Hi Konstantin,
>
> Hi Akhil,
>
> > > > > > > This action type allows the burst of symmetric crypto workload
> > > > > > > using
> the
> > > > > same
> > > > > > > algorithm, key, and direction being processed by CPU cycles
> > > synchronously.
> > > > > > > This flexible action type does not r
This patch adds the feature that supports loading DDP package
according to the device serial number. Prior to loading the
default DDP package (ice.pkg), the driver will check for the
presence of a device-specific DDP package with the name containing
64-bit PCIe Device Serial Number (ice-xxx
In case VIRTIO_F_ORDER_PLATFORM(36) is not negotiated, then the frontend
and backend are assumed to be implemented in software, that is they can
run on identical CPUs in an SMP configuration.
Thus a weak form of memory barriers like rte_smp_r/wmb, other than
rte_cio_r/wmb, is sufficient for this ca
In case VIRTIO_F_ORDER_PLATFORM(36) is not negotiated, then the frontend
and backend are assumed to be implemented in software, that is they can
run on identical CPUs in an SMP configuration.
Thus a weak form of memory barriers like rte_smp_r/wmb, other than
rte_cio_r/wmb, is sufficient for this ca
This patch set replaces the two-way barriers with C11 one-way barriers
for packed vring flags, when the frontend and backend are implemented
in software.
By doing vhost-user + virtio-user case benchmarking, 9% performance gain
in the RFC2544 test was measured on Thunderx2 platform.[1] And by doing
> -Original Message-
> From: Gavin Hu (Arm Technology China) [mailto:gavin...@arm.com]
> Sent: Tuesday, September 17, 2019 11:24 AM
> To: Gavin Hu (Arm Technology China) ; Zhang, Qi Z
> ; dev@dpdk.org
> Cc: nd ; tho...@monjalon.net; Richardson, Bruce
> ; Liu, Yong ; Wang, Yinan
> ; ajit.
Acked-by: abhinandan.guj...@intel.com
> -Original Message-
> From: Hemant Agrawal
> Sent: Friday, September 6, 2019 4:15 PM
> To: dev@dpdk.org
> Cc: jer...@marvell.com; Gujjar, Abhinandan S ;
> Hemant Agrawal
> Subject: [PATCH] test/event_crypto: no service core for HW options
>
> If H
Hi Qi,
> -Original Message-
> From: dev On Behalf Of Gavin Hu (Arm
> Technology China)
> Sent: Tuesday, September 17, 2019 10:08 AM
> To: Zhang, Qi Z ; dev@dpdk.org
> Cc: nd ; tho...@monjalon.net; Richardson, Bruce
> ; Liu, Yong ; Wang,
> Yinan ; ajit.khapa...@broadcom.com;
> somnath.ko.
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Thierry Herbelot
> Sent: Thursday, September 12, 2019 12:01 AM
> To: dev@dpdk.org
> Cc: Guo Fengtian ; Thomas Monjalon
> ; sta...@dpdk.org; Lu, Wenzhuo
> ; Ananyev, Konstantin
>
> Subject: [dpdk-dev] [PATCH 1/1]
> -Original Message-
> From: Thierry Herbelot [mailto:thierry.herbe...@6wind.com]
> Sent: Thursday, September 12, 2019 12:03 AM
> To: dev@dpdk.org
> Cc: Laurent Hardy ; Thomas Monjalon
> ; sta...@dpdk.org; Xing, Beilei
> ; Zhang, Qi Z
> Subject: [PATCH] net/i40e: set speed to undefined
> -Original Message-
> From: Cui, LunyuanX
> Sent: Monday, September 16, 2019 10:43 PM
> To: Yang, Qiming ; Wu, Jingjing
> ; Xing, Beilei ; Zhang, Qi Z
> ; Wang, ShougangX ;
> Stillwell Jr, Paul M
> Cc: dev@dpdk.org; Cui, LunyuanX
> Subject: [RFC v3] net/i40e: enable multi-queue Rx int
Hi Qi,
> -Original Message-
> From: Zhang, Qi Z
> Sent: Tuesday, September 17, 2019 9:53 AM
> To: Gavin Hu (Arm Technology China) ; dev@dpdk.org
> Cc: nd ; tho...@monjalon.net; Richardson, Bruce
> ; Liu, Yong ; Wang, Yinan
> ; ajit.khapa...@broadcom.com;
> somnath.ko...@broadcom.com; Honn
On Mon, Sep 16, 2019 at 4:27 AM Gavin Hu wrote:
> To read the doorbell response, which is held in the host CIO memory,
> rte_cio_rmb is sufficient.
>
> Fixes: 804e746c7b73 ("net/bnxt: add hardware resource manager init code")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Gavin Hu
>
Acked-by: Ajit Kha
On Mon, Sep 16, 2019 at 4:27 AM Gavin Hu wrote:
> As there is an inclusive rte_io_wmb within the following rte_write32()
> API who rings the doorbell, this makes the above rte_wmb unnecessary and
> remove it.
>
> Fixes: 1cd45aeb3270 ("net/bnxt: support Stratus VF device")
> Cc: sta...@dpdk.org
>
On Mon, Sep 16, 2019 at 4:27 AM Gavin Hu wrote:
> The doorbell ringing operation requires a rte_io_mb immediately to make
> the command complete and visible to the device before reading the
> response, otherwise it may read stale or invalid responses.
>
> Fixes: ca241d9a0952 ("net/bnxt: use I/O d
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Gavin Hu
> Sent: Monday, September 16, 2019 7:27 PM
> To: dev@dpdk.org
> Cc: n...@arm.com; tho...@monjalon.net; Richardson, Bruce
> ; Liu, Yong ; Wang, Yinan
> ; ajit.khapa...@broadcom.com;
> somnath.ko...@broadc
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Gavin Hu
> Sent: Monday, September 16, 2019 7:27 PM
> To: dev@dpdk.org
> Cc: n...@arm.com; tho...@monjalon.net; Richardson, Bruce
> ; Liu, Yong ; Wang, Yinan
> ; ajit.khapa...@broadcom.com;
> somnath.ko...@broadc
This patch adds the feature that supports loading DDP package
according to the device serial number. Prior to loading the
default DDP package (ice.pkg), the driver will check for the
presence of a device-specific DDP package with the name containing
64-bit PCIe Device Serial Number (ice-xxx
From: Eduard Serra Miralles
Date: Friday, September 13, 2019 at 1:10 PM
To: Yong Wang
Cc: "dev@dpdk.org"
Subject: RE: [PATCH] net/vmxnet3: fix RSS setting on v4
I think so too. Apparently however, ESX is mandatorily expecting that
underneath. If not set, config will fail.
__
On Mon, Sep 16, 2019 at 5:34 PM Ferruh Yigit wrote:
> +1 to this patch, unrelated to this patch I remember there was an issue with
> the
> nfb & szedata2 dependencies, that their dependencies conflict with each other,
> so it wasn't possible to enable both at the same time.
>
> Jan, Rastislav,
>
On 9/16/2019 4:45 PM, Andrew Rybchenko wrote:
> On 9/16/19 4:22 PM, Ferruh Yigit wrote:
>> On 9/13/2019 8:57 PM, Andrew Rybchenko wrote:
>>> On 9/13/19 7:34 PM, Ferruh Yigit wrote:
On 9/13/2019 5:05 PM, Andrew Rybchenko wrote:
> On 9/13/19 6:39 PM, Ferruh Yigit wrote:
>> On 9/9/2019 12
16/09/2019 17:46, Thomas Monjalon:
> 15/09/2019 14:04, Jan Remeš:
> > On Sat, Sep 14, 2019 at 11:37 AM Thomas Monjalon
> > wrote:
> > >
> > > The library libnfb is part of netcope-common which provides
> > > a pkg-config file: netcope-common.pc.
> > > Looking for this .pc file - with dependency()
14/09/2019 11:04, Thomas Monjalon:
> When trying to compile some examples with libdpdk.pc,
> the right environment (for default target) was not loaded.
> The consequence is to not detect some dependencies because
> of missing directories in PKG_CONFIG_PATH.
>
> The environment preparation is moved
14/09/2019 11:16, Thomas Monjalon:
> The nfb PMD is disabled by default because of its dependency
> on netcope-common package.
> The variable DPDK_DEP_NFB was introduced but not used to notify
> the dependency availability in the build test script.
>
> The AF_XDP PMD is disabled by default because
15/09/2019 14:04, Jan Remeš:
> On Sat, Sep 14, 2019 at 11:37 AM Thomas Monjalon wrote:
> >
> > The library libnfb is part of netcope-common which provides
> > a pkg-config file: netcope-common.pc.
> > Looking for this .pc file - with dependency() - is preferred
> > than looking for the library - w
On 9/16/19 4:22 PM, Ferruh Yigit wrote:
On 9/13/2019 8:57 PM, Andrew Rybchenko wrote:
On 9/13/19 7:34 PM, Ferruh Yigit wrote:
On 9/13/2019 5:05 PM, Andrew Rybchenko wrote:
On 9/13/19 6:39 PM, Ferruh Yigit wrote:
On 9/9/2019 12:58 PM, Andrew Rybchenko wrote:
Enabling/disabling of promiscuous
On 9/15/2019 8:48 AM, Matan Azrad wrote:
> Hi Ferruh
>
> From: Ferruh Yigit
>> On 8/29/2019 8:47 AM, Matan Azrad wrote:
>>> It may be needed by the user to limit the LRO session packet size.
>>> In order to allow the above limitation, add new Rx configuration for
>>> the maximum LRO session size.
On 9/14/2019 10:36 AM, Thomas Monjalon wrote:
> The libraries required for Netcope PMDs can be found in
> https://www.netcope.com/en/company/community-support/dpdk-libsze2
>
> These libraries are compatible with pkg-config, which is a better solution
> than directly looking for libraries and inclu
On 9/16/2019 7:37 AM, Wang, ShougangX wrote:
> Hi Ferruh
>
> Thanks for your reply.
>
>> Not sure if 'reset' command should do more than it says, if there is a
>> requirement that port should be stopped, why not add this condition with an
>> error message so that user can stop the port in advance
> Hi Akhil,
>
> > > > > > > This action type allows the burst of symmetric crypto workload
> > > > > > > using the
> > > > > same
> > > > > > > algorithm, key, and direction being processed by CPU cycles
> > > synchronously.
> > > > > > > This flexible action type does not require external hard
Hi Akhil,
> > > > > > This action type allows the burst of symmetric crypto workload
> > > > > > using the
> > > > same
> > > > > > algorithm, key, and direction being processed by CPU cycles
> > synchronously.
> > > > > > This flexible action type does not require external hardware
> > > > > >
On 9/13/2019 8:57 PM, Andrew Rybchenko wrote:
> On 9/13/19 7:34 PM, Ferruh Yigit wrote:
>> On 9/13/2019 5:05 PM, Andrew Rybchenko wrote:
>>> On 9/13/19 6:39 PM, Ferruh Yigit wrote:
On 9/9/2019 12:58 PM, Andrew Rybchenko wrote:
> Enabling/disabling of promiscuous mode is not always successf
> -Original Message-
> From: Andrew Rybchenko [mailto:arybche...@solarflare.com]
> Sent: Saturday, September 14, 2019 12:37 PM
> To: Lu, Wenzhuo ; Wu, Jingjing
> ; Iremonger, Bernard
>
> Cc: dev@dpdk.org; Ivan Ilchenko
> Subject: [PATCH v3 07/13] app/testpmd: check code of promiscuous mod
As there is an inclusive rte_io_wmb within the following rte_write32()
API who rings the doorbell, this makes the above rte_wmb unnecessary and
remove it.
Fixes: 1cd45aeb3270 ("net/bnxt: support Stratus VF device")
Cc: sta...@dpdk.org
Signed-off-by: Gavin Hu
Reviewed-by: Steve Capper
Reviewed-b
To read the doorbell response, which is held in the host CIO memory,
rte_cio_rmb is sufficient.
Fixes: 804e746c7b73 ("net/bnxt: add hardware resource manager init code")
Cc: sta...@dpdk.org
Signed-off-by: Gavin Hu
---
drivers/net/bnxt/bnxt_hwrm.c | 2 +-
1 file changed, 1 insertion(+), 1 deleti
The doorbell ringing operation requires a rte_io_mb immediately to make
the command complete and visible to the device before reading the
response, otherwise it may read stale or invalid responses.
Fixes: ca241d9a0952 ("net/bnxt: use I/O device memory read/write API")
Cc: sta...@dpdk.org
Signed-o
To guarantee the orderings of successive stores to CIO and MMIO memory,
a lighter weight rte_io_wmb [1] can be used instead of rte_wmb, and since
the ICE_PCI_REG_WRITE API already has an inclusive rte_io_wmb, this
explicit call can even be saved.
[1] http://git.dpdk.org/dpdk/tree/lib/librte_eal/co
To guarantee the orderings of successive stores to CIO and MMIO memory,
a lighter weight rte_io_wmb [1] can be used instead of rte_wmb, and since
the I40E_PCI_REG_WRITE API already has an inclusive rte_io_wmb, this
explicit call can be even saved.
[1] http://git.dpdk.org/dpdk/tree/lib/librte_eal/c
DPDK has well-defined barriers, such as CIO barriers and IO barriers.
X86, as a strong ordering model, implements the barriers as compiler
barriers, but on aarch64, as a weak memory ordering model, has fine
grained barriers. Using correct while as relaxed as possible barriers
makes a perf differen
Hi Vamsi,
> -Original Message-
> From: vattun...@marvell.com [mailto:vattun...@marvell.com]
> Sent: Friday, September 13, 2019 6:41 AM
> To: dev@dpdk.org
> Cc: Lu, Wenzhuo ; Wu, Jingjing
> ; Iremonger, Bernard
> ; tho...@monjalon.net; Vamsi Attunuru
>
> Subject: [dpdk-dev] [PATCH v2 1/1]
https://bugs.dpdk.org/show_bug.cgi?id=349
Bug ID: 349
Summary: i40e/i40evf: Allow bad packets to reach application
(SBP)
Product: DPDK
Version: 18.11
Hardware: All
OS: All
Status: UNCONFIRMED
https://bugs.dpdk.org/show_bug.cgi?id=348
Bug ID: 348
Summary: i40e: packets greater than 1024B are dropped due to a
integer overflow
Product: DPDK
Version: 18.11
Hardware: All
OS: All
Status: UN
Same behavior as in make build system.
Signed-off-by: Igor Ryzhov
---
config/rte_config.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/config/rte_config.h b/config/rte_config.h
index 0bbbe274f..e6a35a170 100644
--- a/config/rte_config.h
+++ b/config/rte_config.h
@@ -98,6 +98,9 @@
#def
For a valid service, the core mask of the service
is checked against the current core and the corresponding
entry in the active_on_lcore array is set or reset.
Upto 8 cores share the same cache line for their
service active_on_lcore array entries since each entry is a uint8_t.
Some number of these
-Original Message-
From: Aaron Conole
Sent: Friday, September 13, 2019 8:45 PM
To: Baran, MarcinX
Cc: dev@dpdk.org; Richardson, Bruce
Subject: Re: [dpdk-dev] [PATCH v2 0/6] examples/ioat: sample app on ioat driver
usage
Marcin Baran writes:
> A new sample app demonstrating use of
In some scenarios, the raw_encap/raw_decap actions could be multiple in
one single flow (e,g. hirepin flow):
... actions raw_decap / raw_encap / raw_decap / raw_encap / ...
This requires the testpmd supports multiple raw_encap/raw_decap data
settings as well.
With the multiple raw_encap/raw_de
>
> Hi Akhil,
>
> I send 2 patch sets: one for new functionality support and another one for
> fixes.
> One patch was sent separately from both of the sets according to your
> requirement:
Ok will have a look.
Thanks.
>
> >> examples/fips: fix bad return code in fips_test_parse_header()
>
https://bugs.dpdk.org/show_bug.cgi?id=347
Bug ID: 347
Summary: TAPPMD frees buffers it fails to send
Product: DPDK
Version: 19.08
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
Priori
Hi Hyong,
On 9/16/19 10:03 AM, Hyong Youb Kim (hyonkim) wrote:
-Original Message-
From: Andrew Rybchenko
Sent: Monday, September 9, 2019 9:13 PM
[...]
Subject: [PATCH 4/7] ethdev: change allmulticast callbacks to return status
From: Ivan Ilchenko
Enabling/disabling of allmulticast
> -Original Message-
> From: Andrew Rybchenko
> Sent: Monday, September 9, 2019 9:13 PM
[...]
> Subject: [PATCH 4/7] ethdev: change allmulticast callbacks to return status
>
> From: Ivan Ilchenko
>
> Enabling/disabling of allmulticast mode is not always successful and
> it should be tak
50 matches
Mail list logo
