In functions rte_dev_probe() and __handle_secondary_request(),
an error message was logged as a failure if the probe returns -EEXIST.
Anyway this error code is not returned by rte_dev_probe()
as it is not considered as an error.
For instance, in multi-process case, some synchronizations may request
While working on multi-process support of failsafe with Raslan,
some issues have been discovered on probing failures.
Thomas Monjalon (3):
eal: remove useless checks for already probed device
eal: remove error logs for already probed device
eal: fix multi-process probe failure handling
lib
If probe fails in multi-process context, the device must removed
in other processes for consistency. This is a rollback mechanism.
However the rollback should not happen for devices which were
already probed before the current probe transaction.
When probing an already probed device, the driver ma
The function eal_dev_hotplug_request_to_secondary() never returns
-EEXIST result. The case of already probed device is filtered out.
The test in __handle_secondary_request() was always true.
The test in rte_dev_probe() was never true, and that's fine not
returning -EEXIST if device is already atta
On 3/1/2019 11:02 AM, Stephen Hemminger wrote:
On Thu, 28 Feb 2019 23:18:47 -0800
Anand Rawat wrote:
Add documentation to build helloworld example
on windows using meson and clang.
Signed-off-by: Anand Rawat
Signed-off-by: Kadam, Pallavi
Reviewed-by: Jeffrey B Shaw
Reviewed-by: Ranjit Meno
This patch enables lock-free read-write concurrency support for
extendable bucket feature.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Dharmik Thakkar
---
doc/guides/prog_guide/hash_lib.rst | 3 +-
lib/librte_hash/rte_cuckoo_hash.c | 150 +++--
lib/librte_hash/r
Add unit test to check for hash lookup and bulk-lookup perf.
Test with lock-free enabled and with lock-free disabled.
Test include:
- hash lookup on keys in ext bkt,
hash delete causing key-shifts of keys from ext bkt to secondary bkt
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Dharmik Th
This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt
Dharmik Thakkar (2):
hash: add lock free support for extendable bucket
test/hash: lock-free rw concurrency test ext bkt
app/test/test
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Friday, March 1, 2019 3:13 PM
> To: Eads, Gage
> Cc: Olivier Matz ; dev@dpdk.org;
> arybche...@solarflare.com; Richardson, Bruce ;
> Ananyev, Konstantin ; gavin...@arm.com;
> honnappa.nagaraha...@arm.com;
01/03/2019 21:53, Eads, Gage:
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> > On Fri, Feb 22, 2019 at 10:06:53AM -0600, Gage Eads wrote:
> > > +#define STACK_F_NB 0x0001
> >
> > What about adding the RTE_ prefix?
>
> I'm fine with either, but there's precedent for flag macros named
> _*.
01/03/2019 21:24, Michael Santana Francisco:
> On 3/1/19 12:51 PM, Thomas Monjalon wrote:
> > 01/03/2019 18:43, Thomas Monjalon:
> >> 01/03/2019 18:08, Michael Santana:
> >>> +# Enable codespell by default. This can be overwritten from a config
> >>> file.
> >>> +# You can also enable codespell by
> -Original Message-
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> Sent: Monday, February 25, 2019 5:28 AM
> To: Eads, Gage
> Cc: dev@dpdk.org; arybche...@solarflare.com; Richardson, Bruce
> ; Ananyev, Konstantin
> ; gavin...@arm.com;
> honnappa.nagaraha...@arm.com; n...@arm.co
Hi Qiming,
For some reason I am not seeing patch 1/2 in this series. Can you make sure you
sent it or re-send it?
Paul
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Qiming Yang
Sent: Friday, March 1, 2019 4:46 AM
To: dev@dpdk.org
Cc: Yang, Qiming
Subject: [dpd
On 3/1/19 12:51 PM, Thomas Monjalon wrote:
01/03/2019 18:43, Thomas Monjalon:
01/03/2019 18:08, Michael Santana:
+# Enable codespell by default. This can be overwritten from a config file.
+# You can also enable codespell by setting DPDK_CHECKPATCH_CODESPELL to a
valid path
+# to a dictionary.
On Thu, 28 Feb 2019 23:18:47 -0800
Anand Rawat wrote:
> Add documentation to build helloworld example
> on windows using meson and clang.
>
> Signed-off-by: Anand Rawat
> Signed-off-by: Kadam, Pallavi
> Reviewed-by: Jeffrey B Shaw
> Reviewed-by: Ranjit Menon
Please add an entry to the MAINT
On Fri, 1 Mar 2019 15:37:34 +0100
Rastislav Cernay wrote:
> From: Rastislav Cernay
>
> Added new net driver for Netcope nfb cards
>
> Signed-off-by: Rastislav Cernay
> ---
Please fix these obvious style issues from checkpatches
ERROR:SPACING: space required before the open brace '{'
#934:
On Fri, 1 Mar 2019 15:37:34 +0100
Rastislav Cernay wrote:
> +/**
> + * Default MAC addr
> + */
> +static struct ether_addr eth_addr = {
> + .addr_bytes = { 0x00, 0x11, 0x17, 0x00, 0x00, 0x00 }
You might want to consider using a random ethernet address.
What does the device do on Linux?
Moving upper level enqueue/dequeue routines to driver. The h/w interface
used to submit request has enough differences to substantiate the need
for separate routines.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
---
drivers/common/cpt/cpt_common.h
The check for prep_req is good enough to flag error. The return var
passed around is redundant. Fixing this. Also making the functions
return correct error values in case of various failures.
In addition, adding unlikely flag for all error checks.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoo
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
---
drivers/common/cpt/cpt_common.h | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/common/cpt/cpt_common.h b/drivers/common/cpt/cpt_common.h
index 8461cd6..8568d5b 100644
--- a/drivers/common/cpt/cpt
On Fri, 1 Mar 2019 10:48:58 +0300
Andrew Rybchenko wrote:
> On 3/1/19 1:47 AM, Stephen Hemminger wrote:
> > Don't need to use snprintf for simple name copy.
> >
> > Signed-off-by: Stephen Hemminger
> > ---
> > lib/librte_ethdev/rte_ethdev.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deleti
On Fri, 1 Mar 2019 20:46:12 +0800
Qiming Yang wrote:
> +
> + if (kvargs_count > 1)
> + PMD_DRV_LOG(WARNING, "More than one argument \"%s\" and only "
> + "the first invalid or last valid one is used !",
Do not add line breaks to error message strings, it makes it har
On Fri, 1 Mar 2019 20:46:12 +0800
Qiming Yang wrote:
> static int
> +ice_parse_pkg_path_handler(__rte_unused const char *key,
> + const char *value,
> + void *opaque)
> +{
> + struct ice_adapter *ad;
> +
> + ad = (struct ice_adapter *)opaque;
On Fri, 1 Mar 2019 20:46:13 +0800
Qiming Yang wrote:
> + PMD_INIT_LOG(WARNING, "Initialize in safe mode,"
> + "some features are disabled.\n");
Don't split a message string, it makes it harder to search.
Also, most drivers define PMD_INIT_LOG to always add a newline and do
not
On Fri, 1 Mar 2019 16:09:47 +0800
Xiaolong Ye wrote:
> When create rte_mempool, flags can be parsed from command line.
> Now, it is possible for testpmd to create a af_xdp friendly
> mempool (which enable zero copy).
>
> Signed-off-by: Qi Zhang
> Signed-off-by: Xiaolong Ye
Please don't expos
On Fri, 1 Mar 2019 16:09:42 +0800
Xiaolong Ye wrote:
> +
> +static int
> +rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
> +{
> + struct rte_kvargs *kvlist;
> + char *if_name = NULL;
> + int queue_idx = ETH_AF_XDP_DFLT_QUEUE_IDX;
> + struct rte_eth_dev *eth_dev;
> + const
On Fri, 1 Mar 2019 16:09:42 +0800
Xiaolong Ye wrote:
> + if (umem->buffer)
> + free(umem->buffer);
Minor nit: you don't need to check for NULL free() already handles this.
01/03/2019 18:08, Michael Santana:
> Fix trivial bug. In sh shell, 'foo = 1' is not the same as
> 'foo=1'. Using 'foo = 1' makes the shell attempt to interpret foo
> as a command, rather than a simple variable assignment.
>
> Signed-off-by: Michael Santana
> Fixes: dafc04c15174 ("devtools: fix re
01/03/2019 18:43, Thomas Monjalon:
> 01/03/2019 18:08, Michael Santana:
> > +# Enable codespell by default. This can be overwritten from a config file.
> > +# You can also enable codespell by setting DPDK_CHECKPATCH_CODESPELL to a
> > valid path
> > +# to a dictionary.txt file if your dictionary.t
01/03/2019 18:08, Michael Santana:
> +# Enable codespell by default. This can be overwritten from a config file.
> +# You can also enable codespell by setting DPDK_CHECKPATCH_CODESPELL to a
> valid path
> +# to a dictionary.txt file if your dictionary.txt is not in the default
> location.
Better
On 01/03/2019 17:32, Ferruh Yigit wrote:
> Define '__rte_deprecated' usage process.
>
> Suggests keeping old API with '__rte_deprecated' marker including
> next LTS, they will be removed just after the LTS release.
>
> Signed-off-by: Ferruh Yigit
> Acked-by: Luca Boccassi
> Acked-by: Neil Horma
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Lukasz Krakowiak
> Sent: Wednesday, February 27, 2019 11:18 AM
> To: De Lara Guarch, Pablo
> Cc: dev@dpdk.org; Trahe, Fiona ; Krakowiak,
> LukaszX
> Subject: [dpdk-dev] [PATCH v2] test: add snow3g test cases wh
Define '__rte_deprecated' usage process.
Suggests keeping old API with '__rte_deprecated' marker including
next LTS, they will be removed just after the LTS release.
Signed-off-by: Ferruh Yigit
Acked-by: Luca Boccassi
Acked-by: Neil Horman
---
Cc: Luca Boccassi
Cc: Kevin Traynor
Cc: Yongseok
Initial process requires oncoming changes described in deprecation
notice should be implemented in a RTE_NEXT_ABI gated way.
This has been discussed in technical board, and since this can cause a
multiple #ifdef blocks in multiple locations of the code, can be
confusing specially for the modificat
The original document written from the point of ABI versioning but later
additions make document confusing, convert document into a ABI/API
policy documentation and organize the document in subsections:
- ABI/API Deprecation
- Experimental APIs
- Library versioning
- ABI versioning
Aim to clarify
01/03/2019 18:05, Ferruh Yigit:
> On 10/11/2017 3:33 PM, jerin.jacob at caviumnetworks.com (Jerin Jacob) wrote:
> > From: Thomas Monjalon
> >> 07/08/2017 14:04, Jerin Jacob:
> >>> baremetal execution environments may have a different
> >>> method to enable RTE_INIT instead of using compiler
> >>>
This patch updates the bbdev test application to include an option to
configure the PF before running FPGA tests.
Signed-off-by: Smith, Eleanor
---
app/test-bbdev/main.c| 15 +-
app/test-bbdev/main.h| 2 ++
app/test-bbdev/test-bbdev.py | 7 +
app/test-b
This series of patches adds a new baseband device driver for
Intel(R) FPGA LTE FEC which enable the acceleration of 4G FEC turbo
encoding and decoding on FPGA through the DPDK librte_bbdev API.
The FEC offloaded UL functionality includes sub block deinterleave,
turbo decoding and CRC checking.
Addition of a FPGA driver for acceleration of 4G turbo encoding and
decoding.
Signed-off-by: Smith, Eleanor
---
config/common_base |6 +
doc/guides/bbdevs/fpga_lte_fec.rst | 316 +++
doc/guides/bbdevs/index.rst|1 +
This patch update bbdev API rte_bbdev_info struct to use rte_device
instead of rte_bus.
Signed-off-by: Smith, Eleanor
---
doc/guides/prog_guide/bbdev.rst | 4 ++--
lib/librte_bbdev/rte_bbdev.c| 6 +++---
lib/librte_bbdev/rte_bbdev.h| 2 +-
3 files changed, 6 insertions(+), 6 deletions(-)
This patch allows dpdk-setup.py and dpdp-devbind.py to be used to bind
baseband devices.
Signed-off-by: Smith, Eleanor
---
usertools/dpdk-devbind.py | 10 +-
usertools/dpdk-setup.sh | 6 +++---
2 files changed, 12 insertions(+), 4 deletions(-)
diff --git a/usertools/dpdk-devbind.py
On 2/26/2019 10:31 AM, Ferruh Yigit wrote:
> On 2/19/2019 1:24 PM, Andrius Sirvys wrote:
>> Shifting signed 32-bit values by 31-bits has the potential for
>> unexpected outcomes as compiler can overwrite a bit.
>> Specified that values are unsigned.
>>
>> Errors are observed from running cppcheck.
On 3/1/2019 5:05 PM, Ferruh Yigit wrote:
> On 10/11/2017 3:33 PM, jerin.jacob at caviumnetworks.com (Jerin Jacob) wrote:
>> -Original Message-
>>> Date: Wed, 11 Oct 2017 15:02:51 +0200
>>> From: Thomas Monjalon
>>> To: Jerin Jacob
>>> Cc: dev at dpdk.org, bruce.richardson at intel.com
>>>
On 10/27/2017 4:31 PM, pablo.de.lara.guarch at intel.com (De Lara Guarch, Pablo)
wrote:
>> From: Mike Stolarchuk [mailto:mike.stolarchuk at bigswitch.com]
>> Sent: Friday, October 27, 2017 4:00 PM
>> To: De Lara Guarch, Pablo
>> Cc: Thomas Monjalon ; Richardson, Bruce
>> ; dev at dpdk.org
>> Subje
Fix trivial bug. In sh shell, 'foo = 1' is not the same as
'foo=1'. Using 'foo = 1' makes the shell attempt to interpret foo
as a command, rather than a simple variable assignment.
Signed-off-by: Michael Santana
Fixes: dafc04c15174 ("devtools: fix return of forbidden addition checks")
---
devtoo
Fixed a minor bug with variable assignment, as well as added an
option for checkpatches
v2->v3:
Also enable codespell by setting a path to a dictionary file.
v1->v2:
Enable codespell by default. Disable via config file
Michael Santana (2):
Enable codespell by default. Can be disabled from
Enable codespell by default.
codespell is a feature by checkpatch.pl that
checks for common spelling mistakes in patches.
This feature is disabled by default. To enable it one must add
the '--codespell' flag to the $options variable in
checkpatches.sh. With this change codespell is enabled by defa
On 10/11/2017 3:33 PM, jerin.jacob at caviumnetworks.com (Jerin Jacob) wrote:
> -Original Message-
>> Date: Wed, 11 Oct 2017 15:02:51 +0200
>> From: Thomas Monjalon
>> To: Jerin Jacob
>> Cc: dev at dpdk.org, bruce.richardson at intel.com
>> Subject: Re: [dpdk-dev] [PATCH] eal: change init
On 1/23/2019 7:16 PM, Ferruh Yigit wrote:
> On 8/7/2017 6:31 PM, keith.wiles at intel.com (Wiles, Keith) wrote:
>>> On Aug 7, 2017, at 11:49 AM, Thomas Monjalon wrote:
>>>
>>> 07/08/2017 15:17, Wiles, Keith:
> On Aug 7, 2017, at 6:35 AM, Thomas Monjalon
> wrote:
>
> Hi,
01/02/2019 18:06, Ferruh Yigit:
> On 1/31/2019 5:17 PM, Thomas Monjalon wrote:
> >> +
> >> +Reminder that new API should follow deprecation process to be able to
> >> replace old API.
> > This last sentence is not clear to me.
> > I think you mean the old API should follow deprecation process
> >
This patch adds new test structure for modexp and modinv
Change-Id: I01de09e65565a4ab3547fbff8c9d1e5f3d2bed1f
Signed-off-by: Damian Nowak
---
test/test/test_cryptodev_asym.c | 279 ++
test/test/test_cryptodev_mod_test_vectors.h | 946
2 files changed, 1225 in
Minutes 28 February 2019
Agenda:
* Release Dates
* Subtrees
* OvS
* Opens
Release Dates
-
* v19.05 dates, no change:
* Proposal Deadline: Friday, 1 March
* RC1: Friday, 29 March
* Release: Friday, 10 May
* Schedule web page upd
On 2/19/2019 6:48 AM, Nithin Kumar Dabilpuram wrote:
> Tx VLAN & QinQ insert enable need not depend on
> Rx VLAN offload ETH_VLAN_EXTEND_OFFLOAD.
+1
> Also enable
> DEV_TX_OFFLOAD_VLAN_INSERT for tx_qinq_set() as it takes
> both vlan id's.
+1
Technically two different but related fix, should i
I was wondering if I could lean on the experts to help me out with an issue?
I'm finally testing this port but don't understand why the following error is
happening:
net_mlx5: mlx5_rxq.c:2151: mlx5_hrxq_drop_new(): port 0 cannot allocate QP for
drop queue
The driver is giving the following er
On 2/4/2019 7:23 AM, Pallantla Poornima wrote:
> sprintf function is not secure as it doesn't check the length of string.
> More secure function snprintf is used.
>
> Fixes: daabf2fb94 ("net/softnic: map flow action to table action")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Pallantla Poornima
R
From: Luca Boccassi
max_ethports was merged after the other patch was written:
e04ea7fcf03c ("build: use integers for numerical options")
So convert this one too like the others have already been.
Signed-off-by: Luca Boccassi
---
meson_options.txt | 2 +-
1 file changed, 1 insertion(+), 1 de
On Fri, 2019-03-01 at 16:09 +0800, Xiaolong Ye wrote:
> Add a new PMD driver for AF_XDP which is a proposed faster version of
> AF_PACKET interface in Linux. More info about AF_XDP, please refer to
> [1]
> [2].
>
> This is the vanilla version PMD which just uses a raw buffer
> registered as
> the
On 2/4/2019 7:22 AM, Pallantla Poornima wrote:
> sprintf function is not secure as it doesn't check the length of string.
> More secure function snprintf is used.
Can you please update title to reflect what actually fixed, something like:
net/nfp: fix possible buffer overflow
>
> Fixes: 896c265e
On Fri, 2019-03-01 at 14:17 +, Bruce Richardson wrote:
> On Fri, Mar 01, 2019 at 03:03:02PM +0100, Thomas Monjalon wrote:
> > 01/03/2019 08:18, Anand Rawat:
> > >
> > [...]
> > > @@ -17,13 +17,19 @@ elif host_machine.system() == 'freebsd'
> > > dpdk_conf.set('RTE_EXEC_ENV_BSDAPP', 1) subdir('b
On Fri, 2019-03-01 at 14:13 +0100, Thomas Monjalon wrote:
> 28/02/2019 18:40, Bruce Richardson:
> > On Wed, Feb 27, 2019 at 01:53:32PM +, Bruce Richardson wrote:
> > > On Wed, Feb 27, 2019 at 12:03:48PM +, Luca Boccassi wrote:
> > > > On Wed, 2019-02-27 at 11:56 +0100, Thomas Monjalon wrote
On Fri, Mar 01, 2019 at 03:26:24PM +0100, Thomas Monjalon wrote:
> Hi,
>
> > Hyong Youb Kim (15):
> > net/enic: remove unused code
> > net/enic: fix flow director SCTP matching
> > net/enic: fix SCTP match for flow API
> > net/enic: allow flow mark ID 0
> > net/enic: check for unsupporte
From: Rastislav Cernay
Added new net driver for Netcope nfb cards
Signed-off-by: Rastislav Cernay
---
v2: remove unnecessary cast
remove unnecessary zeroing
move declaration to not mix with code
restore skeleton example
v3: add release notes
add doc to doc index
add architec
01/03/2019 15:17, Bruce Richardson:
> On Fri, Mar 01, 2019 at 03:03:02PM +0100, Thomas Monjalon wrote:
> > 01/03/2019 08:18, Anand Rawat:
> > > +elif host_machine.system() == 'windows' +
> > > dpdk_conf.set('RTE_EXEC_ENV_WINDOWS', 1)
> >
> > For consistency, it should RTE_EXEC_ENV_WINAPP.
> >
> F
Hi,
> Hyong Youb Kim (15):
> net/enic: remove unused code
> net/enic: fix flow director SCTP matching
> net/enic: fix SCTP match for flow API
> net/enic: allow flow mark ID 0
> net/enic: check for unsupported flow item types
> net/enic: enable limited RSS flow action
> net/enic: enab
26/02/2019 15:15, Bruce Richardson:
> When running ninja, the commands are, by default, always printed on top of
> each other. For those who want more detail in the output, two levels of
> verbose output has been added to the test-meson-builds script. When "-v" is
> passed, or the "TEST_MESON_BUILD
On Fri, Mar 01, 2019 at 03:03:02PM +0100, Thomas Monjalon wrote:
> 01/03/2019 08:18, Anand Rawat:
> > Added initial stub source files for windows support and meson changes
> > to build them.
>
> Thanks for sending some new patches based on meson.
>
> Let's start review with some simple considerat
01/03/2019 08:18, Anand Rawat:
> Added initial stub source files for windows support and meson
> changes to build them.
Thanks for sending some new patches based on meson.
Let's start review with some simple considerations.
> Signed-off-by: Anand Rawat
> Signed-off-by: Kadam, Pallavi
Please a
On Thu, Feb 28, 2019 at 11:18:41PM -0800, Anand Rawat wrote:
> Helloworld example for Windows.
> Includes Windows-specific EAL changes and meson
> changes to build the code on Windows.
>
> Anand Rawat (6):
> eal: eal stub to add windows support
> eal: Add header files to support windows
> ea
From: Pavan Nikhilesh
Use mempool bulk get ops to alloc burst of packets and process them.
If bulk get fails fallback to rte_mbuf_raw_alloc.
Suggested-by: Andrew Rybchenko
Signed-off-by: Pavan Nikhilesh
---
v2 Changes:
- Use bulk ops for fetching segments. (Andrew Rybchenko)
- Fallback to
This patch changes the key pointer data types in cipher, auth,
and aead xforms from "uint8_t *" to "const uint8_t *" for a
more intuitive and safe sessionn creation.
Signed-off-by: Fan Zhang
---
Although it is a relative big patch, but I believe it is the
right thing to do towards a safer and bet
01/03/2019 13:46, Qiming Yang:
> Columbiaville requires a package to be downloaded if need advanced
> features. This patch add package download support in two ways.
> If it configured package path in devargs, will use this path,
> if not, will load the package at /lib/firmware/intel/ice/ddp/ice.pkg
On Fri, Mar 01, 2019 at 02:29:50PM +0100, Thomas Monjalon wrote:
> 31/01/2019 11:11, Phil Yang:
> > Enable native/cross compiling for Cortex-A55 and Cortex-A76 on meson.
> >
> > Signed-off-by: Phil Yang
> > Reviewed-by: Ola Liljedahl
> > Reviewed-by: Gavin Hu
> > ---
> > config/arm/arm64_armv8
31/01/2019 11:11, Phil Yang:
> Enable native/cross compiling for Cortex-A55 and Cortex-A76 on meson.
>
> Signed-off-by: Phil Yang
> Reviewed-by: Ola Liljedahl
> Reviewed-by: Gavin Hu
> ---
> config/arm/arm64_armv8_linuxapp_gcc | 2 ++
> config/arm/meson.build | 2 ++
> 2 files cha
26/02/2019 18:46, luca.bocca...@gmail.com:
> From: Luca Boccassi
>
> pcap has historically shipped a custom pcap-config binary tool which
> does the job of pkg-config. It was never compatible with cross
> compilation.
> Meson uses it when using dependency(), which then means cross
> compilation f
28/02/2019 18:40, Bruce Richardson:
> On Wed, Feb 27, 2019 at 01:53:32PM +, Bruce Richardson wrote:
> > On Wed, Feb 27, 2019 at 12:03:48PM +, Luca Boccassi wrote:
> > > On Wed, 2019-02-27 at 11:56 +0100, Thomas Monjalon wrote:
> > > > 27/02/2019 11:50, Luca Boccassi:
> > > > > On Wed, 2019-
This patch fixes a wrong link in gsg. The
Documentation/kernel-parameters.txt file from the kernel
source tree was moved quite a time ago to
Documentation/admin-guide/kernel-parameters.txt.
Fixes: 1ab07743b21b ("doc: getting started guide for linux")
Cc: sta...@dpdk.org
Signed-off-by: Rami Ro
On 2/28/2019 5:56 AM, Qi Zhang wrote:
> Increase field vector's protocol offset size from 8 bit to 16 bit.
Same comment, I can see 'off' & 'field_off' storage size increased from u8 to
u16.
But why? and what is the impact of it?
If someone from community hist a problem with this and wants to un
This patch adds dynamic SGL allocation instead of static one.
The number of element in SGL can be adjusted in each operation
depend of the request.
Signed-off-by: Tomasz Jozwiak
---
config/common_base | 1 -
doc/guides/compressdevs/qat_comp.rst | 1 -
doc/guides/cryptodevs/qa
This patch adds dynamic sgl allocation in QAT PMD and
depends on 'malloc: add rte_realloc_socket function patch'
(1551429976-16297-1-git-send-email-tomaszx.jozw...@intel.com)
which should be applied first.
Changes
-v2: added rte_realloc_socket instead of rte_realloc
-v3: fixed subject in pat
This patch fixes a wrong tag in guides/nics/features.rst.
The features tags should be, according to the
"Features Overview" section in this doc, one of the following:
"uses", "implements", "provides", or "related".
Hence in Inner RSS section, it should be "uses"
instead of "users".
Fixes: d0a87d
This patch adds dynamic SGL allocation instead of static one.
The number of element in SGL can be adjusted in each operation
depend of the request.
Signed-off-by: Tomasz Jozwiak
---
config/common_base | 1 -
doc/guides/compressdevs/qat_comp.rst | 1 -
doc/guides/cryptodevs/qa
This patch adds dynamic sgl allocation in QAT PMD and
depends on 'malloc: add rte_realloc_socket function patch'
(1551429976-16297-1-git-send-email-tomaszx.jozw...@intel.com)
which should be applied first.
Changes
-v2: added rte_realloc_socket instead of rte_realloc
Tomasz Jozwiak (1):
com
This patch adds the deprecation notice of changing Cryptodev
symmetric xform structure. The proposed change is to making
key pointers in the crypto xforms (cipher, auth, aead) to
indicate neither the library or the drivers will not change
the content of the key buffer.
Signed-off-by: Fan Zhang
--
On 01/03/2019 10:31, Thomas Monjalon wrote:
[..]
Applied
Remy, you are welcome to continue maintaining some of these libraries
with another email address if you plan to have time to dedicate.
I've considered reclaiming them in a personal capacity but I need to see
how time and/or contractual
On 2/28/2019 5:56 AM, Qi Zhang wrote:
> Resolve static analysis reported issue in
> ice_get_itr_intrl_gran and ice_ptg_find_ptype.
Same comment with previous patch, related to the commit log.
Commit log says "static analysis reported issues" are solved, what are they
really? If we know them we ca
01/03/2019 08:15, Remy Horton:
> After today I will no longer be with Intel, so I am
> removing my name from all related maintainer roles.
>
> Signed-off-by: Remy Horton
Applied
Remy, you are welcome to continue maintaining some of these libraries
with another email address if you plan to have
On 2/28/2019 5:56 AM, Qi Zhang wrote:
> Remove static of below functions and declare them as external
> APIs.
>
> ice_aq_add_vsi
> ice_aq_free_vsi
> ice_aq_update_vsi
> ice_aq_add_lan_txq
> ice_init_pkg
Hi Qi,
This is generic comment for the patchset but it is easy to demonstrate in this
patch,
Issue is observed while running 'metrics_autotest' continuously
without quiting. During first execution all test cases pass but
second run onwards first test case fails as library is already
initialized.
To resolve, introduced a new API to deinitialise the library
after all test cases are executed
Once the library usage is over, it must be deinitialized which
will free the shared memory reserved during initialization.
Fixes: observed an issue while running 'metrics_autotest'
continuously without quiting. For the first run 'metrics_autotest'
passes all test cases but second run onwards first
ACK
-Original Message-
From: Zhang, Qi Z
Sent: Wednesday, February 27, 2019 9:57 PM
To: Lu, Wenzhuo ; Yang, Qiming
Cc: Stillwell Jr, Paul M ; dev@dpdk.org; Yigit,
Ferruh ; Zhang, Qi Z ; Greenwalt,
Paul
Subject: [PATCH 22/37] net/ice/base: add RSS key related macro and structures
Add
Currently, rte_realloc will not respect original allocation's
NUMA node when memory cannot be resized, and there is no
NUMA-aware equivalent of rte_realloc. This patch adds such a function.
The new API will ensure that reallocated memory stays on
requested NUMA node, as well as allow moving alloca
On Fri, 2019-03-01 at 10:38 +0300, Andrew Rybchenko wrote:
> On 2/28/19 10:42 PM, Pavan Nikhilesh Bhagavatula wrote:
> > From: Pavan Nikhilesh
> >
> > Use mempool bulk get ops to alloc burst of packets and process them
> > instead of calling pktalloc for every packet.
> >
> > Signed-off-by: Pava
Currently, compress-perf doesn't respect incompressible
data inside one operation.
This patch adds such a functionality. Now the output buffer
in one operation is big enough to store such a data after
compression. Also added segment size checking to pass
values in right range.
Signed-off-by: Toma
When create rte_mempool, flags can be parsed from command line.
Now, it is possible for testpmd to create a af_xdp friendly
mempool (which enable zero copy).
Signed-off-by: Qi Zhang
Signed-off-by: Xiaolong Ye
---
app/test-pmd/parameters.c | 12
app/test-pmd/testpmd.c| 17 ++
Try to check if external mempool (from rx_queue_setup) is fit for
af_xdp, if it is, it will be registered to af_xdp socket directly and
there will be no packet data copy on Rx and Tx.
Signed-off-by: Xiaolong Ye
---
drivers/net/af_xdp/rte_eth_af_xdp.c | 126
1 file ch
Allow create a mempool with page size aligned base address.
Signed-off-by: Qi Zhang
Signed-off-by: Xiaolong Ye
---
lib/librte_mempool/rte_mempool.c | 3 +++
lib/librte_mempool/rte_mempool.h | 1 +
2 files changed, 4 insertions(+)
diff --git a/lib/librte_mempool/rte_mempool.c b/lib/librte_mempo
Overview
This patchset adds a new PMD driver for AF_XDP which is a proposed
faster version of AF_PACKET interface in Linux, see below links [1] [2] for
details of AF_XDP introduction:
AF_XDP roadmap
==
- AF_XDP is included in upstream kernel since 4.18, and AF_XDP support
i
Add a new PMD driver for AF_XDP which is a proposed faster version of
AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1]
[2].
This is the vanilla version PMD which just uses a raw buffer registered as
the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://
This give the option that applicaiton can configure each
memory chunk's size precisely. (by MEMPOOL_F_NO_SPREAD).
Signed-off-by: Qi Zhang
Signed-off-by: Xiaolong Ye
---
lib/librte_mbuf/rte_mbuf.c | 15 ---
lib/librte_mbuf/rte_mbuf.h | 8 +++-
2 files changed, 19 insertions(+),
Now, af_xdp registered memory buffer is managed by rte_mempool.
mbuf be allocated from rte_mempool can be convert to xdp_desc's
address and vice versa.
Signed-off-by: Xiaolong Ye
---
drivers/net/af_xdp/rte_eth_af_xdp.c | 121 +---
1 file changed, 75 insertions(+), 46 dele
100 matches
Mail list logo
