [dpdk-dev] [PATCH] bus: fix driver registration

On Wednesday 05 July 2017 11:17 AM, Shreyansh Jain wrote: > On Wednesday 05 July 2017 03:13 AM, Thomas Monjalon wrote: >> The bus name was stored with embedded double quotes. >> Indeed the bus name is given with a string in a macro, >> which is not used elsewhere. >> These macros are useless becaus

Re: [dpdk-dev] [PATCH v5 0/4] Support NIC reset and keep same port id

Hi, Thomas Would you please have a look at this patch set ? If any question, please let me know . Thanks -Wei -Original Message- From: Wu, Jingjing Sent: Friday, June 30, 2017 6:50 PM To: Dai, Wei ; tho...@monjalon.net; Lu, Wenzhuo ; Ananyev, Konstantin ; Zhang, Helin ; Peng, Yuan

Re: [dpdk-dev] [PATCH] bus: fix driver registration

On Wednesday 05 July 2017 03:13 AM, Thomas Monjalon wrote: > The bus name was stored with embedded double quotes. > Indeed the bus name is given with a string in a macro, > which is not used elsewhere. > These macros are useless because the buses are drivers, > so they must not have any API for the

Re: [dpdk-dev] [PATCH v5 1/3] examples/eventdev_pipeline: added sample app

-Original Message- > Date: Tue, 4 Jul 2017 08:55:25 +0100 > From: "Hunt, David" > To: Jerin Jacob > CC: dev@dpdk.org, harry.van.haa...@intel.com, Gage Eads > , Bruce Richardson > Subject: Re: [PATCH v5 1/3] examples/eventdev_pipeline: added sample app > User-Agent: Mozilla/5.0 (Windows

Re: [dpdk-dev] [PATCH v6 2/3] doc: add sw eventdev pipeline to sample app ug

-Original Message- > Date: Tue, 4 Jul 2017 09:14:22 +0100 > From: David Hunt > To: dev@dpdk.org > CC: jerin.ja...@caviumnetworks.com, harry.van.haa...@intel.com, David Hunt > > Subject: [PATCH v6 2/3] doc: add sw eventdev pipeline to sample app ug > X-Mailer: git-send-email 2.7.4 > > Fr

Re: [dpdk-dev] [PATCH v2 00/40] Introduce NXP DPAA Bus, Mempool and PMD

Hello Thomas, On Wednesday 05 July 2017 05:43 AM, Thomas Monjalon wrote: > Hi Shreyansh, > > 04/07/2017 16:43, Shreyansh Jain: >> This patchset introduces the following: >> 1. DPAA Bus (drivers/bus/dpaa) >> The core of DPAA bus is implemented using 3 main hardware blocks: QMan, >> or Queue Mana

[dpdk-dev] [PATCH v11 1/3] lib: add Generic Receive Offload API framework

Generic Receive Offload (GRO) is a widely used SW-based offloading technique to reduce per-packet processing overhead. It gains performance by reassembling small packets into large ones. This patchset is to support GRO in DPDK. To support GRO, this patch implements a GRO API framework. To enable m

[dpdk-dev] [PATCH v11 3/3] app/testpmd: enable TCP/IPv4 GRO

This patch enables TCP/IPv4 GRO library in csum forwarding engine. By default, GRO is turned off. Users can use command "gro (on|off) (port_id)" to enable or disable GRO for a given port. If a port is enabled GRO, all TCP/IPv4 packets received from the port are performed GRO. Besides, users can set

[dpdk-dev] [PATCH v11 0/3] Support TCP/IPv4 GRO in DPDK

Generic Receive Offload (GRO) is a widely used SW-based offloading technique to reduce per-packet processing overhead. It gains performance by reassembling small packets into large ones. Therefore, we propose to support GRO in DPDK. To enable more flexibility to applications, DPDK GRO is implement

[dpdk-dev] [PATCH v11 2/3] lib/gro: add TCP/IPv4 GRO support

In this patch, we introduce five APIs to support TCP/IPv4 GRO. - gro_tcp4_tbl_create: create a TCP/IPv4 reassembly table, which is used to merge packets. - gro_tcp4_tbl_destroy: free memory space of a TCP/IPv4 reassembly table. - gro_tcp4_tbl_timeout_flush: flush timeout packets from a TCP/IPv4

Re: [dpdk-dev] [PATCH] examples/ip_pipeline: use crc32 in hash functions for arm64

On 4 July 2017 at 21:55, De Lara Guarch, Pablo wrote: > > >> -Original Message- >> From: Thomas Monjalon [mailto:tho...@monjalon.net] >> Sent: Tuesday, July 4, 2017 12:26 AM >> To: Dumitrescu, Cristian ; De Lara Guarch, >> Pablo >> Cc: dev@dpdk.org; Jianbo Liu ; >> jerin.ja...@caviumnetwo

Re: [dpdk-dev] [PATCH v2] net/ixgbe: remove MTU setting limitation when port's stopped

Hi, > -Original Message- > From: Xing, Beilei > Sent: Wednesday, July 5, 2017 10:34 AM > To: Lu, Wenzhuo > Cc: dev@dpdk.org > Subject: [PATCH v2] net/ixgbe: remove MTU setting limitation when port's > stopped > > Currently, setting MTU will fail if MTU requires the support of scattered >

Re: [dpdk-dev] [PATCH v2 1/2] eal: add uevent api for hot plug

hi, thomas On 7/5/2017 7:45 AM, Thomas Monjalon wrote: Hi, This is an interesting step for hotplug in DPDK. 28/06/2017 13:07, Jeff Guo: + netlink_fd = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_KOBJECT_UEVENT); It is monitoring the whole system... +int +rte_uevent_get(int fd, struct rte

[dpdk-dev] [PATCH v2] net/ixgbe: remove MTU setting limitation when port's stopped

Currently, setting MTU will fail if MTU requires the support of scattered packets before scatter is enabled. This patch allows setting this special MTU when device is stopped, cause scatter will be re-configured during starting port. Signed-off-by: Beilei Xing --- v2 changes: - change commit log

Re: [dpdk-dev] [PATCH v2 5/5] net/mlx5: add vectorized Rx/Tx burst for SSE4.1

On Tue, Jul 04, 2017 at 10:58:52AM +0200, Nélio Laranjeiro wrote: > Yongseok, some comments in this huge and great work, > > On Fri, Jun 30, 2017 at 12:23:33PM -0700, Yongseok Koh wrote: > > To make vectorized burst routines enabled, it is required to run on x86_64 > > architecture which can suppo

Re: [dpdk-dev] [PATCH v6 00/19] Generic devargs parsing

> Gaetan Rivet (19): > net/bonding: properly reference PCI header > net/bnxt: properly reference PCI header > net/mlx5: properly reference PCI header > net/e1000: properly reference PCI header > net/ixgbe: properly reference PCI header > net/sfc: properly reference PCI header > app/te

Re: [dpdk-dev] [PATCH v6 19/19] eal: change whitelist / blacklist command line doc

05/07/2017 01:56, Gaetan Rivet: > The use of these commands have evolved. > It is now possible to use whitelist and blacklist on any bus. > > Update the source code accordingly. > > Signed-off-by: Gaetan Rivet You forgot the ack from John.

Re: [dpdk-dev] [PATCH v2 00/40] Introduce NXP DPAA Bus, Mempool and PMD

Hi Shreyansh, 04/07/2017 16:43, Shreyansh Jain: > This patchset introduces the following: > 1. DPAA Bus (drivers/bus/dpaa) > The core of DPAA bus is implemented using 3 main hardware blocks: QMan, > or Queue Manager; BMan, or Buffer Manager and FMan, or Frame Manager. > The patches introduce ne

Re: [dpdk-dev] [PATCH v6 14/19] net/virtio: do not reference device type

On Wed, Jul 05, 2017 at 01:56:44AM +0200, Gaetan Rivet wrote: > Signed-off-by: Gaetan Rivet > --- > drivers/net/virtio/virtio_pci.c | 5 +++-- > 1 file changed, 3 insertions(+), 2 deletions(-) > > diff --git a/drivers/net/virtio/virtio_pci.c b/drivers/net/virtio/virtio_pci.c > index b7b3d61..627

[dpdk-dev] [PATCH v6 18/19] devargs: remove function

Hotplug support introduces the possibility of removing devices from the system. Allocated resources must be freed. Signed-off-by: Gaetan Rivet --- lib/librte_eal/bsdapp/eal/rte_eal_version.map | 1 + lib/librte_eal/common/eal_common_devargs.c | 19 +++ lib/librte_eal/comm

Re: [dpdk-dev] [PATCH v3 0/3] EAL change for using a config file for DPDK

27/06/2017 12:52, Jacek Piasecki: > This patchset introduce a mechanism for running dpdk application with > parameters > provided by configuration file. > > A new API for EAL takes a config file data type - either loaded from file, > or built up programmatically in the application - and extracts

[dpdk-dev] [PATCH v6 19/19] eal: change whitelist / blacklist command line doc

The use of these commands have evolved. It is now possible to use whitelist and blacklist on any bus. Update the source code accordingly. Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/eal_common_options.c | 18 +- lib/librte_eal/common/eal_options.h| 8

[dpdk-dev] [PATCH v6 16/19] devargs: introduce cleaner parsing helper

Introduce a more versatile helper to parse device strings. This helper expects a generic rte_devargs structure as storage in order not to require any API changes in the future, should this structure be updated. The old equivalent function is thus being deprecated, as its API does not allow to acco

[dpdk-dev] [PATCH v6 17/19] devargs: clone function

This function returns a deep copy of an rte_devargs. Signed-off-by: Gaetan Rivet --- lib/librte_eal/bsdapp/eal/rte_eal_version.map | 1 + lib/librte_eal/common/eal_common_devargs.c | 19 +++ lib/librte_eal/common/include/rte_devargs.h | 12 lib/librte_eal

[dpdk-dev] [PATCH v6 15/19] devargs: generic device types

rte_devargs now represents any device from any bus. The related devtypes do not identify a bus anymore, only which scan policy the device subscribes to. The bus itself is identified by a bus handle previously introduced. Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/eal_common_devargs.c

[dpdk-dev] [PATCH v6 12/19] devargs: generic device representation

Remove the dependency of this subsystem upon bus specific device representation. Devargs only validates that a device declaration is correct and handled by a bus. The device interpretation is done afterward within the bus. Signed-off-by: Gaetan Rivet --- app/test-pmd/testpmd.c

[dpdk-dev] [PATCH v6 14/19] net/virtio: do not reference device type

Signed-off-by: Gaetan Rivet --- drivers/net/virtio/virtio_pci.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/virtio/virtio_pci.c b/drivers/net/virtio/virtio_pci.c index b7b3d61..6275359 100644 --- a/drivers/net/virtio/virtio_pci.c +++ b/drivers/net/virtio/v

[dpdk-dev] [PATCH v6 13/19] pci: update device name

Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/eal_common_pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/librte_eal/common/eal_common_pci.c b/lib/librte_eal/common/eal_common_pci.c index 5838cc6..fa9f1b6 100644 --- a/lib/librte_eal/common/eal_common_pci.c +++ b/lib/librte_e

[dpdk-dev] [PATCH v6 10/19] bus: introduce bus scan policies

Scan policies describe the way a bus should scan the system to search for possible devices. Three flags are introduced: RTE_BUS_SCAN_UNDEFINED: Configuration is irrelevant for this bus RTE_BUS_SCAN_WHITELIST: Scanning should be limited to declared devices RTE_BUS_SCAN_BLACKLIST: Scanning sho

[dpdk-dev] [PATCH v6 11/19] devargs: parse bus policies

Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/eal_common_devargs.c | 15 +++ 1 file changed, 15 insertions(+) diff --git a/lib/librte_eal/common/eal_common_devargs.c b/lib/librte_eal/common/eal_common_devargs.c index 102bd8d..16052a3 100644 --- a/lib/librte_eal/common/eal_co

[dpdk-dev] [PATCH v6 08/19] test: properly reference PCI header

Signed-off-by: Gaetan Rivet --- test/test/virtual_pmd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/test/test/virtual_pmd.c b/test/test/virtual_pmd.c index db99894..8e698bc 100644 --- a/test/test/virtual_pmd.c +++ b/test/test/virtual_pmd.c @@ -33,6 +33,7 @@ #include #include +#inclu

[dpdk-dev] [PATCH v6 09/19] dev: device kernel module is a device attribute

It is used in generic device structures and must not be tied to a bus. Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/include/rte_dev.h | 12 lib/librte_eal/common/include/rte_pci.h | 9 - 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/lib/librte_eal

[dpdk-dev] [PATCH v6 07/19] app/testpmd: properly reference PCI header

Signed-off-by: Gaetan Rivet --- app/test-pmd/testpmd.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h index 364502d..f23114a 100644 --- a/app/test-pmd/testpmd.h +++ b/app/test-pmd/testpmd.h @@ -34,6 +34,8 @@ #ifndef _TESTPMD_H_ #define _TES

[dpdk-dev] [PATCH v6 06/19] net/sfc: properly reference PCI header

Signed-off-by: Gaetan Rivet --- drivers/net/sfc/sfc.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/sfc/sfc.h b/drivers/net/sfc/sfc.h index 007ed24..41dff48 100644 --- a/drivers/net/sfc/sfc.h +++ b/drivers/net/sfc/sfc.h @@ -34,6 +34,7 @@ #include +#include #include #in

[dpdk-dev] [PATCH v6 04/19] net/e1000: properly reference PCI header

Signed-off-by: Gaetan Rivet --- drivers/net/e1000/e1000_ethdev.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/e1000/e1000_ethdev.h b/drivers/net/e1000/e1000_ethdev.h index 9266540..3f521a7 100644 --- a/drivers/net/e1000/e1000_ethdev.h +++ b/drivers/net/e1000/e1000_ethdev.h @@ -

[dpdk-dev] [PATCH v6 05/19] net/ixgbe: properly reference PCI header

Signed-off-by: Gaetan Rivet --- drivers/net/ixgbe/ixgbe_ethdev.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ixgbe/ixgbe_ethdev.h b/drivers/net/ixgbe/ixgbe_ethdev.h index 10b9967..bcbd62d 100644 --- a/drivers/net/ixgbe/ixgbe_ethdev.h +++ b/drivers/net/ixgbe/ixgbe_ethdev.h @@ -

[dpdk-dev] [PATCH v6 02/19] net/bnxt: properly reference PCI header

Signed-off-by: Gaetan Rivet --- drivers/net/bnxt/bnxt.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/bnxt/bnxt.h b/drivers/net/bnxt/bnxt.h index 1538aa5..07279f7 100644 --- a/drivers/net/bnxt/bnxt.h +++ b/drivers/net/bnxt/bnxt.h @@ -38,6 +38,7 @@ #include #include +#inclu

[dpdk-dev] [PATCH v6 00/19] Generic devargs parsing

The second part of the work outlined in [1] and [2]. The first part is at [3]. In this patchset, the representation of devices in rte_devargs is made generic to remove some dependencies of the EAL on specific buses implementations. Following the device types being characterized by their bus, the D

[dpdk-dev] [PATCH v6 03/19] net/mlx5: properly reference PCI header

Signed-off-by: Gaetan Rivet --- drivers/net/mlx5/mlx5.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h index 1148dee..9ef2c11 100644 --- a/drivers/net/mlx5/mlx5.h +++ b/drivers/net/mlx5/mlx5.h @@ -54,6 +54,7 @@ #ifdef PEDANTIC #pragma GCC d

[dpdk-dev] [PATCH v6 01/19] net/bonding: properly reference PCI header

Signed-off-by: Gaetan Rivet --- drivers/net/bonding/rte_eth_bond_args.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/bonding/rte_eth_bond_args.c b/drivers/net/bonding/rte_eth_bond_args.c index c718e61..4b99e13 100644 --- a/drivers/net/bonding/rte_eth_bond_args.c +++ b/drivers/

[dpdk-dev] [PATCH v7 6/6] devargs: parse bus info

Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/eal_common_devargs.c | 42 - lib/librte_eal/common/eal_common_vdev.c | 6 +++-- lib/librte_eal/common/include/rte_devargs.h | 3 +++ 3 files changed, 42 insertions(+), 9 deletions(-) diff --git a/lib/librte_

[dpdk-dev] [PATCH v7 5/6] bus: add helper to find a bus from a device name

Find which bus should be able to parse this device name into an internal device representation. Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/eal_common_bus.c | 21 + lib/librte_eal/common/eal_private.h| 12 2 files changed, 33 insertions(+) diff --g

[dpdk-dev] [PATCH v7 3/6] vdev: implement parse bus operation

Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/eal_common_vdev.c | 58 - 1 file changed, 29 insertions(+), 29 deletions(-) diff --git a/lib/librte_eal/common/eal_common_vdev.c b/lib/librte_eal/common/eal_common_vdev.c index 3bad0c4..6ecd1b5 100644 --- a/li

[dpdk-dev] [PATCH v7 4/6] pci: implement parse bus operation

Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/eal_common_pci.c | 15 +++ 1 file changed, 15 insertions(+) diff --git a/lib/librte_eal/common/eal_common_pci.c b/lib/librte_eal/common/eal_common_pci.c index 2c99049..d7e2fb4 100644 --- a/lib/librte_eal/common/eal_common_pci.c +

[dpdk-dev] [PATCH v7 0/6] rte_bus parse API

Following the evolutions announced in [1], here is the first part of the rte_devargs rework planned for 17.08. The rationale has been partially explained in [2]. This first part covers the introduction of the necessary facilities in rte_bus to allow for generic device parsing. This API is implemen

[dpdk-dev] [PATCH v7 2/6] bus: introduce parsing functionality

This operation can be used either to validate that a device representation can be understood by a bus, as well as store the resulting specialized device representation in any format determined by the bus. Signed-off-by: Gaetan Rivet --- lib/librte_eal/common/include/rte_bus.h | 21 ++

[dpdk-dev] [PATCH v7 1/6] bus: fix driver registration

From: Thomas Monjalon The bus name was stored with embedded double quotes. Indeed the bus name is given with a string in a macro, which is not used elsewhere. These macros are useless because the buses are drivers, so they must not have any API for the application writer. The registration can be

Re: [dpdk-dev] [PATCH 0/2] net/softnic: sw fall-back for traffic management

08/06/2017 18:43, Dumitrescu, Cristian: > ... > > > > I'm sure I'm missing something. > > In my understanding, we do not need to change the ops: > > - if the device offers the capability, let's call the ops > > - else call the software fallback function > > > > What you might be missing

Re: [dpdk-dev] [PATCH v2 1/2] eal: add uevent api for hot plug

Hi, This is an interesting step for hotplug in DPDK. 28/06/2017 13:07, Jeff Guo: > + netlink_fd = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_KOBJECT_UEVENT); It is monitoring the whole system... > +int > +rte_uevent_get(int fd, struct rte_uevent *uevent) > +{ > + int ret; > + char

Re: [dpdk-dev] [PATCH v5 10/19] bus: introduce bus scan policies

21/06/2017 01:35, Gaetan Rivet: > Scan policies describe the way a bus should scan the system to search > for possible devices. > > Three flags are introduced: > RTE_BUS_SCAN_UNDEFINED: Configuration is irrelevant for this bus > RTE_BUS_SCAN_WHITELIST: Scanning should be limited to declared de

Re: [dpdk-dev] [PATCH v5 16/19] devargs: introduce cleaner parsing helper

Hi Keith, Thanks for the review. On Tue, Jun 27, 2017 at 11:46:48PM +, Wiles, Keith wrote: > > > On Jun 20, 2017, at 4:35 PM, Gaetan Rivet wrote: > > > > Introduce a more versatile helper to parse device strings. This > > helper expects a generic rte_devargs structure as storage in order n

[dpdk-dev] [PATCH] bus: fix driver registration

The bus name was stored with embedded double quotes. Indeed the bus name is given with a string in a macro, which is not used elsewhere. These macros are useless because the buses are drivers, so they must not have any API for the application writer. The registration can be done with a hardcoded va

Re: [dpdk-dev] [pull-request] next-tm 17.08 pre-rc1

04/07/2017 18:52, Dumitrescu, Cristian: > > Hi Cristian, > > > > > Dumitrescu, Cristian (2): > > > ethdev: add traffic management ops get API > > > ethdev: add traffic management API > > > > The original request was to split this huge patch. > > It is too messy to bring a whole new AP

Re: [dpdk-dev] [PATCH v3 4/4] app/test-pmd: add cmd for dedicated LACP rx/tx queues

On 04/07/17 17:46, Declan Doherty wrote: From: Tomasz Kulasek Add new command to support enable/disable of dedicated tx/rx queue on each slave of a bond device for LACP control plane traffic. set bonding lacp dedicated_queues [enable|disable] When enabled this option creates dedicated q

Re: [dpdk-dev] [PATCH v3 3/4] net/bond: dedicated hw queues for LACP control traffic

On 04/07/17 17:46, Declan Doherty wrote: From: Tomasz Kulasek Add support for hardware flow classification of LACP control plane traffic to be redirect to a dedicated receive queue on each slave which is not visible to application. Also enables a dedicate transmit queue for LACP traffic which a

Re: [dpdk-dev] [PATCH v3 2/4] net/bond: use ptype flags for LACP rx filtering

On 04/07/17 17:46, Declan Doherty wrote: From: Tomasz Kulasek Use packet types flags in mbuf to provide hint for filtering of LACP control plane traffic from the data path. Signed-off-by: Declan Doherty --- ... Acked-by: Declan Doherty

Re: [dpdk-dev] [PATCH v3 1/7] service cores: header and implementation

-Original Message- > Date: Sun, 2 Jul 2017 22:35:08 +0100 > From: Harry van Haaren > To: dev@dpdk.org > CC: jerin.ja...@caviumnetworks.com, tho...@monjalon.net, > keith.wi...@intel.com, bruce.richard...@intel.com, Harry van Haaren > > Subject: [PATCH v3 1/7] service cores: header and im

Re: [dpdk-dev] [pull-request] next-tm 17.08 pre-rc1

> -Original Message- > From: Thomas Monjalon [mailto:tho...@monjalon.net] > Sent: Tuesday, July 4, 2017 4:47 PM > To: Dumitrescu, Cristian > Cc: dev@dpdk.org; jerin.ja...@caviumnetworks.com; > hemant.agra...@nxp.com; Singh, Jasvinder ; > Lu, Wenzhuo ; Yigit, Ferruh > > Subject: Re: [dpd

[dpdk-dev] [PATCH v3 4/4] app/test-pmd: add cmd for dedicated LACP rx/tx queues

From: Tomasz Kulasek Add new command to support enable/disable of dedicated tx/rx queue on each slave of a bond device for LACP control plane traffic. set bonding lacp dedicated_queues [enable|disable] When enabled this option creates dedicated queues on each slave device for LACP control

[dpdk-dev] [PATCH v3 3/4] net/bond: dedicated hw queues for LACP control traffic

From: Tomasz Kulasek Add support for hardware flow classification of LACP control plane traffic to be redirect to a dedicated receive queue on each slave which is not visible to application. Also enables a dedicate transmit queue for LACP traffic which allows complete decoupling of control and da

[dpdk-dev] [PATCH v3 2/4] net/bond: use ptype flags for LACP rx filtering

From: Tomasz Kulasek Use packet types flags in mbuf to provide hint for filtering of LACP control plane traffic from the data path. Signed-off-by: Declan Doherty --- drivers/net/bonding/rte_eth_bond_pmd.c | 9 - 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/b

[dpdk-dev] [PATCH v3 0/4] LACP control packet filtering acceleration

1. Overview Packet processing in the current path for bonding in mode 4, requires parse all packets in the fast path, to classify and process LACP packets. The idea of performance improvement is to use hardware offloads to improve packet classification. 2. Scope of work a) Optimiza

[dpdk-dev] [PATCH v3 1/4] net/bond: calculate number of bonding tx/rx queues

Fixes: 2efb58cb ("bond: new link bonding library") This patch fixes the maximum number of tx an rx queues supported by a bonding device return by the rte_eth_dev_info_get function. The bonding device now calculates the maximum number of supported tx and rx queues based on the slaves bound to the b

[dpdk-dev] [PATCH v10 19/20] doc: add control interface library documentation

Signed-off-by: Ferruh Yigit --- doc/api/doxy-api-index.md | 3 +- doc/api/doxy-api.conf | 1 + doc/guides/prog_guide/ctrl_if_lib.rst | 50 ++ doc/guides/prog_guide/index.rst| 1 + doc/guides/rel_notes/release_17_08.rst | 8

[dpdk-dev] [PATCH v10 20/20] ethdev: add control interface support

To have the support corresponding kernel module (UNCI) needs to be inserted. If kernel module is not there, application will run as it is without kernel control path support. When UNCI module inserted, running application creates a virtual Linux network interface (dpdk$) per DPDK port. This inter

[dpdk-dev] [PATCH v10 18/20] ctrl_if: process ethtool messages

Process ethtool messages and rend response back to kernel. Signed-off-by: Ferruh Yigit --- lib/librte_ctrl_if/rte_ctrl_process.c | 223 ++ lib/librte_ctrl_if/rte_ctrl_process.h | 4 + lib/librte_ctrl_if/rte_nl.c | 4 + 3 files changed, 231 insertions

[dpdk-dev] [PATCH v10 17/20] ctrl_if: process control messages

Receive the requests from virtual interface and process control messages. Signed-off-by: Ferruh Yigit --- lib/librte_ctrl_if/Makefile | 1 + lib/librte_ctrl_if/rte_ctrl_process.c | 167 ++ lib/librte_ctrl_if/rte_ctrl_process.h | 50 ++ lib/lib

[dpdk-dev] [PATCH v10 16/20] ctrl_if: initialize generic netlink interface

Initialize generic netlink sockets to exchange data between kernelspace. Signed-off-by: Ferruh Yigit --- lib/librte_ctrl_if/Makefile | 2 + lib/librte_ctrl_if/rte_ctrl_if.c | 10 ++ lib/librte_ctrl_if/rte_nl.c | 231 +++ lib/librte_ctrl_if/rte_nl.

[dpdk-dev] [PATCH v10 14/20] ctrl_if: add library skeleton

Add base files for new control interface library. Control interface is on top of ethtool and ethdev libraries. Control interface connects to the netlink socket provided by Linux kernel and passes commands received via netlink interface to the network drivers. Signed-off-by: Ferruh Yigit --- MA

[dpdk-dev] [PATCH v10 15/20] ctrl_if: add create destroy interface APIs

Library provides two APIs to create and destroy interfaces. rtnl used to create or destroy interfaces. Signed-off-by: Ferruh Yigit --- lib/librte_ctrl_if/rte_ctrl_if.c | 302 + lib/librte_ctrl_if/rte_ctrl_if.h | 34 lib/librte_ctrl_if/rte_ct

[dpdk-dev] [PATCH v10 13/20] unci: add ethtool support

Add ethtool support to the virtual interface. Ethtool functions also use netlink exec to get data from userspace. Signed-off-by: Ferruh Yigit --- lib/librte_eal/linuxapp/unci/Makefile | 1 + lib/librte_eal/linuxapp/unci/unci_dev.h | 2 + lib/librte_eal/linuxapp/unci/unci_ethtool.c

[dpdk-dev] [PATCH v10 12/20] unci: add netdevice ops

Add ndos for virtual interface. Almost all ndos use netlink exec to pass command to userspace and read response. Signed-off-by: Ferruh Yigit --- .../linuxapp/eal/include/exec-env/unci.h | 17 +++ lib/librte_eal/linuxapp/unci/unci_net.c| 132 - 2 files c

[dpdk-dev] [PATCH v10 11/20] unci: add netlink exec

Add netlink exec function, which sends a message to userspace and waits and receives the response from userspace. Signed-off-by: Ferruh Yigit --- .../linuxapp/eal/include/exec-env/unci.h | 6 + lib/librte_eal/linuxapp/unci/unci_dev.h| 4 + lib/librte_eal/linuxapp/unci/u

[dpdk-dev] [PATCH v10 09/20] unci: add rtnl newlink

Use rtnl to create a new interface. Interface is not setup yet. Pid and port_id should be provided by userspace application that does the call for interface creation. Signed-off-by: Ferruh Yigit --- lib/librte_eal/linuxapp/eal/Makefile | 1 + .../linuxapp/eal/include/exec-env/unc

[dpdk-dev] [PATCH v10 06/20] doc: add ethtool library documentation

Signed-off-by: Ferruh Yigit --- doc/api/doxy-api-index.md | 3 +- doc/api/doxy-api.conf | 1 + doc/guides/prog_guide/ethtool_lib.rst | 62 ++ doc/guides/prog_guide/index.rst| 1 + doc/guides/rel_notes/release_17_08.rst | 5

[dpdk-dev] [PATCH v10 10/20] unci: init netlink

Initialize netlink socket. Userspace application will connect to the socket for data transfer. Signed-off-by: Ferruh Yigit --- .../linuxapp/eal/include/exec-env/unci.h | 33 ++ lib/librte_eal/linuxapp/unci/Makefile | 1 + lib/librte_eal/linuxapp/unci/unci_dev.h

[dpdk-dev] [PATCH v10 04/20] ethtool: update header doxygen syntax

Minor corrections and doxygen syntax fixes on library header file. Signed-off-by: Ferruh Yigit --- lib/librte_ethtool/rte_ethtool.h | 57 +--- 1 file changed, 30 insertions(+), 27 deletions(-) diff --git a/lib/librte_ethtool/rte_ethtool.h b/lib/librte_ethtool

[dpdk-dev] [PATCH v10 08/20] unci: add module skeleton

Base files to have a new kernel module, without actual source code. Signed-off-by: Ferruh Yigit --- MAINTAINERS | 4 +++ config/common_base | 5 config/common_linuxapp | 1 + lib/librte_eal/linuxapp/Makefile| 4 ++

[dpdk-dev] [PATCH v10 07/20] doc: update ethtool sample app doc

Signed-off-by: Ferruh Yigit --- doc/guides/sample_app_ug/ethtool.rst | 36 1 file changed, 4 insertions(+), 32 deletions(-) diff --git a/doc/guides/sample_app_ug/ethtool.rst b/doc/guides/sample_app_ug/ethtool.rst index 67797954d..def48985d 100644 --- a/doc/g

[dpdk-dev] [PATCH v10 05/20] ethtool: enable library

Enable ethtool library for Linux by default. Enable ethtool sample application that uses ethtool library. Signed-off-by: Ferruh Yigit --- config/common_linuxapp | 1 + examples/Makefile | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/config/common_linuxapp b/config/co

[dpdk-dev] [PATCH v10 03/20] ethtool: remove PMD specific API call

ethtool library has ixgbe specific API call, this needs to be removed when moved into lib folder, libraries shouldn't have PMD dependencies. Signed-off-by: Ferruh Yigit --- lib/librte_ethtool/rte_ethtool.c | 23 +-- 1 file changed, 1 insertion(+), 22 deletions(-) diff --git

[dpdk-dev] [PATCH v10 02/20] ethtool: move from sample folder into lib folder

ethtool library initially developed for ethtool sample application, moving it to library folder to reuse it. Sample application will continue to use ethtool library. Sample application disabled for now, it will be enabled again when modifications to the ethtool library finished. Signed-off-by: F

[dpdk-dev] [PATCH v10 01/20] ethtool: add library skeleton

Library is disabled by default. Signed-off-by: Ferruh Yigit --- MAINTAINERS| 3 +++ config/common_base | 5 + doc/guides/rel_notes/release_17_08.rst | 1 + lib/Makefile | 2 ++ lib/librte_eal/common/eal

[dpdk-dev] [PATCH v10 00/20] Userspace Network Control Interface (UNCI)

Userspace Network Control Interface (UNCI), (formerly KCP). When a NIC bound to the DPDK, it can't be controlled by Linux tools. This patch creates a virtual network interface for each DPDK port, initial target is to get some data from those interfaces, in next step target is to control DPDK port

Re: [dpdk-dev] [PATCH v10 2/3] lib/gro: add TCP/IPv4 GRO support

Hi Yuanhan, > -Original Message- > From: Yuanhan Liu [mailto:y...@fridaylinux.org] > Sent: Tuesday, July 4, 2017 5:03 PM > To: Hu, Jiayu > Cc: dev@dpdk.org; Ananyev, Konstantin ; > step...@networkplumber.org; Tan, Jianfeng ; Wu, > Jingjing ; Yao, Lei A ; Bie, > Tiwei > Subject: Re: [PATC

Re: [dpdk-dev] [PATCH v10 1/3] lib: add Generic Receive Offload API framework

Hi Yuanhan, > -Original Message- > From: Yuanhan Liu [mailto:y...@fridaylinux.org] > Sent: Tuesday, July 4, 2017 4:37 PM > To: Hu, Jiayu > Cc: dev@dpdk.org; Ananyev, Konstantin ; > step...@networkplumber.org; Tan, Jianfeng ; Wu, > Jingjing ; Yao, Lei A ; Bie, > Tiwei > Subject: Re: [PATC

Re: [dpdk-dev] [PATCH 0/2] Allow application set mempool handle

Hi Santosh, On Tue, 4 Jul 2017 17:55:54 +0530, santosh wrote: > Hi Olivier, > > On Friday 30 June 2017 07:42 PM, Olivier Matz wrote: > > > Hi, > > > > On Tue, 20 Jun 2017 19:34:15 +0530, Jerin Jacob > > wrote: > >> -Original Message- > >>> Date: Tue, 20 Jun 2017 16:07:17 +0530 >

Re: [dpdk-dev] [dpdk-stable] [PATCH v2] eal: don't advertise a physical address when no hugepages

03/07/2017 12:17, Jan Blunck: > On Mon, Jul 3, 2017 at 12:04 PM, Olivier Matz wrote: > > When populating a mempool with a virtual memory area, the mempool > > library expects to be able to get the physical address of each page. > > > > When started with --no-huge, the physical addresses may not be

Re: [dpdk-dev] [pull-request] next-tm 17.08 pre-rc1

Hi Cristian, > Dumitrescu, Cristian (2): > ethdev: add traffic management ops get API > ethdev: add traffic management API The original request was to split this huge patch. It is too messy to bring a whole new API area in one patch. We have nothing to refer in case of bug, and it is

[dpdk-dev] [pull-request] next-tm 17.08 pre-rc1

The following changes since commit a566400e8b73ec646e0cc6dd0bc44def8535fb98: net: implement CRC for ARM64 NEON (2017-07-04 15:58:45 +0200) are available in the git repository at: http://dpdk.org/git/next/dpdk-next-tm for you to fetch changes up to dcb4c3f881e29e1062a3e298e60474912e8a4ece:

Re: [dpdk-dev] [PATCH v7 3/4] net/mlx4: refactor RSS parent queue allocation

On Tue, Jul 04, 2017 at 11:22:50AM +, Vasily Philipov wrote: > A special "parent" queue must be allocated in addition to a group of > standard Rx queues for RSS to work. This is done automatically outside of > isolated mode by the PMD when applications request several Rx queues. > > Since each

Re: [dpdk-dev] [PATCH v7 4/4] net/mlx4: support flow API RSS action

On Tue, Jul 04, 2017 at 11:22:51AM +, Vasily Philipov wrote: > This commit adds support for the flow API RSS action with the following > limitations: > > - Only supported when isolated mode is enabled. > - The number of queues specified by the action (rte_flow_action_rss.num) >must be a

Re: [dpdk-dev] [PATCH v7 2/4] net/mlx4: implement isolated mode from flow API

On Tue, Jul 04, 2017 at 11:22:49AM +, Vasily Philipov wrote: > The user must request isolated mode before device configuration. > > Signed-off-by: Vasily Philipov Acked-by: Adrien Mazarguil -- Adrien Mazarguil 6WIND

Re: [dpdk-dev] [PATCH v7 1/4] app/testpmd: add isolated mode parameter

On Tue, Jul 04, 2017 at 11:22:48AM +, Vasily Philipov wrote: > Providing this parameter requests flow API isolated mode on all ports at > initialization time. It ensures all traffic is received through the > configured flow rules only (see flow command). > > Ports that do not support this mode

Re: [dpdk-dev] [PATCH v5 0/8] accelerate examples/l3fwd with NEON on ARM64 platform

> Jianbo Liu (8): > examples/l3fwd: extract arch independent code from multi hash lookup > examples/l3fwd: rename l3fwd_em_sse.h to l3fwd_em_sequential.h > examples/l3fwd: extract common code from multi packet send > examples/l3fwd: rearrange the code for lpm_l3fwd > arch/arm: add vcopyq_

Re: [dpdk-dev] [PATCH v3 00/20] traffic manager on i40e and ixgbe

> -Original Message- > From: Lu, Wenzhuo > Sent: Thursday, June 29, 2017 5:24 AM > To: dev@dpdk.org > Cc: Dumitrescu, Cristian ; Singh, Jasvinder > ; Lu, Wenzhuo > Subject: [PATCH v3 00/20] traffic manager on i40e and ixgbe > > Implement the traffic manager APIs on i40e and ixgbe. > Thi

  1   2   3   >