On 03/25/2018 07:20 PM, Andrew Rybchenko wrote:
Populate mempool driver callback is executed a bit later than
register memory area, provides the same information and will
substitute the later since it gives more flexibility and in addition
to notification about memory area allows to customize how
Hi Ajit/Scott,
On 3/26/2018 12:37 AM, Ajit Khaparde wrote:
From: Scott Branden
Update the license header on bnxt files to be the standard
BSD-3-Clause license used for the rest of DPDK,
bring the files in compliance with the DPDK licensing policy.
Signed-off-by: Scott Branden
Signed-off-by:
Hi Ferruh,
On Wed, Mar 21, 2018 at 07:25:57PM +, Ferruh Yigit wrote:
> On 3/8/2018 7:07 PM, Pavan Nikhilesh wrote:
> > Use the new Rx/Tx offload APIs and remove the old style offloads.
> >
> > Signed-off-by: Pavan Nikhilesh
> > ---
> >
> > Checkpatch reports falsepositive for PRIx64
> >
> >
On 3/24/2018 8:46 PM, Anatoly Burakov wrote:
Signed-off-by: Anatoly Burakov
Suggested-by: Jianfeng Tan
Acked-by: Jianfeng Tan
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Zhang, Qi Z
> Sent: Tuesday, March 20, 2018 6:02 PM
> To: wangyunjian; dev@dpdk.org; Rybalchenko, Kirill
> Cc: ca...@huawei.com
> Subject: Re: [dpdk-dev] [PATCH v4] net/i40e: fix intr callback unregister by
> addi
Move commonly used functions across mempool, event and net devices to a
common folder in drivers.
Signed-off-by: Pavan Nikhilesh
---
drivers/common/Makefile| 4 ++
drivers/common/meson.build | 1 +
drivers/common/octeontx/Makefile
Add driver/common folder and skeleton makefile for adding commonly used
functions across mempool, event and net devices.
Signed-off-by: Pavan Nikhilesh
---
v3 Changes:
- Fix common lib naming scheme.
v2 Changes:
- Removed dependency on bus.
Based on discussion on ml
http://dpdk.org/ml/ar
> -Original Message-
> From: Jay Zhou [mailto:jianjay.z...@huawei.com]
> Sent: Sunday, March 25, 2018 9:34 AM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo ; Zhang, Roy Fan
> ; tho...@monjalon.net;
> arei.gong...@huawei.com; Zeng, Xin ;
> weidong.hu...@huawei.com; wangxinxin.w...@huawei.
> -Original Message-
> From: Tomasz Duszynski [mailto:t...@semihalf.com]
> Sent: Wednesday, March 14, 2018 1:13 PM
> To: dev@dpdk.org
> Cc: Richardson, Bruce ; De Lara Guarch, Pablo
> ; Doherty, Declan
> ; Tomasz Duszynski ;
> sta...@dpdk.org
> Subject: [PATCH v2] test/crypto: add MRVL to
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Neil Horman
> Sent: Saturday, March 24, 2018 2:09 AM
> To: Richardson, Bruce
> Cc: Yigit, Ferruh ; Mcnamara, John
> ; Kovacevic, Marko
> ; Thomas Monjalon ; Pattan,
> Reshma ; dev@dpdk.org
> Subject: Re: [dpdk-
On 3/23/2018 5:34 PM, Shreyansh Jain wrote:
Signed-off-by: Shreyansh Jain
---
config/common_base| 5 -
config/defconfig_arm64-dpaa2-linuxapp-gcc | 8 -
doc/guides/nics/dpaa2.rst | 42 +++--
drivers/net/dpaa2/Makefile| 6 -
dr
On 3/23/2018 5:34 PM, Shreyansh Jain wrote:
Signed-off-by: Shreyansh Jain
---
drivers/mempool/dpaa2/Makefile| 6 ---
drivers/mempool/dpaa2/dpaa2_hw_mempool.c | 60 +--
drivers/mempool/dpaa2/dpaa2_hw_mempool_logs.h | 38 +
3 file
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Monday, March 26, 2018 3:46 AM
> To: Zhang, Qi Z ; tho...@monjalon.net
> Cc: dev@dpdk.org; Xing, Beilei ; Wu, Jingjing
> ; Lu, Wenzhuo
> Subject: RE: [PATCH v3 3/3] net/i40e: enable runtime queue setup
>
> Hi Qi,
>
> >
> > Expose
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Tomasz Duszynski
> Sent: Wednesday, March 21, 2018 9:45 AM
> To: dev@dpdk.org
> Cc: d...@marvell.com; nsams...@marvell.com; j...@semihalf.com;
> jianbo@arm.com; De Lara Guarch, Pablo
> ; sta...@dpdk.org; Tomas
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Monday, March 26, 2018 9:29 AM
> To: 'Tomasz Duszynski' ; dev@dpdk.org
> Cc: Richardson, Bruce ; Doherty, Declan
> ; sta...@dpdk.org
> Subject: RE: [PATCH v2] test/crypto: add MRVL to hash test cases
>
>
>
> > -Original Mes
The patch let etherdev driver expose the capability flag through
rte_eth_dev_info_get when it support runtime queue configuraiton,
then base on the flag rte_eth_[rx|tx]_queue_setup could decide
continue to setup the queue or just return fail when device already
started.
Signed-off-by: Qi Zhang
--
According to exist implementation,rte_eth_[rx|tx]_queue_setup will
always return fail if device is already started(rte_eth_dev_start).
This can't satisfied the usage when application want to deferred setup
part of the queues while keep traffic running on those queues already
be setup.
example:
rt
Add new command to setup queue:
queue setup (rx|tx) (port_id) (queue_idx) (ring_size) (offloads)
rte_eth_[rx|tx]_queue_setup will be called corresponsively
Signed-off-by: Qi Zhang
---
v4:
- fix missing offload in command line.
v3:
- add offload parameter to queue setup command.
- couple code r
Expose the runtime queue configuration capability and enhance
i40e_dev_[rx|tx]_queue_setup to handle the situation when
device already started.
Signed-off-by: Qi Zhang
---
v4:
- fix rx/tx conflict check.
- no need conflict check for first rx/tx queue at runtime setup.
v3:
- no queue start/stop
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Trahe, Fiona
> Sent: Friday, March 9, 2018 6:18 PM
> To: Lee Roberts ; Griffin, John
> ; Jain, Deepak K
> Cc: dev@dpdk.org; Trahe, Fiona
> Subject: Re: [dpdk-dev] [PATCH] assign QAT cryptodev to correct NUMA
> n
Hi Maxime,
> -Original Message-
> From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
> Sent: Sunday, March 25, 2018 5:51 PM
> To: Wang, Xiao W ; dev@dpdk.org
> Cc: Wang, Zhihong ; y...@fridaylinux.org; Liang,
> Cunming ; Xu, Rosen ; Chen,
> Junjie J ; Daly, Dan
> Subject: Re: [PATC
On Sun, Mar 25, 2018 at 08:19:29PM +, Ophir Munk wrote:
> Previous to this commit mlx4 CRC stripping was executed by default and
> there was no verbs API to disable it.
>
> Signed-off-by: Ophir Munk
> ---
> v1: initial version
> v2: following internal reviews
> v3: following dpdk.org mailing
On Sun, Mar 25, 2018 at 09:17:20PM +0300, Vladimir Medvedkin wrote:
> Hi,
>
> 2018-03-14 14:09 GMT+03:00 Bruce Richardson :
>
> > On Wed, Feb 21, 2018 at 09:44:54PM +, Medvedkin Vladimir wrote:
> > > RIB is an alternative to current LPM library.
> > > It solves the following problems
> > > -
This patch adds external backend support to vhost library. The patch provides
new APIs for the external backend to register private data, plus pre and post
vhost-user message handlers.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/rte_vhost.h | 45 ++-
li
This patch adds session message handler to vhost crypto.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/vhost_crypto.c | 428
1 file changed, 428 insertions(+)
create mode 100644 lib/librte_vhost/vhost_crypto.c
diff --git a/lib/librte_vhost/vhost_crypto.
This patchset adds crypto backend suppport to vhost_user library,
including a proof-of-concept sample application. The implementation
follows the virtio-crypto specification and have been tested
with qemu 2.11.50 (with several patches applied, detailed later)
with Fedora 24 running in the frontend.
This patch adds public head file API for vhost crypto.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/rte_vhost_crypto.h | 125
1 file changed, 125 insertions(+)
create mode 100644 lib/librte_vhost/rte_vhost_crypto.h
diff --git a/lib/librte_vhost/rte_vhost_c
This patch adds virtio-crypto spec user message structure to
vhost_user.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/vhost_user.h | 36
1 file changed, 32 insertions(+), 4 deletions(-)
diff --git a/lib/librte_vhost/vhost_user.h b/lib/librte_vhost/vhost_use
This patch adds the implementation that parses virtio crypto request
to dpdk crypto operation.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/vhost_crypto.c | 593
1 file changed, 593 insertions(+)
diff --git a/lib/librte_vhost/vhost_crypto.c b/lib/librte
This patch adds public API implementation to vhost crypto.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/vhost_crypto.c | 248
1 file changed, 248 insertions(+)
diff --git a/lib/librte_vhost/vhost_crypto.c b/lib/librte_vhost/vhost_crypto.c
index 1d85829.
This patch updates the Makefile of vhost library to enable vhost crypto
compiling.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/Makefile| 6 --
lib/librte_vhost/meson.build | 8
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/lib/librte_vhost/Makefile b/lib/librt
Signed-off-by: Fan Zhang
---
lib/librte_vhost/rte_vhost_version.map | 11 +++
1 file changed, 11 insertions(+)
diff --git a/lib/librte_vhost/rte_vhost_version.map
b/lib/librte_vhost/rte_vhost_version.map
index df01031..935eebd 100644
--- a/lib/librte_vhost/rte_vhost_version.map
+++ b/li
On Sun, Mar 25, 2018 at 09:35:35PM +0300, Vladimir Medvedkin wrote:
> 2018-03-15 17:27 GMT+03:00 Bruce Richardson :
>
> > On Thu, Feb 22, 2018 at 10:50:55PM +, Medvedkin Vladimir wrote:
> > > RIB is an alternative to current LPM library.
> > > It solves the following problems
> > > - Increase
This patch adds vhost_crypto sample application to DPDK.
Signed-off-by: Fan Zhang
---
examples/vhost_crypto/Makefile | 32 +++
examples/vhost_crypto/main.c | 598 +
2 files changed, 630 insertions(+)
create mode 100644 examples/vhost_crypto/Makefile
c
Signed-off-by: Fan Zhang
---
doc/guides/prog_guide/vhost_lib.rst | 21
doc/guides/sample_app_ug/index.rst| 1 +
doc/guides/sample_app_ug/vhost_crypto.rst | 84 +++
3 files changed, 106 insertions(+)
create mode 100644 doc/guides/sample_app_ug/v
RSS hash key must be 40 Bytes long.
Cc: sta...@dpdk.org
Signed-off-by: Shahaf Shuler
---
drivers/net/mlx5/mlx5_ethdev.c | 3 ++-
drivers/net/mlx5/mlx5_rss.c| 7 +++
2 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/net/mlx5/mlx5_ethdev.c b/drivers/net/mlx5/mlx5_ethde
On Mon, Mar 19, 2018 at 04:33:27PM +0800, Tiwei Bie wrote:
On Fri, Mar 16, 2018 at 04:21:09PM +0100, Jens Freimann wrote:
[...]
diff --git a/drivers/net/virtio/virtio_user_ethdev.c
b/drivers/net/virtio/virtio_user_ethdev.c
index 2636490..ee291b3 100644
--- a/drivers/net/virtio/virtio_user_ethde
The RSS key length returned by rte_eth_dev_info_get command was taken
from the
PMD private structure. This structure initialization was done only after
the port configuration.
Considering Mellanox device supports only 40B long RSS key, reporting
the fixed number instead.
Fixes: 29c1d8bb3e79 ("net
About hot plug in dpdk, We already have proactive way to add/remove devices
through APIs (rte_eal_hotplug_add/remove), and also have fail-safe driver to
offload the fail-safe work from the app user. But there are still lack of a
general mechanism to monitor hotplug event for all driver, now the hot
Use testpmd for example, to show an application how to use device event
mechanism to monitor the hotplug event, involve both hot removal event
and the hot insertion event.
The process is that, testpmd first enable hotplug monitoring and register
the user's callback, when device being hotplug inser
This patch aims to add a general device event monitor mechanism at
EAL device layer, for device hotplug awareness and actions adopted
accordingly. It could also expand for all other type of device event
monitor, but not in this scope at the stage.
To get started, users firstly register or unregist
Add new interrupt handle type of RTE_INTR_HANDLE_DEV_EVENT, for
device event interrupt monitor.
Signed-off-by: Jeff Guo
---
v16->v15:
split into small patch base on the function
---
lib/librte_eal/common/include/rte_eal_interrupts.h | 1 +
lib/librte_eal/linuxapp/eal/eal_interrupts.c | 5 +
Use the new Rx/Tx offload APIs and remove the old style offloads.
Signed-off-by: Pavan Nikhilesh
Acked-by: Santosh Shukla
---
drivers/net/octeontx/octeontx_ethdev.c | 82 +-
drivers/net/octeontx/octeontx_ethdev.h | 3 ++
2 files changed, 65 insertions(+), 20 del
On Mon, Mar 26, 2018 at 01:12:18PM +0300, Shahaf Shuler wrote:
> RSS hash key must be 40 Bytes long.
>
> Cc: sta...@dpdk.org
>
> Signed-off-by: Shahaf Shuler
> ---
> drivers/net/mlx5/mlx5_ethdev.c | 3 ++-
> drivers/net/mlx5/mlx5_rss.c| 7 +++
> 2 files changed, 9 insertions(+), 1 delet
About hot plug in dpdk, We already have proactive way to add/remove devices
through APIs (rte_eal_hotplug_add/remove), and also have fail-safe driver
to offload the fail-safe work from the app user. But there are still lack
of a general mechanism to monitor hotplug event for all driver, now the
hot
Use testpmd for example, to show an application how to use device event
mechanism to monitor the hotplug event, involve both hot removal event
and the hot insertion event.
The process is that, testpmd first enable hotplug monitoring and register
the user's callback, when device being hotplug inser
Add new interrupt handle type of RTE_INTR_HANDLE_DEV_EVENT, for
device event interrupt monitor.
Signed-off-by: Jeff Guo
---
v16->v15:
split into small patch base on the function
---
lib/librte_eal/common/include/rte_eal_interrupts.h | 1 +
lib/librte_eal/linuxapp/eal/eal_interrupts.c | 5 +
This patch aims to add a general device event monitor mechanism at
EAL device layer, for device hotplug awareness and actions adopted
accordingly. It could also expand for all other type of device event
monitor, but not in this scope at the stage.
To get started, users firstly register or unregist
In order to handle the uevent which have been detected from the kernel
side, add uevent parse and process function to translate the uevent into
device event, which user has subscribe to monitor.
Signed-off-by: Jeff Guo
---
1.move all linux specific together
---
lib/librte_eal/linuxapp/eal/eal_de
On Fri, Mar 23, 2018 at 02:12:36PM +0100, Gaëtan Rivet wrote:
> On Fri, Mar 23, 2018 at 07:54:11AM -0400, Neil Horman wrote:
> > On Fri, Mar 23, 2018 at 10:31:22AM +0100, Gaëtan Rivet wrote:
> > > On Thu, Mar 22, 2018 at 08:53:49PM -0400, Neil Horman wrote:
> > > > On Thu, Mar 22, 2018 at 05:27:51P
On Mon, Mar 26, 2018 at 01:12:19PM +0300, Shahaf Shuler wrote:
> The RSS key length returned by rte_eth_dev_info_get command was taken
> from the
> PMD private structure. This structure initialization was done only after
> the port configuration.
>
> Considering Mellanox device supports only 40B l
On 3/25/2018 9:19 PM, Ophir Munk wrote:
> Previous to this commit mlx4 CRC stripping was executed by default and
> there was no verbs API to disable it.
Are you aware of the discussion about CRC [1]? Is this patch compatible with
plans?
[1]
https://dpdk.org/dev/patchwork/patch/36415/
> Signed-o
On Fri, Mar 23, 2018 at 07:45:03PM +0100, Gaetan Rivet wrote:
> Signed-off-by: Gaetan Rivet
> ---
>
> Cc: Neil Horman
>
I'm actually ok with this, but as Keith noted, I'm not sure why you didn't just:
1) Add the ability to create a grouping key, so that key value pairs could
contain a list of
On Thu, Mar 22, 2018 at 10:42:44AM +, Xueming(Steven) Li wrote:
> Just remind, denying unsupported hash function in rte_eth_dev_configure()
> might
> impact some user app using PMD that simply ignoring them silently.
If the default behavior from other devices is to use only possible
values, t
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Saturday, March 24, 2018 1:02 AM
> To: Trahe, Fiona
> Cc: dev@dpdk.org; ahmed.mans...@nxp.com; shally.ve...@cavium.com; De Lara
> Guarch, Pablo
> ; fiona.tr...@gmail.com
> Subject: Re: [dpdk-dev] [PATCH] c
On Mon, Mar 26, 2018 at 12:38:22PM +0100, Ferruh Yigit wrote:
> On 3/25/2018 9:19 PM, Ophir Munk wrote:
> > Previous to this commit mlx4 CRC stripping was executed by default and
> > there was no verbs API to disable it.
>
> Are you aware of the discussion about CRC [1]? Is this patch compatible w
> From: Ma, Liang J
> Sent: Tuesday, March 13, 2018 11:34 AM
> To: jerin.ja...@caviumnetworks.com
> Cc: dev@dpdk.org; Van Haaren, Harry ; Jain, Deepak
> K ; Geary, John ; Mccarthy,
> Peter
> Subject: [PATCH] event/opdl: fix atomic queue race condition issue
>
> If application link one atomic queu
26/03/2018 13:54, Adrien Mazarguil:
> On Mon, Mar 26, 2018 at 12:38:22PM +0100, Ferruh Yigit wrote:
> > On 3/25/2018 9:19 PM, Ophir Munk wrote:
> > > Previous to this commit mlx4 CRC stripping was executed by default and
> > > there was no verbs API to disable it.
> >
> > Are you aware of the disc
Meeting notes for the DPDK technical board meeting
held on 2018-02-28
Attendees:
- Bruce Richardson
- Ferruh Yigit
- Hemant Agrawal
- Konstantin Ananyev
- Olivier Matz
- Stephen Hemminger
- Thomas Monjalon
- Yuanhan Liu
1/ There was an approval to publish the draft for Windows port in
htt
Meeting notes for the DPDK technical board meeting
held on 2018-03-14
Attendees:
- Bruce Richardson
- Ferruh Yigit
- Hemant Agrawal
- Jerin Jacob
- Konstantin Ananyev
- Olivier Matz
- Stephen Hemminger
- Thomas Monjalon
- Yuan
From: Roman Zhukov
Add support of choice the preferred firmware variant to use in device
parameters.
Signed-off-by: Roman Zhukov
Signed-off-by: Andrew Rybchenko
---
doc/guides/nics/sfc_efx.rst | 15 ++
drivers/net/sfc/sfc.c| 123 ++-
drive
From: Roman Zhukov
Signed-off-by: Roman Zhukov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx.h | 7 +++
drivers/net/sfc/base/efx_nic.c | 12
2 files changed, 19 insertions(+)
diff --git a/drivers/net/sfc/base/efx.h b/drivers/net/sfc/base/efx.h
index 499474
From: Gautam Dawar
Signed-off-by: Gautam Dawar
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx.h | 15 ++-
drivers/net/sfc/base/efx_impl.h | 1 +
drivers/net/sfc/base/efx_mcdi.c | 14 ++
drivers/net/sfc/base/efx_nic.c | 23 ++-
dr
Patch 'net/sfc: add device parameter to choose FW variant' has
checkpatches.sh warning since positive errno is used inside the driver.
Gautam Dawar (1):
net/sfc/base: add support to choose firmware variant
Roman Zhukov (2):
net/sfc/base: add values for RxDPCPU firmware id recognition
net/sf
On 03/26/2018 11:05 AM, Wang, Xiao W wrote:
Hi Maxime,
-Original Message-
From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
Sent: Sunday, March 25, 2018 5:51 PM
To: Wang, Xiao W ; dev@dpdk.org
Cc: Wang, Zhihong ; y...@fridaylinux.org; Liang,
Cunming ; Xu, Rosen ; Chen,
Junjie
On 26 Mar 05:29, Van Haaren, Harry wrote:
> > From: Ma, Liang J
> > Sent: Tuesday, March 13, 2018 11:34 AM
> > To: jerin.ja...@caviumnetworks.com
> > Cc: dev@dpdk.org; Van Haaren, Harry ; Jain,
> > Deepak
> > K ; Geary, John ; Mccarthy,
> > Peter
> > Subject: [PATCH] event/opdl: fix atomic queue
Hi Neil,
On Mon, Mar 26, 2018 at 07:38:19AM -0400, Neil Horman wrote:
> On Fri, Mar 23, 2018 at 07:45:03PM +0100, Gaetan Rivet wrote:
> > Signed-off-by: Gaetan Rivet
> > ---
> >
> > Cc: Neil Horman
> >
Keep in mind that all of this is to achieve the trivial task I was
doing in 20 lines or so.
On 3/24/2018 8:46 PM, Anatoly Burakov wrote:
This API is similar to the blocking API that is already present,
but reply will be received in a separate callback by the caller
(callback specified at the time of request, rather than registering
for it in advance).
Under the hood, we create a sepa
On 26-Mar-18 3:15 PM, Tan, Jianfeng wrote:
On 3/24/2018 8:46 PM, Anatoly Burakov wrote:
This API is similar to the blocking API that is already present,
but reply will be received in a separate callback by the caller
(callback specified at the time of request, rather than registering
for it in
From: Natalie Samsonov
The name "mrvl" for Marvell PMD driver for PPv2 Marvell PPv2
(Packet Processor v2) 1/10 Gbps adapter is too generic and causes
problem for adding new PMD drivers for other Marvell devices.
Changed to "mvpp2" for specific Marvell PPv2 PMD.
This patch doesn't introduce any c
> On Mar 26, 2018, at 8:59 AM, Gaëtan Rivet wrote:
>
> Hi Neil,
>
> On Mon, Mar 26, 2018 at 07:38:19AM -0400, Neil Horman wrote:
>> On Fri, Mar 23, 2018 at 07:45:03PM +0100, Gaetan Rivet wrote:
>>> Signed-off-by: Gaetan Rivet
>>> ---
>>>
>>> Cc: Neil Horman
>>>
>
> Keep in mind that all o
The callback allows to customize how objects are stored in the
memory chunk. Default implementation of the callback which simply
puts objects one by one is available.
Suggested-by: Olivier Matz
Signed-off-by: Andrew Rybchenko
---
v2 -> v3:
- none
v1 -> v2:
- fix memory leak if off is bigger t
Callback to populate pool objects has all required information and
executed a bit later than register memory area callback.
Signed-off-by: Andrew Rybchenko
---
v2 -> v3:
- none
v1 -> v2
- none
drivers/mempool/octeontx/rte_mempool_octeontx.c | 25 ++---
1 file changed, 10
The patch series should be applied on top of [7].
The initial patch series [1] is split into two to simplify processing.
The second series relies on this one and will add bucket mempool driver
and related ops.
The patch series has generic enhancements suggested by Olivier.
Basically it adds drive
Populate mempool driver callback is executed a bit later than
register memory area, provides the same information and will
substitute the later since it gives more flexibility and in addition
to notification about memory area allows to customize how mempool
objects are stored in memory.
Signed-off
Flag MEMPOOL_F_NO_PHYS_CONTIG is renamed as MEMPOOL_F_NO_IOVA_CONTIG
to follow IO memory contiguos terminology.
MEMPOOL_F_NO_PHYS_CONTIG is kept for backward compatibility and
deprecated.
Suggested-by: Olivier Matz
Signed-off-by: Andrew Rybchenko
---
v2 -> v3:
- none
v1 -> v2:
- added in v2 a
The callback was introduced to let generic code to know octeontx
mempool driver requirements to use single physically contiguous
memory chunk to store all objects and align object address to
total object size. Now these requirements are met using a new
callbacks to calculate required memory chunk s
Move rte_mempool_xmem_size() code to internal helper function
since it is required in two places: deprecated rte_mempool_xmem_size()
and non-deprecated rte_mempool_op_calc_mem_size_default().
Suggested-by: Olivier Matz
Signed-off-by: Andrew Rybchenko
---
v2 -> v3:
- none
v1 -> v2:
- deprecate
Fixes: 84121f197187 ("mempool: store memory chunks in a list")
Cc: sta...@dpdk.org
Suggested-by: Olivier Matz
Signed-off-by: Andrew Rybchenko
---
v2 -> v3:
- none
v1 -> v2:
- added in v2 as discussed in [1]
[1] https://dpdk.org/ml/archives/dev/2018-March/093329.html
lib/librte_mempool/rte_
From: "Artem V. Andreev"
Callback to calculate required memory area size may require mempool
driver data to be already allocated and initialized.
Signed-off-by: Artem V. Andreev
Signed-off-by: Andrew Rybchenko
---
v2 -> v3:
- none
v1 -> v2:
- add init check to mempool_ops_alloc_once()
- mo
The callback is not required any more since there is a new callback
to populate objects using provided memory area which provides
the same information.
Signed-off-by: Andrew Rybchenko
---
v2 -> v3:
- none
v1 -> v2:
- none
RFCv2 -> v1:
- advertise ABI changes in release notes
doc/guides/rel
From: "Artem V. Andreev"
Mempool get/put API cares about cache itself, but sometimes it is
required to flush the cache explicitly.
The function is moved in the file since it now requires
rte_mempool_default_cache().
Signed-off-by: Artem V. Andreev
Signed-off-by: Andrew Rybchenko
---
v2 -> v3:
From: "Artem V. Andreev"
Primarily, it is intended as a way for the mempool driver to provide
additional information on how it lays up objects inside the mempool.
Signed-off-by: Artem V. Andreev
Signed-off-by: Andrew Rybchenko
---
lib/librte_mempool/rte_mempool.h | 41 ++
From: "Artem V. Andreev"
Signed-off-by: Artem V. Andreev
Signed-off-by: Andrew Rybchenko
---
drivers/mempool/bucket/rte_mempool_bucket.c | 52 +
1 file changed, 52 insertions(+)
diff --git a/drivers/mempool/bucket/rte_mempool_bucket.c
b/drivers/mempool/bucket/rte_
Size of memory chunk required to populate mempool objects depends
on how objects are stored in the memory. Different mempool drivers
may have different requirements and a new operation allows to
calculate memory size in accordance with driver requirements and
advertise requirements on minimum memor
From: "Artem V. Andreev"
Signed-off-by: Artem V. Andreev
Signed-off-by: Andrew Rybchenko
---
drivers/mempool/bucket/rte_mempool_bucket.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/drivers/mempool/bucket/rte_mempool_bucket.c
b/drivers/mempool/bucket/rte_mempool_bucket.c
Signed-off-by: Andrew Rybchenko
---
doc/guides/rel_notes/release_18_05.rst | 9 +
1 file changed, 9 insertions(+)
diff --git a/doc/guides/rel_notes/release_18_05.rst
b/doc/guides/rel_notes/release_18_05.rst
index 016c4ed..c578364 100644
--- a/doc/guides/rel_notes/release_18_05.rst
+++ b
The initial patch series [1] (RFCv1 is [2]) is split into two to simplify
processing. It is the second part which relies on the first one [3].
It should be applied on top of [4] and [3].
The patch series adds bucket mempool driver which allows to allocate
(both physically and virtually) contiguo
From: "Artem V. Andreev"
The manager provides a way to allocate physically and virtually
contiguous set of objects.
Signed-off-by: Artem V. Andreev
Signed-off-by: Andrew Rybchenko
---
MAINTAINERS| 9 +
config/common_base
From: "Artem V. Andreev"
If mempool manager supports object blocks (physically and virtual
contiguous set of objects), it is sufficient to get the first
object only and the function allows to avoid filling in of
information about each block member.
Signed-off-by: Artem V. Andreev
Signed-off-by:
On 2/6/2018 10:33 AM, zhouyangchao wrote:
> Physical addresses in the fifo named alloc_q need to be traversed to
> release in user space. The physical address to the virtual address
> conversion in kernel space is much better.
Yes current approach should be slower but this is not in data path, thi
On 3/21/2018 6:06 PM, Ajit Khaparde wrote:
> From: Darren Edamura
>
> Probe function should exit immediately if pcie bridge detected
>
> Signed-off-by: Darren Edamura
> Signed-off-by: Rahul Gupta
> Signed-off-by: Scott Branden
> Signed-off-by: Ajit Khaparde
> ---
> lib/librte_eal/linuxapp/i
Hi Ferruh,
On 18-03-26 10:24 AM, Ferruh Yigit wrote:
On 3/21/2018 6:06 PM, Ajit Khaparde wrote:
From: Darren Edamura
Probe function should exit immediately if pcie bridge detected
Signed-off-by: Darren Edamura
Signed-off-by: Rahul Gupta
Signed-off-by: Scott Branden
Signed-off-by: Ajit Kh
> -Original Message-
> From: Yongseok Koh [mailto:ys...@mellanox.com]
> Sent: Thursday, March 22, 2018 7:38 PM
<..>
> >
> > Signed-off-by: Allain Legacy
> > Signed-off-by: Nelio Laranjeiro
> > ---
>
> Dahir, Allain
>
> Did you get a chance to test this patch? It would be good to have '
On 3/26/2018 7:05 PM, Scott Branden wrote:
> Hi Ferruh,
>
>
> On 18-03-26 10:24 AM, Ferruh Yigit wrote:
>> On 3/21/2018 6:06 PM, Ajit Khaparde wrote:
>>> From: Darren Edamura
>>>
>>> Probe function should exit immediately if pcie bridge detected
>>>
>>> Signed-off-by: Darren Edamura
>>> Signed-
On 2/27/2018 7:20 AM, Jeff Guo wrote:
> udev could not detect remove and add event of device when hotplug in
> and out devices, that related with the fix about using pointer of
> rte_uio_pci_dev as dev_id instead of uio_device for irq device handler,
> that would result igb uio irq failure when ker
On 2/27/2018 3:11 PM, Olivier Matz wrote:
> Change the prototype and the behavior of dev_ops->eth_mac_addr_set(): a
> return code is added to notify the caller (librte_ether) if an error
> occurred in the PMD.
>
> The new default MAC address is now copied in dev->data->mac_addrs[0]
> only if the o
On 18-03-26 11:20 AM, Ferruh Yigit wrote:
On 3/26/2018 7:05 PM, Scott Branden wrote:
Hi Ferruh,
On 18-03-26 10:24 AM, Ferruh Yigit wrote:
On 3/21/2018 6:06 PM, Ajit Khaparde wrote:
From: Darren Edamura
Probe function should exit immediately if pcie bridge detected
Signed-off-by: Darren
On 2/28/2018 10:12 PM, Ajit Khaparde wrote:
> When the vnic_tpa_cfg HWRM command is sent to the FW,
> we are not passing the VNIC ID in case of disable.
> This can cause the FW to return an error.
> Correct VNIC ID needs to be passed for both enable and disable.
Hi Ajit,
Patch title doesn't tell
On Mon, Mar 26, 2018 at 1:20 PM, Ferruh Yigit
wrote:
> On 2/28/2018 10:12 PM, Ajit Khaparde wrote:
> > When the vnic_tpa_cfg HWRM command is sent to the FW,
> > we are not passing the VNIC ID in case of disable.
> > This can cause the FW to return an error.
> > Correct VNIC ID needs to be passed
1 - 100 of 134 matches
Mail list logo
