Re: [dpdk-dev] [PATCH v5 3/6] ethdev: fix doxygen comments of shared data fields

On 10/18/18 4:23 AM, Thomas Monjalon wrote: Some doxygen comments were wrongly associated to the next field because of syntax /** instead of /**< Some other cleanups (like alignment) are done. Signed-off-by: Thomas Monjalon Reviewed-by: Andrew Rybchenko Yesterday I made similar patch, but

Re: [dpdk-dev] [PATCH v5 4/6] ethdev: free all common data when releasing port

On 10/18/18 4:24 AM, Thomas Monjalon wrote: This is a clean-up of common ethdev data freeing. All data freeing are moved to rte_eth_dev_release_port() and done only in case of primary process. It is probably fixing some memory leaks for PMDs which were not freeing all data. Signed-off-by: Thoma

Re: [dpdk-dev] [PATCH v5 5/6] ethdev: remove release function for secondary process

On 10/18/18 4:24 AM, Thomas Monjalon wrote: After previous changes, the function rte_eth_dev_release_port() can be used for primary or secondary process as well. The only difference with rte_eth_dev_release_port_secondary() is the shared lock used in rte_eth_dev_release_port(). The function rte_

Re: [dpdk-dev] [PATCH v5 2/6] app/testpmd: allow detaching a port not closed

On 10/18/18 4:23 AM, Thomas Monjalon wrote: The testpmd application aim is for testing; so order of operations should not be enforced. There was a test to forbid detaching before closing a port. However, it may interesting to test what happens in such case. It is possible for a PMD to automatica

Re: [dpdk-dev] [PATCH v5 3/3] app/testpmd: add Tx metadata debug commands

On 10/17/2018 1:03 PM, Dekel Peled wrote: > As described in [1],[2] this series adds option to set metadata value as > match pattern when creating a new flow rule. > > This patch introduces code for debug porpuse only. > The new 'config' command takes a 32 bit value and stores it per port: >

Re: [dpdk-dev] [PATCH v4] net/mlx5: support metadata as flow rule criteria

On Wed, Oct 17, 2018 at 02:53:37PM +0300, Dekel Peled wrote: > As described in series starting at [1], it adds option to set > metadata value as match pattern when creating a new flow rule. > > This patch adds metadata support in mlx5 driver, in two parts: > - Add the validation and setting of met

Re: [dpdk-dev] [PATCH v5 00/13] introduce telemetry library

Most of the issues I pointed out in v2 of this patchset is still here. On 2018-10-16 17:57, Kevin Laatz wrote: This patchset introduces a Telemetry library for DPDK Service Assurance. This library provides an easy way to query DPDK Ethdev metrics. The telemetry library provides a method for a s

Re: [dpdk-dev] [PATCH 1/2] eal/bsd: fix FreeBSD build

On 16-Oct-18 1:38 PM, Ferruh Yigit wrote: On 10/16/2018 1:04 PM, Ferruh Yigit wrote: On 10/16/2018 12:41 PM, Jeff Guo wrote: When compiling on FreeBSD, a warning/error is thrown for unused parameter. This patch aim to fix the issue by delete the useless func definition. This function is part

Re: [dpdk-dev] [PATCH v8 3/3] net/tap: allow secondary process to access primary device queues

Hi Ferruh, Yes seems I sent the wrong code I'm sending a V9 with proper code. Kindest regards, Raslan Darawsheh > -Original Message- > From: Ferruh Yigit > Sent: Wednesday, October 17, 2018 7:02 PM > To: Raslan Darawsheh ; keith.wi...@intel.com > Cc: Thomas Monjalon ; dev@dpdk.org; Shah

[dpdk-dev] [PATCH v9 1/3] net/tap: add queue and port ids in Rx/Tx queues structures

Port and queue ids are added to easily map the file descriptors stored in each process private. Signed-off-by: Raslan Darawsheh --- drivers/net/tap/rte_eth_tap.c | 3 +++ drivers/net/tap/rte_eth_tap.h | 3 +++ 2 files changed, 6 insertions(+) diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers

[dpdk-dev] [PATCH v9 2/3] net/tap: move fds of Rx/Tx queues to be in process private

fd's cannot be shared between processes, and each process need to have it's own fd's pointer. Signed-off-by: Raslan Darawsheh --- This patch has dependancy on the following patch http://patches.dpdk.org/patch/46185/ --- --- drivers/net/tap/rte_eth_tap.c | 93 +-

[dpdk-dev] [PATCH v9 3/3] net/tap: allow secondary process to access primary device queues

In the case the device is created by the primary process, the secondary must request some file descriptors to attach the queues. The file descriptors are shared via IPC Unix socket. Thanks to the IPC synchronization, the secondary process is now able to do Rx/Tx on a TAP created by the primary pro

Re: [dpdk-dev] [PATCH v6 3/3] app/testpmd: set packet dump based on verbosity level

Hi, > -Original Message- > From: Ferruh Yigit > Sent: Wednesday, October 17, 2018 7:33 PM > To: Iremonger, Bernard ; Raslan Darawsheh > ; Wu, Jingjing > Cc: Thomas Monjalon ; dev@dpdk.org; Shahaf > Shuler ; Xueming(Steven) Li > ; Ori Kam ; > jerin.ja...@caviumnetworks.com; david.march...

Re: [dpdk-dev] [PATCH v5 3/3] app/testpmd: add Tx metadata debug commands

Thanks, PSB. > -Original Message- > From: Ferruh Yigit > Sent: Thursday, October 18, 2018 10:57 AM > To: Dekel Peled ; wenzhuo...@intel.com; > jingjing...@intel.com; bernard.iremon...@intel.com; > olivier.m...@6wind.com; Adrien Mazarguil ; > Thomas Monjalon ; arybche...@solarflare.com > C

Re: [dpdk-dev] [PATCH v5 6/6] ethdev: complete closing of port

On 10/18/18 4:24 AM, Thomas Monjalon wrote: After closing a port, it cannot be restarted. So there is no reason to not free all associated resources. The last step was done with rte_eth_dev_detach() which is deprecated. Instead of blindly removing the associated rte_device, the driver should che

Re: [dpdk-dev] [PATCH v6 3/3] app/testpmd: set packet dump based on verbosity level

On 10/18/2018 9:19 AM, Raslan Darawsheh wrote: > Hi, > >> -Original Message- >> From: Ferruh Yigit >> Sent: Wednesday, October 17, 2018 7:33 PM >> To: Iremonger, Bernard ; Raslan Darawsheh >> ; Wu, Jingjing >> Cc: Thomas Monjalon ; dev@dpdk.org; Shahaf >> Shuler ; Xueming(Steven) Li >> ;

Re: [dpdk-dev] [PATCH v6 3/3] app/testpmd: set packet dump based on verbosity level

You are right about that my mistake. Kindest regards, Raslan Darawsheh > -Original Message- > From: Ferruh Yigit > Sent: Thursday, October 18, 2018 11:34 AM > To: Raslan Darawsheh ; Iremonger, Bernard > ; Wu, Jingjing > Cc: Thomas Monjalon ; dev@dpdk.org; Shahaf > Shuler ; Xueming(Stev

Re: [dpdk-dev] [PATCH] doc: update release notes for softnic PMD

Acked-by: Marko Kovacevic

[dpdk-dev] [PATCH v2 1/2] vhost: add packed ring support to vring base requests

For packed ring layout, we need save and restore avail and used indexes, and their wrap counter values. Signed-off-by: Maxime Coquelin --- lib/librte_vhost/vhost_user.c | 41 ++- 1 file changed, 35 insertions(+), 6 deletions(-) diff --git a/lib/librte_vhost/vhost

[dpdk-dev] [PATCH v2 2/2] vhost: advertize packed ring layout support

Signed-off-by: Maxime Coquelin --- lib/librte_vhost/vhost.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h index b4abad30c..760f42192 100644 --- a/lib/librte_vhost/vhost.h +++ b/lib/librte_vhost/vhost.h @@ -275,7 +275,8 @@

[dpdk-dev] [PATCH v2 0/2] vhost: packed ring support completion

In this v2, the vring state num field structure is changed to store both used and avail indexes and their wrap counters. Initial series ading packed ring layout support to the vhost library was missing the save and restore of the wrap counters and indexs on vring base requests used for migration.

Re: [dpdk-dev] [PATCH v5 6/6] ethdev: complete closing of port

18/10/2018 10:33, Andrew Rybchenko: > On 10/18/18 4:24 AM, Thomas Monjalon wrote: > > After closing a port, it cannot be restarted. > > So there is no reason to not free all associated resources. > > > > The last step was done with rte_eth_dev_detach() which is deprecated. > > Instead of blindly re

Re: [dpdk-dev] [PATCH v2 0/2] vhost: packed ring support completion

Sorry, just notice I forgot to generate patches again after fixing patch 2, v3 coming soon. On 10/18/2018 11:29 AM, Maxime Coquelin wrote: In this v2, the vring state num field structure is changed to store both used and avail indexes and their wrap counters. Initial series ading packed ring la

[dpdk-dev] [PATCH v3 0/2] vhost: packed ring support completion

In this v3, the vring state num field structure is changed to store both used and avail indexes and their wrap counters. Initial series ading packed ring layout support to the vhost library was missing the save and restore of the wrap counters and indexs on vring base requests used for migration.

[dpdk-dev] [PATCH v3 1/2] vhost: add packed ring support to vring base requests

For packed ring layout, we need save and restore avail and used indexes, and their wrap counter values. Signed-off-by: Maxime Coquelin --- lib/librte_vhost/vhost_user.c | 41 ++- 1 file changed, 35 insertions(+), 6 deletions(-) diff --git a/lib/librte_vhost/vhost

[dpdk-dev] [PATCH v3 2/2] vhost: advertize packed ring layout support

Signed-off-by: Maxime Coquelin --- lib/librte_vhost/vhost.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h index b4abad30c..760f42192 100644 --- a/lib/librte_vhost/vhost.h +++ b/lib/librte_vhost/vhost.h @@ -275,7 +275,8 @@

Re: [dpdk-dev] [PATCH v9 3/3] net/tap: allow secondary process to access primary device queues

On 10/18/2018 9:15 AM, Raslan Darawsheh wrote: > @@ -2082,6 +2215,17 @@ rte_pmd_tap_probe(struct rte_vdev_device *dev) > TAP_LOG(NOTICE, "Initializing pmd_tap for %s as %s", > name, tap_name); > > + /* Register IPC feed callback */ > + if (!tap_devices_count) { > +

[dpdk-dev] [PATCH v10 1/3] net/tap: add queue and port ids in Rx/Tx queues structures

Port and queue ids are added to easily map the file descriptors stored in each process private. Signed-off-by: Raslan Darawsheh --- drivers/net/tap/rte_eth_tap.c | 3 +++ drivers/net/tap/rte_eth_tap.h | 3 +++ 2 files changed, 6 insertions(+) diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers

[dpdk-dev] [PATCH v10 2/3] net/tap: move fds of Rx/Tx queues to be in process private

fd's cannot be shared between processes, and each process need to have it's own fd's pointer. Signed-off-by: Raslan Darawsheh --- This patch has dependancy on the following patch http://patches.dpdk.org/patch/46185/ --- --- drivers/net/tap/rte_eth_tap.c | 93 +-

[dpdk-dev] [PATCH v10 3/3] net/tap: allow secondary process to access primary device queues

In the case the device is created by the primary process, the secondary must request some file descriptors to attach the queues. The file descriptors are shared via IPC Unix socket. Thanks to the IPC synchronization, the secondary process is now able to do Rx/Tx on a TAP created by the primary pro

Re: [dpdk-dev] [PATCH] doc: update i40e guide for PPPoE package release

Acked-by: Marko Kovacevic

[dpdk-dev] [PATCH] app/testpmd: reserve NUMA node per device port and per ring

If user explicitly requested memory to be allocated from a socket via `port-numa-config` and `rxring-numa-config`, and if that socket is valid, add that socket into socket_ids[] so that mempool allocated for that socket. Fixes: dbfb8ec ("app/testpmd: optimize mbuf pool allocation") Suggested-by:

Re: [dpdk-dev] [PATCH v5 1/6] app/testpmd: fix ports list after removing several at once

Hi Wisam, > -Original Message- > From: Thomas Monjalon [mailto:tho...@monjalon.net] > Sent: Thursday, October 18, 2018 2:24 AM > To: Yigit, Ferruh ; arybche...@solarflare.com > Cc: dev@dpdk.org; ophi...@mellanox.com; Iremonger, Bernard > ; rahul.lakkire...@chelsio.com; Wisam Jaddo > > Sub

[dpdk-dev] [PATCH] doc: update softnic doc for flow and qos API support

Update document with flow and qos api support in softnic PMD. Signed-off-by: Jasvinder Singh Signed-off-by: Reshma Pattan --- doc/guides/nics/softnic.rst | 119 1 file changed, 119 insertions(+) diff --git a/doc/guides/nics/softnic.rst b/doc/guides/nics/sof

Re: [dpdk-dev] [PATCH v5 2/6] app/testpmd: allow detaching a port not closed

Hi Thomas, > -Original Message- > From: Andrew Rybchenko [mailto:arybche...@solarflare.com] > Sent: Thursday, October 18, 2018 8:45 AM > To: Thomas Monjalon ; Yigit, Ferruh > > Cc: dev@dpdk.org; ophi...@mellanox.com; Iremonger, Bernard > ; rahul.lakkire...@chelsio.com > Subject: Re: [PATC

[dpdk-dev] DPDK Release Status Meeting 18/10/2018

Minutes 18 October 2018 -- Agenda: * Dates * Subtrees Participants: * Intel * Mellanox Release Dates - * RC1 date *pushed out a week*, it is now *Friday, 26 October 2018* * RC2 date is *Friday, 2 November 2018* * Release date is *Tuesday, 20 November 2018* * RC

Re: [dpdk-dev] [PATCH v10 1/3] net/tap: add queue and port ids in Rx/Tx queues structures

On 10/18/2018 11:17 AM, Raslan Darawsheh wrote: > Port and queue ids are added to easily map the file > descriptors stored in each process private. > > Signed-off-by: Raslan Darawsheh Series applied to dpdk-next-net/master, thanks.

Re: [dpdk-dev] [PATCH v5 2/6] app/testpmd: allow detaching a port not closed

18/10/2018 12:51, Iremonger, Bernard: > From: Andrew Rybchenko [mailto:arybche...@solarflare.com] > > On 10/18/18 4:23 AM, Thomas Monjalon wrote: > > > The testpmd application aim is for testing; so order of operations > > > should not be enforced. > > > > > > There was a test to forbid detaching b

Re: [dpdk-dev] [PATCH v5 1/6] app/testpmd: fix ports list after removing several at once

18/10/2018 12:40, Iremonger, Bernard: > From: Thomas Monjalon [mailto:tho...@monjalon.net] > > > > From: Wisam Jaddo > > > > When detaching a port, the full rte_device is removed. > > If the rte_device was hosting several ports, the testpmd list of ports must > > be > > updated for multiple rem

Re: [dpdk-dev] [PATCH v5 1/6] app/testpmd: fix ports list after removing several at once

Hi Thomas > -Original Message- > From: Thomas Monjalon [mailto:tho...@monjalon.net] > Sent: Thursday, October 18, 2018 12:29 PM > To: Iremonger, Bernard > Cc: dev@dpdk.org; Yigit, Ferruh ; > arybche...@solarflare.com; ophi...@mellanox.com; > rahul.lakkire...@chelsio.com; Wisam Jaddo > Su

Re: [dpdk-dev] [PATCH v5 1/6] app/testpmd: fix ports list after removing several at once

Are we saving cycles by set it to be <= instead of < _ +1? BRs, Wisam Jaddo From: Thomas Monjalon Sent: Thursday, October 18, 2018 2:29 PM To: Iremonger, Bernard Cc: dev@dpdk.org; Yigit, Ferruh

Re: [dpdk-dev] [PATCH] doc: update softnic doc for flow and qos API support

> Update document with flow and qos api support in softnic PMD. > > Signed-off-by: Jasvinder Singh > Signed-off-by: Reshma Pattan > --- > doc/guides/nics/softnic.rst | 119 > > 1 file changed, 119 insertions(+) id 1) > + > +QoS API Support: > +--

Re: [dpdk-dev] [PATCH v5 2/3] app/testpmd: support metadata as flow rule item

> -Original Message- > From: dev On Behalf Of Dekel Peled > Sent: Wednesday, October 17, 2018 3:04 PM > To: wenzhuo...@intel.com; jingjing...@intel.com; > bernard.iremon...@intel.com; olivier.m...@6wind.com; Adrien Mazarguil > ; Thomas Monjalon ; > ferruh.yi...@intel.com; arybche...@sol

[dpdk-dev] Proposed dates for 19.02 release

Hi, There are two constraints within the 19.02 release timeframe this year: * Christmas/New Year's holidays * Chinese Spring Festival Holiday 4th-10th February (with some people out the week before as well). Note this is much earlier than in previous years. Since the majority of the testing is

Re: [dpdk-dev] [PATCH v10 1/3] net/tap: add queue and port ids in Rx/Tx queues structures

On 10/18/2018 11:17 AM, Raslan Darawsheh wrote: > Port and queue ids are added to easily map the file > descriptors stored in each process private. > > Signed-off-by: Raslan Darawsheh For series, Reviewed-by: Ferruh Yigit

Re: [dpdk-dev] [PATCH] app/testpmd: reserve NUMA node per device port and per ring

On 10/18/2018 11:39 AM, phil.y...@arm.com wrote: > If user explicitly requested memory to be allocated from a socket via > `port-numa-config` and `rxring-numa-config`, and if that socket is > valid, add that socket into socket_ids[] so that mempool allocated for > that socket. > > Fixes: dbfb8ec (

Re: [dpdk-dev] [PATCH] doc: update release note for crypto port and action

Acked-by: Marko Kovacevic

[dpdk-dev] Use shared C library to install DPDK

Hi there, I am using Alpine LInux in my Docker container. Since DPDK cannot be installed with *musl* C library, I decided to use *glibc *for Alpine Linux (from here ). It is installed as a shared library on the following path: */usr/glibc-compat/lib*.

Re: [dpdk-dev] [PATCH v3 3/3] doc: document --iova-mode EAL option

Only one thing I noticed: Running git log check: 45999 Wrong headline lowercase: doc: document --iova-mode EAL option All else seem ok. Reviewed-by: Marko Kovacevic

Re: [dpdk-dev] [PATCH v5 1/6] app/testpmd: fix ports list after removing several at once

Hi Wisam, From: Wisam Monther [mailto:wis...@mellanox.com] Sent: Thursday, October 18, 2018 12:49 PM To: Thomas Monjalon ; Iremonger, Bernard Cc: dev@dpdk.org; Yigit, Ferruh ; arybche...@solarflare.com; Ophir Munk ; rahul.lakkire...@chelsio.com Subject: RE: [dpdk-dev] [PATCH v5 1/6] app/testpm

Re: [dpdk-dev] [PATCH v4 1/6] kni: add API to set link status on kernel interface

On 10/17/2018 2:04 AM, Dan Gora wrote: > Add a new API function to KNI, rte_kni_update_link() to allow DPDK > applications to update the link status for KNI network interfaces in > the linux kernel. > > Signed-off-by: Dan Gora > --- > lib/librte_kni/rte_kni.c | 41 +

Re: [dpdk-dev] [PATCH v5 1/6] app/testpmd: fix ports list after removing several at once

18/10/2018 13:41, Iremonger, Bernard: > Hi Thomas > > From: Thomas Monjalon [mailto:tho...@monjalon.net] > > 18/10/2018 12:40, Iremonger, Bernard: > > > From: Thomas Monjalon [mailto:tho...@monjalon.net] > > > > > > > > From: Wisam Jaddo > > > > > > > > When detaching a port, the full rte_device

Re: [dpdk-dev] [PATCH v5 0/3] security: support for pdcp

16/10/2018 16:35, Akhil Goyal: > > Akhil Goyal (3): > >security: support pdcp protocol > >crypto/dpaa2_sec: add sample pdcp descriptor apis > >crypto/dpaa2_sec: support pdcp offload > > > > doc/guides/prog_guide/rte_security.rst | 107 +- > > drivers/crypto/dpaa2_sec/dpaa2_sec_

[dpdk-dev] [PATCH v2] doc: update softnic doc for flow and qos API support

Update document with flow and qos api support in softnic PMD. Signed-off-by: Jasvinder Singh Signed-off-by: Reshma Pattan Reviewed-by: Marko Kovacevic --- v2: fixed the Note. reworded the sentence. --- doc/guides/nics/softnic.rst | 120 1 file changed, 120

[dpdk-dev] [PATCH v2] doc: update softnic doc for flow and qos API support

Update document with flow and qos api support in softnic PMD. Signed-off-by: Jasvinder Singh Signed-off-by: Reshma Pattan Reviewed-by: Marko Kovacevic --- v2: fixed the Note. reworded the sentence. --- doc/guides/nics/softnic.rst | 120 1 file changed, 120

[dpdk-dev] [PATCH] devtools: fix alignment of Marvell build options

Really minor issue: There were extra spaces making the alignment wrong. Fixes: e95faac15110 ("crypto/mrvl: rename PMD to mvsam") Cc: t...@semihalf.com Fixes: 4ccc8d770d3b ("net/mvneta: add PMD skeleton") Cc: z...@semihalf.com Signed-off-by: Thomas Monjalon --- devtools/test-build.sh | 4 ++-- 1

Re: [dpdk-dev] [PATCH v5 01/13] eal: add param register infrastructure

Hi Gaetan, Thanks for reviewing and providing suggestions. On 17/10/2018 16:56, Gaëtan Rivet wrote: + +int +rte_param_parse(char *option) +{ + /* Check if the option is in the registered inits */ + TAILQ_FOREACH(param, &rte_param_list, next) { + if (strcmp(option, pa

Re: [dpdk-dev] [PATCH v1] igb_uio: fix unexpected removal for hot-unplug

On 10/18/2018 7:27 AM, Jeff Guo wrote: > When a device is hot-unplugged, pci_remove will be invoked unexpectedly > before pci_release, it will caused kernel hung issue which will throw the > error info of "Trying to free already-free IRQ XXX". And on the other hand, > if pci_remove before pci_relea

Re: [dpdk-dev] [PATCH] devtools: fix alignment of Marvell build options

On 10/18/2018 4:36 PM, Thomas Monjalon wrote: > Really minor issue: > There were extra spaces making the alignment wrong. > > Fixes: e95faac15110 ("crypto/mrvl: rename PMD to mvsam") > Cc: t...@semihalf.com > Fixes: 4ccc8d770d3b ("net/mvneta: add PMD skeleton") > Cc: z...@semihalf.com Acked-by: F

[dpdk-dev] [PATCH] doc: show internal functions in doxygen

Not sure we want to show the internal functions to users. It may be useful only for PMD developers. Do we vote? +1 / -1 welcome! Signed-off-by: Thomas Monjalon --- doc/api/doxy-api.conf.in | 1 + 1 file changed, 1 insertion(+) diff --git a/doc/api/doxy-api.conf.in b/doc/api/doxy-api.conf.in ind

[dpdk-dev] [PATCH] doc: add deprecated list in doxygen

The option GENERATE_DEPRECATEDLIST will create a page "Deprecated List" in "Related Pages" menu. Signed-off-by: Thomas Monjalon --- doc/api/doxy-api.conf.in | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/api/doxy-api.conf.in b/doc/api/doxy-api.conf.in index c3d8fdef1..3b

Re: [dpdk-dev] [PATCH] doc: add deprecated list in doxygen

On 10/18/2018 5:09 PM, Thomas Monjalon wrote: > The option GENERATE_DEPRECATEDLIST will create a page > "Deprecated List" in "Related Pages" menu. +1 Acked-by: Ferruh Yigit > > Signed-off-by: Thomas Monjalon > --- > doc/api/doxy-api.conf.in | 2 +- > 1 file changed, 1 insertion(+), 1 deletio

Re: [dpdk-dev] [PATCH] doc: show internal functions in doxygen

On 10/18/2018 5:08 PM, Thomas Monjalon wrote: > Not sure we want to show the internal functions to users. > It may be useful only for PMD developers. > Do we vote? +1 / -1 welcome! What is affected from this setting, can you give an example what was not shown will be shown now? > > Signed-off-by

Re: [dpdk-dev] [PATCH] bus/pci: set intr_handle type for secondary processes

On 27-Sep-18 1:30 PM, Alejandro Lucero wrote: Invoking rte_pci_read/write_config functions requires device with a intr_handle type for using VFIO or UIO driver related functions. Secondary processes rely on primary processes for device initialization so they do not usually require using these fu

Re: [dpdk-dev] [PATCH] bus/pci: set intr_handle type for secondary processes

On Thu, Oct 18, 2018 at 5:26 PM Burakov, Anatoly wrote: > On 27-Sep-18 1:30 PM, Alejandro Lucero wrote: > > Invoking rte_pci_read/write_config functions requires device with > > a intr_handle type for using VFIO or UIO driver related functions. > > > > Secondary processes rely on primary processe

Re: [dpdk-dev] [PATCH v5 1/6] app/testpmd: fix ports list after removing several at once

Hi Thomas, > -Original Message- > From: Thomas Monjalon [mailto:tho...@monjalon.net] > Sent: Thursday, October 18, 2018 3:21 PM > To: Iremonger, Bernard > Cc: dev@dpdk.org; Yigit, Ferruh ; > arybche...@solarflare.com; ophi...@mellanox.com; > rahul.lakkire...@chelsio.com; Wisam Jaddo > Su

Re: [dpdk-dev] [PATCH] doc: show internal functions in doxygen

18/10/2018 18:22, Ferruh Yigit: > On 10/18/2018 5:08 PM, Thomas Monjalon wrote: > > Not sure we want to show the internal functions to users. > > It may be useful only for PMD developers. > > Do we vote? +1 / -1 welcome! > > What is affected from this setting, can you give an example what was not

Re: [dpdk-dev] [PATCH v5 1/6] app/testpmd: fix ports list after removing several at once

18/10/2018 18:42, Iremonger, Bernard: > Hi Thomas, > > From: Thomas Monjalon [mailto:tho...@monjalon.net] > > 18/10/2018 13:41, Iremonger, Bernard: > > > Hi Thomas > > > > > > From: Thomas Monjalon [mailto:tho...@monjalon.net] > > > > 18/10/2018 12:40, Iremonger, Bernard: > > > > > From: Thomas Mo

Re: [dpdk-dev] [RFC v2 5/9] ipsec: add SA data-path API

-Original Message- > Date: Tue, 9 Oct 2018 19:23:36 +0100 > From: Konstantin Ananyev > To: dev@dpdk.org > CC: Konstantin Ananyev , Mohammad Abdul Awal > > Subject: [dpdk-dev] [RFC v2 5/9] ipsec: add SA data-path API > X-Mailer: git-send-email 1.7.0.7 > Hi Konstantin, Overall it looks

[dpdk-dev] [PATCH v5 1/4] net/mlx5: refactor TC-flow infrastructure

This commit refactors tc_flow as a preparation to coming commits that sends different type of messages and expect differ type of replies while still using the same underlying routines. Signed-off-by: Moti Haimovsky --- v5: * Split the patch, this patch introduces the new infrastructure and pe

[dpdk-dev] [PATCH v5 2/4] net/mlx5: tc flow to use the new infrastructure

modified TC-flow code to use the new infrastructure introduced in "net/mlx5: refactor TC-flow infrastructure" commit. Signed-off-by: Moti Haimovsky --- v5: * Initial version of this patch. --- drivers/net/mlx5/mlx5_flow_tcf.c | 24 1 file changed, 12 insertions(+), 12 d

[dpdk-dev] [PATCH v5 0/4] support e-switch flow count action

The following series of patches adds support for reading the mlx5 e-switch flow counters. Moti Haimovsky (4): net/mlx5: refactor TC-flow infrastructure net/mlx5: tc flow to use the new infrastructure net/mlx5: add flow query abstraction interface net/mlx5: support e-switch flow count actio

[dpdk-dev] [PATCH v5 3/4] net/mlx5: add flow query abstraction interface

Flow engine now supports multiple driver paths with each having its own flow query implantation routine. This patch adds an abstraction to the flow query routine in accordance to commit 0c76d1c9a18d ("net/mlx5: add abstraction for multiple flow drivers") done by Yongseok Koh. Signed-off-by: Moti H

[dpdk-dev] [PATCH v5 4/4] net/mlx5: support e-switch flow count action

This commit adds support for configuring flows destined to the mlx5 eswitch with 'count' action and for querying these counts at runtime. Each flow rule configured by the mlx5 driver is implicitly assigned with flow counters. These counters can be retrieved when querying the flow rule via Netlink,

Re: [dpdk-dev] [PATCH v4 1/6] kni: add API to set link status on kernel interface

On Thu, Oct 18, 2018 at 10:44 AM Ferruh Yigit wrote: > > KNI sample application calls this API each 100ms, so this keeps writing > "carrier" file. > > What do you think writing to "carrier" file only if status changed? > > And it is possible to register to RTE_ETH_EVENT_INTR_LSC event in sample >

[dpdk-dev] [Bug 96] mlx5: TX error for multi-seg packet where first segment has 14~18 bytes

https://bugs.dpdk.org/show_bug.cgi?id=96 Bug ID: 96 Summary: mlx5: TX error for multi-seg packet where first segment has 14~18 bytes Product: DPDK Version: 18.08 Hardware: x86 OS: Linux Status: C

[dpdk-dev] [PATCH] doc: spelling fixes

Trivial pelling errors found by codespell. Signed-off-by: Stephen Hemminger --- doc/guides/eventdevs/opdl.rst | 2 +- doc/guides/nics/axgbe.rst | 2 +- doc/guides/nics/enic.rst | 2 +- doc/guides/nics/mvpp2.rst | 2 +- doc/guides/nics/virtio.rst| 2 +- 5 files changed, 5 inserti

[dpdk-dev] [PATCH] examples/vdpa: fix spelling error in message

Signed-off-by: Stephen Hemminger --- examples/vdpa/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/vdpa/main.c b/examples/vdpa/main.c index c5e8f58ec6d2..2ffbf2d8b4a3 100644 --- a/examples/vdpa/main.c +++ b/examples/vdpa/main.c @@ -334,7 +334,7 @@ static void c

Re: [dpdk-dev] [PATCH] examples/vdpa: fix spelling error in message

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen Hemminger > Sent: Thursday, October 18, 2018 3:35 PM > To: dev@dpdk.org > Cc: Stephen Hemminger > Subject: [dpdk-dev] [PATCH] examples/vdpa: fix spelling error in message > > Signed-off-by: Stephen Hemming

[dpdk-dev] [PATCH v5 0/5] kni: add API to set link status on kernel interface

Hi All, Attached is version 5 of a patchset to add a new API function to set the link status on kernel interfaces created with the KNI kernel module. v5 * Update Kernel NIC Interface document with new rte_kni option, move kernel module parameter description here from KNI sample app docum

[dpdk-dev] [PATCH v5 1/5] kni: add API to set link status on kernel interface

Add a new API function to KNI, rte_kni_update_link() to allow DPDK applications to update the link status for KNI network interfaces in the linux kernel. Signed-off-by: Dan Gora --- lib/librte_kni/rte_kni.c | 41 lib/librte_kni/rte_kni.h | 20 lib/li

[dpdk-dev] [PATCH v5 2/5] kni: set default carrier state of interface

Add module parameter 'carrier='on|off' to set the default carrier state for linux network interfaces created by the KNI module. The default carrier state is 'off'. For KNI interfaces which need to reflect the carrier state of a physical Ethernet port controlled by the DPDK application, the defaul

[dpdk-dev] [PATCH v5 4/5] examples/kni: add log msgs to show and clear stats

Add logging messages showing the commands necessary for the user to have the application display and zero the statistics. Signed-off-by: Dan Gora --- examples/kni/main.c | 16 +--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/examples/kni/main.c b/examples/kni/main.

[dpdk-dev] [PATCH v5 5/5] examples/kni: improve zeroing statistics

The worker threads incrementing the rx/tx_packets race with the signal handler from the main thread zeroing the entire statistics structure. This can cause the statistics to fail to be zeroed, even when there is no traffic on those interfaces. Improve zeroing the statistics by only incrementing rx

[dpdk-dev] [PATCH v5 3/5] examples/kni: monitor and update link status continually

Update KNI example to add the command line flag '-m' to enable a function to continuously monitor the Ethernet link status of the physical link and update the link status of the corresponding interfaces with rte_kni_update_link(). Signed-off-by: Dan Gora --- .../sample_app_ug/kernel_nic_interfac

[dpdk-dev] [PATCH v6 1/6] app/testpmd: update port list for multiple removals

From: Wisam Jaddo When detaching a port, the full rte_device is removed. If the rte_device was hosting several ports, the testpmd list of ports must be updated for multiple removals. Signed-off-by: Wisam Jaddo --- app/test-pmd/testpmd.c | 37 ++--- 1 file change

[dpdk-dev] [PATCH v6 0/6] ethdev port freeing

The function rte_eth_dev_detach() is freeing a port and its underlying rte_device object. The issue is that we may have several ports associated to the same rte_device. The right replacement is to free the port, and free the rte_device if no more ports. At ethdev level, the public function for por

[dpdk-dev] [PATCH v6 5/6] ethdev: remove release function for secondary process

After previous changes, the function rte_eth_dev_release_port() can be used for primary or secondary process as well. The only difference with rte_eth_dev_release_port_secondary() is the shared lock used in rte_eth_dev_release_port(). The function rte_eth_dev_release_port_secondary() was recently

[dpdk-dev] [PATCH v6 4/6] ethdev: free all common data when releasing port

This is a clean-up of common ethdev data freeing. All data freeing are moved to rte_eth_dev_release_port() and done only in case of primary process. It is probably fixing some memory leaks for PMDs which were not freeing all data. Signed-off-by: Thomas Monjalon Acked-by: Andrew Rybchenko --- d

[dpdk-dev] [PATCH v6 3/6] ethdev: fix doxygen comments of shared data fields

Some doxygen comments were wrongly associated to the next field because of syntax /** instead of /**< Some other cleanups (like alignment) are done. Signed-off-by: Thomas Monjalon Reviewed-by: Andrew Rybchenko --- lib/librte_ethdev/rte_ethdev_core.h | 28 +--- 1 file ch

[dpdk-dev] [PATCH v6 2/6] app/testpmd: allow detaching a port not closed

The testpmd application aim is for testing; so order of operations should not be enforced. There was a test to forbid detaching before closing a port. However, it may interesting to test what happens in such case. It is possible for a PMD to automatically close the port when detaching. in order t

[dpdk-dev] [PATCH v6 6/6] ethdev: complete closing of port

After closing a port, it cannot be restarted. So there is no reason to not free all associated resources. The last step was done with rte_eth_dev_detach() which is deprecated. Instead of blindly removing the associated rte_device, the driver should check if no more port (ethdev, cryptodev, etc) is

Re: [dpdk-dev] [PATCH v2 13/14] crypto/caam_jr: add security offload

12/10/2018 16:40, Gagandeep Singh: > From: Hemant Agrawal > > This patch provides the support for protocol offload > to the hardware. following security operations are > added: > - session_create > - session_destroy > - capabilities_get > > Signed-off-by: Hemant Agrawal I think you need to