[dpdk-dev] ConnectX4 100GbE - Compilation problem

Hi Adrien, Thanks for the prompt reply! You are right, I didn't go via the DPDK route, in the hope that Mellanox will provide the exact source and configuration. DPDK 16.07 from dpdk.org works like a charm and my NIC is in PMD mode, thanks a lot for your guidance! Best regards, Georgios On Thu,

[dpdk-dev] ConnectX4 100GbE - Compilation problem

Hi George, On Thu, Aug 18, 2016 at 05:41:38PM +0200, george.dit at gmail.com wrote: > Hi, > > I have a single port Mellanox ConnectX 4 100GbE NIC and I want to test its > Rx/Tx capabilites using DPDK. > My system runs a Linux kernel 4.4 compiled from sources. > > I found the PMD driver for

[dpdk-dev] Not able to bring up the VM with dpdk enabled ovs bridge

Hi, When I try to add the virtio interface to dpdk enabled ovs bridge I am getting below error message. "Unable to add port vnet1 to OVS bridge ovsbr0" I have added created the ovs bridge and added ports to the same as below. $OVS_DIR/utilities/ovs-vsctl add-port ovsbr0 vhost-user1 -- set

[dpdk-dev] ConnectX4 100GbE - Compilation problem

Hi, I have a single port Mellanox ConnectX 4 100GbE NIC and I want to test its Rx/Tx capabilites using DPDK. My system runs a Linux kernel 4.4 compiled from sources. I found the PMD driver for this NIC as provided by Mellanox here

[dpdk-dev] [PATCH] eal/armv8: high-resolution cycle counter

Existing cntvct_el0 based rte_rdtsc() provides portable means to get wall clock counter at user space. Typically it runs at <= 100MHz. The alternative method to enable rte_rdtsc() for high resolution wall clock counter is through armv8 PMU subsystem. The PMU cycle counter runs at CPU frequency,

[dpdk-dev] [PATCH 7/7] vhost: simplify features set/get

No need to use a pointer to store/retrieve features. Signed-off-by: Yuanhan Liu --- lib/librte_vhost/vhost_user.c | 20 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c index ef4a0c1..eee99e9 100644

[dpdk-dev] [PATCH 6/7] vhost: get device once

Invoke get_device() at the beginning of vhost_user_msg_handler, so that we could check the return value once. Which could save tons of duplicate get-and-check device. Signed-off-by: Yuanhan Liu --- lib/librte_vhost/vhost_user.c | 160 +- 1 file changed,

[dpdk-dev] [PATCH 5/7] vhost: unify function names

Some functions are with prefix "user_", while others with "vhost_". Making them all starting with "vhost_user_" to unify the function names. Signed-off-by: Yuanhan Liu --- lib/librte_vhost/vhost_user.c | 60 +-- 1 file changed, 30 insertions(+), 30

[dpdk-dev] [PATCH 4/7] vhost: fold common message handlers

Due to history reason (that we have 2 vhost implementations), some messages are handled in two calls: vhost specific implementation handles it first and then invoke the common one to do another handling. We have one implementation only now, we could write one method for each message. Here fold

[dpdk-dev] [PATCH 3/7] vhost: refactor source code structure

The code structure is a bit messy now. For example, vhost-user message handling is spread to three different files: vhost-net-user.c virtio-net.c virtio-net-user.c Where, vhost-net-user.c is the entrance to handle all those messages and then invoke the right method for a specific message.

[dpdk-dev] [PATCH 2/7] vhost: remove sub source dir

We now have one vhost implementation; no sub source dir is needed. Rmove it by move them to upper dir. Signed-off-by: Yuanhan Liu --- lib/librte_vhost/Makefile | 6 +++--- lib/librte_vhost/{vhost_user => }/fd_man.c | 0 lib/librte_vhost/{vhost_user =>

[dpdk-dev] [PATCH 1/7] vhost: remove vhost-cuse

remove vhost-cuse code, including the eventfd_link kernel module that is for vhost-cuse only. The lib/virt/qemu-wrap.py is also removed, as it's mainly for vhost-cuse usage. As we have one vhost implementation now, one vhost config option is needed only. Thus, CONFIG_RTE_LIBRTE_VHOST_USER is

[dpdk-dev] [PATCH 0/7] vhost: vhost-cuse removal and code path refactoring

The first patch removes the vhost-cuse (see following link for the deprecate note) http://dpdk.org/ml/archives/dev/2016-July/044080.html After the removal, there is no reason to keep the vhost_user sub source dir any more. This also brings a chance to rename all those files in a more proper

[dpdk-dev] [PATCH 2/2] examples/vhost: support multiple socket files

On Thu, Aug 18, 2016 at 10:27:55AM +0200, Maxime Coquelin wrote: > > > On 08/16/2016 06:14 PM, Jiayu Hu wrote: > >When examples/vhost runs in client mode, only one QEMU can be connected. > >This is because that examples/vhost just supports one socket file. This > >patch is to add multiple

[dpdk-dev] [PATCH 1/2] examples/vhost: rename dev-basename

On Thu, Aug 18, 2016 at 10:22:38AM +0200, Maxime Coquelin wrote: > Hi Jiayu, > > On 08/16/2016 06:14 PM, Jiayu Hu wrote: > >In examples/vhost, "dev-basename" is a program option, which is to set > >the vhost-net socket used by vhost-user, or the character device used > >by vhost-cuse. Since

[dpdk-dev] vhost [query] : support for multiple ports and non VMDQ devices in vhost switch

On Wed, Aug 17, 2016 at 03:54:21PM +0530, Pankaj Chauhan wrote: > My use case is that my machine/board which is not sitting as end node of > network but somewhere in between like an router. So the traffic looks > something like this: > > Physical port 1 -> Enter VM(s) through virtio -> exit from

[dpdk-dev] [PATCH 2/2] examples/vhost: support multiple socket files

On Tue, Aug 16, 2016 at 12:14:39PM -0400, Jiayu Hu wrote: > +/* > + * This function is used to unregister drivers. > + */ > +static void > +unregister_drivers(int socket_num) > +{ Redundant comment. The function name already explains it well. > /* Register vhost user driver to handle

[dpdk-dev] [PATCH v3 2/4] virtio: move SSE based Rx implementation to separate file

On Tue, Jul 05, 2016 at 06:19:24PM +0530, Jerin Jacob wrote: > Split out SSE instruction based virtio simple Rx > implementation to a separate file > > Signed-off-by: Jerin Jacob Hi, I was about to apply this set. I then did some build test and found a weird issue: it breaks the build with

[dpdk-dev] [RFC PATCH 5/5] app/test_pmd: add tests for new API's

add test for vf vlan anti spoof add test for vf mac anti spoof add test for vf ping add test for vf vlan strip add test for vf vlan insert add test for tx loopback add test for all queues drop enable bit add test for vf split drop enable bit add test for vf mac address add new API's to the testpmd

[dpdk-dev] [RFC PATCH 4/5] net/ixgbe: add functions for VF management

Add new functions to configure and manage VF's on a Niantic NIC. add ixgbe_vf_ping function. add ixgbe_set_vf_vlan_anti_spoof function. add ixgbe_set_vf_mac_anti_spoof function. Signed-off-by: azelezniak add ixgbe_set_vf_vlan_strip function add ixgbe_set_vf_vlan_insert function. add

[dpdk-dev] [RFC PATCH 3/5] librte_ether: add API's for VF management

Add new API functions to configure and manage VF's on a NIC. add rte_eth_dev_vf_ping function. add rte_eth_dev_set_vf_vlan_anti_spoof function. add rte_eth_dev_set_vf_mac_anti_spoof function. Signed-off-by: azelezniak add rte_eth_dev_set_vf_vlan_strip function. add

[dpdk-dev] [RFC PATCH 2/5] net/ixgbe: add callback to user app on VF to PF mbox msg

call _rte_eth_dev_callback_process_vf from ixgbe_rcv_msg_from_vf function. The callback asks the user application if it is allowed to perform the function. If the cb_param.retval is RTE_ETH_MB_EVENT_PROCEED then continue, if 0, do nothing and send ACK to VF if > 1, do nothing and send NAK to VF.

[dpdk-dev] [RFC PATCH 1/5] librte_ether: add internal callback functions

add _rte_eth_dev_callback_process_vf function. add _rte_eth_dev_callback_process_generic function Adding a callback to the user application on VF to PF mailbox message, allows passing information to the application controlling the PF when a VF mailbox event message is received, such as VF reset.

[dpdk-dev] [RFC PATCH 0/5] add API's for VF management

This RFC patchset contains new DPDK API's requested by AT for use with the Virtual Function Daemon (VFD). The need to configure and manage VF's on a NIC has grown to the point where AT have devloped a DPDK based tool, VFD, to do this. This RFC proposes to add the following API extensions to

[dpdk-dev] VLAN with ixgbevf pmd

Hi, I am trying to get tagged packets to work in SRIOV mode. I am using dpdk 2.1 version with an application on KVM. The setup is as below: The same configuration works for untagged packets. Guest VM (Virtual Function/Created tagged kni interfaces)--- > KVM host (PF/no tag on the VF )

[dpdk-dev] [PATCH 2/2] app/test: add test cases for NULL for Intel QAT driver

Added NULL algorithm to test file for Intel(R) QuickAssist Technology Driver Signed-off-by: Deepak Kumar Jain --- app/test/test_cryptodev.c | 10 ++ 1 file changed, 10 insertions(+) diff --git a/app/test/test_cryptodev.c b/app/test/test_cryptodev.c index 8553759..67ca912 100644 ---

[dpdk-dev] [PATCH 1/2] crypto/qat: add NULL capability to Intel QAT driver

enabled NULL crypto for Intel(R) QuickAssist Technology Signed-off-by: Deepak Kumar Jain --- doc/guides/cryptodevs/qat.rst| 3 ++- drivers/crypto/qat/qat_adf/qat_algs_build_desc.c | 2 ++ drivers/crypto/qat/qat_crypto.c | 4 3 files changed, 8

[dpdk-dev] [PATCH 0/2] add NULL crypto support in Intel QAT driver

This patchset adds support of NULL crypto in Intel(R) QuickAssist Technology driver. This patchset depends on following patchset: "crypto/qat: add aes-sha384-hmac capability to Intel QAT driver" (http://dpdk.org/dev/patchwork/patch/15228/) Deepak Kumar Jain (2): crypto/qat: add NULL

[dpdk-dev] [PATCH 2/2] app/test: add test cases for aes-sha384-hmac for Intel QAT driver

From: "Jain, Deepak K" Added aes-sha384-hmac algorithm to test file for Intel(R) QuickAssist Technology Driver Signed-off-by: Deepak Kumar Jain --- app/test/test_cryptodev_aes.c | 6 -- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git

[dpdk-dev] [PATCH 1/2] crypto/qat: add aes-sha384-hmac capability to Intel QAT driver

From: "Jain, Deepak K" enabled support of aes-sha384-hmac in Intel(R) QuickAssist driver Signed-off-by: Deepak Kumar Jain --- doc/guides/cryptodevs/qat.rst| 1 + drivers/crypto/qat/qat_adf/qat_algs_build_desc.c | 33

[dpdk-dev] [PATCH 0/2] add aes-sha384-hmac support to Intel QAT driver

This patchset adds support of aes-sha384-hmac in Intel(R) QuickAssist Technology driver. This patchset depends on following patchset: "crypto/qat: add aes-sha224-hmac capability to Intel QAT driver" (http://dpdk.org/dev/patchwork/patch/15226/) Jain, Deepak K (2): crypto/qat: add

[dpdk-dev] [PATCH 2/2] app/test: add test cases for aes-sha224-hmac for Intel QAT driver

From: "Jain, Deepak K" Added aes-sha224-hmac algorithm to test file for Intel(R) QuickAssist Technology Driver Signed-off-by: Deepak Kumar Jain --- app/test/test_cryptodev_aes.c | 6 -- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git

[dpdk-dev] [PATCH 1/2] crypto/qat: add aes-sha224-hmac capability to Intel QAT driver

From: "Jain, Deepak K" Added support of aes-sha224-hmac in Intel(R) QuickAssist driver Signed-off-by: Deepak Kumar Jain --- doc/guides/cryptodevs/qat.rst| 1 + drivers/crypto/qat/qat_adf/qat_algs_build_desc.c | 33

[dpdk-dev] [PATCH 0/2] add aes-sha224-hmac support to Intel QAT driver

This patchset adds support of aes-sha224-hmac in Intel(R) QuickAssist Technology driver. This patchset depends on following patchset: "crypto/qat: add MD5 HMAC capability to Intel QAT driver" (http://dpdk.org/dev/patchwork/patch/15165/) Jain, Deepak K (2): crypto/qat: add aes-sha224-hmac

[dpdk-dev] [PATCH] ivshmem: remove integration in dpdk

> Following discussions on the mailing list [1] and since nobody stood up to > implement the necessary cleanups, here is the ivshmem integration removal. > > There is not much to say about this patch, a lot of code is being removed. > The default configuration file for packet_ordering example is

[dpdk-dev] [PATCH] optimize vhost enqueue

Thanks Maxime and Yuanhan for your review and suggestions! Please help review the v2 of this patch. > -Original Message- > From: Yuanhan Liu [mailto:yuanhan.liu at linux.intel.com] > Sent: Wednesday, August 17, 2016 5:51 PM > To: Maxime Coquelin > Cc: Wang, Zhihong ; dev at dpdk.org >

[dpdk-dev] How to get the number of used descriptors for vHost-users

Hi all Is there a function -like rte_eth_rx_queue_count()- to get the number of used (or free) descriptors in a vHost RX/TX's queue? I used rte_vhost_avail_entries() but I'm not sure it is correct way. Thanks in advance. - Volkan

[dpdk-dev] [PATCH] vhost: add back support for concurrent enqueue

On Mon, Aug 15, 2016 at 7:37 PM, Yuanhan Liu wrote: > On Mon, Aug 15, 2016 at 01:00:24PM -0700, Rich Lane wrote: > > Concurrent enqueue is an important performance optimization when the > number > > of cores used for switching is different than the number of vhost queues. > > I've observed a 20%

[dpdk-dev] vhost [query] : support for multiple ports and non VMDQ devices in vhost switch

Hi Maxime, > -Original Message- > From: Maxime Coquelin [mailto:maxime.coquelin at redhat.com] > Sent: Thursday, August 18, 2016 3:43 PM > To: Tan, Jianfeng; Yuanhan Liu; Pankaj Chauhan > Cc: dev at dpdk.org; hemant.agrawal at nxp.com; shreyansh.jain at nxp.com > Subject: Re: [dpdk-dev]

[dpdk-dev] vhost [query] : support for multiple ports and non VMDQ devices in vhost switch

Hi Maxime, On 8/17/2016 7:18 PM, Maxime Coquelin wrote: > Hi Jianfeng, > > On 08/17/2016 04:33 AM, Tan, Jianfeng wrote: >> Hi, >> >> Please review below proposal of Pankaj and myself after an offline >> discussion. (Pankaj, please correct me if I'm going somewhere wrong). >> >> a. Remove HW

[dpdk-dev] [PATCH 1/2] examples/vhost: rename dev-basename

On 08/18/2016 10:35 AM, Yuanhan Liu wrote: > On Thu, Aug 18, 2016 at 10:22:38AM +0200, Maxime Coquelin wrote: >> Hi Jiayu, >> >> On 08/16/2016 06:14 PM, Jiayu Hu wrote: >>> In examples/vhost, "dev-basename" is a program option, which is to set >>> the vhost-net socket used by vhost-user, or the

[dpdk-dev] [PATCH 2/2] examples/vhost: support multiple socket files

On 08/16/2016 06:14 PM, Jiayu Hu wrote: > When examples/vhost runs in client mode, only one QEMU can be connected. > This is because that examples/vhost just supports one socket file. This > patch is to add multiple sockets support for examples/vhost. > > Signed-off-by: Jiayu Hu > --- >

[dpdk-dev] [PATCH 1/2] examples/vhost: rename dev-basename

Hi Jiayu, On 08/16/2016 06:14 PM, Jiayu Hu wrote: > In examples/vhost, "dev-basename" is a program option, which is to set > the vhost-net socket used by vhost-user, or the character device used > by vhost-cuse. Since vhost-cuse should be dropped, and "dev-basename" > is not a suitable name for

[dpdk-dev] [PATCH] examples/vhost: remove VLAN strip option

Hi Maxime, > -Original Message- > From: Maxime Coquelin [mailto:maxime.coquelin at redhat.com] > Sent: Thursday, August 18, 2016 3:52 PM > To: Tan, Jianfeng; dev at dpdk.org > Cc: yuanhan.liu at linux.intel.com > Subject: Re: [dpdk-dev] [PATCH] examples/vhost: remove VLAN strip option >

[dpdk-dev] [PATCH] examples/vhost: remove VLAN strip option

On 08/18/2016 07:46 AM, Jianfeng Tan wrote: > When VMDQ is enabled, different NICs have different behaviors for > disabling VLAN strip. In detail, i40e only enables/disables it of > PF's main vsi; fm10k cannot disable VLAN strip, etc. We now remove > this option, --vlan-strip, to reduce any

[dpdk-dev] vhost [query] : support for multiple ports and non VMDQ devices in vhost switch

Hi, On 08/18/2016 04:35 AM, Tan, Jianfeng wrote: > Hi Maxime, > > On 8/17/2016 7:18 PM, Maxime Coquelin wrote: >> Hi Jianfeng, >> >> On 08/17/2016 04:33 AM, Tan, Jianfeng wrote: >>> Hi, >>> >>> Please review below proposal of Pankaj and myself after an offline >>> discussion. (Pankaj, please

[dpdk-dev] [PATCH v2 6/6] vhost: optimize cache access

This patch reorders the code to delay virtio header write to optimize cache access efficiency for cases where the mrg_rxbuf feature is turned on. It reduces CPU pipeline stall cycles significantly. Signed-off-by: Zhihong Wang --- lib/librte_vhost/vhost_rxtx.c | 23 --- 1

[dpdk-dev] [PATCH v2 5/6] vhost: batch update used ring

This patch enables batch update of the used ring for better efficiency. Signed-off-by: Zhihong Wang --- lib/librte_vhost/vhost-net.h | 4 +++ lib/librte_vhost/vhost_rxtx.c | 68 +-- lib/librte_vhost/virtio-net.c | 15 -- 3 files changed, 68

[dpdk-dev] [PATCH v2 4/6] vhost: add desc prefetch

This patch adds descriptor prefetch to hide cache access latency. Signed-off-by: Zhihong Wang --- lib/librte_vhost/vhost_rxtx.c | 5 + 1 file changed, 5 insertions(+) diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c index 939957d..7db83d0 100644 ---

[dpdk-dev] [PATCH v2 3/6] vhost: remove useless volatile

This patch removes useless volatile attribute to allow compiler optimization. Signed-off-by: Zhihong Wang --- lib/librte_vhost/vhost-net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/librte_vhost/vhost-net.h b/lib/librte_vhost/vhost-net.h index 38593a2..51fdf3d

[dpdk-dev] [PATCH v2 2/6] vhost: remove obsolete

This patch removes obsolete functions. Signed-off-by: Zhihong Wang --- lib/librte_vhost/vhost_rxtx.c | 408 -- 1 file changed, 408 deletions(-) diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c index 8e6d782..939957d 100644 ---

[dpdk-dev] [PATCH v2 1/6] vhost: rewrite enqueue

This patch implements the vhost logic from scratch into a single function designed for high performance and better maintainability. Signed-off-by: Zhihong Wang --- lib/librte_vhost/vhost_rxtx.c | 212 -- 1 file changed, 205 insertions(+), 7 deletions(-)

[dpdk-dev] [PATCH v2 0/6] vhost: optimize enqueue

This patch set optimizes the vhost enqueue function. It implements the vhost logic from scratch into a single function designed for high performance and good maintainability, and improves CPU efficiency significantly by optimizing cache access, which means: * For fast frontends (eg. DPDK