Acked-by: Viacheslav Ovsiienko
> -Original Message-
> From: Ori Kam
> Sent: Sunday, July 5, 2020 12:24
> To: jer...@marvell.com; xiang.w.w...@intel.com; Matan Azrad
> ; Slava Ovsiienko ;
> Shahaf Shuler
> Cc: g...@marvell.com; dev@dpdk.org; pbhagavat...@marvell.com;
> hemant.agra...@nxp
Acked-by: Viacheslav Ovsiienko
> -Original Message-
> From: Ori Kam
> Sent: Sunday, July 5, 2020 12:24
> To: jer...@marvell.com; xiang.w.w...@intel.com; Matan Azrad
> ; Slava Ovsiienko ;
> Shahaf Shuler
> Cc: g...@marvell.com; dev@dpdk.org; pbhagavat...@marvell.com;
> hemant.agra...@nxp
Acked-by: Viacheslav Ovsiienko
> -Original Message-
> From: Ori Kam
> Sent: Sunday, July 5, 2020 12:24
> To: jer...@marvell.com; xiang.w.w...@intel.com; Matan Azrad
> ; Slava Ovsiienko ;
> Shahaf Shuler
> Cc: g...@marvell.com; dev@dpdk.org; pbhagavat...@marvell.com;
> hemant.agra...@nxp
This patch makes vhost-vswitch be able to use vhost asynchronous
api for enqueue operations. Demonstrated how the application
leverage IOAT DMA channel with vhost async api. Since this is an
early preview patch, the performance has not been fully
optimized and it's not suggested to use this patch a
Acked-by: Viacheslav Ovsiienko
> -Original Message-
> From: Ori Kam
> Sent: Sunday, July 5, 2020 12:24
> To: jer...@marvell.com; xiang.w.w...@intel.com; Matan Azrad
> ; Slava Ovsiienko ;
> Shahaf Shuler ; Ray Kinsella ;
> Neil Horman
> Cc: g...@marvell.com; dev@dpdk.org; pbhagavat...@ma
Acked-by: Viacheslav Ovsiienko
> -Original Message-
> From: Ori Kam
> Sent: Sunday, July 5, 2020 12:24
> To: jer...@marvell.com; xiang.w.w...@intel.com; Matan Azrad
> ; Slava Ovsiienko ;
> Shahaf Shuler
> Cc: g...@marvell.com; dev@dpdk.org; pbhagavat...@marvell.com;
> hemant.agra...@nxp
Acked-by: Viacheslav Ovsiienko
> -Original Message-
> From: Ori Kam
> Sent: Sunday, July 5, 2020 12:24
> To: jer...@marvell.com; xiang.w.w...@intel.com; Matan Azrad
> ; Slava Ovsiienko ;
> Shahaf Shuler ; Ray Kinsella ;
> Neil Horman
> Cc: g...@marvell.com; dev@dpdk.org; pbhagavat...@ma
This patch defines new RSS offload types for IPv6 prefix with 32, 48,
64 bits of both SRC and DST IPv6 address.
Signed-off-by: Junfeng Guo
---
lib/librte_ethdev/rte_ethdev.h | 51 ++
1 file changed, 51 insertions(+)
diff --git a/lib/librte_ethdev/rte_ethdev.h b/l
RSS for IPv6 prefix fields are supported in this patch, so that we
can use prefixes instead of full IPv6 address for RSS. These prefixes
include the first 32, 48, 64 bits of both SRC and DST IPv6 address.
This feature is mainly for NAT64 scenarios.
v4:
* Code rebase.
v3:
* Code rebase.
v2:
* Spl
This patch adds testpmd cmdline support for IPv6 prefix.
Signed-off-by: Junfeng Guo
---
app/test-pmd/cmdline.c | 6 ++
app/test-pmd/config.c | 3 +++
2 files changed, 9 insertions(+)
diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c
index 81c87c8c3..4d4612395 100644
--- a/app/te
RSS for IPv6 prefix fields are supported in this patch, so that we
can use prefixes instead of full IPv6 address for RSS. These prefixes
include the first 32, 48, 64 bits of both SRC and DST IPv6 address.
Signed-off-by: Junfeng Guo
---
drivers/net/ice/ice_hash.c | 207 +++
On Wed, 8 Jul 2020 06:43:57 +, Tal Shnaiderman wrote:
[snip]
Thanks for the testing.
> Do you think this is enough or do we want to give the user further indication
> that configuration action from his side might be needed? Something alike
> "Please verify OS Large-Page support is enabled f
This patch enables cloud filter for IPv4/6_UDP/TCP/SCTP with
SRC port only or DST port only.
This supports different filter types for the same packet type.
E.g. one IPv4_UDP rules with SRC port only and another IPv4_UDP rule
with DST port only.
Signed-off-by: Guinan Sun
---
v6:
* Modify commit lo
The value of vsi->nb_msix shouldn`t be zero, otherwise, all of
interrupts will be bind to vector 0.
Fixes: 4861cde461 (i40e: new poll mode driver)
Cc: sta...@dpdk.org
Signed-off-by: Jiang Mao
---
drivers/net/i40e/i40e_ethdev.c | 31 +++
drivers/net/i40e/i40e_ethdev.h
> -Original Message-
> From: Yan, Zhirun
> Sent: Wednesday, July 8, 2020 6:52 PM
> To: Zhang, Qi Z
> Cc: Cao, Yahui ; Su, Simei ;
> Wang, Xiao W ; dev@dpdk.org; Yan, Zhirun
>
> Subject: [PATCH] net/ice: add support for src MAC filter on FDIR
>
> This patch enables FDIR with src mac f
Fdir allocating msix resource is not strictly necessary, if no
resource left, print a warning message.
Fixes: 4861cde461 (i40e: new poll mode driver)
Cc: sta...@dpdk.org
Signed-off-by: Jiang Mao
---
drivers/net/i40e/i40e_ethdev.c | 11 +++
1 file changed, 11 insertions(+)
diff --git a/d
> -Original Message-
> From: Sun, GuinanX
> Sent: Wednesday, July 8, 2020 3:41 PM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Guo, Jia ; Sun,
> GuinanX
> Subject: [PATCH v6] net/i40e: support cloud filter with L4 port
>
> This patch enables cloud filter for IPv4/6_UDP/TCP/SCTP with SRC po
> -Original Message-
> From: Guo, Junfeng
> Sent: Wednesday, July 8, 2020 3:34 PM
> To: Zhang, Qi Z ; Ye, Xiaolong
> ; Xing, Beilei ; Yigit, Ferruh
>
> Cc: dev@dpdk.org; Guo, Jia ; Guo, Junfeng
> ; Su, Simei
> Subject: [PATCH v4 0/3] add RSS support for IPv6 prefix
>
> RSS for IPv6 p
Addded needed files and fixes for windows in order to get
librte_net compiling under Windows.
v3:
* replaced htons with rte_cpu_to_be_16.
* rebased to current master.
Fady Bader (3):
net: fix s_addr redefinition in Windows
net: replace htons with rte_cpu_to_be_16
eal/windows: librt
librte_net wasn't compiling under Windows.
To solve this, needed exports and files were added for Windows.
Signed-off-by: Fady Bader
---
lib/librte_eal/common/meson.build | 1 +
lib/librte_eal/rte_eal_exports.def | 1 +
lib/librte_eal/windows/include/netinet/in.h | 25 ++
htons wasn't defined in Windows for the minGW compiler.
htons was replaced with rte_cpu_to_be_16 in order to compile
under Windows.
Signed-off-by: Fady Bader
---
lib/librte_net/rte_arp.c | 11 +++
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/lib/librte_net/rte_arp.c b/li
s_addr in Windows is defined in windows.h so its
undefined in order to be defined as part of rte_ether_hdr.
Signed-off-by: Fady Bader
---
lib/librte_net/rte_ether.h | 9 +
1 file changed, 9 insertions(+)
diff --git a/lib/librte_net/rte_ether.h b/lib/librte_net/rte_ether.h
index 0ae4e75b
> -Original Message-
> From: Guo, Junfeng
> Sent: Wednesday, July 8, 2020 12:26 PM
> To: Zhang, Qi Z ; Ye, Xiaolong
> ; Xing, Beilei
> Cc: dev@dpdk.org; Guo, Jia ; Guo, Junfeng
> ; Su, Simei
> Subject: [PATCH v4 0/2] add FD support for GTPU with outer IP on PF and VF
>
> Add FDir sup
On Wed, Jul 8, 2020 at 2:14 AM Honnappa Nagarahalli
wrote:
>
>
>
> > Subject: Re: [dpdk-dev] [PATCH v5 2/4] build: add arm32 meson build flags
> >
> > On Mon, Jul 6, 2020 at 1:59 PM Juraj Linkeš
> > wrote:
> > >
> > > Base the flags on config/defconfig_arm-armv7a-linuxapp-gcc.
> > > Omit driver
> -Original Message-
> From: dev On Behalf Of chenmin@intel.com
> Sent: Saturday, June 13, 2020 02:00
> To: Zhang, Qi Z ; Xing, Beilei ;
> Wu, Jingjing
>
> Cc: dev@dpdk.org; Sun, Chenmin
> Subject: [dpdk-dev] [PATCH] net/i40e: i40e FDIR update rate optimization
>
> From: Chenmin Su
> -Original Message-
> From: Guo, Junfeng
> Sent: Wednesday, July 8, 2020 11:28 AM
> To: Zhang, Qi Z ; Ye, Xiaolong
> ; Xing, Beilei
> Cc: dev@dpdk.org; Guo, Jia ; Guo, Junfeng
> ; Su, Simei
> Subject: [PATCH v5 0/2] add RSS support for ipv4 ipv6 mix of GTP on PF and
> VF
>
> RSS for
> -Original Message-
> From: dev On Behalf Of Xing, Beilei
> Sent: Wednesday, July 8, 2020 4:20 PM
> To: Sun, GuinanX ; dev@dpdk.org
> Cc: Guo, Jia
> Subject: Re: [dpdk-dev] [PATCH v6] net/i40e: support cloud filter with L4
> port
>
>
>
> > -Original Message-
> > From: Sun,
Hello Louise,
On Thu, Jul 2, 2020 at 12:37 PM Louise Kilheeney
wrote:
>
> v3: fix comments on v2.
>
> This patch set converts all python scripts in the project to use
> python3 only. This is due to python2 being EOL in January 2020.
Thanks for working on this.
Looking at the deprecation notice
> -Original Message-
> From: dev On Behalf Of Chenxu Di
> Sent: Wednesday, July 8, 2020 9:19 AM
> To: dev@dpdk.org
> Cc: Yang, Qiming ; Di, ChenxuX
>
> Subject: [dpdk-dev] [PATCH v4 0/5] re-implement legacy filter functions by
> private API
>
> The legacy filter API will be superseded
The flow rule with symmetric toeplitz hash function and SRC_ONLY
or DST_ONLY RSS type together should not be created successfully.
Fix the RSS action parse function to stop the rule creation in
this situation.
Fixes: 5ad3db8d4bdd ("net/ice: enable advanced RSS")
Cc: sta...@dpdk.org
Signed-off-by:
08/07/2020 10:25, Fady Bader:
> --- /dev/null
> +++ b/lib/librte_eal/windows/include/netinet/in.h
> @@ -0,0 +1,25 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright 2020 Mellanox Technologies, Ltd
> + */
As said previously, the license and copyright are not correct.
Please keep the ori
Hi, Weifeng Li
On 2020/7/7 22:38, Weifeng Li wrote:
From: Weifeng Li
A dpdk bonding 802.3ad network as follows:
+--+ +---+
|dpdk lacp |slave1 <--> port1|switch lacp|
| |slave2 <--> port2| |
+--+ +--
This adds the ConnectX-6 Lx device id to the list of supported
Mellanox devices that run the MLX5 PMD.
The device is still in development stage.
Signed-off-by: Ali Alnubani
Acked-by: Raslan Darawsheh
---
drivers/common/mlx5/mlx5_common.h | 1 +
drivers/net/mlx5/mlx5.c | 4
2 file
Fixes: ecb160456aed ("net/mlx5: add device parameter for MPRQ stride size")
Cc: akozy...@mellanox.com
Signed-off-by: Ali Alnubani
---
doc/guides/nics/mlx5.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index b51aa67a7..
On Wed, Jul 8, 2020 at 2:33 AM Ori Kam wrote:
>
> Hi Jerin,
Hi Ori,
>
> > -Original Message-
> > From: Jerin Jacob
> >
> > On Tue, Jul 7, 2020 at 11:51 AM Ori Kam wrote:
> > >
> > > Hi Jerin,
> > > Thanks you for your quick reply.
> > >
> > > > -Original Message-
> > > > From:
From: Alvin Zhang
When mapping a PCI BAR containing an MSI-X table, some devices do not
need to actually map this BAR or only need to map part of them, which
may cause the mapping to fail. Now some checks are added and a non-NULL
initial value is set to the variable to avoid this situation.
Fixe
On Wed, Jul 8, 2020 at 2:47 AM Rasesh Mody wrote:
>
> Add support for .get_reg eth_dev ops which will be used to collect the
> firmware debug data.
>
> PMD on detecting on some HW errors will collect the FW/HW Dump to a
> buffer and then it will save it to a file implemented in
> qede_save_fw_dump
On Wed, Jul 8, 2020 at 11:26 AM wrote:
>
> From: Alvin Zhang
>
> When mapping a PCI BAR containing an MSI-X table, some devices do not
> need to actually map this BAR or only need to map part of them, which
> may cause the mapping to fail. Now some checks are added and a non-NULL
> initial value
Hi Thomas:
Sorry for late reply, see comment inline.
On 2020/7/7 19:06, Thomas Monjalon wrote:
16/06/2020 10:16, Junfeng Guo:
This patch defines new RSS offload types for IPv6 prefix with 32, 48,
64 bits of both SRC and DST IPv6 address.
Signed-off-by: Junfeng Guo
---
lib/librte_ethdev/rt
Because capability memzone of compression does not have lookup
call, second and subsequent devices cannot be created.
Fixes: 0e6fff16a7a2 ("drivers: add multi process handling of capabilities in
QAT")
Signed-off-by: Arek Kusztal
---
drivers/compress/qat/qat_comp_pmd.c | 9 ++---
1 file cha
Hi Jerin
> -Original Message-
> From: Jerin Jacob
>
> On Wed, Jul 8, 2020 at 2:33 AM Ori Kam wrote:
> >
> > Hi Jerin,
>
> Hi Ori,
>
> >
> > > -Original Message-
[..nip ..]
> > > > > I think, simple API change would be to accommodate "rte_shared_ctx
> > > > > *ctx, rte_flow_ac
Hi Akhil,
Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Akhil Goyal
> Sent: Wednesday, July 8, 2020 12:51 AM
> To: Ankur Dwivedi ; dev@dpdk.org
> Cc: declan.dohe...@intel.com; Hemant Agrawal
> ; Vakul Garg ; Anoob
> Joseph
> Subject: [EXT] RE: [PATCH] test/crypto: chan
08/07/2020 11:45, Zhang, Qi Z:
> On 2020/7/7 19:06, Thomas Monjalon wrote:
> > 16/06/2020 10:16, Junfeng Guo:
> >> This patch defines new RSS offload types for IPv6 prefix with 32, 48,
> >> 64 bits of both SRC and DST IPv6 address.
> >>
> >> Signed-off-by: Junfeng Guo
> >> ---
> >> lib/librte_et
Thanks David, I will get on to that now and add warnings hopefully have it up
by the end of day.
Lousie
> -Original Message-
> From: David Marchand
> Sent: Wednesday 8 July 2020 09:59
> To: Kilheeney, Louise
> Cc: dev ; Robin Jarry ; Burakov,
> Anatoly ; Richardson, Bruce
>
> Subject
08/07/2020 05:37, Wei Hu (Xavier):
> On 2020/7/7 22:11, Thomas Monjalon wrote:
> > 06/07/2020 09:06, Wei Hu (Xavier):
> >> Currently, there is a potential problem that calling the API function
> >> rte_eth_dev_set_vlan_offload to start VLAN hardware offloads which the
> >> driver does not support.
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, July 8, 2020 12:10 PM
> To: Fady Bader
> Cc: dev@dpdk.org; Tasnim Bashar ; Tal Shnaiderman
> ; Yohad Tor ;
> dmitry.kozl...@gmail.com; harini.ramakrish...@microsoft.com;
> ocard...@microsoft.com; pallavi.ka...@intel.com; r
abidiff can provide some more information about the ABI difference it
detected.
In all cases, a discussion on the mailing must happen but we can give
some hints to know if this is a problem with the script calling abidiff,
a potential ABI breakage or an unambiguous ABI breakage.
Signed-off-by: Dav
07/07/2020 19:50, Ray Kinsella:
> Few documentation fixexs, clarifing the Windows ABI policy and aliases to
> experimental mode.
>
> Ray Kinsella (2):
> doc: reword abi policy for windows
> doc: clarify alias to experimental period
>
> v2:
> Addressed feedback from Thomas Monjalon.
One mor
On Wed, Jul 8, 2020 at 3:17 PM Ori Kam wrote:
>
> Hi Jerin
>
> > -Original Message-
> > From: Jerin Jacob
> >
> > On Wed, Jul 8, 2020 at 2:33 AM Ori Kam wrote:
> > >
> > > Hi Jerin,
> >
> > Hi Ori,
> >
> > >
> > > > -Original Message-
> [..nip ..]
>
> > > > > > I think, simple AP
Reviewed-by: Hemant Agrawal
> -Original Message-
> From: dev On Behalf Of Honnappa Nagarahalli
> Sent: Friday, July 3, 2020 7:58 PM
> To: dev@dpdk.org; honnappa.nagaraha...@arm.com; ruifeng.w...@arm.com;
> jer...@marvell.com; hemant.agra...@nxp.com;
> ajit.khapa...@broadcom.com; igo...@amazon.com; tho...@monjalon
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, July 8, 2020 5:58 PM
> To: Ye, Xiaolong ; Xing, Beilei
> ; Zhang, Qi Z
> Cc: dev@dpdk.org; Guo, Jia ; Guo, Junfeng
> ; Su, Simei ; Yigit, Ferruh
> ; arybche...@solarflare.com;
> viachesl...@mellanox.com; jer...@marvell.com
> Move dir24_8 table layout and lookup defenition into the
> private header file. This is necessary for implementing a
> vectorized lookup function in a separate .с file.
>
> Signed-off-by: Vladimir Medvedkin
> ---
Acked-by: Konstantin Ananyev
> 2.7.4
> Move trie table layout and lookup defenition into the
> private header file. This is necessary for implementing a
> vectorized lookup function in a separate .с file.
>
> Signed-off-by: Vladimir Medvedkin
> --
Acked-by: Konstantin Ananyev
> 2.7.4
On 7/3/2020 4:57 PM, Adrian Moreno wrote:
> This series adds Vhost-user protocol features support
> to Virtio-user PMD's Vhost-user backend.
>
> The first patch introduces protocol features
> negotiation, and the second one reply-ack feature.
>
> ---
> Changes since v3:
> - [Chenbo] Do not proces
On Fri, Jun 26, 2020 at 8:46 PM Jerin Jacob wrote:
>
> On Thu, Jun 11, 2020 at 1:06 PM Nithin Dabilpuram
> wrote:
> >
> > Interrupt callback unregister can fail with -EAGAIN
> > when interrupt handler is active in interrupt thread.
> > Hence retry before reporting a failure or proceeding further.
On Thu, Jun 11, 2020 at 06:24:25PM +0800, Phil Yang wrote:
> The event status is defined as a volatile variable and shared
> between threads. Use c11 atomics with explicit ordering instead
> of rte_atomic ops which enforce unnecessary barriers on aarch64.
>
> Signed-off-by: Phil Yang
> Reviewed-b
On Wed, Jul 08, 2020 at 04:48:33AM +, Phil Yang wrote:
> > -Original Message-
> > From: Stephen Hemminger
> > Sent: Wednesday, July 8, 2020 1:13 AM
> > To: Phil Yang
> > Cc: david.march...@redhat.com; dev@dpdk.org; d...@linux.vnet.ibm.com;
> > Honnappa Nagarahalli ;
> > olivier.m...@6
Hi,
On Tue, Jul 07, 2020 at 06:10:33PM +0800, Phil Yang wrote:
> Use C11 atomics with explicit ordering instead of rte_atomic ops which
> enforce unnecessary barriers on aarch64.
>
> Signed-off-by: Phil Yang
> Reviewed-by: Ruifeng Wang
> ---
> v2:
> Fix ABI issue: revert the rte_mbuf_ext_shared
On Tue, Jul 7, 2020 at 1:44 AM Honnappa Nagarahalli
wrote:
>
> rte_cio_*mb APIs will be deprecated in 20.11 release.
>
> Signed-off-by: Honnappa Nagarahalli
> Acked-by: Jerin Jacob
Reviewed-by: David Christensen
Acked-by: Ajit Khaparde
Acked-by: Konstantin Ananyev
Series applied, thanks.
-
08/07/2020 13:00, Jerin Jacob:
> Driver side it is OKAY but how the application can update it? The PMD does not
> need or does not have a shared object.
>
> Otherway to ask is, Could you have share the API call sequence using
> "rte_flow_shared_action_update(uint16_port port, rte_shared_ctx *ctx,
08/07/2020 13:10, Zhang, Qi Z:
> From: Thomas Monjalon
> > 08/07/2020 11:45, Zhang, Qi Z:
> > > On 2020/7/7 19:06, Thomas Monjalon wrote:
> > > > 16/06/2020 10:16, Junfeng Guo:
> > > >> This patch defines new RSS offload types for IPv6 prefix with 32,
> > > >> 48,
> > > >> 64 bits of both SRC and
On 08/07/2020 11:32, Thomas Monjalon wrote:
> 07/07/2020 19:50, Ray Kinsella:
>> Few documentation fixexs, clarifing the Windows ABI policy and aliases to
>> experimental mode.
>>
>> Ray Kinsella (2):
>> doc: reword abi policy for windows
>> doc: clarify alias to experimental period
>>
>> v2
while using memif with app, the resources are not cleaned on exit,
So an error occurred on running it second time. The cause of this problem
is that remove() of memif driver is not called by rte_eal_cleanup() which
is counterpart of probe() called from rte_eal_init(). This is a case for
all other d
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, July 8, 2020 7:57 PM
> To: Xing, Beilei ; Zhang, Qi Z
> Cc: dev@dpdk.org; Guo, Jia ; Guo, Junfeng
> ; Su, Simei ; Yigit, Ferruh
> ; arybche...@solarflare.com;
> viachesl...@mellanox.com; jer...@marvell.com;
> ajit.khapa...
Hi Jerin and Andrey,
> -Original Message-
> From: Jerin Jacob
> Subject: Re: [dpdk-dev] [PATCH] add flow shared action API
>
> On Wed, Jul 8, 2020 at 3:17 PM Ori Kam wrote:
> >
> > Hi Jerin
> >
> > > -Original Message-
> > > From: Jerin Jacob
> > >
> > > On Wed, Jul 8, 2020 at
>
> Add new lookup implementation for FIB6 trie algorithm using
> AVX512 instruction set
>
> Signed-off-by: Vladimir Medvedkin
> ---
> lib/librte_fib/Makefile | 10 ++
> lib/librte_fib/meson.build | 9 ++
> lib/librte_fib/rte_fib6.h| 3 +-
> lib/librte_fib/trie.c| 21
08/07/2020 14:05, Zhang, Qi Z:
> From: Thomas Monjalon
> > 08/07/2020 13:10, Zhang, Qi Z:
> > > From: Thomas Monjalon
> > > > 08/07/2020 11:45, Zhang, Qi Z:
> > > > > On 2020/7/7 19:06, Thomas Monjalon wrote:
> > > > > > 16/06/2020 10:16, Junfeng Guo:
> > > > > >> This patch defines new RSS offlo
On Thu, Jun 11, 2020 at 12:25 PM Phil Yang wrote:
>
> The event status is defined as a volatile variable and shared
> between threads. Use c11 atomics with explicit ordering instead
> of rte_atomic ops which enforce unnecessary barriers on aarch64.
>
> Signed-off-by: Phil Yang
> Reviewed-by: Ruif
Forwarding to dev alias also.
From: Rajesh Sharma
Sent: Tuesday, July 7, 2020 12:24 PM
To: us...@dpdk.org
Subject: KNI: Can not open /dev/kni
Hi,
We have been trying to make a sample DPDK application work on RHEL 7.0 and keep
getting these errors. There are no i
Sorry.
I thought that it does not need to have any explanation since it is obvious
as you said.
But will add an explanation right now and push again.
Thanks for your attention.
Best,
Levend
On Tue, Jul 7, 2020 at 6:01 PM Van Haaren, Harry
wrote:
> > -Original Message-
> > From: Thomas
Sure.
I am really sorry for not being verbose enough.
>From lib/librte_acl/rte_acl.h
#define RTE_ACL_RULE_DEF(name, fld_num) struct name {\
struct rte_acl_rule_data data; \
struct rte_acl_field field[fld_num]; \
}
RTE_ACL_RULE_DEF(rte_acl_rule,);
When you put the d
Yes you are totally right.
I overlooked the alignment of struct components.
Sorry for that.
But imho, not to have such confusions,
Another define can be added such as
#define RTE_ACL_RULE_SIZE(xz) sizeof(struct xz)
Thanks for your time.
Best,
Levend
On Tue, Jul 7, 2020 at 7:45 PM Ananyev,
From: Levend Sayar
"extern C" define is added to rte_service_component.h file
to be able to use in C++ context.
Signed-off-by: Levend Sayar
Acked-by: Harry van Haaren
---
lib/librte_eal/include/rte_service_component.h | 9 +
1 file changed, 9 insertions(+)
diff --git a/lib/librte_eal
On 07/07/2020 16:15, Ruifeng Wang wrote:
Currently, the tbl8 group is freed even though the readers might be
using the tbl8 group entries. The freed tbl8 group can be reallocated
quickly. This results in incorrect lookup results.
RCU QSBR process is integrated for safe tbl8 group reclaim.
Refe
On 07/07/2020 16:15, Ruifeng Wang wrote:
From: Honnappa Nagarahalli
Add performance tests for RCU integration. The performance
difference with and without RCU integration is very small
(~1% to ~2%) on both Arm and x86 platforms.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
Rev
Hi Ruifeng,
Just a few nits
On 07/07/2020 16:15, Ruifeng Wang wrote:
Add positive and negative tests for API rte_lpm_rcu_qsbr_add.
Also test LPM library behavior when RCU QSBR is enabled.
Signed-off-by: Ruifeng Wang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
---
app/test/test
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, July 8, 2020 8:26 PM
> To: Xing, Beilei ; Zhang, Qi Z
> Cc: dev@dpdk.org; Guo, Jia ; Guo, Junfeng
> ; Su, Simei ; Yigit, Ferruh
> ; arybche...@solarflare.com;
> viachesl...@mellanox.com; jer...@marvell.com;
> ajit.khapa...
On Tue, Jul 7, 2020 at 1:23 AM Ananyev, Konstantin
wrote:
> > OVS and some other applications have been hacking into DPDK internals to
> > fake EAL threads and avoid performance penalty of only having non-EAL
> > threads.
> >
> > This series proposes to add a new type of lcores and maps those thre
On Mon, Jul 6, 2020 at 10:53 PM David Marchand
wrote:
>
> OVS and some other applications have been hacking into DPDK internals to
> fake EAL threads and avoid performance penalty of only having non-EAL
> threads.
>
> This series proposes to add a new type of lcores and maps those threads
> to suc
+ Aaron
On 08/07/2020 11:22, David Marchand wrote:
> abidiff can provide some more information about the ABI difference it
> detected.
> In all cases, a discussion on the mailing must happen but we can give
> some hints to know if this is a problem with the script calling abidiff,
> a potential AB
On Wed, Jul 8, 2020 at 3:09 PM Kinsella, Ray wrote:
>
> + Aaron
>
> On 08/07/2020 11:22, David Marchand wrote:
> > abidiff can provide some more information about the ABI difference it
> > detected.
> > In all cases, a discussion on the mailing must happen but we can give
> > some hints to know if
On 7/6/2020 12:24 PM, Adrian Moreno wrote:
> From: Maxime Coquelin
>
> This patch checks whether vDPA device configuration
> succeed and does not set the CONFIGURED flag if it
> didn't.
>
> Signed-off-by: Maxime Coquelin
> ---
> lib/librte_vhost/vhost_user.c | 7 +--
> 1 file changed, 5 in
On 08/07/2020 14:15, David Marchand wrote:
> On Wed, Jul 8, 2020 at 3:09 PM Kinsella, Ray wrote:
>>
>> + Aaron
>>
>> On 08/07/2020 11:22, David Marchand wrote:
>>> abidiff can provide some more information about the ABI difference it
>>> detected.
>>> In all cases, a discussion on the mailing m
On Tue, Jul 7, 2020 at 9:25 PM Phil Yang wrote:
>
> The n_poll_lcores counter and poll_lcore array are shared between lcores
> and the update of these variables are out of the protection of spinlock
> on each lcore timer list. The read-modify-write operations of the counter
> are not atomic, so it
From: Junfeng Guo
This patch adds testpmd cmdline support for IPv6 prefix.
Signed-off-by: Junfeng Guo
Signed-off-by: Qi Zhang
---
app/test-pmd/cmdline.c | 12
app/test-pmd/config.c | 6 ++
2 files changed, 18 insertions(+)
diff --git a/app/test-pmd/cmdline.c b/app/test-pmd
From: Junfeng Guo
RSS for IPv6 prefix fields are supported in this patch, so that we
can use prefixes instead of full IPv6 address for RSS. These prefixes
include the first 32, 48, 64 bits of both SRC and DST IPv6 address.
Signed-off-by: Junfeng Guo
Acked-by: Qi Zhang
---
drivers/net/ice/ice_
From: Junfeng Guo
This patch defines new RSS offload types for IPv6 prefix with 32, 40, 48,
56, 64, 96 bits of both SRC and DST IPv6 address.
Ref https://tools.ietf.org/html/rfc6052.
Signed-off-by: Junfeng Guo
Signed-off-by: Qi Zhang
---
v5:
- add 40 56, 96 according to RFC6052
- add more des
The rte_service_lcore_reset_all function stops execution of services
on all lcores and switches them back from ROLE_SERVICE to ROLE_RTE.
However the thread loop for slave lcores (eal_thread_loop) distincts these
roles to set lcore state after processing delegated function.
It sets WAIT state for RO
24/06/2020 16:26, Arek Kusztal:
> From: Fiona Trahe
>
> This patch adds function that can check if queue pair
> was already setup. This may be useful when dealing with
> multi process approach in cryptodev.
That's all? No more justification?
No usage in example apps?
No addition in test apps?
Is
David Marchand writes:
> On Thu, Jun 11, 2020 at 12:25 PM Phil Yang wrote:
>>
>> The event status is defined as a volatile variable and shared
>> between threads. Use c11 atomics with explicit ordering instead
>> of rte_atomic ops which enforce unnecessary barriers on aarch64.
>>
>> Signed-off-b
"Kinsella, Ray" writes:
> + Aaron
>
> On 08/07/2020 11:22, David Marchand wrote:
>> abidiff can provide some more information about the ABI difference it
>> detected.
>> In all cases, a discussion on the mailing must happen but we can give
>> some hints to know if this is a problem with the scrip
Hi Thomas,
On 06/07/2020 20:31, Thomas Monjalon wrote:
06/07/2020 19:00, Vladimir Medvedkin:
Add RIB/FIB library into the API doxygen index.
Move LPM/LPM6 under separate section "Longest prefix match"
[...]
--- a/doc/api/doxy-api-index.md
+++ b/doc/api/doxy-api-index.md
- **QoS**:
@@ -116,6
Hi Alvin,
CC the maintainers. Comments below.
> -Original Message-
> From: dev On Behalf Of alvinx.zh...@intel.com
> Sent: Wednesday, July 8, 2020 5:25 PM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Guo, Jia
> Subject: [dpdk-dev] [PATCH] bus/pci: fix mmap PCI resource
>
> From: Alvin Zhang
On Wed, Jul 8, 2020 at 3:43 PM Aaron Conole wrote:
> > Note: checking on the test-report ml, I saw nothing, but ovsrobot did
> > catch the issue with this change too, Aaron?
>
> I don't have archives back to Jun 11 on the robot server. I think it
> doesn't preserve forever (and the archives seem
On 08/07/2020 14:45, Aaron Conole wrote:
> "Kinsella, Ray" writes:
>
>> + Aaron
>>
>> On 08/07/2020 11:22, David Marchand wrote:
>>> abidiff can provide some more information about the ABI difference it
>>> detected.
>>> In all cases, a discussion on the mailing must happen but we can give
>>>
From: Medvedkin, Vladimir
Sent: Wednesday, July 8, 2020 8:37 PM
To: Ruifeng Wang ; Bruce Richardson
Cc: dev@dpdk.org; m...@ashroe.eu; konstantin.anan...@intel.com; Honnappa
Nagarahalli ; nd
Subject: Re: [PATCH v7 2/3] test/lpm: add LPM RCU integration functional tests
Hi Ruifeng,
Just a fe
Hi Thomas,
>
> 24/06/2020 16:26, Arek Kusztal:
> > From: Fiona Trahe
> >
> > This patch adds function that can check if queue pair
> > was already setup. This may be useful when dealing with
> > multi process approach in cryptodev.
>
> That's all? No more justification?
> No usage in example app
From: Medvedkin, Vladimir
Sent: Wednesday, July 8, 2020 8:37 PM
To: Ruifeng Wang ; Bruce Richardson
Cc: dev@dpdk.org; m...@ashroe.eu; konstantin.anan...@intel.com; Honnappa
Nagarahalli ; nd
Subject: Re: [PATCH v7 3/3] test/lpm: add RCU integration performance tests
On 07/07/2020 16:15, Rui
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, July 8, 2020 2:38 PM
> To: akhil.go...@nxp.com; Trahe, Fiona ; Kusztal,
> ArkadiuszX
>
> Cc: dev@dpdk.org; Yigit, Ferruh ; Richardson, Bruce
> ; or...@mellanox.com; jer...@marvell.com;
> step...@networkplumber.org; olivie
1 - 100 of 208 matches
Mail list logo
