From: Kiran Kumar K
Adding support to parse GTPU flag for RSS hash index calculation in
octeontx2.
Signed-off-by: Kiran Kumar K
---
drivers/net/octeontx2/otx2_rss.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/octeontx2/otx2_rss.c b/drivers/net/octeontx2/otx2_rss.c
index
From: Kiran Kumar K
Adding support to enable GTPU eth flow type for RSS hash
index calculation.
Signed-off-by: Kiran Kumar K
---
lib/librte_ethdev/rte_ethdev.h | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/lib/librte_ethdev/rte_ethdev.h b/lib/librte_ethdev/rte_ethdev.h
Hi Xiaolong,
I tried, but compile issue exist.
-Original Message-
From: Ye, Xiaolong
Sent: Tuesday, September 3, 2019 2:23 PM
To: Pei, Andy
Cc: dev@dpdk.org; Zhang, Qi Z ; Yigit, Ferruh
; Xu, Rosen
Subject: Re: [PATCH v3] net/ipn3ke: setup MTU when HW init
On 09/03, Pei, Andy wrote:
On 09/03, Pei, Andy wrote:
[snip]
> tmp = RTE_MAX(tmp, RTE_ETHER_MIN_MTU);
>
>>+ if (tmp > IPN3KE_MAC_FRAME_SIZE_MAX - IPN3KE_ETH_OVERHEAD)
>>+ tmp = IPN3KE_MAC_FRAME_SIZE_MAX - IPN3KE_ETH_OVERHEAD;
>
> tmp = RTE_MIN(tmp, IPN3KE_MAC_FRAME_SIZE_MAX - IPN3KE_ETH_OVERHEAD);
On Tue, 3 Sep 2019 10:21:17 +0530
Suraj R Gupta wrote:
> These are the links to Timers documentation.
> https://doc.dpdk.org/api/rte__timer_8h.html
> https://doc.dpdk.org/guides/prog_guide/timer_lib.html
>
> As per my understanding of the documentation,
> PENDING means timer is scheduled to run
On Thu, Aug 29, 2019 at 09:59:55AM +0200, Maxime Coquelin wrote:
> In order to support multi-queue, we need to implement the control
> path. The problem is that both the Vhost-user master and slave use
> VAs in their processes address spaces as IOVAs, which creates
> collusions between the data rin
> -Original Message-
> From: Anoob Joseph
> Sent: Friday, August 30, 2019 11:58 AM
> To: Akhil Goyal ; Pablo de Lara
> ; Thomas Monjalon
>
> Cc: Anoob Joseph ; Jerin Jacob Kollanukkaran
> ; Narayana Prasad Raju Athreya
> ; Ankur Dwivedi ;
> Tejasree Kondoj ; dev@dpdk.org
> Subject: [PATCH
On Thu, Aug 29, 2019 at 09:59:59AM +0200, Maxime Coquelin wrote:
> This patch implements the vDPA .get_notify_area()
> callback.
>
> Signed-off-by: Maxime Coquelin
> ---
> drivers/net/virtio/virtio_vdpa.c | 33
> 1 file changed, 33 insertions(+)
>
> diff --git a
Hi All,
I am trying to receive packets transmitted by another DPDK
application running on different system. I am able to transmit packets with
a burst value of 1 using rte_eth_tx_burst Api, but unable to receive
packets with a burst value less than 4 using rte_eth_rx_burst Api. can
anyone
These are the links to Timers documentation.
https://doc.dpdk.org/api/rte__timer_8h.html
https://doc.dpdk.org/guides/prog_guide/timer_lib.html
As per my understanding of the documentation,
PENDING means timer is scheduled to run but not started.(in a list)
RUNNING means timer is presently running
On Thu, Aug 29, 2019 at 09:59:58AM +0200, Maxime Coquelin wrote:
> This patch implements the vDPA .get_vfio_group_fd() and
> .get_vfio_device_fd() callbacks.
>
> Signed-off-by: Maxime Coquelin
> ---
> drivers/net/virtio/virtio_vdpa.c | 34
> 1 file changed, 34 in
From: Kiran Kumar K
Adding support to check TX and RX descriptor status.
Signed-off-by: Kiran Kumar K
---
app/test-pmd/cmdline.c | 111
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 8 ++
2 files changed, 119 insertions(+)
diff --git a/app/test-pmd/
From: Kiran Kumar K
Adding support for tx descriptor status dev ops for octeontx2.
Signed-off-by: Kiran Kumar K
---
doc/guides/nics/features/octeontx2.ini | 1 +
drivers/net/octeontx2/otx2_ethdev.c | 1 +
drivers/net/octeontx2/otx2_ethdev.h | 1 +
drivers/net/octeontx2/otx2_ethdev_
HI Xiaolong,
Reply inline.
-Original Message-
From: Ye, Xiaolong
Sent: Monday, September 2, 2019 5:24 PM
To: Pei, Andy
Cc: dev@dpdk.org; Zhang, Qi Z ; Yigit, Ferruh
; Xu, Rosen
Subject: Re: [PATCH v3] net/ipn3ke: setup MTU when HW init
Hi, Andy
On 09/02, Andy Pei wrote:
>set up mtu
If flow creation fails because of an HWRM command failure or
or some other reason, reset the vnic and rxq info set earlier.
Signed-off-by: Ajit Khaparde
Reviewed-by: Rahul Gupta
Reviewed-by: Venkat Duvvuru
Reviewed-by: Kalesh Anakkur Purayil
---
drivers/net/bnxt/bnxt_flow.c | 68 +
When a drop action for L2 filters is specified, support it.
Signed-off-by: Ajit Khaparde
Reviewed-by: Rahul Gupta
Reviewed-by: Somnath Kotur
Reviewed-by: Kalesh Anakkur Purayil
---
drivers/net/bnxt/bnxt_filter.h | 6
drivers/net/bnxt/bnxt_flow.c | 61 ++
From: Venkat Duvvuru
Currently, there are four flow related functions, namely
bnxt_flow_create, bnxt_flow_destroy, bnxt_flow_validate,
bnxt_flow_flush. All these functions are not multi-thread safe.
This patch fixes it by synchronizing these functions with a lock.
Reviewed-by: Kalesh Anakkur Pu
We are not freeing all the flows when a flow_flush is called.
Iterate through all the flows belonging to all the VNICs in use and
free the filters.
Signed-off-by: Ajit Khaparde
Reviewed-by: Rahul Gupta
Reviewed-by: Venkat Duvvuru
Reviewed-by: Kalesh Anakkur Purayil
---
drivers/net/bnxt/bnxt_f
From: Rahul Gupta
Initialize all rings to INVALID_HW_RING_ID.
This can be used to determine the rings to free if allocation fails.
Signed-off-by: Rahul Gupta
Reviewed-by: Venkat Duvvuru
Reviewed-by: Kalesh Anakkur Purayil
Reviewed-by: Ajit Khaparde
Signed-off-by: Ajit Khaparde
---
drivers/
From: Venkat Duvvuru
In bnxt_rss_hash_update_op, driver is proceeding with
bnxt_hwrm_vnic_rss_cfg even though RSS hashkey length is invalid.
This patch fixes the problem by returning -EINVAL when RSS hashkey length
is invalid.
Signed-off-by: Venkat Duvvuru
Reviewed-by: Somnath Kotur
Reviewed-
Parse priority attribute during flow creation.
This information will be used to give a hint to the FW to
place the flow rule accordingly in the CFA tables.
Reviewed-by: Rahul Gupta
Reviewed-by: Lance Richardson
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_filter.h | 1 +
drivers/net
Check device is started before flow creation.
Since the vnic data structures aren't created until device start,
the driver dereferences NULL vnic if flow creation is attempted before
device is started,
Reported-by: Stephen Hemminger
Signed-off-by: Ajit Khaparde
Reviewed-by: Somnath Kotur
Review
Check if the application is trying to create filters using
broadcast and multicast MAC address and reject it.
Signed-off-by: Ajit Khaparde
Reviewed-by: Rahul Gupta
Reviewed-by: Santoshkumar Karanappa Rastapur
---
drivers/net/bnxt/bnxt_flow.c | 16
1 file changed, 16 insertions
Add support for RSS action during flow creation.
group id should not be 0 when RSS action is specified. Driver will
return an error for such a flow.
If a group id is used to create a filter with “n” RSS queues, it cannot
be used to create a filter with a different number of RSS queues till
all th
From: Somnath Kotur
If driver init/probe fails as part of cleanup/rollback, we may end
up invoking this HWRM cmd even on an invalid vNIC which will unecessarily
log an error message as the cmd will fail.
Check for invalid ID before issuing the HWRM cmd
Signed-off-by: Somnath Kotur
Reviewed-by:
Once the last filter associated with a VNIC is deleted when using
RSS action or the Queue action free the VNIC. Also free the RSS
context if the VNIC is using it.
Signed-off-by: Ajit Khaparde
Reviewed-by: Rahul Gupta
Reviewed-by: Venkat Duvvuru
---
drivers/net/bnxt/bnxt_filter.c | 18 +
When an application issues flow validate, we free the temporary
filter that is created. But the vnic is not freed up. This can
potentially interfere with subsequent flow creation. So free the vnic.
Signed-off-by: Ajit Khaparde
Reviewed-by: Rahul Gupta
Reviewed-by: Venkat Duvvuru
---
drivers/ne
We are currently creating only outer DMAC filters.
Create SMAC and inner DMAC filters using HWRM_CFA_L2_FILTER_ALLOC.
For this the HWRM_CFA_L2_FILTER_ALLOC has already been updated.
Reviewed-by: Somnath Kotur
Reviewed-by: Rahul Gupta
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt.h
Refactor code to allow dynamic creation of VNIC for RSS
or Queue Action during flow create.
Signed-off-by: Ajit Khaparde
Reviewed-by: Rahul Gupta
Reviewed-by: Venkat Duvvuru
---
drivers/net/bnxt/bnxt.h| 1 +
drivers/net/bnxt/bnxt_ethdev.c | 54 ++
drive
Currently flow creation is allowed with queue action only
when RSS is disabled. Remove this restriction. Flows can be
created when RSS is enabled.
Signed-off-by: Ajit Khaparde
Reviewed-by: Rahul Gupta
Reviewed-by: Venkat Duvvuru
---
drivers/net/bnxt/bnxt.h| 1 +
drivers/net/bnxt/bnxt
If the FW returns an error for an HWRM request, it does not necessarily
return standard error codes. Convert these HWRM errors to standard errno.
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_hwrm.c | 16 ++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/dr
Among other changes, this patchset adds support to:
- create filters with RSS action.
- create source MAC filters.
- use user provided priority to place rule appropriately in HW.
This series is dependent on the series "bnxt patchset" submitted earlier
https://patchwork.dpdk.org/project/dpdk/list/?
This patch enables VF to support multi-queue Rx interrupt.
Current implementation is that only one Rx queue can support interrupt,
because all queues are mapped in the same vector id in vfio_enable_msix().
So VF can not support multi-queue Rx interrupt in the interrupt mode.
In this patch, if the
On 9/2/2019 11:32 AM, Igor Russkikh wrote:
>
>
> On 01.09.2019 17:36, Andrew Rybchenko wrote:
>> From: Ivan Ilchenko
>>
>> atl_dev_info_get() is declared twice in atl_ethdev.c.
>> Delete one of these declararions.
>>
>> Fixes: bb42aa9ffe4e ("net/atlantic: configure device start/stop")
>> Cc: sta
On 8/19/2019 12:41 PM, David Marchand wrote:
> Make use of the newly introduced wrapper.
>
> Signed-off-by: David Marchand
<...>
> diff --git a/drivers/net/mlx4/mlx4.c b/drivers/net/mlx4/mlx4.c
> index 931e4f4..c71b68e 100644
> --- a/drivers/net/mlx4/mlx4.c
> +++ b/drivers/net/mlx4/mlx4.c
> @@
On 09/02, Di ChenxuX wrote:
>Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources
> for the port can be freed by rte_eth_dev_close().
>
>Signed-off-by: Di ChenxuX
>---
> drivers/net/e1000/e1000_ethdev.h | 1 +
> drivers/net/e1000/igb_ethdev.c | 142 +-
Hi, Chenxu
On 09/02, Di ChenxuX wrote:
>Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources
> for the port can be freed by rte_eth_dev_close().
>
>Signed-off-by: Di ChenxuX
>---
> drivers/net/ice/ice_ethdev.c | 33 ++---
> drivers/net/ice/ice_ethdev.h |
On Mon, Sep 02, 2019 at 05:12:36PM +0530, Suraj R Gupta wrote:
>Hi,
>If I am right, rte_timer_stop() stops the timer after the call back
>execution.
>It is said that if rte_timer_stop() is called during timer running,
>function will fail.
>I want to know if timer can be stop
This commit adds support for modifying the VLAN ID (VID) field
in an about-to-be-pushed VLAN header.
This feature can only modify the VID field of a new VLAN header yet
to be pushed. It does not support modifying an existing or already
pushed VLAN headers.
Signed-off-by: Moti Haimovsky
---
doc/g
This commit adds support for modifying the VID of the outermost VLAN
header already present in the packet.
Signed-off-by: Moti Haimovsky
---
doc/guides/nics/mlx5.rst| 20 -
drivers/net/mlx5/mlx5_flow.h| 3 +-
drivers/net/mlx5/mlx5_flow_dv.c | 90 +
This commit adds support for modifying the VLAN priority (PCP) field
in about-to-be-pushed VLAN header.
This feature can only modify the PCP field of a new VLAN header yet
to be pushed. It does not support modifying an existing or already
pushed VLAN headers.
Signed-off-by: Moti Haimovsky
---
do
This commit adds a helper routine that supports searching for a
specific action in a list of actions.
Signed-off-by: Moti Haimovsky
---
drivers/net/mlx5/mlx5_flow.c | 23 +++
drivers/net/mlx5/mlx5_flow.h | 3 +++
2 files changed, 26 insertions(+)
diff --git a/drivers/net/ml
This commit adds support for RTE_FLOW_ACTION_TYPE_OF_PUSH_VLAN using
direct verbs flow rules.
If present in the flow, The VLAN default values are taken from the
VLAN item configuration.
In this commit only the VLAN TPID value can be set since VLAN
modification actions are not supported yet.
Signed
This commit adds the mlx5dv VLAN push and pop commands to mlx5_glue
interface.
Signed-off-by: Moti Haimovsky
---
drivers/net/mlx5/Makefile| 5 +
drivers/net/mlx5/meson.build | 2 ++
drivers/net/mlx5/mlx5_glue.c | 29 +
drivers/net/mlx5/mlx5_glue.h | 6 +
This commit adds support for RTE_FLOW_ACTION_TYPE_OF_POP_VLAN via
direct verbs flow rules.
Signed-off-by: Moti Haimovsky
---
doc/guides/nics/mlx5.rst| 6
drivers/net/mlx5/mlx5.c | 9 +
drivers/net/mlx5/mlx5.h | 1 +
drivers/net/mlx5/mlx5_flow.h| 5 ++-
dr
VLAN actions support is implemented in librte_ethdev, and in
test-pmd application, based on [1] Generic flow API.
These actions conform to the VLAN actions defined in
[2] the OpenFlow Switch Specification.
rte_flow defines the following VLAN actions:
1. OF_POP_VLAN
Pop the outer-most VLAN hea
On Mon, Sep 2, 2019 at 1:55 AM Loftus, Ciara wrote:
>
> > > Hi Ciara,
> > >
> > > I haven't tried this patch but have a question.
> > >
> > > On Thu, Aug 29, 2019 at 8:04 AM Ciara Loftus
> > wrote:
> > > >
> > > > This patch enables the unaligned chunks feature for AF_XDP which
> > > > allows chu
This patch adds the stateful decompression feature
to the DPDK QAT PMD.
Signed-off-by: Adam Dybkowski
---
drivers/compress/qat/qat_comp.c | 256 +---
drivers/compress/qat/qat_comp.h | 32
drivers/compress/qat/qat_comp_pmd.c | 166 --
drivers/
This patch adds the information about stateful decompression
feature in QAT PMD.
Signed-off-by: Adam Dybkowski
---
doc/guides/compressdevs/features/default.ini | 37 ++--
doc/guides/compressdevs/features/qat.ini | 21 +--
doc/guides/compressdevs/qat_comp.rst |
This patch adds QAT RAM bank definitions and related macros.
Signed-off-by: Adam Dybkowski
---
drivers/common/qat/qat_adf/icp_qat_fw_comp.h | 73
1 file changed, 73 insertions(+)
diff --git a/drivers/common/qat/qat_adf/icp_qat_fw_comp.h
b/drivers/common/qat/qat_adf/icp_qat
This patch adds two new tests that cover the stateful
decompression feature.
Signed-off-by: Adam Dybkowski
---
app/test/test_compressdev.c | 452 +++-
1 file changed, 395 insertions(+), 57 deletions(-)
diff --git a/app/test/test_compressdev.c b/app/test/test_comp
On 8/19/2019 12:41 PM, David Marchand wrote:
> The function rte_log_register_type_and_pick_level() fills a gap for
> dynamically loaded code (especially drivers) who would not pick up
> the log level passed at startup.
>
> Let's promote it to stable and export it for use by drivers via
> a wrapper
This patch adds QAT RAM bank definitions and related macros.
Signed-off-by: Adam Dybkowski
---
drivers/common/qat/qat_adf/icp_qat_fw_comp.h | 73
1 file changed, 73 insertions(+)
diff --git a/drivers/common/qat/qat_adf/icp_qat_fw_comp.h
b/drivers/common/qat/qat_adf/icp_qat
On 8/19/2019 12:41 PM, David Marchand wrote:
> All (but the Solarflare net driver) drivers currently do not care about
> the log level the user might have passed at init time.
Is this comment for the shared libraries?
Because otherwise drivers set loglevel during initialization and init time
setti
This patch adds QAT RAM bank definitions and related macros.
Signed-off-by: Adam Dybkowski
---
drivers/common/qat/qat_adf/icp_qat_fw_comp.h | 73
1 file changed, 73 insertions(+)
diff --git a/drivers/common/qat/qat_adf/icp_qat_fw_comp.h
b/drivers/common/qat/qat_adf/icp_qat
This patch adds the stateful decompression feature
to the DPDK QAT PMD.
Signed-off-by: Adam Dybkowski
---
drivers/compress/qat/qat_comp.c | 256 +---
drivers/compress/qat/qat_comp.h | 32
drivers/compress/qat/qat_comp_pmd.c | 166 --
drivers/
Hi, Ferruh Yigit
On 2019/8/30 23:14, Ferruh Yigit wrote:
> On 8/23/2019 2:47 PM, Wei Hu (Xavier) wrote:
>> This patch adds multiple process support for hns3 PMD driver.
>> Multi-process support selection queue by configuring RSS or
>> flow director. The primary process supports various managemen
On 8/29/2019 6:05 PM, Thomas Monjalon wrote:
> 28/08/2019 16:29, Andrew Rybchenko:
>> On 8/28/19 4:42 PM, Aaron Conole wrote:
>>> Andrew Rybchenko writes:
On 8/27/19 11:47 PM, Aaron Conole wrote:
> Andrew Rybchenko writes:
>
>> It is the first patch series to get rid of void retu
As per current support, scatter Gather is only supported
for out of place input and output buffers.
This patch add support for scatter gather for inplace buffers.
Signed-off-by: Akhil Goyal
---
doc/guides/cryptodevs/features/openssl.ini | 1 +
drivers/crypto/openssl/rte_openssl_pmd.c | 82 +++
From: Gagandeep Singh
Virtual to physical conversions are optimized using the
DPAAX tables. This patch integrates DPAAX with caam_jr PMD.
Signed-off-by: Gagandeep Singh
Acked-by: Akhil Goyal
---
drivers/crypto/caam_jr/Makefile | 1 +
drivers/crypto/caam_jr/caam_jr_pvt.h | 6 ++
2 fil
From: Hemant Agrawal
Reducing the functional traces from data path and critical session path
Signed-off-by: Hemant Agrawal
Acked-by: Akhil Goyal
---
drivers/crypto/caam_jr/caam_jr.c | 37
1 file changed, 4 insertions(+), 33 deletions(-)
diff --git a/drivers/c
If the application enables the use of ESN in the
ipsec_xform for security session create, pdb options
are set for enabling ESN.
Signed-off-by: Akhil Goyal
---
drivers/crypto/caam_jr/caam_jr.c| 4
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 4
drivers/crypto/dpaa_sec/dpaa_
crypto queues need to be detached while session destroy
so that they can be reused.
Signed-off-by: Akhil Goyal
---
drivers/crypto/dpaa_sec/dpaa_sec.c | 48 ++
1 file changed, 23 insertions(+), 25 deletions(-)
diff --git a/drivers/crypto/dpaa_sec/dpaa_sec.c
b/drivers
On 8/27/2019 3:25 PM, Andrew Rybchenko wrote:
> From: Ivan Ilchenko
>
> Add eth_dev_info_get_print_err() which is a wrapper for
> rte_eth_dev_info_get() printing error if rte_eth_dev_info_get()
> fails and returning its status code.
>
> Signed-off-by: Ivan Ilchenko
> Signed-off-by: Andrew Rybch
From: Hemant Agrawal
Signed-off-by: Hemant Agrawal
Signed-off-by: Vakul Garg
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 12 ++--
drivers/crypto/dpaa2_sec/dpaa2_sec_priv.h | 20
2 files changed, 30 insertions(+), 2 deletions(-)
diff
From: Vakul Garg
Add Kasumi processing for non PDCP proto offload cases.
Also add support for pre-computed IV in Kasumi-f9
Signed-off-by: Vakul Garg
Signed-off-by: Hemant Agrawal
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/desc/algo.h | 64 +++--
1 file changed,
From: Vakul Garg
Signed-off-by: Vakul Garg
Signed-off-by: Hemant Agrawal
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/desc/algo.h | 94 +
1 file changed, 94 insertions(+)
diff --git a/drivers/crypto/dpaa2_sec/hw/desc/algo.h
b/drivers/crypto/dpaa2_sec/hw/desc
From: Hemant Agrawal
Adding basic framework to use snow3g f8 and f9 based
ciphering or integrity with direct crypto apis.
This patch does not support any combo usages yet.
Signed-off-by: Hemant Agrawal
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 236 ++-
From: Vakul Garg
This patch support following algo combinations(ENC-AUTH).
- AES-SNOW
- SNOW-AES
- AES-ZUC
- ZUC-AES
- SNOW-ZUC
- ZUC-SNOW
Signed-off-by: Vakul Garg
Signed-off-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/desc/pdcp.h | 211
1 file changed, 140 inser
From: Vakul Garg
Add support for snow-f9 in non pdcp protocol offload mode.
This essentially add support to pass pre-computed IV to SEC.
Signed-off-by: Vakul Garg
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/desc/algo.h | 51 +
1 file changed, 26 insertions(+)
From: Vakul Garg
This patch support AES-AES PDCP enc-auth case for
devices which do not support PROTOCOL command for 18bit
Signed-off-by: Vakul Garg
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/desc/pdcp.h | 151 +++-
1 file changed, 150 insertions(+), 1 deletion(
From: Vakul Garg
PDCP descriptors in some cases internally use commands which overwrite
memory with extra '0s' if write-safe is kept enabled. This breaks
correct functional behavior of PDCP apis and they in many cases give
incorrect crypto output. There we disable 'write-safe' bit in FLC for
PDCP
From: Vakul Garg
This patch support SNOW-SNOW (enc-auth) 18bit PDCP case
for devices which do not support PROTOCOL command
Signed-off-by: Vakul Garg
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/desc/pdcp.h | 133 +++-
1 file changed, 132 insertions(+), 1 deletion(
From: Vakul Garg
This patch add support for non-protocol offload mode
of snow-f8 algo
Signed-off-by: Vakul Garg
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/desc/algo.h | 20 +---
1 file changed, 5 insertions(+), 15 deletions(-)
diff --git a/drivers/crypto/dpaa2_sec/
This patch add support for chained input or output
mbufs for PDCP operations.
Signed-off-by: Akhil Goyal
---
drivers/crypto/dpaa_sec/dpaa_sec.c | 120 +++--
1 file changed, 115 insertions(+), 5 deletions(-)
diff --git a/drivers/crypto/dpaa_sec/dpaa_sec.c
b/drivers/crypt
From: Hemant Agrawal
This patch add support for chained input or output
mbufs for PDCP and ipsec protocol offload cases.
Signed-off-by: Hemant Agrawal
Signed-off-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 134 +++-
drivers/crypto/dpaa2_sec/dpaa2_sec_logs
From: Vakul Garg
This patch support ZUC-ZUC PDCP enc-auth case for
devices which do not support PROTOCOL command for 18bit.
Signed-off-by: Vakul Garg
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/desc/pdcp.h | 126 +++-
1 file changed, 125 insertions(+), 1 deletion
For sec era 8, NULL auth using protocol command does not add
4 bytes of null MAC-I and treat NULL integrity as no integrity which
is not correct.
Hence converting this particular case of null integrity on 12b SN
on SEC ERA 8 from protocol offload to non-protocol offload case.
Signed-off-by: Akhil
Support following cases
int-only (NULL-NULL, NULL-SNOW, NULL-AES, NULL-ZUC)
enc-only (SNOW-NULL, AES-NULL, ZUC-NULL)
Signed-off-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/desc/pdcp.h | 532 +++-
1 file changed, 420 insertions(+), 112 deletions(-)
diff --git a/drivers/cr
PDCP protocol offload using rte_security are supported in
dpaa2_sec and dpaa_sec drivers.
Wireless algos(SNOW/ZUC) without protocol offload are also
supported as per crypto APIs.
Akhil Goyal (5):
security: add hfn override option in PDCP
crypto/dpaaX_sec: update dpovrd for hfn override in PD
From: Hemant Agrawal
Adding minimal support for CAAM HW era 10 (used in LX2)
Primary changes are:
1. increased shard desc length form 6 bit to 7 bits
2. support for several PDCP operations as PROTOCOL offload.
Signed-off-by: Hemant Agrawal
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/d
HFN can be given as a per packet value also.
As we do not have IV in case of PDCP, and HFN is
used to generate IV. IV field can be used to get the
per packet HFN while enq/deq
If hfn_ovrd field in pdcp_xform is set,
application is expected to set the per packet HFN
in place of IV. Driver will extra
HFN can be updated on per packet basis. DPOVRD register
can be updated with the per packet value if it is enabled
in session configuration.
Signed-off-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 18 ++
drivers/crypto/dpaa2_sec/dpaa2_sec_priv.h | 4 +++-
d
From: Vakul Garg
PDCP u-plane may optionally support integrity as well.
This patch add support for supporting integrity along with
confidentiality.
Signed-off-by: Vakul Garg
Acked-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 67 +--
drivers/crypto/dpaa2_sec/hw/de
From: Vakul Garg
Added support for 12-bit c-plane. We implement it using 'u-plane for RN'
protocol descriptors. This is because 'c-plane' protocol descriptors
assume 5-bit sequence numbers. Since the crypto processing remains same
irrespective of c-plane or u-plane, we choose 'u-plane for RN' pro
When OS sends more packets than are beaing read with a single
'rte_eth_rx_burst' call, rx packets are getting stucked in the tap pmd
and are unable to receive, because trigger_seen is getting updated
and consecutive calls are not getting any packets.
Do not update trigger_seen unless less than a m
Hi,
If I am right, rte_timer_stop() stops the timer after the call back
execution.
It is said that if rte_timer_stop() is called during timer running,
function will fail.
I want to know if timer can be stopped in middle abruptly? i.e If I have
timer started for 500 ms and i want to stop it in 10
On Mon, Sep 02, 2019 at 11:02:16AM +0530, Suraj R Gupta wrote:
> Hi all,
> I am working with DPDK timers.
> In the documentation of timers, it has been said that dpdk based rte-timers
> cannot stopped while running. I would like to know if there is any way to
> stop it in middle or any workaround i
Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources
for the port can be freed by rte_eth_dev_close().
Signed-off-by: Di ChenxuX
---
drivers/net/ice/ice_ethdev.c | 33 ++---
drivers/net/ice/ice_ethdev.h | 1 +
2 files changed, 23 insertions(+), 11 de
Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources
for the port can be freed by rte_eth_dev_close().
Signed-off-by: Di ChenxuX
---
drivers/net/ixgbe/ixgbe_ethdev.c | 176 +--
drivers/net/ixgbe/ixgbe_ethdev.h | 2 +
2 files changed, 100 insertions(
Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources
for the port can be freed by rte_eth_dev_close().
Signed-off-by: Di ChenxuX
---
drivers/net/i40e/i40e_ethdev.c| 131 +++---
drivers/net/i40e/i40e_ethdev_vf.c | 25 --
2 files changed, 83 insert
Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources
for the port can be freed by rte_eth_dev_close().
Signed-off-by: Di ChenxuX
---
drivers/net/fm10k/fm10k.h| 3 +
drivers/net/fm10k/fm10k_ethdev.c | 122 ++-
2 files changed, 75 insertions(+
Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources
for the port can be freed by rte_eth_dev_close().
This patch cover all the intel drivers.
Di ChenxuX (5):
net/e1000: release port upon close
net/fm10k: release port upon close
net/i40e: release port upon close
net/ice: r
Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private resources
for the port can be freed by rte_eth_dev_close().
Signed-off-by: Di ChenxuX
---
drivers/net/e1000/e1000_ethdev.h | 1 +
drivers/net/e1000/igb_ethdev.c | 142 +--
2 files changed, 81 insertions(+
On 01.09.2019 17:36, Andrew Rybchenko wrote:
> From: Ivan Ilchenko
>
> atl_dev_info_get() is declared twice in atl_ethdev.c.
> Delete one of these declararions.
>
> Fixes: bb42aa9ffe4e ("net/atlantic: configure device start/stop")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Ivan Ilchenko
> Sign
Hi,
> -Original Message-
> From: dev On Behalf Of Christian Ehrhardt
> Sent: Tuesday, August 13, 2019 2:29 PM
> To: dev
> Cc: Luca Boccassi ; Thomas Monjalon
> ; Frank Heimes ;
> Christian Ehrhardt
> Subject: [dpdk-dev] [PATCH 1/1] net/mlx4: fix build on PPC64
>
> The AltiVec header fi
Hi, Xiao
This patch failed to apply on top of dpdk-next-net-intel/for-next-net, could
you help to do a rebase?
Thanks,
Xiaolong
On 09/02, Zhang Xiao wrote:
>The link status for 82599eb got from link status register was not correct,
>check the enable/disable flag of tx laser when getting the link
From: Krzysztof Kanas
process_dup was intending to close it's own fd's but failed to do so
Fixes: af75078fece3 ("first public release")
Signed-off-by: Krzysztof Kanas
---
v2:
* remove unnecessary commit msg information
app/test/process.h | 40 +++-
1 file
On 8/29/2019 5:56 PM, Thomas Monjalon wrote:
> 28/08/2019 16:39, Andrew Rybchenko:
>> On 8/28/19 2:26 PM, Jan Viktorin wrote:
>>> Andrew Rybchenko wrote:
On 8/28/19 12:51 PM, Jan Viktorin wrote:
> Andrew Rybchenko wrote:
>> From: Ivan Ilchenko
>> + * @return
>> + * - (0) i
Hi, Andy
On 09/02, Andy Pei wrote:
>set up mtu to the minimun in tx mtu, rx mtu and IPN3KE_MAC_FRAME_SIZE_MAX.
>
>Signed-off-by: Andy Pei
>---
>Cc: qi.z.zh...@intel.com
>Cc: ferruh.yi...@intel.com
>Cc: rosen...@intel.com
>Cc: xiaolong...@intel.com
>
>v2:
>modify low bound and upper bound.
>
>v3:
1 - 100 of 111 matches
Mail list logo
