Hi, Adrien
> -Original Message-
> From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com]
> Sent: Wednesday, August 2, 2017 9:41 PM
> To: Lu, Wenzhuo
> Cc: Zhao1, Wei ; TETSURO NAKAMURA
> ; Mcnamara, John
> ; TAKADA Naoki ;
> Satoshi NISHIYAMA ; dev@dpdk.org
> Subject: Re: using rte_fl
Signed-off-by: Wenfeng Liu
---
drivers/net/af_packet/rte_eth_af_packet.c | 14 +++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/drivers/net/af_packet/rte_eth_af_packet.c
b/drivers/net/af_packet/rte_eth_af_packet.c
index 9a47852..a6cab9b 100644
--- a/drivers/net/af_pa
Signed-off-by: Wenfeng Liu
---
v2:
* Fixed coding style issues reported by checkpatch
drivers/net/af_packet/rte_eth_af_packet.c | 15 ---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/net/af_packet/rte_eth_af_packet.c
b/drivers/net/af_packet/rte_eth_af_packe
Signed-off-by: Wenfeng Liu
---
v3:
* Remove trailing whitespace
v2:
* Fixed coding style issues reported by checkpatch
drivers/net/af_packet/rte_eth_af_packet.c | 15 ---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/net/af_packet/rte_eth_af_packet.c
b/driv
Rename the structs rte_eth_txconf and rte_eth_rxconf to
rte_eth_txq_conf and rte_eth_rxq_conf respectively as those
structs represent per queue configuration.
Signed-off-by: Shahaf Shuler
---
lib/librte_ether/rte_ethdev.c | 4 ++--
lib/librte_ether/rte_ethdev.h | 24 +---
2
Tx offloads configuration is per queue. Tx offloads are enabled by default,
and can be disabled using ETH_TXQ_FLAGS_NO* flags.
This behaviour is not consistent with the Rx side where the Rx offloads
configuration is per port. Rx offloads are disabled by default and enabled
according to bit field
Introduce a new API to configure Rx offloads.
The new API will re-use existing DEV_RX_OFFLOAD_* flags
to enable the different offloads. This will ease the process
of adding a new Rx offloads, as no ABI breakage is involved.
In addition, the offload configuration can be done per queue,
instead of p
Introduce a new API to configure Tx offloads.
The new API will re-use existing DEV_TX_OFFLOAD_* flags
to enable the different offloads. This will ease the process
of adding a new Tx offloads, as no ABI breakage is involved.
In addition, the Tx offloads will be disabled by default and be
enabled pe
A new offloads API was introduced by commits:
commit 8b07fcae6061 ("ethdev: introduce Tx queue offloads API")
commit c6504557763e ("ethdev: introduce Rx queue offloads API")
In order to enable PMDs to support only one of the APIs,
and applications to avoid branching according to the underlying de
07/08/2017 05:07, Yang, Zhiyong:
> Hi, Thomas:
> Need I sent another V3 patch to update commit log according to Remy's
> suggestion?
Yes it would be better if you can do it please
In crypto latency test, when some crypto operations cannot be
enqueued, they are returned to its mempool.
However, instead of freeing the operations in the array passed
to the enqueue function, the app was freeing the operations
in the array passed to the dequeue function, leading to incorrect
resu
04/08/2017 16:20, John McNamara:
> Fix grammar, spelling and formatting of DPDK 17.08 release notes.
>
> Signed-off-by: John McNamara
Applied, thanks
Please, would you like to prepare a blank release notes for 17.11?
Hi,
06/07/2017 16:56, Keith Wiles:
> +# Locate the rte_version.h file and parse out the version strings.
I think this script is not needed because we have already
something in mk/rte.sdkconfig.mk.
Example:
% make showversion
17.08.0-rc4
Do you need more?
baremetal execution environments may have a different
method to enable RTE_INIT instead of using compiler
constructor scheme. Move RTE_INIT* definition under
exec-env to support different execution environments.
Signed-off-by: Jerin Jacob
---
app/test-eventdev/evt_test.h |
07/08/2017 05:16, Pablo de Lara:
> In crypto latency test, when some crypto operations cannot be
> enqueued, they are returned to its mempool.
> However, instead of freeing the operations in the array passed
> to the enqueue function, the app was freeing the operations
> in the array passed to the
This is an API/ABI change notice for DPDK 17.11 announcing the redefinition
of port_id. port_id is currently defined as uint8_t, which is limited to
the range 0 to 255. A larger range is required for vdev scalability.
It is necessary for a redefinition of port_id to extend it from 1 bytes to
2 byt
Hi all,
It seems some deprecation notices have not been reviewed enough.
The 17.08 release should be closed today.
Please take time to review them, even if you don't feel very concerned
at first sight. It is a community effort to approve the important changes.
There are 14 pending notices, all se
Some devices do not support reset of eth stats. An application
may need to know not to clear shadow stats if the device cannot.
rte_eth_stats_reset is updated to provide a return code to
share whether the device supports reset or not.
Signed-off-by: David Harton
---
lib/librte_ether/rte_ethdev
> On Aug 7, 2017, at 6:35 AM, Thomas Monjalon wrote:
>
> Hi,
>
> 06/07/2017 16:56, Keith Wiles:
>> +# Locate the rte_version.h file and parse out the version strings.
>
> I think this script is not needed because we have already
> something in mk/rte.sdkconfig.mk.
> Example:
> % make sho
Some devices do not support reset of eth stats. An application
may need to know not to clear shadow stats if the device cannot.
rte_eth_stats_reset is updated to provide a return code to
share whether the device supports reset or not.
Signed-off-by: David Harton
---
v2:
* Fixed soft tab issue
-Original Message-
> Date: Fri, 4 Aug 2017 13:44:02 +
> From: "Mcnamara, John"
> To: "Tan, Jianfeng" , "dev@dpdk.org"
> CC: "Tan, Jianfeng" , Thomas Monjalon
>
> Subject: Re: [dpdk-dev] [PATCH v2] doc: deprecate Xen support
>
>
>
> > -Original Message-
> > From: dev [mail
DMA window size needs to be big enough to span all memory segment's
physical addresses. We do not need multiple levels of IOMMU tables
as we already span ~70TB of physical memory with 16MB hugepages.
Signed-off-by: Jonas Pfefferle
---
lib/librte_eal/linuxapp/eal/eal_vfio.c | 25 +
> > -Original Message-
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Jianfeng Tan
> > Sent: Thursday, August 3, 2017 9:38 PM
> > To: dev@dpdk.org
> > Cc: Tan, Jianfeng ; Thomas Monjalon
> >
> > Subject: [dpdk-dev] [PATCH v2] doc: deprecate Xen support
> >
> > Following the calls
Friday, August 4, 2017 9:56 AM, Remy Horton:
> On 04/08/2017 06:27, Zhiyong Yang wrote:
> > This is an API/ABI change notice for DPDK 17.11 on redefinition of
> > port_id. port_id is defined as uint8_t by now, which is just ranged
> > from 0 to 255. For more and more scenerioes, more than 256 ports
After commit 8f094a9ac5d7 is it much harder to detect a "double free".
If the developer makes a copy of an mbuf pointer and frees it twice, this
condition is never detected and the mbuf gets returned to the pool twice.
Since this requires extra work to track, make this behavior conditional
on CONF
After commit 8f094a9ac5d7 ("mbuf: set mbuf fields while in pool") is it
much harder to detect a "double free". If the developer makes a copy
of an mbuf pointer and frees it twice, this condition is never detected
and the mbuf gets returned to the pool twice.
Since this requires extra work to trac
07/08/2017 15:17, Wiles, Keith:
>
> > On Aug 7, 2017, at 6:35 AM, Thomas Monjalon wrote:
> >
> > Hi,
> >
> > 06/07/2017 16:56, Keith Wiles:
> >> +# Locate the rte_version.h file and parse out the version strings.
> >
> > I think this script is not needed because we have already
> > something i
> 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,
>>>
>>> 06/07/2017 16:56, Keith Wiles:
+# Locate the rte_version.h file and parse out the version strings.
>>>
>>> I think thi
Some devices do not support reset of eth stats. An application may
need to know not to clear shadow stats if the device cannot.
rte_eth_stats_reset is updated to provide a return code to share
whether the device supports reset or not.
Signed-off-by: David Harton
---
v3:
* overcame noob errors
04/08/2017 07:26, Hemant Agrawal:
> On 8/3/2017 9:02 PM, Akhil Goyal wrote:
> > Support for security operations is planned to be added
> > in ethdev and cryptodev for the 17.11 release.
> >
> > For this following changes are required.
> > - rte_cryptodev and rte_eth_dev structures need to be added
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> 04/08/2017 07:26, Hemant Agrawal:
> > On 8/3/2017 9:02 PM, Akhil Goyal wrote:
> > > Support for security operations is planned to be added in ethdev and
> > > cryptodev for the 17.11 release.
> > >
> > > For this following changes are required.
> > > The replacement function rte_log_get_level() has just been implemented in
> > > 17.08. Better to postpone the removal of legacy functions to 17.11.
> > >
> > > Fixes: 4f0981e6ec6c ("eal: deprecate log functions")
> > > Cc: olivier.m...@6wind.com
> > >
> > > Signed-off-by: Thomas Monjalon
> On Jul 6, 2017, at 8:07 AM, Stephen Hemminger
> wrote:
>
> VMBUS support will use GUID in eth_dev_data name field which requires
> at least 37 characters. Plan for increase in size now.
>
> Signed-off-by: Stephen Hemminger
> ---
> doc/guides/rel_notes/deprecation.rst | 4
> 1 file chang
12/07/2017 01:25, Jan Blunck:
> The enum rte_devtype will need to get extended every time we add a bus.
> Mark all related functions as deprecated for 17.11.
>
> Signed-off-by: Jan Blunck
> ---
> --- a/doc/guides/rel_notes/deprecation.rst
> +++ b/doc/guides/rel_notes/deprecation.rst
> +* devargs:
09/07/2017 11:28, Jan Blunck:
> Add deprecation notice necessary to do devargs refactoring for 17.11.
>
> Signed-off-by: Jan Blunck
> ---
> --- a/doc/guides/rel_notes/deprecation.rst
> +++ b/doc/guides/rel_notes/deprecation.rst
> +* devargs: An ABI change is planned for 17.11 for the structure
>
> > These changes have been implemented.
> >
> > Signed-off-by: Gaetan Rivet
>
> Acked-by: John McNamara
Applied and merged with http://dpdk.org/dev/patchwork/patch/27443/
04/08/2017 15:29, Gaetan Rivet:
> Signed-off-by: Gaetan Rivet
> ---
> --- a/doc/guides/rel_notes/deprecation.rst
> +++ b/doc/guides/rel_notes/deprecation.rst
> +* eal: several API and ABI changes are planned for ``rte_devargs`` in v17.11.
> + The format of device command line parameters will chan
> > > Following the calls on the mailing list:
> > > http://dpdk.org/ml/archives/dev/2017-June/068151.html
> > > The Technical Board decided to drop Xen dom0 support from EAL:
> > > http://dpdk.org/ml/archives/dev/2017-June/068615.html
> > >
> > > Signed-off-by: Thomas Monjalon
> > > Signed-o
> > > > When we run DPDK on guest or VFIO mode on host,
> > > > the dpdk library or device will not be directly accessing
> > > > the physical address. Instead, the device does go through
> > > > an IO address translation memory management unit. On x86,
> > > > we call it as IOMMU and on ARM as SMM
> > > An API/ABI change is planned for 17.11 to change following
> > >
> > > * Remove unused flag param from rte_mempool_generic_get and _put.
> > > * Change data type for mempool 'flag' from int to unsigned int.
> > > Refer [1].
> > > * Add struct rte_mempool * param into func rte_mempool_xmem_
> -Original Message-
> From: Yang, Zhiyong
> Sent: Monday, August 7, 2017 8:43 PM
> To: dev@dpdk.org
> Cc: Tan, Jianfeng ; y...@fridaylinux.org;
> jerin.ja...@caviumnetworks.com; tho...@monjalon.net; Horton, Remy
> ; Yang, Zhiyong
> Subject: [PATCH v3] doc: announce API and ABI change for
Tuesday, August 8, 2017 1:20 AM, Yongseok Koh:
> > On Jul 6, 2017, at 8:07 AM, Stephen Hemminger
> wrote:
> >
> > VMBUS support will use GUID in eth_dev_data name field which requires
> > at least 37 characters. Plan for increase in size now.
> >
> > Signed-off-by: Stephen Hemminger
> > ---
> > d
Monday, August 7, 2017 9:07 PM, Boris Pismenny:
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > 04/08/2017 07:26, Hemant Agrawal:
> > > On 8/3/2017 9:02 PM, Akhil Goyal wrote:
> > > > Support for security operations is planned to be added in ethdev
> > > > and cryptodev for the 17.11 rel
Add a mode type check for MAC VLAN mode, if fdir is
in this mode, it do not need to do Sanity check for x550.
Fixes: dc0c16105d2d2 ("ixgbe: fix X550 flow director check")
Signed-off-by: Wei Zhao
Signed-off-by: root
---
drivers/net/ixgbe/ixgbe_fdir.c | 3 ++-
1 file changed, 2 insertions(+), 1
Add a mode type check for MAC VLAN mode, if fdir is
in this mode, it do not need to do Sanity check for x550.
Fixes: dc0c16105d2d2 ("ixgbe: fix X550 flow director check")
Signed-off-by: Wei Zhao
---
drivers/net/ixgbe/ixgbe_fdir.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --
Hi Pablo/Declan,
On 8/4/2017 8:55 PM, De Lara Guarch, Pablo wrote:
-Original Message-
From: Akhil Goyal [mailto:akhil.go...@nxp.com]
Sent: Thursday, August 3, 2017 4:32 PM
To: dev@dpdk.org; Doherty, Declan ;
tho...@monjalon.net; Nicolau, Radu ;
avia...@mellanox.com; bor...@mellanox.co
46 matches
Mail list logo
