> > On Fri, Aug 27, 2021 at 12:59 AM Andrew Rybchenko
> > wrote:
> > >
> > > On 8/27/21 4:19 AM, Ferruh Yigit wrote:
> > > > Add 'RTE_ETH' namespace to all enums & macros in a backward
> > compatible
> > > > way. The macros for backward compatibility can be removed in next
> LTS.
> > > >
> > > > I
> -Original Message-
> From: Wang, Jie1X
> Sent: Friday, August 27, 2021 16:18
> To: dev@dpdk.org
> Cc: Li, Xiaoyun ; andrew.rybche...@oktetlabs.ru;
> tho...@monjalon.net; Yigit, Ferruh ; Wang, Jie1X
>
> Subject: [PATCH v8 2/2] app/testpmd: fix testpmd doesn't show RSS hash
> offload
>
The usage of priority is converse in pipeline mode and
non-pipeline mode. Refine attribute priority support of flow
filter in PF driver. When priority is 0, rules are created in
switch filter first and FDIR is used as backup. When priority
is 1, rules are all created in switch filter. Other filters
> -Original Message-
> From: Xu, Rosen
> > > On Fri, Aug 27, 2021 at 12:59 AM Andrew Rybchenko
> > > wrote:
> > > >
> > > > On 8/27/21 4:19 AM, Ferruh Yigit wrote:
> > > > > Add 'RTE_ETH' namespace to all enums & macros in a backward
> > > compatible
> > > > > way. The macros for backward
> -Original Message-
> From: dev On Behalf Of Qiming Chen
> Sent: Monday, August 30, 2021 10:10 AM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Qiming Chen
>
> Subject: [dpdk-dev] [PATCH v2] net/i40e: solve vf vlan strip
>
> Kernel PF+DPDK VF mode, after vf adds vlan, the test result shows
> -Original Message-
> From: Qiming Chen
> Sent: Monday, August 30, 2021 11:32
> To: dev@dpdk.org
> Cc: Wang, Haiyue ; Qiming Chen
> ; sta...@dpdk.org
> Subject: [PATCH] net/ixgbe: fix rx multicst count isn't clear
>
> In the implementation of the vf driver ixgbevf_update_stats to obtain
From: Chengchang Tang
Current, the max waiting time for MBX response is 500ms, but in
some scenarios, it is not enough. Since it depends on the response
of the kernel mode driver, and its response time is related to the
scheduling of the system. In this special scenario, most of the
cores are iso
In the implementation of the vf driver ixgbevf_update_stats to obtain
statistics, the multicast count hw_stats->vfmprc has been obtained,
but it is not cleared in the corresponding ixgbevf_dev_stats_reset
interface.
Fixes: abf7275bbaa2 ("ixgbe: move to drivers/net/")
Cc: sta...@dpdk.org
Signed-of
As announced in the deprecation note, i40evf has been removed. So removing
deprecation notice from the notes.
Signed-off-by: Robin Zhang
---
doc/guides/rel_notes/deprecation.rst | 8
1 file changed, 8 deletions(-)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/rel_note
Due to i40evf will be removed, so there's no need to keep the devargs
option "driver=i40evf" in iavf.
Signed-off-by: Robin Zhang
---
drivers/net/iavf/iavf_ethdev.c | 52 ++
1 file changed, 2 insertions(+), 50 deletions(-)
diff --git a/drivers/net/iavf/iavf_ethdev
The default VF driver for Intel 700 Series Ethernet Controller already
switch to iavf in DPDK 21.05. And i40evf is no need to maintain now,
so remove i40evf related code.
Signed-off-by: Robin Zhang
---
drivers/net/i40e/i40e_ethdev.h|1 -
drivers/net/i40e/i40e_ethdev_vf.c | 3015 -
In DPDK 21.05, iavf already became the default VF for i40e devices.
So remove i40evf due to it's no need to maintain now.
Robin Zhang (3):
net/i40e: remove i40evf
net/iavf: remove i40evf devargs option
doc: remove old deprecation notice for i40e
doc/guides/rel_notes/deprecation.rst |8
When the port is probed, if the eth_from_pcaps function fails, the
previously opened pcap resources are not released, causing resource
leakage.
The patch solves the problem of resource leakage caused by abnormal
branch exit during the port probe process.
Signed-off-by: Qiming Chen
---
v2:
Clea
When the port is probed, if the eth_from_pcaps function fails, the
previously opened pcap resources are not released, causing resource
leakage.
The patch solves the problem of resource leakage caused by abnormal
branch exit during the port probe process.
Signed-off-by: Qiming Chen
---
drivers/n
Hi,
> -Original Message-
> From: Wisam Monther
> Sent: Sunday, August 29, 2021 16:18
> To: Ajit Khaparde ; Andrew Rybchenko
>
> Cc: Yigit, Ferruh ; Tahhan, Maryam
> ; Pattan, Reshma ;
> Jerin Jacob ; Dumitrescu, Cristian
> ; Li, Xiaoyun ; NBU-
> Contact-Thomas Monjalon ; Jayatheerthan, J
Kernel PF+DPDK VF mode, after vf adds vlan, the test result shows that the
vlan received from vf has been stripped.
The patch solves the problem that the kernel i40e.ko driver strips the vlan
by default after vf adds vlan. Determine whether to strip vlan through
the DEV_RX_OFFLOAD_VLAN_STRIP mask
Kernel PF+DPDK VF mode, after vf adds vlan, the test result shows that the
vlan received from vf has been stripped.
The patch solves the problem that the kernel i40e.ko driver strips the vlan
by default after vf adds vlan. Determine whether to strip vlan through
the DEV_RX_OFFLOAD_VLAN_STRIP mask
> -Original Message-
> From: Tudor Cornea
> Sent: Thursday, August 5, 2021 7:35 PM
> To: Wu, Jingjing ; Xing, Beilei
> Cc: Zhang, Qi Z ; dev@dpdk.org; Tudor Cornea
>
> Subject: [PATCH] net/iavf: fix overflow in maximum packet length config
>
> The len variable, used in the computatio
> -Original Message-
> From: dev On Behalf Of Qiming Chen
> Sent: Thursday, August 26, 2021 10:10 PM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Qiming Chen
>
> Subject: [dpdk-dev] [PATCH v3] net/i40e: solve vf vlan strip
>
> Kernel PF+DPDK VF mode, after vf adds vlan, the test result sho
> -Original Message-
> From: Andrew Rybchenko
> Sent: Sunday, August 29, 2021 4:23 PM
> To: Xueming(Steven) Li ; Viacheslav Galaktionov
>
> Cc: Ajit Khaparde ; Somnath Kotur
> ; John Daley
> ; Hyong Youb Kim ; Beilei Xing
> ; Qiming Yang
> ; Qi Zhang ; Haiyue Wang
> ; Matan Azrad
>
> On 8/23/21 1:02 PM, Akhil Goyal wrote:
> > Reassembly is a costly operation if it is done in
> > software, however, if it is offloaded to HW, it can
> > considerably save application cycles.
> > The operation becomes even more costlier if IP fragmants
> > are encrypted.
> >
> > To resolve above t
> -Original Message-
> From: Wang, Jie1X
> Sent: Tuesday, August 24, 2021 11:13 PM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Wang, Jie1X ;
> sta...@dpdk.org
> Subject: [PATCH v2] net/ice: fix queue config in DCF
>
> When DCF configures rx_queues, it may cause the pointer of rx_queues to g
> -Original Message-
> From: Yu Wenjun
> Sent: Thursday, August 19, 2021 8:10 PM
> To: Yang, Qiming ; Zhang, Qi Z
>
> Cc: dev@dpdk.org; sta...@dpdk.org; Yu Wenjun
> Subject: [PATCH] net/ice: fix deadlock in ice_flow_query()
>
> It will cause deadlock when use switch-default, so fix i
The device specific structures - rte_cryptodev
and rte_cryptodev_data are moved to cryptodev_pmd.h
to hide it from the applications.
Signed-off-by: Akhil Goyal
---
lib/cryptodev/cryptodev_pmd.h | 62
lib/cryptodev/rte_cryptodev_core.h | 76 --
PMD is updated to use the new API for all enqueue
and dequeue paths.
Signed-off-by: Akhil Goyal
---
drivers/crypto/scheduler/scheduler_failover.c | 23 +++
.../crypto/scheduler/scheduler_multicore.c| 22 ++
.../scheduler/scheduler_pkt_size_distr.c | 22 ++
scheduler PMD has 4 variants, which uses same
name for all the enqueue and dequeue functions.
This causes multiple definitions of same function
with the new framework of datapath APIs.
Hence the function names are updated to specify the
the variant it is for.
Signed-off-by: Akhil Goyal
---
drive
All crypto drivers are updated to use the new API
for all enqueue and dequeue paths.
Signed-off-by: Akhil Goyal
---
drivers/crypto/aesni_gcm/aesni_gcm_pmd.c | 10 --
drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c | 11 +--
drivers/crypto/armv8/rte_armv8_pmd.c
The datapath inline APIs (rte_cryptodev_enqueue_burst/
rte_cryptodev_dequeue_burst) are updated to use the new
rte_crytodev_api->enqueue_burst/rte_cryptodev_api->dequeue_burst
APIs based on the dev_id
Signed-off-by: Akhil Goyal
---
lib/cryptodev/rte_cryptodev.h | 62 +++--
Add helper functions and macros to help drivers to
transition to new datapath interface.
Signed-off-by: Akhil Goyal
---
lib/cryptodev/cryptodev_pmd.h | 246 ++
lib/cryptodev/rte_cryptodev.c | 40 +-
lib/cryptodev/version.map | 4 +
3 files changed, 289
Move fastpath inline function pointers from rte_cryptodev into a
separate structure accessed via a flat array.
The intension is to make rte_cryptodev and related structures private
to avoid future API/ABI breakages.
Signed-off-by: Akhil Goyal
---
lib/cryptodev/cryptodev_pmd.c | 33 +
A new header file rte_cryptodev_core.h is added and all
internal data structures which need not be exposed directly to
application are moved to this file. These structures are mostly
used by drivers, but they need to be in the public header file
as they are accessed by datapath inline functions for
Structures rte_cryptodev and rte_cryptodev_data are not
supposed to be directly used by the application. These
are made public as they are used by inline datapath
public APIs.
This patchset, creates a new rte_cryptodev_core.h file
which helps in defining a data structure to hold datapath
APIs in a
Hi,
> -Original Message-
> From: Ajit Khaparde
> Sent: Saturday, August 28, 2021 5:26 PM
> To: Andrew Rybchenko
> Cc: Ferruh Yigit ; Maryam Tahhan
> ; Reshma Pattan ;
> Jerin Jacob ; Wisam Monther ;
> Cristian Dumitrescu ; Xiaoyun Li
> ; NBU-Contact-Thomas Monjalon
> ; Jay Jayatheerthan
> -Original Message-
> From: Zhang, AlvinX
> Sent: Wednesday, August 18, 2021 10:32 AM
> To: Zhang, Qi Z ; Guo, Junfeng
>
> Cc: dev@dpdk.org; Zhang, AlvinX ; Ajit Khaparde
> ; Singh, Aman Deep
>
> Subject: [PATCH v5] ethdev: add IPv4 and L4 checksum RSS offload types
>
> This patch d
> -Original Message-
> From: Wu, Wenjun1
> Sent: Tuesday, August 17, 2021 4:43 PM
> To: dev@dpdk.org; Zhang, Qi Z
> Cc: Wu, Wenjun1
> Subject: [PATCH v3 0/2] fix default RSS field for IP fragment packets
>
> This patch set removes redundant default RSS field for both IPv4 and
> IPv6
> -Original Message-
> From: dev On Behalf Of Haiyue Wang
> Sent: Tuesday, August 17, 2021 3:17 PM
> To: dev@dpdk.org
> Cc: Wang, Haiyue ; Wu, Jingjing
> ; Xing, Beilei
> Subject: [dpdk-dev] [PATCH v1 4/4] common/iavf: update the driver version
>
> Update the driver version to trace th
> -Original Message-
> From: dev On Behalf Of Haiyue Wang
> Sent: Tuesday, August 17, 2021 3:17 PM
> To: dev@dpdk.org
> Cc: Wang, Haiyue ; Wu, Jingjing
> ; Xing, Beilei
> Subject: [dpdk-dev] [PATCH v1 3/4] common/iavf: remove the FDIR query
> opcode
>
> The VIRTCHNL_OP_QUERY_FDIR_FILT
> -Original Message-
> From: dev On Behalf Of Haiyue Wang
> Sent: Tuesday, August 17, 2021 3:17 PM
> To: dev@dpdk.org
> Cc: Zhang, AlvinX ; Wang, Haiyue
> ; Wu, Jingjing ; Xing, Beilei
>
> Subject: [dpdk-dev] [PATCH v1 2/4] common/iavf: add proto hdr field support
> for
> L4 checksum
> -Original Message-
> From: dev On Behalf Of Haiyue Wang
> Sent: Tuesday, August 17, 2021 3:17 PM
> To: dev@dpdk.org
> Cc: Guo, Junfeng ; Wang, Haiyue
> ; Wu, Jingjing ; Xing, Beilei
>
> Subject: [dpdk-dev] [PATCH v1 1/4] common/iavf: add QFI fields for GTPU UL
> and DL
>
> From: Jun
> -Original Message-
> From: dev On Behalf Of Wenjun Wu
> Sent: Tuesday, August 17, 2021 2:50 PM
> To: dev@dpdk.org; Wu, Jingjing ; Xing, Beilei
>
> Cc: Wu, Wenjun1
> Subject: [dpdk-dev] [PATCH v2] net/iavf: support FDIR L3 fields for IPv6
> fragment packets
>
> This patch adds L3 fi
> -Original Message-
> From: dev On Behalf Of Wenjun Wu
> Sent: Tuesday, August 17, 2021 2:50 PM
> To: dev@dpdk.org; Wu, Jingjing ; Xing, Beilei
>
> Cc: Wu, Wenjun1
> Subject: [dpdk-dev] [PATCH v2] net/iavf: fix wrong FDIR L3 field set for IPv4
> fragment packets
>
> Originally, the
> -Original Message-
> From: Jerin Jacob
> Sent: Thursday, August 26, 2021 7:28 PM
> To: Xueming(Steven) Li
> Cc: Jack Min ; dpdk-dev ; Xiaoyun Li
>
> Subject: Re: [dpdk-dev] [PATCH v2 06/15] app/testpmd: add common fwd wrapper
> function
>
> On Wed, Aug 18, 2021 at 7:38 PM Xueming(
> -Original Message-
> From: Huang, ZhiminX
> Sent: Tuesday, August 17, 2021 4:00 PM
> To: Zhang, Qi Z ; Yang, Qiming
>
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: RE: [PATCH] net/ice: fix wrong rxdid
>
> > -Original Message-
> > From: Zhang, Qi Z
> > Sent: Tuesday, August
> -Original Message-
> From: Wang, Haiyue
> Sent: Friday, August 13, 2021 2:22 PM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Wang, Haiyue
> ; sta...@dpdk.org; David Marchand
> ; Yang, Qiming ;
> Xiaolong Ye ; Xing, Beilei ;
> Wang, Ying A
> Subject: [PATCH v1] net/ice: fix memzone leak whe
> -Original Message-
> From: dev On Behalf Of Wenjun Wu
> Sent: Tuesday, August 3, 2021 3:24 PM
> To: dev@dpdk.org; qiming.y...@intel.com--annotate
> Cc: Wu, Wenjun1
> Subject: [dpdk-dev] [PATCH v2] net/ice/base: support L2 and L3 FDIR field for
> IP
> fragment packets
>
> Add L2 and
> -Original Message-
> From: dev On Behalf Of Renata Saiakhova
> Sent: Monday, August 2, 2021 10:14 PM
> To: Wang, Haiyue
> Cc: dev@dpdk.org; Renata Saiakhova
> Subject: [dpdk-dev] [PATCH 1/1] drivers/net/e1000: igbvf_vlan_offload_config
> and igbvf_vlan_offload_set implementation
The
Apply the same fix that for iavf to DCF
commit: ead06572bd8f ("net/iavf: fix performance with writeback policy")
Fixes: 4b0d391f0eab ("net/ice: add queue config in DCF")
Cc: sta...@dpdk.org
Signed-off-by: Qi Zhang
---
drivers/net/ice/ice_dcf_ethdev.c | 9 +++--
1 file changed, 7 insertions(
When virtio_init_queue returns error, the memory of vq is freed.
But the value of hw->vqs[queue_idx] does not restore.
If virtio_init_queue returns error, the memory of vq is freed again
in virtio_free_queues.
Fixes: 69c80d4ef89b ("net/virtio: allocate queue at init stage")
Cc: sta...@dpdk.org
Si
EAL:
- add oops support
http://patches.dpdk.org/project/dpdk/patch/20210817032723.3997054-2-jer...@marvell.com/
- make rte_intr_handle hidden for better ABI
https://patches.dpdk.org/project/dpdk/patch/20210826145726.102081-2-hka...@marvell.com/
ethdev:
- mtr: enhance input color table features
ht
On 8/28/21 4:22 PM, Xueming(Steven) Li wrote:
>
>
>> -Original Message-
>> From: Viacheslav Galaktionov
>> Sent: Friday, August 27, 2021 5:48 PM
>> To: Xueming(Steven) Li
>> Cc: Andrew Rybchenko ; Ajit Khaparde
>> ; Somnath Kotur
>> ; John Daley ; Hyong Youb
>> Kim ; Beilei Xing
>> ;
On Sat, Aug 28, 2021 at 7:56 PM Ajit Khaparde
wrote:
>
> On Fri, Aug 27, 2021 at 12:59 AM Andrew Rybchenko
> wrote:
> >
> > On 8/27/21 4:19 AM, Ferruh Yigit wrote:
> > > Add 'RTE_ETH' namespace to all enums & macros in a backward compatible
> > > way. The macros for backward compatibility can be
51 matches
Mail list logo