On Tue, May 01, 2018 at 11:13:20PM -0700, Yongseok Koh wrote:
> rte_eth_devices[] is not shared between primary and secondary process, but
> a static array to each process. The backward pointer of device (priv->dev)
> must be reset when a secondary process attaches to a device.
>
> Fixes: f8b9a3ba
On Tue, May 01, 2018 at 02:18:05PM +0300, Shahaf Shuler wrote:
> Upon success, mlx5_socket_connect should return the fd descriptor of the
> primary process
>
> Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno values")
> Cc: nelio.laranje...@6wind.com
>
> Signed-off-by: Yongseok Koh
On Wed, May 02, 2018 at 01:54:37AM +, Yongseok Koh wrote:
>
> > On May 1, 2018, at 4:18 AM, Shahaf Shuler wrote:
> >
> > mlx5 prefixed function returns a negative errno value.
> > the error handler on mlx5_pci_probe is doing the same.
> >
> > Fixes: a6d83b6a9209 ("net/mlx5: standardize on n
On Tue, May 01, 2018 at 12:58:49PM +0300, Shahaf Shuler wrote:
> A new ethdev API was exposed by
> commit 3be82f5cc5e3 ("ethdev: support PMD-tuned Tx/Rx parameters")
>
> Enabling the PMD to provide default parameters in case no strict request
> from application in order to improve the out of the b
rte_eth_devices[] is not shared between primary and secondary process, but
a static array to each process. The backward pointer of device (priv->dev)
must be reset when a secondary process attaches to a device.
Fixes: f8b9a3bad467 ("net/mlx5: install a socket to exchange a file descriptor")
Cc: st
> -Original Message-
> From: Wu, Yanglong
> Sent: Saturday, April 28, 2018 5:37 PM
> To: dev@dpdk.org
> Cc: Zhang, Helin ; Zhang, Qi Z
> ; Dai, Wei ; Wu, Yanglong
>
> Subject: [PATCH v2] net/i40e: fix missing some offload capabilities
>
> MULTI_SEGS and JUMBO_FRAME offload capability shou
Tuesday, May 1, 2018 5:01 PM, Ferruh Yigit:
> Subject: ethdev new offloading API switch in PMDs
>
> Hi,
>
> Following PMDs still has .txq_flags in use, after basic grep, no in-dept
> investigation done.
>
> With PMDs switch to new API, that flag no longer should be needed.
>
> Old applications
Tuesday, May 1, 2018 11:41 PM, Thomas Monjalon:
> Subject: [dpdk-dev] ethdev flags and capabilities
>
> Since DPDK 18.05-rc1, we have 2 new fields in rte_eth_dev_info:
> const uint32_t *dev_flags;
> uint64_t dev_capa;
>
> The field dev_flags
> (https://emea01.safelinks.protection.outl
>Some files were left with full license and wrong copyright format.
>They are switched to this format:
> SPDX-License-Identifier: BSD-3-Clause
> Copyright 2017 Mellanox Technologies, Ltd
>
>Fixes: 5feecc57d90b ("align SPDX Mellanox copyrights")
Acked-by: Hemant Agrawal
Hi, Maxime
During the 18.05-rc1 performance testing, I find this patch set will bring
slightly performance drop on mergeable and normal path, and big performance
drop on vector path. Could you have a check on this? I know this patch is
important for security. Not sure if there is any way to impro
Since we move to new offload APIs, txq_flags is no long needed.
This patch remove the dependence on that.
Fixes: 7497d3e2f777 ("net/i40e: convert to new Tx offloads API")
Signed-off-by: Qi Zhang
---
v2:
- remove wrong fixes line.
drivers/net/i40e/i40e_ethdev.c | 2 --
drivers/net/i40e
Add missing queue offload initialization.
Fixes: 7497d3e2f777 ("net/i40e: convert to new Tx offloads API")
Fixes: c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API")
Signed-off-by: Qi Zhang
---
v2:
- add missing part in i40e_vf_represent.
drivers/net/i40e/i40e_ethdev.c | 1 +
d
Since we move to new offload APIs, txq_flags is no long needed.
This patch remove the dependence on that.
Fixes: e5c05e6590ea ("net/e1000: convert to new Tx offloads API")
Signed-off-by: Qi Zhang
---
drivers/net/e1000/igb_ethdev.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/net
Since we move to new offload APIs, txq_flags is no long needed.
This patch remove the dependence on that.
Fixes: 51215925a32f ("net/ixgbe: convert to new Tx offloads API")
Signed-off-by: Qi Zhang
---
drivers/net/ixgbe/ixgbe_ethdev.c | 6 --
drivers/net/ixgbe/ixgbe_rxtx.c | 2 --
drivers/n
Since we move to new offload APIs, txq_flags is no long needed.
This patch remove the dependence on that.
Fixes: 30f3ce999e6a ("net/fm10k: convert to new Tx offloads API")
Signed-off-by: Qi Zhang
---
drivers/net/fm10k/fm10k.h| 1 -
drivers/net/fm10k/fm10k_ethdev.c | 4 +---
2 files chan
The patchset remove txq_flags dependence on Intel devices: ixgbe, e1000, fm10k.
(i40e has been covered on another fix patchset)
Qi Zhang (3):
net/ixgbe: remove dependence on Tx queue flags
net/e1000: remove dependence on Tx queue flags
net/fm10k: remove dependence on Tx queue flags
drivers
Hi Ferruh:
> -Original Message-
> From: Zhang, Qi Z
> Sent: Wednesday, May 2, 2018 10:44 AM
> To: Yigit, Ferruh ; Ananyev, Konstantin
>
> Cc: dev@dpdk.org; Xing, Beilei ; Zhang, Qi Z
>
> Subject: [PATCH 2/2] net/i40e: remove dependence on Tx queue flags
>
> Since we move to new offload
Since we move to new offload APIs, txq_flags is no long needed.
This patch remove the dependence on that.
Fixes: 7497d3e2f777 ("net/i40e: convert to new Tx offloads API")
Fixes: c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API")
Signed-off-by: Qi Zhang
---
drivers/net/i40e/i40e_ethdev.c
Add missing queue offload initialization.
Fixes: 7497d3e2f777 ("net/i40e: convert to new Tx offloads API")
Fixes: c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API")
Signed-off-by: Qi Zhang
---
drivers/net/i40e/i40e_ethdev.c | 1 +
drivers/net/i40e/i40e_ethdev_vf.c | 1 +
dri
> On May 1, 2018, at 4:18 AM, Shahaf Shuler wrote:
>
> mlx5 prefixed function returns a negative errno value.
> the error handler on mlx5_pci_probe is doing the same.
>
> Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno values")
> Cc: nelio.laranje...@6wind.com
>
> Signed-off-by:
We are still using the txq_flags which is no longer needed with the
new offload API. Cleaning it up.
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_ethdev.c | 1 -
drivers/net/bnxt/bnxt_txq.h| 1 -
2 files changed, 2 deletions(-)
diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers
Hi Helin, Qi, Wenzhuo,
Any update for this patch.
Anything else needed or can this be merged ?
Thanks,
Shweta
On Thu, Apr 26, 2018 at 11:56 AM, Ferruh Yigit
wrote:
> On 4/26/2018 11:20 AM, Shweta Choudaha wrote:
> > Hi Ferruh/ Helin,
> >
> > Anything else needed for this patch
> >
> > htt
Ethdev RX offloads API has changed since: commit ce17eddefc20
("ethdev: introduce Rx queue offloads API")
This patch adopts the new RX Offload API in vmxnet3 driver.
Signed-off-by: Louis Luo
Acked-by: Yong Wang
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 61 ++--
Since DPDK 18.05-rc1, we have 2 new fields in rte_eth_dev_info:
const uint32_t *dev_flags;
uint64_t dev_capa;
The field dev_flags (http://dpdk.org/commit/736b30ebf2)
is a pointer to rte_eth_dev_data.dev_flags for these bits:
RTE_ETH_DEV_INTR_LSC
RTE_ETH_DEV_BONDED_S
Some files were left with full license and wrong copyright format.
They are switched to this format:
SPDX-License-Identifier: BSD-3-Clause
Copyright 2017 Mellanox Technologies, Ltd
Fixes: 5feecc57d90b ("align SPDX Mellanox copyrights")
Signed-off-by: Thomas Monjalon
---
devtools
Fixes: 582bed1e1d1d ("mem: support mapping hugepages at runtime")
Signed-off-by: Thomas Monjalon
---
lib/librte_eal/linuxapp/eal/eal_memalloc.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/librte_eal/linuxapp/eal/eal_memalloc.c
b/lib/librte_eal/linuxapp/eal/eal_me
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Thomas Monjalon
---
lib/librte_eal/common/include/rte_common.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_eal/common/include/rte_common.h
b/lib/librte_eal/common/include/rte_commo
01/05/2018 20:10, Louis Luo:
> Ethdev RX offloads API has changed since: commit ce17eddefc20
> ("ethdev: introduce Rx queue offloads API")
>
> This patch adopts the new RX Offload API in vmxnet3 driver.
>
> Signed-off-by: Louis Luo
>
> Acked-by: Yong Wang
It looks to be a v2.
Please use -v2 a
01/05/2018 19:28, Ferruh Yigit:
> --- a/lib/librte_ethdev/rte_ethdev.c
> +++ b/lib/librte_ethdev/rte_ethdev.c
> -static int ethdev_logtype;
> -
> -#define ethdev_log(level, fmt, ...) \
> - rte_log(RTE_LOG_ ## level, ethdev_logtype, fmt "\n", ## __VA_ARGS__)
> +int ethdev_logtype;
>
[...]
> --
Ethdev RX offloads API has changed since: commit ce17eddefc20
("ethdev: introduce Rx queue offloads API")
This patch adopts the new RX Offload API in vmxnet3 driver.
Signed-off-by: Louis Luo
Acked-by: Yong Wang
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 61 ++--
> -Original Message-
> From: Richardson, Bruce
> Sent: Tuesday, May 1, 2018 3:14 PM
> To: Xing, Beilei ; Zhang, Qi Z
> Cc: dev@dpdk.org; Yigit, Ferruh ; Ananyev, Konstantin
> ; Richardson,
> Bruce
> Subject: [PATCH v2] net/i40e: fix Tx fn selection when using new ethdev
> offloads
>
Hi Ferruh,
Thanks for your review! Initially I did use PRIx64 there, but checkpatch.sh
always failed and complained about it for Camel case. So I just replaced it
with %lx. I will change it back and resend the review.
Thanks,
Louis
On 5/1/18, 7:58 AM, "Ferruh Yigit" wrote:
On 4/30/2018
Signed-off-by: Ferruh Yigit
---
lib/librte_ethdev/rte_ethdev.c | 17 +++--
lib/librte_ethdev/rte_ethdev.h | 5 +
2 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/lib/librte_ethdev/rte_ethdev.c b/lib/librte_ethdev/rte_ethdev.c
index 5a67e6a7d..a1fbb081d 100644
---
Replace RTE_PMD_DEBUG_TRACE with RTE_ETHDEV_LOG.
RTE_PMD_DEBUG_TRACE is using hardcoded PMD logtype and ERR log level,
controlled by compile time flags.
RTE_ETHDEV_LOG is using dynamic ethdev_logtype.
Also a few minor cleanups, like
- use %u for unsigned values like port_id which is uint16_t
- us
On 5/1/2018 11:44 AM, Hemant Agrawal wrote:
> Fixes: 4fa5e0bbc573 ("net/dpaa: support hashed RSS")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Hemant Agrawal
Series applied to dpdk-next-net/master, thanks.
01/05/2018 17:46, Kevin Traynor:
> On 05/01/2018 03:16 PM, Aaron Conole wrote:
> > Thomas Monjalon writes:
> >> So the questions are:
> >>- What we must wait before pushing a backport in the stable tree?
> >>- What we must wait before tagging a stable release?
> >>
> >> I think it is reaso
01/05/2018 17:30, Thomas Monjalon:
> 01/05/2018 15:33, Ferruh Yigit:
> > Many sample applications fail because of
> > dev_info.flow_type_rss_offloads check in rte_eth_dev_configure()
> >
> > The sample applications need to be fixed/updated before returning error
> > on rte_eth_dev_configure()
> >
On 5/1/2018 3:37 PM, Ferruh Yigit wrote:
> On 5/1/2018 3:16 PM, Bruce Richardson wrote:
>> On Tue, May 01, 2018 at 03:13:54PM +0100, Bruce Richardson wrote:
>>> The Tx function selection code in the driver only used the older txq
>>> flags values to check whether the scalar or vector functions shou
On 05/01/2018 03:16 PM, Aaron Conole wrote:
> Thomas Monjalon writes:
>
>> 25/04/2018 12:03, Luca Boccassi:
>>> On Wed, 2018-04-25 at 09:33 +0100, Ferruh Yigit wrote:
On 4/20/2018 4:52 PM, Aaron Conole wrote:
> Kevin Traynor writes:
>> On 04/18/2018 02:28 PM, Thomas Monjalon wrote:
On 5/1/2018 4:41 PM, Ferruh Yigit wrote:
> On 4/30/2018 4:30 PM, Declan Doherty wrote:
>> Changes introduced by e0cb96204b71 modified the default name generated
>> for the i40e PF PMD, this patch reverts the default name to the
>> original PCI BDBF.
>>
>> Fixes: e0cb96204b71 ("net/i40e: add support
On 4/30/2018 4:30 PM, Declan Doherty wrote:
> Changes introduced by e0cb96204b71 modified the default name generated
> for the i40e PF PMD, this patch reverts the default name to the
> original PCI BDBF.
>
> Fixes: e0cb96204b71 ("net/i40e: add support for representor ports")
> Signed-off-by: Decla
01/05/2018 15:33, Ferruh Yigit:
> Many sample applications fail because of
> dev_info.flow_type_rss_offloads check in rte_eth_dev_configure()
>
> The sample applications need to be fixed/updated before returning error
> on rte_eth_dev_configure()
>
> This patch keeps the error log but removes ret
> -Original Message-
> From: Rao, Nikhil
> Sent: Tuesday, February 20, 2018 1:31 PM
> To: Dumitrescu, Cristian
> Cc: dev@dpdk.org; Shelton, Benjamin H ;
> Vangati, Narender ; Gujjar, Abhinandan S
> ; Rao, Nikhil
> Subject: [PATCH] ethdev: add support for WRED thresholds in bytes
>
> WR
> -Original Message-
> From: Shelton, Benjamin H
> Sent: Wednesday, March 21, 2018 3:46 PM
> To: dev@dpdk.org; Dumitrescu, Cristian
> Cc: Shelton, Benjamin H
> Subject: [PATCH] ethdev: Fix issue in Doxygen for TM API
>
> The rte_tm_node_wfq_weight_mode_update() API function operates on
01/05/2018 15:50, luca.bocca...@gmail.com:
> From: Luca Boccassi
>
> With the legacy build system MODULE_CFLAGS can be set to pass compiler
> flags specific for the kernel modules builds.
> This is used currently by Ubuntu and Debian.
> Set ccflags-y in the Kbuild to achieve the same result with
On 4/30/2018 11:20 PM, Louis Luo wrote:
> Ethdev RX offloads API has changed since: commit ce17eddefc20
> ("ethdev: introduce Rx queue offloads API")
>
> This patch adopts the new RX Offload API in vmxnet3 driver.
>
> Signed-off-by: Louis Luo
Hi Louis,
Overall patch looks good, only there is 32
On 5/1/2018 3:16 PM, Bruce Richardson wrote:
> On Tue, May 01, 2018 at 03:13:54PM +0100, Bruce Richardson wrote:
>> The Tx function selection code in the driver only used the older txq
>> flags values to check whether the scalar or vector functions should be
>> used. This caused performance regress
On 5/1/2018 3:12 PM, Thomas Monjalon wrote:
> 01/05/2018 16:08, Ferruh Yigit:
>> On 5/1/2018 3:01 PM, Thomas Monjalon wrote:
>>> 01/05/2018 15:33, Ferruh Yigit:
Many sample applications fail because of
dev_info.flow_type_rss_offloads check in rte_eth_dev_configure()
>>>
>>> We need to def
On Tue, May 01, 2018 at 03:13:54PM +0100, Bruce Richardson wrote:
> The Tx function selection code in the driver only used the older txq
> flags values to check whether the scalar or vector functions should be
> used. This caused performance regressions with testpmd io-fwd as the
> scalar path rath
Thomas Monjalon writes:
> 25/04/2018 12:03, Luca Boccassi:
>> On Wed, 2018-04-25 at 09:33 +0100, Ferruh Yigit wrote:
>> > On 4/20/2018 4:52 PM, Aaron Conole wrote:
>> > > Kevin Traynor writes:
>> > > > On 04/18/2018 02:28 PM, Thomas Monjalon wrote:
>> > > > > 18/04/2018 14:28, Ferruh Yigit:
>> >
The Tx function selection code in the driver only used the older txq
flags values to check whether the scalar or vector functions should be
used. This caused performance regressions with testpmd io-fwd as the
scalar path rather than the vector one was being used in the default
case. Fix this by cha
01/05/2018 16:08, Ferruh Yigit:
> On 5/1/2018 3:01 PM, Thomas Monjalon wrote:
> > 01/05/2018 15:33, Ferruh Yigit:
> >> Many sample applications fail because of
> >> dev_info.flow_type_rss_offloads check in rte_eth_dev_configure()
> >
> > We need to define the API behaviour in doxygen.
> >
> >> Th
> -Original Message-
> From: Richardson, Bruce
> Sent: Tuesday, May 1, 2018 2:53 PM
> To: Ananyev, Konstantin
> Cc: Xing, Beilei ; Zhang, Qi Z ;
> dev@dpdk.org; Yigit, Ferruh
> Subject: Re: [dpdk-dev] [PATCH] net/i40e: fix Tx fn selection when using new
> ethdev offloads
>
> On Tue,
On 5/1/2018 3:01 PM, Thomas Monjalon wrote:
> 01/05/2018 15:33, Ferruh Yigit:
>> Many sample applications fail because of
>> dev_info.flow_type_rss_offloads check in rte_eth_dev_configure()
>
> We need to define the API behaviour in doxygen.
>
>> The sample applications need to be fixed/updated b
01/05/2018 13:04, Ferruh Yigit:
> On 4/23/2018 7:14 PM, Thomas Monjalon wrote:
> > 23/04/2018 18:06, Ferruh Yigit:
> >> On 4/20/2018 3:30 PM, Xueming Li wrote:
> >>> Add supported RSS hash function check in device configuration to
> >>> have better error verbosity for application developers.
> >>>
01/05/2018 15:33, Ferruh Yigit:
> Many sample applications fail because of
> dev_info.flow_type_rss_offloads check in rte_eth_dev_configure()
We need to define the API behaviour in doxygen.
> The sample applications need to be fixed/updated before returning error
> on rte_eth_dev_configure()
>
>
Hi,
Following PMDs still has .txq_flags in use, after basic grep, no in-dept
investigation done.
With PMDs switch to new API, that flag no longer should be needed.
Old applications still use it but ethdev converts them to the offloads, so that
PMDs can only concern about offloads.
Can maintaine
On Tue, May 01, 2018 at 02:24:39PM +0100, Ananyev, Konstantin wrote:
> Hi Bruce,
>
> >
> > The Tx function selection code in the driver only used the older txq
> > flags values to check whether the scalar or vector functions should be
> > used. This caused performance regressions with testpmd io-
From: Luca Boccassi
With the legacy build system MODULE_CFLAGS can be set to pass compiler
flags specific for the kernel modules builds.
This is used currently by Ubuntu and Debian.
Set ccflags-y in the Kbuild to achieve the same result with Meson, and
to keep backward compatbility with older scr
Looks good, thanks.
How do you think rss_hf, normally people think it best effort.
> -Original Message-
> From: Ferruh Yigit
> Sent: Tuesday, May 1, 2018 9:34 PM
> To: Thomas Monjalon
> Cc: dev@dpdk.org; Ferruh Yigit ; Xueming(Steven) Li
>
> Subject: [PATCH] ethdev: fix applications f
> -Original Message-
> From: luca.bocca...@gmail.com [mailto:luca.bocca...@gmail.com]
> Sent: Tuesday, May 1, 2018 2:39 PM
> To: dev@dpdk.org
> Cc: Richardson, Bruce ; Luca Boccassi
> ; sta...@dpdk.org
> Subject: [PATCH] igb_uio: pass MODULE_CFLAGS in new Kbuild
>
> From: Luca Boccassi
From: Luca Boccassi
With the legacy build system MODULE_CFLAGS can be set to pass compiler
flags specific for the kernel modules builds.
This is used currently by Ubuntu and Debian.
Set ccflags-y in the Kbuild to achieve the same result with Meson, and
to keep backward compatbility with older scr
Many sample applications fail because of
dev_info.flow_type_rss_offloads check in rte_eth_dev_configure()
The sample applications need to be fixed/updated before returning error
on rte_eth_dev_configure()
This patch keeps the error log but removes returning error.
Fixes: 8863a1fbfc66 ("ethdev: a
On Tue, May 01, 2018 at 02:24:39PM +0100, Ananyev, Konstantin wrote:
> Hi Bruce,
>
> >
> > The Tx function selection code in the driver only used the older txq
> > flags values to check whether the scalar or vector functions should be
> > used. This caused performance regressions with testpmd io-
Hi Bruce,
>
> The Tx function selection code in the driver only used the older txq
> flags values to check whether the scalar or vector functions should be
> used. This caused performance regressions with testpmd io-fwd as the
> scalar path rather than the vector one was being used in the default
The Tx function selection code in the driver only used the older txq
flags values to check whether the scalar or vector functions should be
used. This caused performance regressions with testpmd io-fwd as the
scalar path rather than the vector one was being used in the default
case. Fix this by cha
<...>
> Added initial tests for Compressdev library.
> The tests are performed compressing a test buffer (or multiple test buffers)
> with compressdev or Zlib, and decompressing it/them with the other library
> (if compression is done with compressdev, decompression is done with Zlib,
> and vicev
On 01/05/2018 10:47 AM, Ananyev, Konstantin wrote:
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Declan Doherty
Sent: Monday, April 30, 2018 4:33 PM
To: dev@dpdk.org
Cc: Doherty, Declan
Subject: [dpdk-dev] [PATCH 3/3] net/ixgbe: add null pointer check for pf_
On 01/05/2018 10:46 AM, Ananyev, Konstantin wrote:
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Declan Doherty
Sent: Monday, April 30, 2018 4:33 PM
To: dev@dpdk.org
Cc: Doherty, Declan
Subject: [dpdk-dev] [PATCH 2/3] net/ixgbe: initialise nb_representor_port
On Tuesday 01 May 2018 06:22 PM, Shreyansh Jain wrote:
From: Hemant Agrawal
Enhance the RSS hash fields supported by DPAA1.
The RSS Hash key fields are configured external to DPDK, through SoC
specific scripts.
Signed-off-by: Hemant Agrawal
Acked-by: Shreyansh Jain
---
Self NACK.
Patchset
From: Hemant Agrawal
Add RSS Hash fields supported and set default values to other device
information fields.
Signed-off-by: Hemant Agrawal
Acked-by: Shreyansh Jain
---
drivers/net/dpaa2/dpaa2_ethdev.c | 5 +
drivers/net/dpaa2/dpaa2_ethdev.h | 6 ++
2 files changed, 11 insertions(+)
From: Hemant Agrawal
Enhance the RSS hash fields supported by DPAA1.
The RSS Hash key fields are configured external to DPDK, through SoC
specific scripts.
Signed-off-by: Hemant Agrawal
Acked-by: Shreyansh Jain
---
drivers/net/dpaa/dpaa_ethdev.h | 12
1 file changed, 4 insertions
mlx5 prefixed function returns a negative errno value.
the error handler on mlx5_pci_probe is doing the same.
Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno values")
Cc: nelio.laranje...@6wind.com
Signed-off-by: Shahaf Shuler
---
drivers/net/mlx5/mlx5.c | 8 ++--
1 file chang
Upon success, mlx5_socket_connect should return the fd descriptor of the
primary process
Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno values")
Cc: nelio.laranje...@6wind.com
Signed-off-by: Yongseok Koh
Signed-off-by: Shahaf Shuler
---
drivers/net/mlx5/mlx5.c| 2 +-
dri
On 4/23/2018 7:14 PM, Thomas Monjalon wrote:
> 23/04/2018 18:06, Ferruh Yigit:
>> On 4/20/2018 3:30 PM, Xueming Li wrote:
>>> Add supported RSS hash function check in device configuration to
>>> have better error verbosity for application developers.
>>>
>>> Signed-off-by: Xueming Li
>>> Acked-by:
Add the hashed RSS support info and other fields in device info.
Signed-off-by: Hemant Agrawal
---
drivers/net/dpaa2/dpaa2_ethdev.c | 5 +
drivers/net/dpaa2/dpaa2_ethdev.h | 6 ++
2 files changed, 11 insertions(+)
diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_e
Fixes: 4fa5e0bbc573 ("net/dpaa: support hashed RSS")
Cc: sta...@dpdk.org
Signed-off-by: Hemant Agrawal
---
drivers/net/dpaa/dpaa_ethdev.h | 12
1 file changed, 4 insertions(+), 8 deletions(-)
diff --git a/drivers/net/dpaa/dpaa_ethdev.h b/drivers/net/dpaa/dpaa_ethdev.h
index c051ae3
Signed-off-by: Nipun Gupta
---
MAINTAINERS| 1 +
doc/guides/index.rst | 1 +
doc/guides/rawdevs/dpaa2_qdma.rst | 140 +
doc/guides/rawdevs/index.rst | 14
doc/guides/rel_notes/release_18_05.rst
Signed-off-by: Nipun Gupta
---
drivers/raw/dpaa2_qdma/dpaa2_qdma.c| 333 +
drivers/raw/dpaa2_qdma/dpaa2_qdma.h| 21 ++
drivers/raw/dpaa2_qdma/rte_pmd_dpaa2_qdma.h| 70 +
.../raw/dpaa2_qdma/rte_pmd_dpaa2_qdma_version.map | 4 +
4
Signed-off-by: Nipun Gupta
---
doc/api/doxy-api-index.md | 1 +
doc/api/doxy-api.conf | 1 +
drivers/raw/dpaa2_qdma/Makefile| 2 +
drivers/raw/dpaa2_qdma/dpaa2_qdma.c| 375 +
driver
Signed-off-by: Nipun Gupta
Acked-by: Hemant Agrawal
---
drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h
b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h
index e081afb..09ea603 100644
--- a/driver
DPAA2 QDMA driver uses MC DPDMAI object. This driver enables
the user (app) to perform data DMA without involving CPU in
the DMA process
Signed-off-by: Nipun Gupta
---
MAINTAINERS| 8 +
config/common_base | 5 +
config/c
'dpdmai' devices detected on fsl-mc bus are represented by DPAA2 QDMA
devices in DPDK.
Signed-off-by: Nipun Gupta
Acked-by: Shreyansh Jain
---
drivers/bus/fslmc/fslmc_bus.c | 2 ++
drivers/bus/fslmc/fslmc_vfio.c | 1 +
drivers/bus/fslmc/rte_fslmc.h | 2 ++
3 files changed, 5 insertions(+)
di
Signed-off-by: Shreyansh Jain
Signed-off-by: Nipun Gupta
---
drivers/meson.build | 3 ++-
drivers/raw/meson.build | 7 +++
drivers/raw/skeleton_rawdev/meson.build | 8
3 files changed, 17 insertions(+), 1 deletion(-)
create mode 100644 drivers/ra
This patch adds the DPDMAI (Data Path DMA Interface)
object support in MC driver.
Signed-off-by: Cristian Sovaiala
Signed-off-by: Nipun Gupta
Acked-by: Shreyansh Jain
---
drivers/bus/fslmc/Makefile | 9 +-
drivers/bus/fslmc/mc/dpdmai.c | 429 +++
According to ethtool_link_setting API recommendation ETHTOOL_GLINKSETTINGS
should be called before ETHTOOL_GSET as the later one deprecated.
Fixes: f47ba80080ab ("net/mlx5: remove kernel version check")
Signed-off-by: Shahaf Shuler
Acked-by: Nelio Laranjeiro
---
On v2:
- no change.
--
driver
This patch set introduces DPAA2 based QDMA device driver.
It provide means to initiate a DMA transaction from CPU.
The initiated DMA is performed without CPU being involved
in the actual DMA transaction.
This patch series is rebased on dpdk master branch
Patch 1:
Support meson build in raw
Pat
A new ethdev API was exposed by
commit 3be82f5cc5e3 ("ethdev: support PMD-tuned Tx/Rx parameters")
Enabling the PMD to provide default parameters in case no strict request
from application in order to improve the out of the box experience.
While the current API lacks the means for the PMD to prov
Interested in learning more about SPDK? Want to learn how it can help
accelerate your storage solutions? Attend the SPDK summit and discover the SPDK
experience. SPDK is based off of DPDK and implements User space, lockless,
polled-mode libraries to accelerate storage solution. It helps minimiz
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Declan Doherty
> Sent: Monday, April 30, 2018 4:33 PM
> To: dev@dpdk.org
> Cc: Doherty, Declan
> Subject: [dpdk-dev] [PATCH 3/3] net/ixgbe: add null pointer check for
> pf_ethdev
>
> Add NULL parameter check fo
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Declan Doherty
> Sent: Monday, April 30, 2018 4:33 PM
> To: dev@dpdk.org
> Cc: Doherty, Declan
> Subject: [dpdk-dev] [PATCH 2/3] net/ixgbe: initialise nb_representor_ports
> value
>
> Initialise rte_ethdev_args
On Thursday 26 April 2018 03:44 PM, Nipun Gupta wrote:
Signed-off-by: Nipun Gupta
---
drivers/bus/fslmc/rte_bus_fslmc_version.map | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/bus/fslmc/rte_bus_fslmc_version.map
b/drivers/bus/fslmc/rte_bus_fslmc_version.map
index 70fb719..d4337
On Thursday 26 April 2018 03:44 PM, Nipun Gupta wrote:
This patch set introduces DPAA2 based Command Interface
device driver.
This driver is provides communication between the GPP and
AIOP Firmware.
This patchset is based on top of:
https://dpdk.org/dev/patchwork/patch/38798/
Patches 1-3:
M
30/04/2018 20:46, Olivier Matz:
> Le 30 avril 2018 17:45:52 GMT+02:00, Maxime Coquelin
> a écrit :
> >I face a deadlock issue with your series, that Jianfeng patch does not
> >resolve ("eal: fix threads block on barrier"). Reverting the series and
> >Jianfeng patch makes the issue to disappear.
[
Dear all
Thanks to Linux Foundation's work, now DPDK registration is open. You can go to
http://dpdk.org/events and see there are two options. One is to register
LinuxCon + DPDK, and the other is to register DPDK only. You can register
depends on your preference. And DPDK PRC Summit registration
95 matches
Mail list logo
