On Fri, Mar 09, 2018 at 11:03:51PM +0530, Hemant Agrawal wrote:
> Hi,
> On 3/9/2018 3:35 PM, Ferruh Yigit wrote:
> >On 3/9/2018 9:39 AM, Tomasz Duszynski wrote:
> >>Signed-off-by: Tomasz Duszynski
> >>---
> >> drivers/net/mrvl/Makefile | 35 ---
> >> drivers/n
Signed-off-by: Tomasz Duszynski
---
v2:
- Keep the year of the first copyright claim unchanged.
drivers/net/mrvl/Makefile | 35 ---
drivers/net/mrvl/mrvl_ethdev.c | 36
drivers/net/mrvl/mrvl_ethdev.h | 36 -
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Tomasz Duszynski
> Sent: Monday, March 12, 2018 1:02 PM
> To: dev@dpdk.org
> Cc: m...@semihalf.com; d...@marvell.com; nsams...@marvell.com;
> j...@semihalf.com; jianbo@arm.com; Tomasz Duszynski
>
> Subject: [dp
Signed-off-by: Tomasz Duszynski
---
drivers/crypto/mrvl/Makefile | 35 -
drivers/crypto/mrvl/rte_mrvl_compat.h | 36 --
drivers/crypto/mrvl/rte_mrvl_pmd.c | 36 --
drivers/crypto/mrvl/rt
-Original Message-
> Date: Thu, 8 Mar 2018 15:54:00 -0600
> From: Erik Gabriel Carrillo
> To: pbhagavat...@caviumnetworks.com
> CC: dev@dpdk.org, jerin.ja...@caviumnetworks.com, nipun.gu...@nxp.com,
> hemant.agra...@nxp.com
> Subject: [PATCH v7 1/7] eventtimer: add event timer adapter API
-Original Message-
> Date: Thu, 8 Mar 2018 15:54:01 -0600
> From: Erik Gabriel Carrillo
> To: pbhagavat...@caviumnetworks.com
> CC: dev@dpdk.org, jerin.ja...@caviumnetworks.com, nipun.gu...@nxp.com,
> hemant.agra...@nxp.com
> Subject: [PATCH v7 2/7] eventtimer: add common code
> X-Mailer:
Existed testpmd commands can't support per queue offload configuration.
And there are different commands to enable or disable different offloading.
This patch set add following commands to support new Tx/Rx offloading API test.
To get Rx offload capability of a port, please run:
testpmd > rx_offlo
Add following testpmd run-time commands to support test of
new Tx offload API:
tx_offload get capability
tx_offload get configuration
tx_offload enable|disable per_port vlan_insert|udp_cksum...
tx_offload enable|disable per_queue vlan_insert|udp_cksum...
Above last 2 commands should be run wh
Add following testpmd run-time commands to support test of
new Rx offload API:
rx_offload get capability
rx_offload get configuration
rx_offload enable|disable per_port vlan_strip|ipv4_cksum...
rx_offload enable|disable per_queue vlan_strip|iipv4_cksum...
Above last 2 commands should be run w
This patch series comes along with a set of features,
documentation updates and fixes.
Below one can find a short summary of introduced changes:
o Added support for selective Tx queue start and stop.
o Added support for Rx flow control.
o Added support for extended statistics counters.
o Added su
Add extended statistics implementation.
Signed-off-by: Natalie Samsonov
Signed-off-by: Tomasz Duszynski
---
doc/guides/nics/features/mrvl.ini | 1 +
doc/guides/nics/mrvl.rst | 1 +
drivers/net/mrvl/mrvl_ethdev.c| 205 +-
3 files changed, 206
Add ingress policer support.
Signed-off-by: Natalie Samsonov
Signed-off-by: Tomasz Duszynski
---
drivers/net/mrvl/mrvl_ethdev.c | 6 ++
drivers/net/mrvl/mrvl_ethdev.h | 1 +
drivers/net/mrvl/mrvl_qos.c| 160 +++--
drivers/net/mrvl/mrvl_qos.h| 3
Add egress scheduler and egress rate limiter support.
Signed-off-by: Natalie Samsonov
Signed-off-by: Tomasz Duszynski
---
drivers/net/mrvl/mrvl_ethdev.c | 6 +-
drivers/net/mrvl/mrvl_qos.c| 141 +++--
drivers/net/mrvl/mrvl_qos.h| 19 ++
3 files
Add documentation and example for ingress policer, egress scheduler
and egress rate limiter.
Signed-off-by: Natalie Samsonov
Signed-off-by: Tomasz Duszynski
---
doc/guides/nics/mrvl.rst | 86
1 file changed, 80 insertions(+), 6 deletions(-)
diff
From: Natalie Samsonov
Fixes: 0ddc9b815b11 ("net/mrvl: add net PMD skeleton")
Cc: sta...@dpdk.org
Signed-off-by: Natalie Samsonov
Signed-off-by: Tomasz Duszynski
---
drivers/net/mrvl/mrvl_ethdev.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/mrvl/mrvl_ethd
On 03/12/2018 11:15 AM, Wei Dai wrote:
Add following testpmd run-time commands to support test of
new Rx offload API:
rx_offload get capability
rx_offload get configuration
rx_offload enable|disable per_port vlan_strip|ipv4_cksum...
rx_offload enable|disable per_queue vlan_strip|iipv4_cksum...
Add Rx side flow control support.
Signed-off-by: Natalie Samsonov
Signed-off-by: Tomasz Duszynski
---
doc/guides/nics/features/mrvl.ini | 1 +
doc/guides/nics/mrvl.rst | 1 +
drivers/net/mrvl/mrvl_ethdev.c| 78 +++
3 files changed, 80 insertion
Add classifier configuration support via rte_flow api.
Signed-off-by: Natalie Samsonov
Signed-off-by: Tomasz Duszynski
---
doc/guides/nics/mrvl.rst | 168 +++
drivers/net/mrvl/Makefile |1 +
drivers/net/mrvl/mrvl_ethdev.c | 59 +
drivers/net/mrvl/mrvl_ethdev.h | 10 +
driver
Add Tx queue start/stop feature.
Signed-off-by: Natalie Samsonov
Signed-off-by: Tomasz Duszynski
---
doc/guides/nics/mrvl.rst | 1 +
drivers/net/mrvl/mrvl_ethdev.c | 92 +-
2 files changed, 91 insertions(+), 2 deletions(-)
diff --git a/doc/guides/
-Original Message-
> Date: Thu, 8 Mar 2018 15:54:02 -0600
> From: Erik Gabriel Carrillo
> To: pbhagavat...@caviumnetworks.com
> CC: dev@dpdk.org, jerin.ja...@caviumnetworks.com, nipun.gu...@nxp.com,
> hemant.agra...@nxp.com
> Subject: [PATCH v7 3/7] eventtimer: add default software driver
On 12-Mar-18 1:42 AM, Tan, Jianfeng wrote:
On 3/8/2018 12:56 AM, Anatoly Burakov wrote:
If we receive messages that don't have a callback registered for
them, and we haven't finished initialization yet, it can be reasonably
inferred that we shouldn't have gotten the message in the first
place.
Signed-off-by: Shreyansh Jain
---
drivers/bus/fslmc/Makefile | 5 -
drivers/bus/fslmc/fslmc_bus.c| 64 +
drivers/bus/fslmc/fslmc_logs.h | 31 +++
drivers/bus/fslmc/fslmc_vfio.c | 151 +++
drivers/bus/fsl
Signed-off-by: Shreyansh Jain
---
drivers/mempool/dpaa2/Makefile| 6 ---
drivers/mempool/dpaa2/dpaa2_hw_mempool.c | 60 +--
drivers/mempool/dpaa2/dpaa2_hw_mempool_logs.h | 38 +
3 files changed, 75 insertions(+), 29 deletions(-)
creat
Signed-off-by: Shreyansh Jain
---
config/common_base| 5 -
config/defconfig_arm64-dpaa2-linuxapp-gcc | 9 -
doc/guides/nics/dpaa2.rst | 44 ++---
drivers/net/dpaa2/Makefile| 6 -
drivers/net/dpaa2/base/dpaa2_hw_dpni.c| 30 ++--
d
DPAA2 devices are enabled by:
- bus/fslmc
- net/dpaa2
- mempool/dpaa2
- event/dpaa2
and
- crypto/dpaa2_sec
This patch series converts the existing static debugging macros - for
control and datapath, both - into dynamic logging macros.
Identified for logs are:
FSLMC bus - bus.fslmc
Mempool Driver
Some changes had already been pushed via SHA:72654f090a11 patch. This
patch updates them.
Cc: nipun.gu...@nxp.com
Signed-off-by: Shreyansh Jain
---
doc/guides/eventdevs/dpaa2.rst| 14 -
drivers/event/dpaa2/dpaa2_eventdev.c | 49 +++
drivers/ev
Digest and IV length variable declarations have changed.
These were escaping builds as the debugging macro was disabled.
During dynamic logging change, they were discoverd.
Fixes: 0fbd75a99fc9 ("cryptodev: move IV parameters to session")
Cc: pablo.de.lara.gua...@intel.com
Fixes: 7f0034275a24 ("cry
Signed-off-by: Shreyansh Jain
---
drivers/bus/fslmc/fslmc_logs.h | 40
1 file changed, 40 deletions(-)
diff --git a/drivers/bus/fslmc/fslmc_logs.h b/drivers/bus/fslmc/fslmc_logs.h
index 1f3fe8e66..9750b8c8d 100644
--- a/drivers/bus/fslmc/fslmc_logs.h
+++
Signed-off-by: Shreyansh Jain
---
config/common_base | 3 -
config/defconfig_arm64-dpaa2-linuxapp-gcc | 7 -
doc/guides/cryptodevs/dpaa2_sec.rst | 21 +-
drivers/crypto/dpaa2_sec/Makefile | 5 -
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 366
On Fri, Mar 09, 2018 at 05:25:29PM -0800, Yongseok Koh wrote:
> mlx5dv_create_wq() is added.
>
> Signed-off-by: Yongseok Koh
> ---
> drivers/net/mlx5/mlx5_glue.c | 9 +
> drivers/net/mlx5/mlx5_glue.h | 4
> 2 files changed, 13 insertions(+)
>
> diff --git a/drivers/net/mlx5/mlx5_gl
Hi Ravi,
> -Original Message-
> From: Ravi Kumar [mailto:ravi1.ku...@amd.com]
> Sent: Friday, March 9, 2018 8:35 AM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo
> Subject: [PATCH v4 20/20] crypto/ccp: moved license headers to SPDX
> format
As Ferruh suggested for "axgbe", could you use
On Fri, Mar 09, 2018 at 05:25:30PM -0800, Yongseok Koh wrote:
> Multi-Packet Rx Queue (MPRQ a.k.a Striding RQ) can further save PCIe
> bandwidth by posting a single large buffer for multiple packets. Instead of
> posting a buffer per a packet, one large buffer is posted in order to
> receive multip
Friday, March 2, 2018 6:08 PM, Timothy Redaelli:
> On Fri, 2 Mar 2018 15:15:17 +0100
> Adrien Mazarguil wrote:
>
> > Glue object files are looked up in RTE_EAL_PMD_PATH by default when
> > set and should be installed in this directory.
> >
> > During startup, EAL attempts to load them automatical
Hi,
We are running performance characterization for our customized DPDK
application in the KVM Guest using Intel XL710 SRIOV VF.
The Host is Netra X72 with XL710 NIC Quad port with 32 core.
We are seeing RX packet drops at the VF level even for small packet rates
(~200Mbps) & the DPDK rx_discard c
On 3/12/2018 9:25 AM, Shreyansh Jain wrote:
> Signed-off-by: Shreyansh Jain
<...>
> @@ -188,11 +188,6 @@ CONFIG_RTE_LIBRTE_DPAA2_USE_PHYS_IOVA=y
> # Compile burst-oriented NXP DPAA2 PMD driver
> #
> CONFIG_RTE_LIBRTE_DPAA2_PMD=n
> -CONFIG_RTE_LIBRTE_DPAA2_DEBUG_INIT=n
> -CONFIG_RTE_LIBRTE_DPA
On 3/10/2018 4:24 PM, Keith Wiles wrote:
> Signed-off-by: Keith Wiles
Acked-by: Ferruh Yigit
-Original Message-
> Date: Thu, 8 Mar 2018 15:54:05 -0600
> From: Erik Gabriel Carrillo
> To: pbhagavat...@caviumnetworks.com
> CC: dev@dpdk.org, jerin.ja...@caviumnetworks.com, nipun.gu...@nxp.com,
> hemant.agra...@nxp.com
> Subject: [PATCH v7 6/7] doc: add event timer adapter section to
>-Original Message-
>From: De Lara Guarch, Pablo [mailto:pablo.de.lara.gua...@intel.com]
>Sent: Monday, March 12, 2018 2:49 PM
>To: Kumar, Ravi1 ; dev@dpdk.org
>Subject: RE: [PATCH v4 20/20] crypto/ccp: moved license headers to SPDX format
>
>Hi Ravi,
>
>> -Original Message-
>> F
>
>-Original Message-
>From: Stephen Hemminger [mailto:step...@networkplumber.org]
>Sent: Monday, March 12, 2018 5:02 AM
>To: Kumar, Ravi1
>Cc: dev@dpdk.org; ferruh.yi...@intel.com
>Subject: Re: [dpdk-dev] [PATCH v3 18/18] net/axgbe: moved license headers to
>SPDX format
>
>On Fri, 9 M
>
>
>-Original Message-
>From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
>Sent: Friday, March 09, 2018 10:09 PM
>To: Kumar, Ravi1 ; dev@dpdk.org
>Cc: Hemant Agrawal ; Thomas Monjalon
>
>Subject: Re: [dpdk-dev] [PATCH v3 01/18] net/axgbe: add minimal dev init and
>uninit support
>
>On
>
>
>-Original Message-
>From: Hemant Agrawal [mailto:hemant.agra...@nxp.com]
>Sent: Friday, March 09, 2018 11:17 PM
>To: Hemant Agrawal ; Kumar, Ravi1
>; dev@dpdk.org
>Cc: pablo.de.lara.gua...@intel.com
>Subject: RE: [dpdk-dev] [PATCH v4 01/20] crypto/ccp: add AMD ccp skeleton PMD
>
>Ple
-Original Message-
> Date: Thu, 8 Mar 2018 15:54:06 -0600
> From: Erik Gabriel Carrillo
> To: pbhagavat...@caviumnetworks.com
> CC: dev@dpdk.org, jerin.ja...@caviumnetworks.com, nipun.gu...@nxp.com,
> hemant.agra...@nxp.com
> Subject: [PATCH v7 7/7] doc: add event timer adapter documentat
The strncpy function is error prone for doing "safe" string copies, so
we generally try to use "snprintf" instead in the code. The function
"strlcpy" is a better alternative, since it better conveys the
intention of the programmer, and doesn't suffer from the non-null
terminating behaviour of it's
Since we have support for the strlcpy function in DPDK, replace all
instances where a string is copied using snprintf.
Signed-off-by: Bruce Richardson
---
app/pdump/main.c | 11 +--
app/test-pmd/parameters.c
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Friday 9 March 2018 21:11
> To: dev@dpdk.org
> Cc: Mokhtar, Amr
> Subject: [PATCH] drivers: rename bbdev directory to baseband
>
> The drivers directory contains some sub-directories
> for each kind of devic
On Mon, Mar 12, 2018 at 11:33:00AM +, Bruce Richardson wrote:
> Since we have support for the strlcpy function in DPDK, replace all
> instances where a string is copied using snprintf.
>
> Signed-off-by: Bruce Richardson
> ---
Forgot to include Stephen's review from RFC, so adding here for
pa
On Mon, Mar 12, 2018 at 11:32:59AM +, Bruce Richardson wrote:
> The strncpy function is error prone for doing "safe" string copies, so
> we generally try to use "snprintf" instead in the code. The function
> "strlcpy" is a better alternative, since it better conveys the
> intention of the progr
On 3/12/2018 4:34 PM, Ferruh Yigit wrote:
On 3/12/2018 9:25 AM, Shreyansh Jain wrote:
Signed-off-by: Shreyansh Jain
<...>
@@ -188,11 +188,6 @@ CONFIG_RTE_LIBRTE_DPAA2_USE_PHYS_IOVA=y
# Compile burst-oriented NXP DPAA2 PMD driver
#
CONFIG_RTE_LIBRTE_DPAA2_PMD=n
-CONFIG_RTE_LIBRTE_DPAA2
On 3/12/2018 2:55 PM, Shreyansh Jain wrote:
DPAA2 devices are enabled by:
- bus/fslmc
- net/dpaa2
- mempool/dpaa2
- event/dpaa2
and
- crypto/dpaa2_sec
This patch series converts the existing static debugging macros - for
control and datapath, both - into dynamic logging macros.
Please also sp
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson
> Sent: Friday, February 16, 2018 4:54 PM
> To: dev@dpdk.org
> Cc: Richardson, Bruce
> Subject: [dpdk-dev] [PATCH 1/3] app: generalize building of apps using meson
>
> Since most apps are built in largely the same way, genera
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson
> Sent: Friday, February 16, 2018 4:54 PM
> To: dev@dpdk.org
> Cc: Richardson, Bruce
> Subject: [dpdk-dev] [PATCH 3/3] app: add all remaining apps to meson build
>
> Add remaining subdirectories in the app folder to the meson
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson
> Sent: Friday, February 16, 2018 4:54 PM
> To: dev@dpdk.org
> Cc: Richardson, Bruce
> Subject: [dpdk-dev] [PATCH 2/3] app/proc_info: rename folder to remove
> underscore
>
> All other apps in the app folder use "-" rather th
On 3/12/2018 2:55 PM, Shreyansh Jain wrote:
DPAA2 devices are enabled by:
- bus/fslmc
- net/dpaa2
- mempool/dpaa2
- event/dpaa2
and
- crypto/dpaa2_sec
This patch series converts the existing static debugging macros - for
control and datapath, both - into dynamic logging macros.
Identified for l
ICC warning #188 already disabled globally via commit [1], no
need individual arguments in PMDs.
[1]
Fixes: 1b80b9c854c3 ("mk: disable icc warning 188")
Cc: sta...@dpdk.org
Signed-off-by: Ferruh Yigit
---
drivers/net/bnx2x/Makefile | 4
drivers/net/cxgbe/Makefile | 8
drivers/net/
With icc (ICC) 18.0.1 20171018, -wd usage generates following warning:
icc: command line remark #10010: option '-wd3656' is deprecated and will
be removed in a future release. See '-help deprecated'
"icc -help deprecated" output is:
-wd use -diag-disable
Based on above infor
This series applies on top of [1] and cleans up the DPDK API implementation
for the link status.
[1] https://dpdk.org/dev/patchwork/patch/35653/
Changes in v2:
- Removes kernel version verification, the bug it tried to detected was fixed
several commit after in the PMD. Implementation in mlx5
Kernel version check was introduced in
commit 3a49ffe38a95 ("net/mlx5: fix link status query")
due to a bug fixed by
commit ef09a7fc7620 ("net/mlx5: fix inconsistent link status query")
This patch restore the previous behavior as described in Linux API.
Signed-off-by: Nelio Laranjeiro
Acked-by:
This behavior is mixed between what should be handled by the application
and what is under PMD responsibility.
According to DPDK API:
- link_update() should only query the link status [1]
- link_set_{up,down}() should only set the link to the according status [1]
- dev_{start,stop}() should enable
Wait to complete is present to let the application get a correct status
when it requires it, it should not be ignored.
Fixes: e313ef4c2fe8 ("net/mlx5: fix link state on device start")
Fixes: cb8faed7dde8 ("mlx5: support link status update")
Cc: shah...@mellanox.com
Cc: adrien.mazarg...@6wind.com
C
--Shahaf
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ferruh Yigit
> Sent: Friday, March 2, 2018 11:44 PM
> To: Mordechay Haimovsky ;
> pascal.ma...@6wind.com
> Cc: dev@dpdk.org; Shahaf Shuler
> Subject: Re: [dpdk-dev] [PATCH V5 2/2] net/tap: use new Rx o
> -Original Message-
> From: Jerin Jacob [mailto:jerin.ja...@caviumnetworks.com]
> Sent: Monday, March 12, 2018 1:25 AM
> To: Eads, Gage
> Cc: dev@dpdk.org; Van Haaren, Harry ;
> hemant.agra...@nxp.com; Richardson, Bruce ;
> santosh.shu...@caviumnetworks.com; nipun.gu...@nxp.com
> Subjec
-Original Message-
> Date: Mon, 12 Mar 2018 14:30:49 +
> From: "Eads, Gage"
> To: Jerin Jacob
> CC: "dev@dpdk.org" , "Van Haaren, Harry"
> , "hemant.agra...@nxp.com"
> , "Richardson, Bruce"
> , "santosh.shu...@caviumnetworks.com"
> , "nipun.gu...@nxp.com"
>
> Subject: RE: [PATCH
Allow TAP PMD to pass user desired MAC address as argument.
The argument value is processed as string delimited by ':',
is parsed and converted to HEX MAC address after validation.
Signed-off-by: Vipin Varghese
Acked-by: Pascal Mazon
---
Changes in V2:
- updated the auto variable for user_mac
Previously, the sw PMD would enqueue either all or no events, depending on
if enough inflight credits were available for the new events in the burst.
If a port is enqueueing a large burst (i.e. a multiple of the credit update
quanta), this can result in suboptimal performance, and requires an
under
Which per port offloads are enabled is not clear. Printing offloads
values at forwarding start.
CRC strip offload value was printed in more verbose manner, it is
removed since Rx/Tx offload values covers it and printing only CRC one
can cause confusion.
Hexadecimal offloads values are not very us
Which per port offloads are enabled is not clear. Printing offloads
values at forwarding start.
CRC strip offload value was printed in more verbose manner, it is
removed since Rx/Tx offload values covers it and printing only CRC one
can cause confusion.
Hexadecimal offloads values are not very us
On Fri, Feb 16, 2018 at 04:53:33PM +, Bruce Richardson wrote:
> Put the building of the apps into a foreach loop as is done with the libs
> and drivers in the DPDK meson build. This will reduce the path needed to
> call the compiled binaries in the build directory by one level, while the
> main
On Wed, Feb 21, 2018 at 01:56:10PM +0100, Maxime Coquelin wrote:
>
>
> On 02/16/2018 06:21 PM, Bruce Richardson wrote:
> > Signed-off-by: Bruce Richardson
> > ---
> > drivers/net/meson.build| 2 +-
> > drivers/net/virtio/meson.build | 27 +++
> > 2 files chan
On 3/12/2018 8:21 PM, Vipin Varghese wrote:
> @@ -1591,7 +1632,7 @@ enum ioctl_mode {
> int speed;
> char tap_name[RTE_ETH_NAME_MAX_LEN];
> char remote_iface[RTE_ETH_NAME_MAX_LEN];
> - int fixed_mac_type = 0;
> + struct ether_addr user_mac = { .addr_bytes = {0, 0, 0, 0, 0,
On Thu, Feb 22, 2018 at 11:30:44PM +0530, Hemant Agrawal wrote:
> On 2/22/2018 10:50 PM, Bruce Richardson wrote:
> > Rather than trying to use meson's build-in detection for libpcap, and
> > having to special-case cross-building, just check for the presence of
> > pcap.h and the pcap library.
> >
The ip_pipeline and qos_meter example apps now use experimental APIs so
this fact needs to be flagged in their meson.build files.
Fixes: c06ddf9698e0 ("meter: add configuration profile")
Signed-off-by: Bruce Richardson
---
examples/ip_pipeline/meson.build | 1 +
examples/qos_meter/meson.build
On Mon, Mar 12, 2018 at 03:28:20PM +, Bruce Richardson wrote:
> The ip_pipeline and qos_meter example apps now use experimental APIs so
> this fact needs to be flagged in their meson.build files.
>
> Fixes: c06ddf9698e0 ("meter: add configuration profile")
>
> Signed-off-by: Bruce Richardson
Sure Ferruh, I will spin a new one.
> -Original Message-
> From: Yigit, Ferruh
> Sent: Monday, March 12, 2018 8:39 PM
> To: Varghese, Vipin ; dev@dpdk.org;
> pascal.ma...@6wind.com
> Subject: Re: [PATCH v2] net/tap: allow user MAC to be passed as args
>
> On 3/12/2018 8:21 PM, Vipin Vargh
Hi All,
(I tried to CC key people part of related discussions but likely missed
many, feel free to add them back)
The following RFC formalizes what has been discussed so far regarding switch
offload control using rte_flow through port/VF representors. It doesn't
bring new ideas besides the "trans
On Fri, Mar 09, 2018 at 10:42:03AM +, Burakov, Anatoly wrote:
> On 09-Mar-18 9:15 AM, Pavan Nikhilesh wrote:
> > On Thu, Mar 08, 2018 at 08:33:21PM +, Burakov, Anatoly wrote:
> > > On 08-Mar-18 8:11 PM, Burakov, Anatoly wrote:
> > > > On 08-Mar-18 2:36 PM, Burakov, Anatoly wrote:
> > > > >
Hi Shally, Ahmed, and anyone else interested in compressdev,
I mentioned last week that we've been exploring using something other than
mbufs to pass src/dst buffers to compressdev PMDs.
Reasons:
- mbuf data is limited to 64k-1 in each segment of a chained mbuf. Data for
compression
can be
Allow TAP PMD to pass user desired MAC address as argument.
The argument value is processed as string delimited by ':',
is parsed and converted to HEX MAC address after validation.
Signed-off-by: Vipin Varghese
Acked-by: Pascal Mazon
---
Changed in V3:
- change the default init for user_mac -
Hi Jerin,
Thanks for reviewing. I've responded in-line:
> -Original Message-
> From: Jerin Jacob [mailto:jerin.ja...@caviumnetworks.com]
> Sent: Monday, March 12, 2018 2:54 AM
> To: Carrillo, Erik G
> Cc: pbhagavat...@caviumnetworks.com; dev@dpdk.org;
> nipun.gu...@nxp.com; hemant.agra.
Use strcmp to compare device names as the strncmp in original code
causes find_vdev to return -EEXIST for names that are prefix
of another. The creation of interfaces fails unpredictably based
on the order of their creation. An easy way hit this bug is to create
eth_vhost1 after eth_vhost11.
Fixe
On 3/12/2018 2:20 PM, Shahaf Shuler wrote:
>
>
> --Shahaf
>
>
>> -Original Message-
>> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ferruh Yigit
>> Sent: Friday, March 2, 2018 11:44 PM
>> To: Mordechay Haimovsky ;
>> pascal.ma...@6wind.com
>> Cc: dev@dpdk.org; Shahaf Shuler
>>
In Enhanced Multi-Packet Send (eMPW), entire packet data is prefetched to
LLC if it isn't inlined. Even though this helps reducing jitter when HW
fetches data by DMA, this can thresh the LLC with evicting precious data.
And if the size of queue is large and there are many queues, this might not
be
> On Mar 12, 2018, at 8:05 AM, Ferruh Yigit wrote:
>
> Which per port offloads are enabled is not clear. Printing offloads
> values at forwarding start.
>
> CRC strip offload value was printed in more verbose manner, it is
> removed since Rx/Tx offload values covers it and printing only CRC one
On Tue, 13 Mar 2018 01:51:34 +0530
Vipin Varghese wrote:
> +static int parse_user_mac(struct ether_addr *user_mac,
> + const char *value)
> +{
> + unsigned int index = 0;
> + char mac_temp[strlen(ETH_TAP_USR_MAC_FMT) + 1], *mac_byte = NULL;
> +
> + if (user_mac == NULL ||
On 3/12/2018 9:53 PM, Vipin Varghese wrote:
> Allow TAP PMD to pass user desired MAC address as argument.
> The argument value is processed as string delimited by ':',
> is parsed and converted to HEX MAC address after validation.
>
> Signed-off-by: Vipin Varghese
> Acked-by: Pascal Mazon
Revi
On Wed, 17 Jan 2018, Chas Williams wrote:
> From: "Charles (Chas) Williams"
>
> If a reconfiguration happens, queuedesc is reallocated. Any queues that
> are preserved point to the previous queuedesc since the queues are only
> configured during queue setup. Delay configuration of the shared
On 3/12/2018 5:26 PM, Yongseok Koh wrote:
>
>> On Mar 12, 2018, at 8:05 AM, Ferruh Yigit wrote:
>>
>> Which per port offloads are enabled is not clear. Printing offloads
>> values at forwarding start.
>>
>> CRC strip offload value was printed in more verbose manner, it is
>> removed since Rx/Tx o
Refactored the IP pipeline application. As result, the code base
size (lines of code) reduces by ~60%.
1. Moved table actions into the librte_pipeline library. As result,
the pre-fabricated pipelines from the application pipeline folder
were removed. The flexibility is greatly improved, as n
This API provides a common set of actions for pipeline tables to speed up
application development.
Each match-action rule added to a pipeline table has associated data
that stores the action context. This data is input to the table
action handler called for every input packet that hits the rule as
Add API to specify action related parameters such as action
handler, table entry data size, etc. for the pipeline table.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_pipeline_version.map | 1 +
lib/librte_pipeline/rte_table_action.c | 132 ++-
li
Add traffic metering action implementation.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/Makefile | 3 +-
lib/librte_pipeline/meson.build | 2 +-
lib/librte_pipeline/rte_pipeline_version.map | 4 +
lib/librte_pipeline/rte_table_action.c | 64
Add implementation of ttl update action.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_pipeline_version.map | 1 +
lib/librte_pipeline/rte_table_action.c | 155 +++
lib/librte_pipeline/rte_table_action.h | 66
3 files changed,
Add implementation of traffic manager action.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/Makefile | 2 +-
lib/librte_pipeline/meson.build| 2 +-
lib/librte_pipeline/rte_table_action.c | 130 -
lib/librte_pipeline/rte_table_act
Add implementation of Network Address Translation(NAT) action.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_table_action.c | 162 +
lib/librte_pipeline/rte_table_action.h | 39
2 files changed, 201 insertions(+)
diff --git a/lib/librte
Add implementation of different type of packet encap
such as vlan, qinq, mpls, pppoe, etc.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_table_action.c | 440 -
lib/librte_pipeline/rte_table_action.h | 129 ++
2 files changed, 568 insertio
Add implementation of stats read action
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_pipeline_version.map | 1 +
lib/librte_pipeline/rte_table_action.c | 112 ++-
lib/librte_pipeline/rte_table_action.h | 78 +++
3 files cha
Add implementation of timestamp action.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_pipeline_version.map | 1 +
lib/librte_pipeline/rte_table_action.c | 79 +++-
lib/librte_pipeline/rte_table_action.h | 31 +++
3 files changed, 110
remove passthrough pipeline.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/Makefile | 2 -
examples/ip_pipeline/init.c| 2 -
examples/ip_pipeline/meson.build | 2 -
.../ip_pipeline/
Remove routing pipeline.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/Makefile |2 -
examples/ip_pipeline/init.c|2 -
examples/ip_pipeline/meson.build |2 -
examples/ip_pipel
Remove flow classification pipeline.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/Makefile |2 -
examples/ip_pipeline/init.c|2 -
examples/ip_pipeline/meson.build |2 -
.../p
remove master pipeline.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/Makefile |6 -
examples/ip_pipeline/app.h | 12 -
examples/ip_pipeline/{pipeline => }/hash_func.h|3 +-
.../ip_pipeline/{
1 - 100 of 149 matches
Mail list logo
