Hi Mattias,
> -Original Message-
> From: Mattias Rönnblom
> Sent: 09 November 2021 13:58
> To: Kundapura, Ganapati ;
> jer...@marvell.com; Jayatheerthan, Jay
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: Re: [PATCH] eventdev: fix Rx adapter stalls on event device
> backpressure
>
> On
> > 1) Please sync the doc order with flag definition order in header file[1]
> > 2) You can remove RTE_EVENT_DEV_CAP_REQUIRES_MAINT from the
> > list(*CAP_REQUIRES*) as this
> > is limitation.
> >
> >
>
> Maybe we should negate RTE_EVENT_DEV_CAP_REQUIRES_MAINT to make it
> fit
> better with the o
From: Dapeng Yu
The ice DCF device reset has been supported. Release notes is updated
to synchronize with the feature.
Signed-off-by: Dapeng Yu
---
doc/guides/rel_notes/release_21_11.rst | 1 +
1 file changed, 1 insertion(+)
diff --git a/doc/guides/rel_notes/release_21_11.rst
b/doc/guides/re
When set port DCB mode enabled, it should remove RSS HASH offload
before reconfiguring the device and queues.
Because port multi-queue mode is changed from RSS to DCB.
Fixes: 2a977b891f99 ("app/testpmd: fix DCB configuration")
Signed-off-by: Jie Wang
---
v2:
* update commit log.
* remove RSS
On Tue, Nov 09, 2021 at 10:29:25PM -0800, Stephen Hemminger wrote:
> On Wed, 10 Nov 2021 04:20:52 +
> Tyler Retzlaff wrote:
>
> > > >
> > > > High performance applications benefit from an option to raise the
> > > > priority of their threads to avoid being preemted by other threads on
> > >
10/11/2021 04:01, Narcisa Ana Maria Vasile:
> Narcisa Vasile (13):
> eal: add basic threading functions
> eal: add thread attributes
> eal/windows: translate Windows errors to errno-style errors
> eal: implement functions for thread affinity management
> eal: implement thread priority man
> -Original Message-
> From: Mattias Rönnblom
> Sent: Wednesday, November 10, 2021 9:29 AM
> To: jer...@marvell.com; Jerin Jacob ; Sunil Kumar Kori
>
> Cc: dev@dpdk.org; Pavan Nikhilesh Bhagavatula ;
> Hemant Agrawal ; Nipun Gupta
> ; Van Haaren, Harry ;
> Thomas Monjalon ; David Marchand
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, November 10, 2021 1:56 PM
> To: mattias.ronnblom ; jer...@marvell.com;
> Jayatheerthan, Jay
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: RE: [PATCH] eventdev: fix Rx adapter stalls on event device
> backpressure
>
>
On Wed, Nov 10, 2021 at 3:37 PM Mattias Rönnblom
wrote:
>
> On 2021-11-10 10:55, Van Haaren, Harry wrote:
> >> -Original Message-
> >> From: Mattias Rönnblom
> >> Sent: Wednesday, November 10, 2021 9:29 AM
> >> To: jer...@marvell.com; Jerin Jacob ; Sunil Kumar
> >> Kori
> >>
> >> Cc: de
On Wed, Oct 27, 2021 at 4:55 PM Dumitrescu, Cristian
wrote:
> > This test was never added to the list of tests to run in CI.
> > Its name does not follow the implicit convention of ending with
> > _autotest.
> > Let's fix this.
> >
> > Fixes: 5e9647fd5a1a ("test/bitmap: test scan after half cachel
On Thu, Oct 28, 2021 at 2:25 PM Ananyev, Konstantin
wrote:
> > Add the test content of the fragment_offset(offset and MF)
> > to the test_ip_frag function. Add test data for a fragment
> > that is not the last fragment.
> >
> > Signed-off-by: huichao cai
> Acked-by: Konstantin Ananyev
Applied,
> -Original Message-
> From: dev On Behalf Of Jim Harris
> Sent: Friday, November 5, 2021 11:54 PM
> To: dev@dpdk.org; Hunt, David ;
> david.march...@redhat.com
> Cc: Harris, James R
> Subject: [dpdk-dev] [PATCH v2] power: fix unused-but-set variable error
>
> clang-13 rightfully complai
On Sat, Nov 6, 2021 at 6:54 PM David Marchand wrote:
>
> Trying to disable the vhost library, meson will complain it can't build
> the vhost* and vdpa examples when passing -Dexamples=all.
>
> -Dexamples=all skips examples if the example itself announces it can't
> be built (for external dependenc
On Mon, Nov 8, 2021 at 5:57 PM Stephen Hemminger
wrote:
> > The RTE_PORT_PCAP variable is used to signal libpcap availability,
> > though its name seems to refer to pcap support in the port library.
> > Prefer a generic name and add explicit link dependencies where needed.
> >
> > Fixes: 7a944656b
On Mon, Nov 8, 2021 at 6:53 PM David Christensen
wrote:
>
> Enable Github Actions to cross-compile code for POWER systems.
>
> Signed-off-by: David Christensen
> Reviewed-by: David Marchand
Applied, thanks.
--
David Marchand
> -Original Message-
> From: Yu, DapengX
> Sent: Tuesday, November 9, 2021 3:50 PM
> To: Yang, Qiming ; Zhang, Qi Z
>
> Cc: dev@dpdk.org; Wang, Haiyue ; Yu, DapengX
> ; sta...@dpdk.org
> Subject: [PATCH] net/ice: fix AdminQ handling on DCF passive reset
>
> From: Dapeng Yu
>
> DCF t
On Wed, Nov 10, 2021 at 11:56 AM Jiang, YuX wrote:
> We verify this patch
> http://patches.dpdk.org/project/dpdk/patch/20211105155351.350403-1-james.r.har...@intel.com/
> based on dpdk21.11-rc2 main
> branch(f4801fdb7828f45ddc4ada148b1b0a230a226570), still verify failed.
> Could you pls have a
Looks good. Thanks for posting this change!
Acked-by: Jay Jayatheerthan
> -Original Message-
> From: Mattias Rönnblom
> Sent: Wednesday, November 10, 2021 4:44 PM
> To: jerinjac...@gmail.com; Jayatheerthan, Jay ;
> Kundapura, Ganapati
> ; jer...@marvell.com
> Cc: dev @ dpdk . org ; mat
Hi Anoob,
> -Original Message-
> From: dev On Behalf Of Anoob Joseph
> Sent: Monday, November 8, 2021 3:20 PM
> To: Akhil Goyal ; Doherty, Declan
> ; Zhang, Roy Fan
> Cc: Anoob Joseph ; Jerin Jacob ;
> Archana Muniganti ; Tejasree Kondoj
> ; Hemant Agrawal ;
> Nicolau, Radu ; Power, Ciar
> -Original Message-
> From: David Marchand
> Sent: Wednesday, November 10, 2021 7:08 PM
> To: Jiang, YuX
> Cc: Harris, James R ; dev@dpdk.org; Hunt, David
>
> Subject: Re: [dpdk-dev] [PATCH v2] power: fix unused-but-set variable error
>
> On Wed, Nov 10, 2021 at 11:56 AM Jiang, YuX wr
The RV PCI Root Complex Device is not visible to DPDK on the PCI bus
via pci_search_device on some OSs including Ubuntu and Yocto. This
makes it impossible to determine which machine DPDK/axgbe is running
on. As a result, DPDK/axgbe does not work on v1000.
Let's use the Raven Internal PCIe GPP Bri
Hi Pablo,
Thanks for the review. Please see inline.
Thanks,
Anoob
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Wednesday, November 10, 2021 4:54 PM
> To: Anoob Joseph ; Akhil Goyal
> ; Doherty, Declan ;
> Zhang, Roy Fan
> Cc: Jerin Jacob Kollanukkaran ; Archana Muniganti
09/11/2021 05:39, Gagandeep Singh:
> Gagandeep Singh (5):
> dma/dpaa: introduce DPAA DMA driver
> dma/dpaa: add device probe and remove functionality
> dma/dpaa: support basic operations
> dma/dpaa: support DMA operations
> dma/dpaa: support statistics
Applied with multiple minor details
NULL cipher is used for validating auth only cases. With NULL cipher,
validating plain text should not be done as the PMD is only expected
to update auth data.
Fixes: e847fc512817 ("test/crypto: add encrypted digest case for AES-CTR-CMAC")
Cc: adamx.dybkow...@intel.com
Signed-off-by: Anoob Joseph
10/11/2021 00:32, Radha Mohan Chintakuntla:
> The octeontx2_dma rawdev driver is removed in DPDK-21.11. The new driver
> for the same device uses the dmadev. So this patch updates the device
> naming and lists it under dma devices section.
>
> Signed-off-by: Radha Mohan Chintakuntla
Applied, tha
On 11/10/2021 7:48 AM, Apeksha Gupta wrote:
ENETFEC (Fast Ethernet Controller) is a network poll mode driver
for NXP SoC i.MX 8M Mini.
This patch adds skeleton for enetfec driver with probe function.
Signed-off-by: Sachin Saxena
Signed-off-by: Apeksha Gupta
<...>
@@ -0,0 +1,133 @@
+.. SPD
On 11/10/2021 7:48 AM, Apeksha Gupta wrote:
This patch adds Rx/Tx queue configuration setup operations.
On packet reception the respective BD Ring status bit is set
which is then used for packet processing.
Signed-off-by: Sachin Saxena
Signed-off-by: Apeksha Gupta
<...>
+
+ rte_write
On 11/10/2021 7:48 AM, Apeksha Gupta wrote:
This patch adds burst enqueue and dequeue operations to the enetfec
PMD. Loopback mode is also added, compile time flag 'ENETFEC_LOOPBACK' is
used to enable this feature. By default loopback mode is disabled.
Basic features added like promiscuous enable
On 11/10/2021 7:48 AM, Apeksha Gupta wrote:
This patch adds checksum and VLAN offloads in enetfec network
poll mode driver.
Signed-off-by: Sachin Saxena
Signed-off-by: Apeksha Gupta
<...>
@@ -191,7 +195,12 @@ enet_free_buffers(struct rte_eth_dev *dev)
static int
enetfec_eth_configure(s
Running in 'csum' mode, the 'from' and 'to' parameters are not in correct
order when calling rte_ether_addr_copy() which means the src/dst mac addresses
will be overwriten.
As a result, the packets will not be recognized and received by the receiver(s).
Test CLI:
./app/dpdk-testpmd -n 1 -l 1-2 -a
The testsuite_setup function in the compressdev_autotest test case,
the rte_compressdev_count() return 0 due to the lack of device init.
It is considered that there is no equitment to skip execution.
So add rte_vdev_init init compress_zlib device.
Signed-off-by: Changsheng Wu
---
app/test/te
-Original Message-
From: Stephen Hemminger
Sent: Tuesday, November 9, 2021 8:00 PM
To: Narcisa Ana Maria Vasile
Cc: thomas ; dev@dpdk.org; Dmitry Kozlyuk
; Khoa To ; Dmitry Malloy
; Tyler Retzlaff ; talshn
; Omar Cardona ;
bruce.richard...@intel.com; david.march...@redhat.com; Kad
On 11/2/2021 5:04 PM, David Marchand wrote:
On Tue, Nov 2, 2021 at 4:59 PM Andrew Rybchenko
wrote:
IMHO, spamming of testpmd logs in described case should be fixed
in testpmd itself to avoid logs in the case of ENOTSUP. That's it.
I think we should not call this API in testpmd
if not doing rt
On 10/23/2021 12:39 PM, Ananyev, Konstantin wrote:
22/10/2021 23:14, Bing Zhao:
In the function "eth_dev_fp_ops_reset", a structure assignment
operation is used to reset one queue's callback functions, etc., but
it is not thread safe.
The structure assignment is not atomic, a lot of instruct
Hi Ferruh,
> >> 22/10/2021 23:14, Bing Zhao:
> >>> In the function "eth_dev_fp_ops_reset", a structure assignment
> >>> operation is used to reset one queue's callback functions, etc., but
> >>> it is not thread safe.
> >>>
> >>> The structure assignment is not atomic, a lot of instructions will
> Matan Azrad (2):
> common/mlx5: add wrapped MR create API
> vdpa/mlx5: workaround dirty bitmap MR creation
>
> Michael Baum (3):
> common/mlx5: glue MR registration with IOVA
> vdpa/mlx5: workaround guest MR registrations
> net/mlx5: workaround MR creation for flow counter
Applied, th
10/11/2021 15:37, Ananyev, Konstantin:
>
> Hi Ferruh,
>
> > >> 22/10/2021 23:14, Bing Zhao:
> > >>> In the function "eth_dev_fp_ops_reset", a structure assignment
> > >>> operation is used to reset one queue's callback functions, etc., but
> > >>> it is not thread safe.
> > >>>
> > >>> The struct
Removing the szedata2 device driver as the platform is no longer
supported.
Signed-off-by: Martin Spinler
---
MAINTAINERS |6 -
doc/guides/nics/features/szedata2.ini | 18 -
.../img/szedata2_nfb200g_architecture.svg | 214 --
doc/guides/nics/i
Update the software dependency link because of website shutdown.
Netcope Technologies was recently renamed to Magmio and no longer
provides packages and support for the FPGA cards and NDK platform.
However the project Liberouter@CESNET continues with the maintenance
of Network Development Kit and
09/11/2021 22:04, Stephen Hemminger:
> These tests are testing with strings with hostname (dpdk.org)
> and this makes test code do a DNS lookup. In container test
> runs, DNS is unavailable. Replace dpdk.org with the current
> IP and IPV6 addresses. Actual addresses don't matter the purpose
> of
Yes +1
Let the application handle it once there is an issue.
BR. Bing
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, November 10, 2021 10:58 PM
> To: Yigit, Ferruh ; Bing Zhao
> ; Ananyev, Konstantin
>
> Cc: andrew.rybche...@oktetlabs.ru; dev@dpdk.org
> Subject: Re: [P
08/11/2021 11:08, David Marchand:
> Since two components wants to know if the jansson library is available,
> move it to config/.
>
> Signed-off-by: David Marchand
Applied, thanks.
Remove the szedata2 device driver as the platform is no longer
supported.
Signed-off-by: Martin Spinler
---
MAINTAINERS |6 -
doc/guides/nics/features/szedata2.ini | 18 -
.../img/szedata2_nfb200g_architecture.svg | 214 --
doc/guides/nics/ind
Update the software dependency link because of website shutdown.
Netcope Technologies was recently renamed to Magmio and no longer
provides packages and support for the FPGA cards and NDK platform.
However the project Liberouter@CESNET continues with the maintenance
of Network Development Kit and
the primary program(such as ofp app) run first, then run the secondary
program(such as dpdk-pdump), the primary program would receive signal
SIGSEGV. the function stack as follow:
aived signal SIGSEGV, Segmentation fault.
[Switching to Thread 0x7fffee60e700 (LWP 112613)]
0x75f2cc0b in buck
On Wed, Nov 10, 2021 at 4:57 PM Tianli Lai wrote:
>
> the primary program(such as ofp app) run first, then run the secondary
> program(such as dpdk-pdump), the primary program would receive signal
> SIGSEGV. the function stack as follow:
Is OpenFastPath linked against the same dpdk binary than yo
On Wed, 10 Nov 2021 08:17:59 +
"Xu, Wei1" wrote:
> eth_hdr = rte_pktmbuf_mtod(m, struct
> rte_ether_hdr *);
> -
> rte_ether_addr_copy(&peer_eth_addrs[fs->peer_addr],
> -
> ð_
Yes, OpenFastPath is the same dpdk binary with dpdk-pdump tool.
On 11/10/2021 3:39 PM, Martin Spinler wrote:
Remove the szedata2 device driver as the platform is no longer
supported.
Signed-off-by: Martin Spinler
Thanks Martin for the update.
It would be better to announce the removal a release in advance,
to let possible users know about it and cover the
On 11/10/2021 3:39 PM, Martin Spinler wrote:
Update the software dependency link because of website shutdown.
Netcope Technologies was recently renamed to Magmio and no longer
provides packages and support for the FPGA cards and NDK platform.
However the project Liberouter@CESNET continues with
These tests were using strings with hostname (dpdk.org) and this makes
test code do a DNS lookup. In container environment used for OpenSuse
build, DNS is unavailable. Replace dpdk.org with an IPv4 address
reserved for documentation (RFC 5737) and use IPv6 in one example (RFC 3849).
Actual address
On 10/18/2021 3:43 PM, Bing Zhao wrote:
After yellow color actions in the metering policy were supported,
the RSS could be used for both green and yellow colors and only the
queues attribute could be different.
When specifying the attributes of a RSS, some fields can be ignored
and some default
Looking at drivers/compress/octeontx/meson.build:
# SPDX-License-Identifier: BSD-3-Clause
# Copyright(c) 2018 Cavium, Inc
if not is_linux or not dpdk_conf.get('RTE_ARCH_64')
build = false
reason = 'only supported on 64-bit Linux'
subdir_done()
endif
sources = files('otx_zip.c', 'otx_z
This series extends the optional libraries list adding to them testpmd
non essential dependencies.
We were not testing the disable_libs option, so let's add a minimum target
in the the public CI script (mainly for GHA) and in test-meson-builds.sh
script.
The last patch is an idea for enhancing th
Disabling optional libraries was not tested.
Add a new target in test-meson-builds.sh and GHA.
The Bluefield target is removed from test-meson-builds.sh to save space
and compilation time in exchange of the new target.
Signed-off-by: David Marchand
---
.ci/linux-build.sh| 3 +++
.gi
GRO and GSO integration in testpmd is relatively self contained and easy
to extract.
Those libraries can be made optional as they provide standalone
features.
Signed-off-by: David Marchand
---
app/test-pmd/cmdline.c | 14 ++
app/test-pmd/config.c| 6 ++
app/test-pmd/csumon
metrics, bitratestats, jobstats and latencystats libraries can be made
optional as they provide standalone features.
Signed-off-by: David Marchand
---
app/proc-info/main.c | 16
app/proc-info/meson.build | 5 -
app/test-pmd/meson.build | 5 -
app/test-pmd/testpmd
This library can be made optional.
dumpcap and pdump applications depend on this library, check for
dependencies like what we have for examples.
Signed-off-by: David Marchand
---
app/meson.build | 18 +-
app/test/meson.build | 10 +-
lib/meson.build | 1 +
3 fi
There is currently no way to know which libraries are optional.
Introduce a enable_libs option (close to what we have for drivers) so
that packagers or projects consuming DPDK can more easily select the
optional libraries that matter to them and disable other optional
libraries.
Note: the enabled_
MP servers distributes Rx packets between clients according to
round-robin scheme.
Current implementation always started packets distribution from
the first client. That procedure resulted in uniform distribution
in cases when Rx packets number was around clients number
multiplication. However, if
On 10/12/2021 11:02 AM, Chengfeng Ye wrote:
The lock sh->txpp.mutex was not correctly released on one path
of cleanup function return, potentially causing the deadlock.
Fixes: d133f4cdb7 ("net/mlx5: create clock queue for packet pacing")
Cc: sta...@dpdk.org
Signed-off-by: Chengfeng Ye
---
dr
MP servers distributes Rx packets between clients according to
round-robin scheme.
Current implementation always started packets distribution from
the first client. That procedure resulted in uniform distribution
in cases when Rx packets number was around clients number
multiplication. However, if
Hi Anoob,
>-Original Message-
>From: Anoob Joseph
>Sent: Wednesday 10 November 2021 13:04
>To: Akhil Goyal ; Doherty, Declan
>; Zhang, Roy Fan ; De
>Lara Guarch, Pablo
>Cc: Anoob Joseph ; Jerin Jacob ;
>Archana Muniganti ; Tejasree Kondoj
>; Hemant Agrawal ;
>Nicolau, Radu ; Power, Ciara
On Wed, Nov 10, 2021 at 9:38 PM Tianli Lai wrote:
>
> the primary program(such as ofp app) run first, then run the secondary
> program(such as dpdk-pdump), the primary program would receive signal
> SIGSEGV. the function stack as follow:
>
> aived signal SIGSEGV, Segmentation fault.
> [Switching t
Hi Anoob,
> -Original Message-
> From: Power, Ciara
> Sent: Wednesday, November 10, 2021 5:01 PM
> To: Anoob Joseph ; Akhil Goyal ;
> Doherty, Declan ; Zhang, Roy Fan
> ; De Lara Guarch, Pablo
>
> Cc: Jerin Jacob ; Archana Muniganti
> ; Tejasree Kondoj ; Hemant
> Agrawal ; Nicolau, Radu
On Wed, Nov 10, 2021 at 05:48:14PM +0100, David Marchand wrote:
> There is currently no way to know which libraries are optional.
> Introduce a enable_libs option (close to what we have for drivers) so
> that packagers or projects consuming DPDK can more easily select the
> optional libraries that
On Wed, Nov 10, 2021 at 05:48:09PM +0100, David Marchand wrote:
> This series extends the optional libraries list adding to them testpmd
> non essential dependencies.
>
> We were not testing the disable_libs option, so let's add a minimum target
> in the the public CI script (mainly for GHA) and i
Multiple drivers are defining macros for VLAN header length, to remove
the redundancy defining macro in the ether header.
And updated drivers to use the new macro.
Signed-off-by: Ferruh Yigit
---
drivers/net/bnx2x/bnx2x_vfpf.c | 2 +-
drivers/net/bnx2x/bnx2x_vfpf.h | 2 --
drivers/ne
FD -> File Descriptor
GUID-> Globally Unique Identifier
Netlink -> Linux Netlink socket family
PCIe-> Peripheral Component Interconnect Express
Signed-off-by: Ferruh Yigit
---
devtools/words-case.txt | 4
1 file changed, 4 insertions(+)
diff --git a/devtools/words-case.txt b/d
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Tuesday, November 9, 2021 11:46 AM
> To: Medvedkin, Vladimir ; dev@dpdk.org
> Cc: tho...@monjalon.net; Wang, Yipeng1 ;
> Gobriel, Sameh ; Richardson, Bruce
> ; nd ; nd
> Subject: RE: [dpdk-dev] [PATCH] hash: clarify comments for
>
This patch adds a comment for RTE_HASH_BUCKET_ENTRIES
explaining why a particular value was chosen.
Signed-off-by: Vladimir Medvedkin
---
lib/hash/rte_cuckoo_hash.h | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/lib/hash/rte_cuckoo_hash.h b/lib/hash/rte_cuckoo_hash.h
On Wed, Nov 10, 2021 at 5:02 PM Mattias Rönnblom
wrote:
>
> Replace RTE_EVENT_DEV_CAP_REQUIRES_MAINT, which signaled the need
> for the application to call rte_event_maintain(), with
> RTE_EVENT_DEV_CAP_MAINTENANCE_FREE, which does the opposite (i.e.,
> signifies that the event device does not req
On Wed, Nov 10, 2021 at 4:53 PM Jayatheerthan, Jay
wrote:
>
> Looks good. Thanks for posting this change!
>
> Acked-by: Jay Jayatheerthan
Changed the subject to: eventdev/eth_rx: fix stalls on event device backpressure
Applied to dpdk-next-net-eventdev/for-main. Thanks
>
> > -Original Mes
On Wed, Nov 10, 2021 at 11:30 AM Naga Harish K S V
wrote:
>
> This patch fixes heap-use-after-free reported by ASAN,
> please reference https://bugs.dpdk.org/show_bug.cgi?id=869
>
> The application can use the queue_id as `-1` to delete all
> the queues of the eth_device that are added to tx_adapt
>
> This patch adds a comment for RTE_HASH_BUCKET_ENTRIES explaining why a
> particular value was chosen.
>
> Signed-off-by: Vladimir Medvedkin
Looks good
Reviewed-by: Honnappa Nagarahalli
> ---
> lib/hash/rte_cuckoo_hash.h | 8 +++-
> 1 file changed, 7 insertions(+), 1 deletion(-)
>
>
> Subject: [PATCH v1 11/12] app/bbdev: use compiler atomics for thread sync
There are multiple fields which are getting synchronized. How about the
following:
app/bbdev: use compiler atomics for synchronizing shared data
>
> Convert rte_atomic usages to compiler atomic built-ins for thread par
> Subject: [PATCH v1 07/12] app/eventdev: use compiler atomic builtins for
> packets sync
How about the following:
app/eventdev: use compiler atomic builtins for shared data synchronization
>
> Convert rte_atomic usages to compiler atomic built-ins for outstanding_pkts
> sync in eventdev cases.
-Original Message-
From: Bruce Richardson
Sent: Wednesday, November 10, 2021 1:21 AM
To: Stephen Hemminger
Cc: Tyler Retzlaff ; Narcisa Ana Maria Vasile
; thomas ; dev@dpdk.org;
Dmitry Kozlyuk ; Khoa To ; Dmitry
Malloy ; talshn ; Omar Cardona
; david.march...@redhat.com; Kadam, Pa
> -Original Message-
> From: Yigit, Ferruh
> Sent: Thursday, November 11, 2021 01:40
> To: Rasesh Mody ; Shahed Shaikh ;
> Rahul Lakkireddy
> ; Zhang, Qi Z ; Wang,
> Xiao W
> ; Ziyang Xuan ; Xiaoyun Wang
> ; Guoyang Zhou ; Xing,
> Beilei
> ; Wu, Jingjing ; Yang, Qiming
> ;
> Xu, Rosen
From: Narcisa Vasile
Add function to translate Windows error codes to
errno-style error codes. The possible return values are chosen
so that we have as much semantical compatibility between platforms as
possible.
Signed-off-by: Narcisa Vasile
---
lib/eal/windows/rte_thread.c | 48 +
From: Narcisa Vasile
EAL thread API
**Problem Statement**
DPDK currently uses the pthread interface to create and manage threads.
Windows does not support the POSIX thread programming model,
so it currently
relies on a header file that hides the Windows calls under
pthread matched interfaces. Gi
From: Narcisa Vasile
Use a portable, type-safe representation for the thread identifier.
Add functions for comparing thread ids and obtaining the thread id
for the current thread.
Signed-off-by: Narcisa Vasile
---
lib/eal/common/meson.build| 1 +
lib/eal/{unix => common}/rte_threa
From: Narcisa Vasile
Implement functions for getting/setting thread affinity.
Threads can be pinned to specific cores by setting their
affinity attribute.
Signed-off-by: Narcisa Vasile
Signed-off-by: Dmitry Malloy
---
lib/eal/common/rte_thread.c | 16
lib/eal/include/rte_thread.h |
From: Narcisa Vasile
Implement thread attributes for:
* thread affinity
* thread priority
Implement functions for managing thread attributes.
Priority is represented through an enum that allows for two levels:
- RTE_THREAD_PRIORITY_NORMAL
- RTE_THREAD_PRIORITY_REALTIME_CRITICAL
From: Narcisa Vasile
Add functions for mutex init, destroy, lock, unlock, trylock.
Windows does not have a static initializer. Initialization
is only done through InitializeCriticalSection(). To overcome this,
RTE_INIT_MUTEX macro is added to replace static initialization
of mutexes. The macro c
From: Narcisa Vasile
Add functions for thread creation, joining, detaching.
The *rte_thread_create()* function can optionally receive
an rte_thread_attr_t object that will cause the thread to be
created with the affinity and priority described by the
attributes object. If no rte_thread_attr_t is
From: Narcisa Vasile
Add functions for setting and getting the priority of a thread.
Priorities on multiple platforms are similarly determined by
a priority value and a priority class/policy.
Currently in DPDK most threads operate at the OS-default
priority level but there are cases when increas
From: Narcisa Vasile
Add functions for barrier init, destroy, wait.
A portable type is used to represent a barrier identifier.
The rte_thread_barrier_wait() function returns the same value
on all platforms.
Add unit tests to verify that the barrier correctly
synchronizes all threads. Verify tha
This patch fixes coverity issue by directly passing the address
of the meter data to subfunction.
Coverity issue: 373858
Fixes: 91f27b2e39ab ("net/iavf: refactor RSS")
Cc: sta...@dpdk.org
Signed-off-by: Alvin Zhang
---
drivers/net/iavf/iavf_hash.c | 5 ++---
1 file changed, 2 insertions(+), 3
On Tue, Oct 26, 2021 at 09:45:20AM +0200, Morten Brørup wrote:
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Thomas Monjalon
> > Sent: Monday, 25 October 2021 21.14
> >
> > 15/03/2021 20:34, Tyler Retzlaff:
> > > The proposal has resulted from request to review [1] the following
> > > f
https://bugs.dpdk.org/show_bug.cgi?id=881
Bug ID: 881
Summary: [dpdk-21.11] drivers/libtmp_rte_bus_fslmc.a.p build
failed on OS Fedora35 with clang 13.0.0
Product: DPDK
Version: 21.11
Hardware: All
OS: All
On Sat, Oct 23, 2021 at 12:29:00PM +0200, David Marchand wrote:
> __reserved is a reserved keyword in Windows system headers.
>
fwiw it's the c standard that stipulates identifiers starting with __
are reserved for any use.
C11/C99 "ANSI-C"
7.1.3 Reserved Identifiers
`All identifiers that be
This patch fixes coverity issue by directly passing the address
of the meter data to lower function.
Coverity issue: 373867
Fixes: 91f27b2e39ab ("net/iavf: refactor RSS")
Cc: sta...@dpdk.org
Signed-off-by: Alvin Zhang
---
drivers/net/iavf/iavf_hash.c | 5 ++---
1 file changed, 2 insertions(+),
When processing front-end memory regions messages,
vhost saves the guest/host physical address mappings to guest pages
and merges adjacent contiguous pages if hpa is contiguous,
however gpa is likely not contiguous in PA mode
and merging will cause the gpa range to change.
This patch distinguishes
On Wed, 2021-11-10 at 16:12 +, Ferruh Yigit wrote:
> On 11/10/2021 3:39 PM, Martin Spinler wrote:
> > Update the software dependency link because of website shutdown.
> >
> > Netcope Technologies was recently renamed to Magmio and no longer
> > provides packages and support for the FPGA cards
>-Original Message-
>From: Thomas Monjalon
>Sent: Tuesday, November 9, 2021 5:05 PM
>To: Sunil Kumar Kori ; Jerin Jacob
>
>Cc: Jerin Jacob Kollanukkaran ; Nikhil Rao
>; Pavan Nikhilesh Bhagavatula
>; Hemant Agrawal
>; Nipun Gupta ; Van
>Haaren, Harry ; Mattias Rönnblom
>; Liang Ma ; dpdk-
This patch adds support for max burst size configuration for
TX scheduler. This feature can be tuned on by devargs:
-a :18:00.0,max_burst_size=x
The value of x should between 64 and 1023*1024.
Signed-off-by: Wenjun Wu
---
drivers/net/ice/ice_ethdev.c | 36
Hi, Ferruh
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, November 10, 2021 18:57
> To: Chengfeng Ye ; david.march...@redhat.com;
> Slava Ovsiienko ; Shahaf Shuler
> ; Matan Azrad
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v5] net/mlx5: fix mutex u
>
>
> > Subject: [PATCH v1 07/12] app/eventdev: use compiler atomic builtins
> > for packets sync
> How about the following:
> app/eventdev: use compiler atomic builtins for shared data synchronization
>
Yes, please see next version.
> >
> > Convert rte_atomic usages to compiler atomic built-i
99 matches
Mail list logo
