Since rte_memcpy is more optimized it should be used instead of memcpy
Signed-off-by: Sarosh Arif
---
lib/librte_mbuf/rte_mbuf.c | 2 +-
lib/librte_mbuf/rte_mbuf.h | 3 ++-
lib/librte_mbuf/rte_mbuf_dyn.c | 8 +---
3 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/lib/lib
v2: * fixed style issue.
v3: * replaced htons with rte_cpu_to_be_16.
* rebased to current master.
v4: * removed the use of rte_random in librte_net.
* replaced htons with RTE_BE16.
Fady Bader (3):
net: fix s_addr redefinition in Windows
net: replace htons with RTE_BE16
eal/windows:
s_addr in Windows is defined in defined winsock2.h which is included by
windows.h so its undefined in order to be defined as part of
rte_ether_hdr.
Signed-off-by: Fady Bader
---
lib/librte_net/rte_ether.h | 9 +
1 file changed, 9 insertions(+)
diff --git a/lib/librte_net/rte_ether.h b/l
htons wasn't defined in Windows for the minGW compiler.
htons was replaced with RTE_BE16 in order to compile
under Windows.
Signed-off-by: Fady Bader
---
lib/librte_net/rte_arp.c | 11 +--
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/lib/librte_net/rte_arp.c b/lib/librte
librte_net wasn't compiling under Windows.
To solve this, needed header files were added.
Signed-off-by: Fady Bader
---
lib/librte_eal/windows/include/netinet/in.h | 23 +++
lib/librte_eal/windows/include/netinet/ip.h | 10 ++
lib/librte_net/rte_ether.c
Acked-by: Hemant Agrawal
-Original Message-
From: Xu, Rosen
Sent: Thursday, July 23, 2020 7:26 AM
To: Richardson, Bruce ; dev@dpdk.org
Cc: Richardson, Bruce ; Nipun Gupta
; Hemant Agrawal
Subject: RE: [dpdk-dev] [PATCH 2/2] doc: add deprecation notice for change of
rawdev APIs
Import
Hi Arek,
> >
> > Hi Arek,
> >
> > > Subject: [PATCH v3 5/5] doc: add documentation for multi process
> > > crypto app
> >
> > Please do not make separate patches for documentation.
> > Your first patch description says more info can be found in mp_crypto.rst.
> > But it is not there in that patch.
Hi,
> -Original Message-
> From: Alexander Kozyrev
> Sent: Wednesday, July 22, 2020 11:33 PM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Raslan Darawsheh ; Slava
> Ovsiienko
> Subject: [PATCH] net/mlx5: fix vectorized mini-CQE prefetching
>
> There was an optimization work to prefetch all
Hi,
> -Original Message-
> From: dev On Behalf Of Raslan Darawsheh
> Sent: Wednesday, July 22, 2020 12:08 PM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Slava Ovsiienko
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix VF MAC address set over Bluefield
>
> When trying to set MAC address of an e
Acked-by: Zhiyong Yang
-Original Message-
From: dev On Behalf Of Sachin Saxena (OSS)
Sent: Tuesday, July 14, 2020 7:33 PM
To: dev@dpdk.org; Yigit, Ferruh
Subject: [dpdk-dev] [PATCH] net/dpaa: announce extended definition of port_id
in API 'rte_pmd_dpaa_set_tx_loopback'
From: Sachin Sa
This patch addresses specific configuration:
PMD was explicitly configured to inline TX data info WQE with the
`txq_inline_min' PMD parameter and run-time TX no-inline dynamic
flag was added.
TX processing was broken for packets with length less than TXQ
minimal inline size.
Fixes: cacb44a09962 (
> -Original Message-
> From: Zhang, Qi Z
> Sent: Wednesday, July 22, 2020 1:26 PM
> To: Wang, Xiao W
> Cc: dev@dpdk.org; Yang, Qiming ; Yao, Lei A
> ; Wu, Jingjing ; sta...@dpdk.org
> Subject: RE: [PATCH] net/ice: fix default RSS key configuration
>
>
>
> > -Original Message-
On 7/22/2020 10:07 AM, Raslan Darawsheh wrote:
> When trying to set MAC address of an ethethet device and if it was
> a representor, PMD sets the MAC over the corresponding VF instead.
>
> For the case of HPF (Host PF representor on BluueField), PMD shouldn't
> attempt to set it, since it doesn't
There was the typo introducing the bug, affected the mlx5 vectorized
rx_burst on ARM architectures in case if CQE compression was enabled.
Fixes: 6c55b622a956 ("net/mlx5: set dynamic flow metadata in Rx queues")
Cc: sta...@dpdk.org
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_r
Hi,
> -Original Message-
> From: Ferruh Yigit
> Sent: Thursday, July 23, 2020 1:44 PM
> To: Raslan Darawsheh ; dev@dpdk.org
> Cc: sta...@dpdk.org; Slava Ovsiienko
> Subject: Re: [dpdk-stable] [PATCH] net/mlx5: fix VF MAC address set over
> Bluefield
>
> On 7/22/2020 10:07 AM, Raslan Dar
When trying to set MAC address of an ethethet device and if it was
a representor, PMD sets the MAC over the corresponding VF instead.
For the case of HPF (Host PF representor on BluueField), PMD shouldn't
attempt to set it, since it doesn't have any corresponding VF and fails.
This will fix the i
> -Original Message-
> From: Dharmappa, Savinay
> Sent: Thursday, July 16, 2020 2:22 PM
> To: Dharmappa, Savinay ; dev@dpdk.org
> Cc: Dumitrescu, Cristian ; Singh, Jasvinder
>
> Subject: [PATCH v2] doc: add deprecation notice for sched changes
>
> Add deprecation note for making chang
Hi,
> -Original Message-
> From: dev On Behalf Of Raslan Darawsheh
> Sent: Thursday, July 23, 2020 2:06 PM
> To: dev@dpdk.org
> Cc: ferruh.yi...@intel.com; sta...@dpdk.org; Slava Ovsiienko
>
> Subject: [dpdk-dev] [PATCH v2] net/mlx5: fix VF MAC address set over
> Bluefield
>
> When tryi
Minutes 23 July 2020
Agenda:
* Release Dates
* -rc2 status
* Subtrees
* Opens
Participants:
* Arm
* Broadcom
* Debian/Microsoft
* Intel
* Nvidia
* NXP
* Red Hat
Release Dates
-
* v20.08 dates:
* -rc2 is released on Tuesday, 21 July 2020
* http://inbox.dpd
> -Original Message-
> From: dev On Behalf Of Viacheslav Ovsiienko
>
> The User Access Region is a special mechanism to provide direct
> access to the hardware registers, and is the part of PCI address
> space that is mapped to CPU virtual address. The mapping can be
> performed with t
Since this script has no maintainer who is responsible for providing ACK or
NAK on the patches related to this script?
On Tue, Jun 2, 2020 at 12:39 PM Sarosh Arif wrote:
> Combine https://patches.dpdk.org/patch/67855/ with v2 of this patch to fix
> the overall behaviour of dpdk-setup.sh on non-a
Hi,
> -Original Message-
> From: Ori Kam
> Sent: Thursday, July 23, 2020 2:58 PM
> To: Slava Ovsiienko ; dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Thomas Monjalon ;
> Dekel Peled
> Subject: RE: [dpdk-dev] [PATCH] net/mlx5: fix UAR memory mapping type
>
>
>
> > -Origina
> -Original Message-
> From: Jiang, MaoX
> Sent: Friday, July 24, 2020 12:12 AM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org; sta...@dpdk.org; Jiang, MaoX
> Subject: [PATCH v4 2/2] net/i40e: fix fdir allocating msix resource error
>
> Fdir allocating msix resource is not strictly necessary,
> -Original Message-
> From: Jiang, MaoX
> Sent: Thursday, July 23, 2020 11:27 PM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org; sta...@dpdk.org; Jiang, MaoX
> Subject: [PATCH v4 1/2] net/i40e: fix binding interrupt without msix vectors
>
> The value of vsi->nb_msix shouldn`t be zero, otherwi
> -Original Message-
> From: dev On Behalf Of Yang, Qiming
> Sent: Thursday, July 23, 2020 9:57 AM
> To: Wang, ShougangX ; dev@dpdk.org
> Cc: Xing, Beilei ; Guo, Jia ; Wang,
> ShougangX ; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3] net/i40e: fix incorrect hash look up table
>
Now that the vhost library saves the guest notifications
enablement value in its virtqueues metadata, it is not
necessary to do it in the vring_state_changed callback.
One effect of the patch is also to prevent possible
deadlock happening in vhost library.
Fixes: 604052ae5395 ("net/vhost: support
Hi,
This series aims at fixing the performance degradation reported
by Intel QE. I managed to reproduce the issue, and this series
fixes it.
I only tested the first test case provided in the Bz[0], but wanted
to send early for Intel QE to try and confirm it solves the issue.
I will work on repro
If rte_vhost_enable_guest_notification is called before
the virtqueue is ready, the configuration is lost.
This patch fixes this by saving the guest notification
enablement value requested by the application, and apply
it before the virtqueue is made ready to the application.
Fixes: 604052ae5395
Hi,
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Thursday, July 23, 2020 1:54 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Alexander Kozyrev ;
> sta...@dpdk.org
> Subject: [PATCH] net/mlx5: fix metadata storing for NEON vectorized Rx
> burst
>
> There was t
Acked-by: Nipun Gupta
> -Original Message-
> From: Apeksha Gupta
> Sent: Monday, July 13, 2020 5:14 PM
> To: jerin.ja...@caviumnetworks.com
> Cc: tho...@monjalon.net; dev@dpdk.org; Hemant Agrawal
> ; Nipun Gupta ; Apeksha
> Gupta ; sta...@dpdk.org
> Subject: [PATCH v3 2/2] event/dpaa2: A
On 7/22/20 11:54 AM, Jerin Jacob wrote:
> External Email
>
> --
> On Wed, Jul 22, 2020 at 2:57 PM Thomas Monjalon wrote:
>>
>> 22/07/2020 11:09, Jerin Jacob:
>>> On Wed, Jul 22, 2020 at 2:26 PM Thomas Monjalon wrote:
[...]
>> Be
The ConnectX NICs can transfer data from the host memory with two
approaches: provide the pointer to the data buffer, or do data inline
- copy the data to the transmit descriptor (WQE) entirely or only the
part of data. In some configurations the NIC hardware requires the
minimal data to be inline
On 7/23/2020 10:23 AM, Yang, Zhiyong wrote:
>
> -Original Message-
> From: dev On Behalf Of Sachin Saxena (OSS)
> Sent: Tuesday, July 14, 2020 7:33 PM
> To: dev@dpdk.org; Yigit, Ferruh
> Subject: [dpdk-dev] [PATCH] net/dpaa: announce extended definition of port_id
> in API 'rte_pmd_dpa
From: Yunjian Wang
Currently, we will create new user mem map entry for the same memory
segment, but in fact it has already been added to the user mem maps.
It's not necessary to create it twice.
To resolve the issue, add support to remove the same entry in the
function compact_user_maps().
Fix
On 7/22/2020 12:56 PM, Wei Hu (Xavier) wrote:
> Add release notes for Hisilicon hns3 PMD driver.
>
> Signed-off-by: Wei Hu (Xavier)
Applied to dpdk-next-net/master, thanks.
Hi,
> -Original Message-
> From: Gregory Etelson
> Sent: Thursday, July 23, 2020 5:21 PM
> To: dev@dpdk.org
> Cc: Gregory Etelson ; Matan Azrad
> ; Raslan Darawsheh ;
> Slava Ovsiienko ; Shahaf Shuler
>
> Subject: [PATCH v2] net/mlx5: fix dynamic inline hint handling
>
> The ConnectX NI
Phil Yang writes:
> Hi Aaron,
>
> It seems Travis CI cannot capture this timeout issue.
That's probably because we use -t 3 to multiply the timeout. We needed
to do that because a few of the tests were on the cusp of failure in the
Travis environment since it's a bit lower power. In more brawn
From: Mike Baucom
- Add TCAM shadow tables for searching
- Add Search API to allow reuse of TCAM entries
Signed-off-by: Mike Baucom
Reviewed-by: Randy Schacher
---
drivers/net/bnxt/tf_core/tf_core.c| 73 +++
drivers/net/bnxt/tf_core/tf_core.h| 101
drivers/net/bnxt/tf_co
From: Kishore Padmanabha
Add support to enable or disable the NAT global registers.
The NAT feature is enabled in hardware during initialization
and disabled at deinitialization of the application.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/bnxt_
Some fixes, cleanups and changes to augment pre-existing
support in infrastructure
Please apply
Kishore Padmanabha (7):
net/bnxt: nat global registers support
net/bnxt: parif for offload miss rules
net/bnxt: nat template changes
net/bnxt: configure parif for the egress rules
net/bnxt: i
From: Kishore Padmanabha
For the offload miss rules, the parif miss path needs to be
considered. The higher parif are reserved for handling this.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_def_rules.c | 4 ++--
drivers/net/bnxt/tf_ulp/ulp_p
From: Mike Baucom
modified ulp mappper to use the new tf_search_tcam_entry API.
When search before allocation is requested, mapper calls
tc_search_tcam_entry with the alloc flag.
- On HIT, the result and tcam index is returned.
- On MISS, the tcam index is returned but the result is
created and
From: Mike Baucom
Added tf_hash API for common hash uses across tf_core functions
Signed-off-by: Mike Baucom
Reviewed-by: Farah Smith
Reviewed-by: Kishore Padmanabha
---
drivers/net/bnxt/meson.build | 1 +
drivers/net/bnxt/tf_core/Makefile | 1 +
drivers/net/bnxt/tf_core/tf_hash.c
From: Venkat Duvvuru
When a packet is looped back from VF to VFR, it is marked to identify
the VFR interface. However, this mark_id shouldn't be percolated up to
the OVS as it is internal to pmd.
This patch fixes it by skipping mark injection into mbuf if the packet
is received on VFR interface.
From: Kishore Padmanabha
The template is updated to support additional combinations
of NAT actions.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_template_db_act.c | 412 +++-
drivers/net/bnxt/tf_ulp/ulp_template_db_class.c
From: Mike Baucom
Removed the hash calculation from tf_shadow_tcam in favor of using a new
common implementation.
Signed-off-by: Mike Baucom
Reviewed-by: Kishore Padmanabha
Reviewed-by: Farah Smith
Reviewed-by: Ajit Kumar Khaparde
---
drivers/net/bnxt/tf_core/tf_shadow_tcam.c | 77 +
From: Kishore Padmanabha
Added egress template with VLAN tag match
Signed-off-by: Kishore Padmanabha
Reviewed-by: Shahaji Bhosle
---
drivers/net/bnxt/tf_ulp/ulp_template_db_class.c | 501 +++-
drivers/net/bnxt/tf_ulp/ulp_template_db_enum.h | 28 +-
2 files changed, 509 i
From: Kishore Padmanabha
This is a work around for the OVS setting offload rules that
are passing vlan priority mask as wild card and currently we
do not support it.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_rte_parser.c | 9 +
1 fil
From: Mike Baucom
- Added Index Table shadow tables for searching
- Added Search API to allow reuse of Table entries
Signed-off-by: Mike Baucom
Reviewed-by: Farah Smith
---
drivers/net/bnxt/tf_core/tf_core.c| 66 ++-
drivers/net/bnxt/tf_core/tf_core.h| 79 ++-
drivers/net/bn
From: Kishore Padmanabha
The parif for the egress rules need to be dynamically
configured based on the port type.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_def_rules.c | 11 ++---
drivers/net/bnxt/tf_ulp/ulp_mapper.c| 35
From: Venkat Duvvuru
Truflow stack adds VFR to VF and VF to VFR conduits when VF
representor is created. However, in the ingress direction the
VF's fw rules conflict with Truflow rules, resulting in not hitting
the Truflow VFR rules. To fix this, fw is going to remove it’s
VF rules when vf repres
From: Venkat Duvvuru
Currently, the flow_ids of port_to_app/app_to_port & tx_cfa_action
for the first port are getting over-written by the second port because
these fields are stored in the ulp context which is common across the
ports.
This patch fixes the problem by having per port structure to
From: Mike Baucom
modified ulp mappper to use the new tf_search_tbl_entry API.
When search before allocation is requested, mapper calls
tc_search_tbl_entry with the alloc flag.
- On HIT, the result and table index is returned.
- On MISS, the table index is returned but the result is
created and
From: Mike Baucom
Turn on shadow memory in the core to allow search before allocate.
This allows reuse of constrained resources.
Signed-off-by: Mike Baucom
Reviewed-by: Venkat Duvvuru
---
drivers/net/bnxt/tf_ulp/bnxt_ulp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/dr
From: Mike Baucom
Moved setting the refcnt for shadow tcam and table entries to the
allocation path only. The insert can be called multiple times for
updates and was resetting the refcnt to 1 each time. Now multiple
insertion/modifications will not change the reference count.
Signed-off-by: Mi
From: Mike Baucom
Search before alloc allows reuse of constrained resources such as tcam,
encap, and source modifications. The new templates will search the
entry and alloc only if necessary.
Signed-off-by: Mike Baucom
Reviewed-by: Venkat Duvvuru
---
drivers/net/bnxt/tf_ulp/ulp_template_db_a
From: Kishore Padmanabha
Added support for tcam table processing to enable the search
and allocate support. This also includes the tcam entry update
support.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_mapper.c | 317
No need to access rx_cfa_code, cfa_code_map from the VF-Rep functions
anymore.
Fixes: 322bd6e70272 ("net/bnxt: add port representor infrastructure")
Reviewed-by: Venkat Duvvuru
Signed-off-by: Somnath Kotur
---
drivers/net/bnxt/bnxt.h | 1 -
drivers/net/bnxt/bnxt_reps.c | 75 +
On Thu, 23 Jul 2020 12:02:40 +0500
Sarosh Arif wrote:
> Since rte_memcpy is more optimized it should be used instead of memcpy
>
> Signed-off-by: Sarosh Arif
Really did you measure this.
For fixed size structures, compiler can inline memcpy small set of instructions.
Some fixes, cleanups and changes to augment pre-existing
support in infrastructure
Please apply
Kishore Padmanabha (7):
net/bnxt: nat global registers support
net/bnxt: parif for offload miss rules
net/bnxt: nat template changes
net/bnxt: configure parif for the egress rules
net/bnxt: i
From: Kishore Padmanabha
Add support to enable or disable the NAT global registers.
The NAT feature is enabled in hardware during initialization
and disabled at deinitialization of the application.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/bnxt_
From: Kishore Padmanabha
For the offload miss rules, the parif miss path needs to be
considered. The higher parif are reserved for handling this.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_def_rules.c | 4 ++--
drivers/net/bnxt/tf_ulp/ulp_p
From: Mike Baucom
- Add TCAM shadow tables for searching
- Add Search API to allow reuse of TCAM entries
Signed-off-by: Mike Baucom
Reviewed-by: Randy Schacher
---
drivers/net/bnxt/tf_core/tf_core.c| 73 +++
drivers/net/bnxt/tf_core/tf_core.h| 101
drivers/net/bnxt/tf_co
From: Mike Baucom
modified ulp mappper to use the new tf_search_tcam_entry API.
When search before allocation is requested, mapper calls
tc_search_tcam_entry with the alloc flag.
- On HIT, the result and tcam index is returned.
- On MISS, the tcam index is returned but the result is
created and
From: Mike Baucom
Added tf_hash API for common hash uses across tf_core functions
Signed-off-by: Mike Baucom
Reviewed-by: Farah Smith
Reviewed-by: Kishore Padmanabha
---
drivers/net/bnxt/meson.build | 1 +
drivers/net/bnxt/tf_core/Makefile | 1 +
drivers/net/bnxt/tf_core/tf_hash.c
From: Venkat Duvvuru
When a packet is looped back from VF to VFR, it is marked to identify
the VFR interface. However, this mark_id shouldn't be percolated up to
the OVS as it is internal to pmd.
This patch fixes it by skipping mark injection into mbuf if the packet
is received on VFR interface.
From: Kishore Padmanabha
This is a work around for the OVS setting offload rules that
are passing vlan priority mask as wild card and currently we
do not support it.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_rte_parser.c | 9 +
1 fil
From: Kishore Padmanabha
The template is updated to support additional combinations
of NAT actions.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_template_db_act.c | 412 +++-
drivers/net/bnxt/tf_ulp/ulp_template_db_class.c
From: Mike Baucom
Removed the hash calculation from tf_shadow_tcam in favor of using a new
common implementation.
Signed-off-by: Mike Baucom
Reviewed-by: Kishore Padmanabha
Reviewed-by: Farah Smith
Reviewed-by: Ajit Kumar Khaparde
---
drivers/net/bnxt/tf_core/tf_shadow_tcam.c | 77 +
From: Mike Baucom
modified ulp mappper to use the new tf_search_tbl_entry API.
When search before allocation is requested, mapper calls
tc_search_tbl_entry with the alloc flag.
- On HIT, the result and table index is returned.
- On MISS, the table index is returned but the result is
created and
From: Kishore Padmanabha
The parif for the egress rules need to be dynamically
configured based on the port type.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_def_rules.c | 11 ++---
drivers/net/bnxt/tf_ulp/ulp_mapper.c| 35
From: Kishore Padmanabha
Added egress template with VLAN tag match
Signed-off-by: Kishore Padmanabha
Reviewed-by: Shahaji Bhosle
---
drivers/net/bnxt/tf_ulp/ulp_template_db_class.c | 501 +++-
drivers/net/bnxt/tf_ulp/ulp_template_db_enum.h | 28 +-
2 files changed, 509 i
From: Venkat Duvvuru
Truflow stack adds VFR to VF and VF to VFR conduits when VF
representor is created. However, in the ingress direction the
VF's fw rules conflict with Truflow rules, resulting in not hitting
the Truflow VFR rules. To fix this, fw is going to remove it’s
VF rules when vf repres
From: Mike Baucom
- Added Index Table shadow tables for searching
- Added Search API to allow reuse of Table entries
Signed-off-by: Mike Baucom
Reviewed-by: Farah Smith
---
drivers/net/bnxt/tf_core/tf_core.c| 66 ++-
drivers/net/bnxt/tf_core/tf_core.h| 79 ++-
drivers/net/bn
From: Mike Baucom
Moved setting the refcnt for shadow tcam and table entries to the
allocation path only. The insert can be called multiple times for
updates and was resetting the refcnt to 1 each time. Now multiple
insertion/modifications will not change the reference count.
Signed-off-by: Mi
From: Venkat Duvvuru
Currently, the flow_ids of port_to_app/app_to_port & tx_cfa_action
for the first port are getting over-written by the second port because
these fields are stored in the ulp context which is common across the
ports.
This patch fixes the problem by having per port structure to
From: Kishore Padmanabha
Added support for tcam table processing to enable the search
and allocate support. This also includes the tcam entry update
support.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_mapper.c | 317
From: Mike Baucom
Search before alloc allows reuse of constrained resources such as tcam,
encap, and source modifications. The new templates will search the
entry and alloc only if necessary.
Signed-off-by: Mike Baucom
Reviewed-by: Venkat Duvvuru
---
drivers/net/bnxt/tf_ulp/ulp_template_db_a
From: Mike Baucom
Turn on shadow memory in the core to allow search before allocate.
This allows reuse of constrained resources.
Signed-off-by: Mike Baucom
Reviewed-by: Venkat Duvvuru
---
drivers/net/bnxt/tf_ulp/bnxt_ulp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/dr
No need to access rx_cfa_code, cfa_code_map from the VF-Rep functions
anymore.
Fixes: 322bd6e70272 ("net/bnxt: add port representor infrastructure")
Reviewed-by: Venkat Duvvuru
Signed-off-by: Somnath Kotur
---
drivers/net/bnxt/bnxt.h | 1 -
drivers/net/bnxt/bnxt_reps.c | 75 +
>
> >
> > > > Subject: Re: [dpdk-dev] [PATCH v3] net/mlx5: relaxed ordering for
> > > > multi-packet RQ buffer refcnt
> > > >
> > > > Hi,
> > > >
> > > > We are also doing C11 atomics converting for other components.
> > > > Your insight would be much appreciated.
> > > >
> > > > Thanks,
> > > > P
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Wednesday, July 22, 2020 7:50 PM
> To: Van Haaren, Harry ; David Marchand
>
> Cc: dev@dpdk.org; igor.roma...@oktetlabs.ru; Yigit, Ferruh
> ; nd ; acon...@redhat.com;
> l.wojciec...@partner.samsung.com; Phil Yang ;
> Honnappa Nagara
On Thu, 23 Jul 2020 17:13:17 +0500
Sarosh Arif wrote:
> Since this script has no maintainer who is responsible for providing ACK or
> NAK on the patches related to this script?
>
> On Tue, Jun 2, 2020 at 12:39 PM Sarosh Arif wrote:
>
> > Combine https://patches.dpdk.org/patch/67855/ with v2 of
Add all type queue capability check before configuring event device
for pipeline atq test.
Fixes: 6bf570a9911 ("app/eventdev: add pipeline atq test")
Cc: sta...@dpdk.org
Signed-off-by: Apeksha Gupta
Acked-by: Pavan Nikhilesh
---
v4:
- removed checkpatch warning
- updated commit title and messag
DPAA2 eventdev device is capable of all type queue feature.
Fix the capability flag to reflect the same.
Fixes: 8f4a294c23 ("event/dpaa2: apply new capability flags")
Cc: sta...@dpdk.org
Signed-off-by: Apeksha Gupta
Acked-by: Nipun Gupta
---
v4:
- removed checkpatch warning
- updated commit tit
There are several drivers which duplicate bit generation macro.
Introduce a generic bit macros so that such drivers avoid redefining
same in multiple drivers.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
Acked-by: Morten Brørup
---
lib/librte_eal/include/rte_bitops.h | 8
1 file
From: Thomas Monjalon
Define each sub-directory on its own line ended with a comma,
and use a simple indent.
Signed-off-by: Thomas Monjalon
---
drivers/meson.build | 24 +---
1 file changed, 13 insertions(+), 11 deletions(-)
diff --git a/drivers/meson.build b/drivers/meson
This series introduces mlx5 bus to support multiple class of devices
for a single PCI device.
Motivation and example
--
mlx5 PCI device supports multiple class of devices such as net, vdpa
and regex devices.
Currently only one pmd (either net or vdpa) can bind to this device.
From: Thomas Monjalon
Drivers dependencies are evaluated in the order defined per
their parent directory (also called class).
This strict ordering prevent from having 2 different drivers
of the same class with different dependencies ordering.
This problem occurs if drivers/common/mlx5 depends on
Following two errors are reported when compiled with
gcc (GCC) 8.3.1 20191121 (Red Hat 8.3.1-5).
drivers/common/mlx5/linux/mlx5_glue.h:188:2:
error: function declaration isn't a prototype [-Werror=strict-prototypes]
drivers/common/mlx5/linux/mlx5_glue.h:188:2:
error: function declaration isn't a
From: Thomas Monjalon
Add generic mlx5 PCI PMD layer as part of existing common_mlx5
module. This enables multiple classes (net, regex, vdpa) PMDs
to be supported at same time.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
---
drivers/Makefile | 10 +-
driver
mlx5 PCI Device supports multiple classes of devices such as net, vdpa,
and/or regex.
To support these multiple classes, change mlx5_class to a
bitmap values so that if users asks to enable multiple of them, all
supported classes can be parsed.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
-
mlx5_common is shared library between mlx5 net, VDPA and regex PMD.
It is better to use common initialization helper instead of using
RTE_INIT_CLASS priority.
Signed-off-by: Parav Pandit
---
drivers/common/mlx5/mlx5_common.c | 13 +++--
drivers/common/mlx5/mlx5_common.h
When fail to initialize the device, avoid segmentation fault while
accessing unintialized priv.
Fixes: cfc672a90b74 ("regex/mlx5: support probing")
Signed-off-by: Parav Pandit
---
drivers/regex/mlx5/mlx5_regex.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/r
Now that mlx5_pci PMD checks for enabled classes and performs
probe(), remove() of associated classes, individual class driver
does not need to check if other driver is enabled.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
---
drivers/common/mlx5/mlx5_common.c | 37
Migrate mlx5 net, vdpa and regex PMD to start using mlx5 common class
driver.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
---
Changelog:
v7->v8:
- Extended support for newly added mlx5 regex driver
---
drivers/common/mlx5/mlx5_common_pci.c | 6 ++
drivers/net/mlx5/Makefile
On 7/23/2020 12:08 AM, Fady Bader wrote:
v2: * fixed style issue.
v3: * replaced htons with rte_cpu_to_be_16.
* rebased to current master.
v4: * removed the use of rte_random in librte_net.
* replaced htons with RTE_BE16.
Fady Bader (3):
net: fix s_addr redefinition in Windows
When adding a RSS rule with GTPU_DWN/UP, it will search profile
table from the top index. If a RSS rule with GTPU_EH already exists,
then GTPU_DWN/UP packet will match GTPU_EH profile. This patch solves
this issue by removing existed GTPU_EH rule before creating a new
GTPU_DWN/UP rule.
Fixes: 2e28
Add GTPU_IP and GTPU_EH hash in default.
Signed-off-by: Jeff Guo
---
drivers/net/iavf/iavf_hash.c | 12
1 file changed, 12 insertions(+)
diff --git a/drivers/net/iavf/iavf_hash.c b/drivers/net/iavf/iavf_hash.c
index 40bb9dddc..8c7f13b01 100644
--- a/drivers/net/iavf/iavf_hash.c
+++
> -Original Message-
> From: Zhang, Qi Z
> Sent: Thursday, July 23, 2020 8:53 PM
> To: Yang, Qiming ; Wang, ShougangX
> ; dev@dpdk.org
> Cc: Xing, Beilei ; Guo, Jia ; Wang,
> ShougangX ; sta...@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH v3] net/i40e: fix incorrect hash look up table
>
>
1 - 100 of 110 matches
Mail list logo
