On Mon, 27 May 2024 14:15:28 +0800
Howard Wang wrote:
> r8125 is for Realtek 2.5 Gigabit Ethernet NICs.
>
> Signed-off-by: Howard Wang
To the two drivers have any common code? Many drivers in DPDK use
drivers/common for cases
where two drivers can reuse same code.
Hi all,
I have two dpdk app, one primary and one secondary. I create a hash table
in the primary dpdk app like this:
static struct rte_hash_parameters ut_params = {
.name = "BufferTable2",
.entries = 1024*256,
.key_len = sizeof(uint64_t),
.hash_func = rte_jhash,
//.extra_flag=
21/05/2024 03:01, Stephen Hemminger:
> If fortify is enabled, it will generate a warning if memcpy
> src is NULL even if size is zero. This happens if the MP message
> sync is called with no file descriptors.
>
> Bugzilla ID 1446
> Fixes: 6a84c37e3975 ("net/virtio-user: add vhost-user adapter laye
From: Ferruh Yigit
Date: Wednesday, May 22, 2024 at 2:00 PM
To: Damodharam Ammepalli , Ajit Khaparde
Cc: dev@dpdk.org , Thomas Monjalon ,
huangdengdui , lihuisong (C) ,
step...@networkplumber.org ,
fengcheng...@huawei.com , haij...@huawei.com <
haij...@huawei.com>
Subject: Re: [RFC 0/2] Add supp
Reviewed-by: Jeremy Spewock
Reviewed-by: Jeremy Spewock
I think there was just one typo, otherwise:
Reviewed-by: Jeremy Spewock
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> This commit introduces a new "params" module, which adds a new way
> to manage command line parameters. The provided Params dataclass
> is able to read the fields of i
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> The way nodes and interactive shells interact makes it difficult to
> develop for static type checking and hinting. The current system relies
> on a top-down approach, attempting to give a generic interface to the
> test developer, hiding the
Reviewed-by: Jeremy Spewock
This looks good, the only comment I had was in some classes the
docstrings didn't get updated to what was discussed previously in the
comments (making sure the comments are included in the class'
docstring). I tried to point out a few places where I noticed it.
Other than those comments however:
R
Reviewed-by: Jeremy Spewock
Reviewed-by: Jeremy Spewock
On 24/05/2024 13:20, Morten Brørup wrote:
>> From: Paul Szczepanek [mailto:paul.szczepa...@arm.com]
>> Sent: Friday, 24 May 2024 10.37
>>
>> +size_t rte_mempool_get_obj_alignment(struct rte_mempool *mp)
>> +{
>> +if (mp == NULL)
>> +return 0;
>> +
>> +if (mp->flags & RTE_MEMPO
On 24/05/2024 10:09, Konstantin Ananyev wrote:
>
>
>> I have added macros to help find the parameters and I have added mempool
>> functions that allow you to determine if you can use the mempool and
>> what params it needs. The new mempool functions are mentioned in the
>> docs for ptr compres
Hello,
First of all, sorry if this is not the right place for this subject.
I'm trying to get involved and contribute to dpdk, I went through the
contribution page in docs but I think it doesn have enough info, I can see
some bugs reported on BugZilla, the question is
How to get a bug assigned to m
Provided a review for the wrong version...
Tested-by: Nicholas Pratte
Reviewed-by: Nicholas Pratte
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> Make it so that interactive shells accept an implementation of `Params`
> for app arguments. Convert EalParameters to use `Params` instead.
On Tue, May 28, 2024 at 2:18 PM Rahul Bhansali wrote:
>
> If promiscuous mode is enabled and default MAC address is set
> again then promiscuous mode gets disabled in hardware.
>
> This change will restore promiscuous behavior after configuring
> default MAC address.
>
> Fixes: 5fe86db2a0dd ("net/
Hi, I've added the Ubuntu 24.04 environment to the Community Lab but
without werror enabled as the rte_pcapng.c warning would cause them to
fail. Once the rte_pcapng.c warning is fixed, I will re-enable werror. I
will send an email to the ci mailing list with the logs of the warning so
that people
On 2024-05-28 11:07, Morten Brørup wrote:
From: Mattias Rönnblom [mailto:hof...@lysator.liu.se]
Sent: Tuesday, 28 May 2024 11.00
On 2024-05-28 10:27, Bruce Richardson wrote:
On Tue, May 28, 2024 at 10:19:15AM +0200, Mattias Rönnblom wrote:
On 2024-05-28 09:43, Mattias Rönnblom wrote:
Provide
On Tue, May 28, 2024 at 12:43 PM Nithin Dabilpuram
wrote:
>
> From: Srujana Challa
>
> Defines CPT HW result format for PMD API,
> rte_pmd_cnxk_inl_ipsec_res().
>
> Signed-off-by: Srujana Challa
Series applied to dpdk-next-net-mrvl/for-main. Thanks
On 2024-05-28 16:59, Stephen Hemminger wrote:
On Tue, 28 May 2024 10:19:15 +0200
Mattias Rönnblom wrote:
I've tested this patch some with DSW micro benchmarks, and the result is
a 2.5% reduction of the DSW+testapp overhead with cc/libc memcpy. GCC 11.4.
We've also run characteristic test
Tested-by: Nicholas Pratte
Reviewed-by: Nicholas Pratte
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> Implement all the testpmd shell parameters into a data structure.
>
> Signed-off-by: Luca Vizzarro
> Reviewed-by: Paul Szczepanek
> ---
> dts/framework/params/testpmd.py
Tested-by: Nicholas Pratte
Reviewed-by: Nicholas Pratte
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> Interactive shells that inherit DPDKShell initialise their params
> classes from a kwargs dict. Therefore, static type checking is
> disabled. This change uses the functionality of Un
Tested-by: Nicholas Pratte
Reviewed-by: Nicholas Pratte
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> The way nodes and interactive shells interact makes it difficult to
> develop for static type checking and hinting. The current system relies
> on a top-down approach, attempting to g
Tested-by: Nicholas Pratte
Reviewed-by: Nicholas Pratte
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> Update the buffer scatter test suite to use TestPmdParameters
> instead of the StrParams implementation.
>
> Signed-off-by: Luca Vizzarro
> Reviewed-by: Paul Szczepanek
> ---
> dts
Tested-by: Nicholas Pratte
Reviewed-by: Nicholas Pratte
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> Remove the imports in the testbed_model and remote_session modules init
> file, to avoid the initialisation of unneeded modules, thus removing or
> limiting the risk of circular depen
Tested-by: Nicholas Pratte
Reviewed-by: Nicholas Pratte
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> Move EalParams to its own module to avoid circular dependencies.
>
> Signed-off-by: Luca Vizzarro
> Reviewed-by: Paul Szczepanek
> ---
> dts/framework/params/eal.py
Tested-by: Nicholas Pratte
Reviewed-by: Nicholas Pratte
On Tue, Mar 26, 2024 at 3:04 PM Luca Vizzarro wrote:
>
> Make it so that interactive shells accept an implementation of `Params`
> for app arguments. Convert EalParameters to use `Params` instead.
>
> String command line parameters can sti
Tested-by: Nicholas Pratte
Reviewed-by: Nicholas Pratte
On Thu, May 9, 2024 at 7:21 AM Luca Vizzarro wrote:
>
> This commit introduces a new "params" module, which adds a new way
> to manage command line parameters. The provided Params dataclass
> is able to read the fields of its child class a
On Tue, May 28, 2024 at 07:59:36AM -0700, Stephen Hemminger wrote:
> On Tue, 28 May 2024 10:19:15 +0200
> Mattias Rönnblom wrote:
>
> > >
> >
> > I've tested this patch some with DSW micro benchmarks, and the result is
> > a 2.5% reduction of the DSW+testapp overhead with cc/libc memcpy. GCC
On Tue, 28 May 2024 07:54:22 +
"florian.duesin...@web.de" wrote:
> Dear Developers of pktgen,
> After the recent updates of pktgen I was finally able to compile the code but
> I get 2 critical errors when I try to use pktgen.
I don't think pktgen is maintained anymore.
Hi Mattia,
Have you looked into the O-RAN OSC open fronthaul phy implementation?
https://docs.o-ran-sc.org/projects/o-ran-sc-o-du-phy/en/latest/Architecture-Overview_fh.html
Cheers,
Lincoln
On Tue, May 28, 2024 at 10:31 AM Mattia Milani
wrote:
> Dear DPDK Dev community,
>
> I hope this is the
Dear Developers of pktgen,
After the recent updates of pktgen I was finally able to compile the code but I
get 2 critical errors when I try to use pktgen.
First:
I testet the newest pktgen code from git on a virtual Machine using EVE-NG and
a physical Computer with an Intel i9 and 2 1G Nics. On
Hi Ferruh:
The Ethernet controller connected to the "GPY215 PHY" is the integrated Gigabit
Ethernet (GbE) controller from the Intel Amston Lake CPU.
The output of `lspci` is as follows:
00:1e.4 Ethernet controller [0200]: Intel Corporation Device [8086:54ac]
Best Regards,
Amy Shih
Advantech IC
- On May 28, 2024, at 1:55 AM, Dmitry Kozlyuk dmitry.kozl...@gmail.com
wrote:
> Hi Lewis,
>
> Memory reserved by eal_get_virtual_area() is not yet useful,
> but it is very large, so by excluding it from dumps,
> DPDK prevents dumps from including large zero-filled parts.
>
> It also makes
On 24/05/2024 17:17, Patrick Robb wrote:
Luca, I assume what you had in mind was we will run
dts-check-format.sh, so including isort and pylama, as opposed to just
mypy? Thanks.
I originally thought of mypy only, Juraj suggested the dts-check-format.
I guess it is a good suggestion, and we shoul
On 24/05/2024 15:51, Patrick Robb wrote:
I think this is fine. Another option would be to move sut_nodes and
tg_nodes up as DTSRunner attributes. I like preserving the type hint,
but it also might just be cluttering the code to do this... up to you.
I made the change because of a complaint comi
Aaron,
I have been trying to submit a patch with a dependency on another patch, but it
keeps failing, and the error message "Apply patch set 140352 failed: 404 Not
Found" isn't very helpful.
Could you please take a look at it and let me know what's going on:
https://patchwork.dpdk.org/project/d
> -Original Message-
> From: Bruce Richardson
> Sent: Tuesday, May 28, 2024 3:10 PM
> To: Pavan Nikhilesh Bhagavatula
> Cc: Jerin Jacob ; Nithin Kumar Dabilpuram
> ; Kiran Kumar Kokkilagadda
> ; Sunil Kumar Kori ; Satha
> Koteswara Rao Kottidi ; Harman Kalra
> ; Shijith Thotton ; Anato
The HW flag action is supported by adding the tag to packet, with the
default tag value.
Signed-off-by: Shun Hao
Acked-by: Suanming Mou
---
drivers/net/mlx5/mlx5_flow_hw.c | 15 +++
1 file changed, 15 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow_hw.c b/drivers/net/mlx5/mlx
The HW flag action is supported by adding the tag to packet, with the
default tag value.
Signed-off-by: Shun Hao
Acked-by: Suanming Mou
---
drivers/net/mlx5/mlx5_flow_hw.c | 14 ++
1 file changed, 14 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow_hw.c b/drivers/net/mlx5/mlx5
On Tue, May 28, 2024 at 09:23:12AM +, Pavan Nikhilesh Bhagavatula
wrote:
> > On Mon, May 27, 2024 at 09:04:29PM +0530, pbhagavat...@marvell.com
> > wrote:
> > > From: Pavan Nikhilesh
> > >
> > > Disable building template files when CNXK_DIS_TMPLT_FUNC is defined
> > > as a part of c_args. Thi
> On Mon, May 27, 2024 at 09:04:29PM +0530, pbhagavat...@marvell.com
> wrote:
> > From: Pavan Nikhilesh
> >
> > Disable building template files when CNXK_DIS_TMPLT_FUNC
> > is defined as a part of c_args.
> > This option can be used when reworking datapath or debugging
> > issues to reduce Rx/Tx p
> From: Mattias Rönnblom [mailto:hof...@lysator.liu.se]
> Sent: Tuesday, 28 May 2024 11.00
>
> On 2024-05-28 10:27, Bruce Richardson wrote:
> > On Tue, May 28, 2024 at 10:19:15AM +0200, Mattias Rönnblom wrote:
> >> On 2024-05-28 09:43, Mattias Rönnblom wrote:
> >>> Provide build option to have fun
On 2024-05-28 10:27, Bruce Richardson wrote:
On Tue, May 28, 2024 at 10:19:15AM +0200, Mattias Rönnblom wrote:
On 2024-05-28 09:43, Mattias Rönnblom wrote:
Provide build option to have functions in delegate to
the standard compiler/libc memcpy(), instead of using the various
traditional, handc
On Mon, May 27, 2024 at 6:13 PM wrote:
>
> From: Pavan Nikhilesh
>
> Add support to configure higher chunk size by using the new
> OPEN_V2 mailbox, this improves performance as the number of
> mempool allocs are reduced.
> Add timeout when polling for queue idle timeout.
>
> Signed-off-by: Pavan
If promiscuous mode is enabled and default MAC address is set
again then promiscuous mode gets disabled in hardware.
This change will restore promiscuous behavior after configuring
default MAC address.
Fixes: 5fe86db2a0dd ("net/cnxk: support MAC address set")
Cc: sta...@dpdk.org
Signed-off-by: R
On Tue, May 28, 2024 at 10:19:15AM +0200, Mattias Rönnblom wrote:
> On 2024-05-28 09:43, Mattias Rönnblom wrote:
> > Provide build option to have functions in delegate to
> > the standard compiler/libc memcpy(), instead of using the various
> > traditional, handcrafted, per-architecture rte_memcpy
On Tue, May 28, 2024 at 09:43:54AM +0200, Mattias Rönnblom wrote:
> Provide build option to have functions in delegate to
> the standard compiler/libc memcpy(), instead of using the various
> traditional, handcrafted, per-architecture rte_memcpy()
> implementations.
>
> A new meson build option '
On 2024-05-28 09:43, Mattias Rönnblom wrote:
Provide build option to have functions in delegate to
the standard compiler/libc memcpy(), instead of using the various
traditional, handcrafted, per-architecture rte_memcpy()
implementations.
A new meson build option 'use_cc_memcpy' is added. The de
unint32_t type has been introduced in the function idpf_vc_queue_switch().
This helps in providing right queue type while calling the function.
Signed-off-by: Soumyadeep Hore
---
drivers/net/cpfl/cpfl_ethdev.c | 8
drivers/net/cpfl/cpfl_rxtx.c | 8
2 files changed, 8 insertio
unint32_t type has been introduced in the function idpf_vc_queue_switch().
This helps in providing right queue type while calling the function.
Signed-off-by: Soumyadeep Hore
---
drivers/net/idpf/idpf_rxtx.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/
unint32_t type has been introduced in the function idpf_vc_queue_switch().
This helps in providing right queue type while calling the function.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/idpf_common_virtchnl.c | 8 ++--
drivers/common/idpf/idpf_common_virtchnl.h | 2 +-
2 files c
Increasing size of xn_index in idpf_xn.c from u8 to u16
for fixing compilation warning.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/idpf_xn.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/common/idpf/base/idpf_xn.c
b/drivers/common/idpf/base/idpf_xn
Introducing ETH_ALEN macro for mac address length.
this definition is used in idpf_xn.c and was missing
previously.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/idpf_common_device.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/common/idpf/idpf_common_device.h
b/driver
Based on latest implemenation of struct VIRTCHNL_QUEUE_TYPE_RX
in virtchnl2.h, qg_info field is removed and its members are
added in the above mentioned structure. Hence updating the same.
Signed-off-by: Soumyadeep Hore
---
drivers/net/cpfl/cpfl_ethdev.c | 28 ++--
1 file
Based on latest implemenation of struct VIRTCHNL_QUEUE_TYPE_RX
in virtchnl2.h, qg_info field is removed and its members are
updated in the abve mentioned structure. Hence updating the same.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/idpf_common_virtchnl.c | 2 +-
1 file changed, 1 in
The function virtchnl2_vc_validate_vf_msg() currently has
implementation based on Linux 6.5 kernel and is redundant
for dpdk.
In future if required new implementation will be added.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/virtchnl2.h | 326 ---
1 file
Removing idpf_common.c file and its definitions as it
is primarily used for WINDOWS and ESX driver support.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/idpf_common.c| 382 --
drivers/common/idpf/base/idpf_prototype.h | 23 --
drivers/common/idpf/base/meso
Adding a new structure for the context descriptor that contains
the support for timesync packets, where the index for timestamping is set.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/idpf_lan_txrx.h | 20 +++-
1 file changed, 19 insertions(+), 1 deletion(-)
diff
Introduced through customer's feedback in their attempt to address some
bugs this introduces a memory barrier before posting ctlq tail. This
makes sure memory writes have a chance to take place before HW starts
messing with the descriptors.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/
In the arm random config file, kconfig option 'CONFIG_AEABI' is
disabled which results in adding the compiler flag '-mabi=apcs-gnu'.
This causes the compiler to add padding in virtchnl2_ptype
structure to align it to 8 bytes, resulting in size check failure.
Avoid the compiler padding by using "__
With the introduction of the flex array support, DECLARE_FLEX_ARRAY
macro was used in virtchnl2_rss_key struct with the wrong assumption
that it adds the required padding byte (8 byte structure alignment),
to avoid the compiler added padding. But the actual padding byte
was added by the compiler (f
This capability bit indicates both inline as well as side band flow
steering capability.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/virtchnl2.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/common/idpf/base/virtchnl2.h
b/drivers/common/idpf/base/vi
Support added for xn transaction apis to send/receive control queue
messages.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/idpf_osdep.c | 71 +
drivers/common/idpf/base/idpf_osdep.h | 80 -
drivers/common/idpf/base/idpf_xn.c| 439 ++
drivers/c
Dont initialize the variables if not needed.
Also use 'err' instead of 'status', 'ret_code', 'ret' etc.
for consistency and change the return label 'sq_send_command_out'
to 'err_unlock'.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/idpf_controlq.c | 60 +--
.
On Mon, May 27, 2024 at 8:47 PM Anoob Joseph wrote:
>
> Add Odyssey ODM DMA device. This PMD abstracts ODM hardware unit on
> Odyssey SoC which can perform mem to mem copies.
>
> The hardware unit can support upto 32 queues (vchan) and 16 VFs. It
> supports 'fill' operation with specific values. I
The current virtchnl header uses 1-sized array to address
the dynamic size of the virtchnl structure. For example in the
following structure, the size of the struct depends on the 'num_chunks'
and we use 'chunks[1]' to dereference each chunk information.
struct virtchnl2_queue_reg_chunks {
Kernel coding style prefers the use of enums, so we must change
all groups of related defines to enums. The names of the enums
are chosen to follow the common part of the naming pattern
as much as possible.
Replaced the common labels from the comments with the enum names.
While at it, modify head
Based on the upstream feedback, driver should not use any
defensive programming strategy by checking for NULL pointers
and other conditional checks unnecessarily in the code flow
to fall back, instead fail and fix the bug in a proper way.
Some of the checks checks are identified and removed/wrappe
There is an issue of recursive header file includes in accessing the
idpf_hw structure. The controlq.h has the structure definition and osdep
header file needs that. The problem is the controlq.h also needs
the osdep header file contents, basically both dependent on each other.
Today it was resolv
Removed unused VIRTCHNL2_CAP_ADQ capability and use that bit for
VIRTCHNL2_CAP_INLINE_FLOW_STEER capability.
Added VIRTCHNL2_VPORT_INLINE_FLOW_STEER_ENA port flag to allow
enable/disable per vport.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/virtchnl2.h | 5 +++--
1 file changed
When the message for getting timestamp latches is sent by the driver,
number of latches is equal to 0. Current implementation of message
validation function incorrectly notifies this kind of message length as
invalid.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/virtchnl2.h | 4 ++
Some compilers will use 64-bit addressing and compiler will detect
such loss of data
virtchnl2.h(1890,40): warning C4244: '=': conversion from '__int64' to
'__le32', possible loss of data
on line 1890
offset = (u8 *)(&groups->groups[0]) - (u8 *)groups;
Removed unnecessary zero init
Signed-off-b
Update IDPF VF device id to 145C removing the support for legacy AVF of
0x1889.
In accordance to DCR-3788 added device ID for S-IOV device.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/idpf_devids.h | 12 +++-
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/
The aim of the changes is to remove NVME dependency on
memory allocations, and to use a prepared buffer instead.
The changes do not affect other components.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/idpf_controlq.c | 27 +---
drivers/common/idpf/base/idpf_c
This patchset updates IDPF base driver to latest shared code snapshot.
Soumyadeep Hore (25):
common/idpf: added NVME CPF specific code with defines
common/idpf: updated IDPF VF device ID
common/idpf: update ADD QUEUE GROUPS offset
common/idpf: update in PTP message validation
common/idpf
Provide build option to have functions in delegate to
the standard compiler/libc memcpy(), instead of using the various
traditional, handcrafted, per-architecture rte_memcpy()
implementations.
A new meson build option 'use_cc_memcpy' is added. The default is
true. It's not obvious what should be
From: Srujana Challa
Defines CPT HW result format for PMD API,
rte_pmd_cnxk_inl_ipsec_res().
Signed-off-by: Srujana Challa
---
drivers/net/cnxk/cn10k_ethdev_sec.c | 4 +--
drivers/net/cnxk/rte_pmd_cnxk.h | 40 +++--
2 files changed, 40 insertions(+), 4 deletions(-)
From: Sunil Kumar Kori
Currently only NIX stats are cleared during xstats
reset and CGX stats are left as it is.
Clearing CGX stats too during xstats reset.
Fixes: 8075b057b620 ("net/cnxk: support extended statistics")
Signed-off-by: Sunil Kumar Kori
---
drivers/net/cnxk/cnxk_stats.c | 2 ++
From: Sunil Kumar Kori
Similar to NIX stats reset API, adding API to reset
CGX stats.
When user requests to reset the stats then it clears
if nix_lf is PF otherwise silently discard the request.
Signed-off-by: Sunil Kumar Kori
---
drivers/common/cnxk/roc_nix.h | 1 +
drivers/common/cnxk/
When the rte_memcpy() size is 16, the same 16 bytes are copied twice.
In the case where the size is known to be 16 at build tine, omit the
duplicate copy.
Reduced the amount of effectively copy-pasted code by using #ifdef
inside functions instead of outside functions.
Suggested-by: Stephen Hemmin
Fix issue with outbound security path while handling mixed traffic i.e
both plain and inline outbound pkts being present as part of burst
and burst size is > 32. The loop needs to be broken when
we don't have space for 4 pkts in LMT lines for CPT considering
both the full lmt lines and partial lmt
Add option to explicitly disable custom meta aura. Currently
custom meta aura is enabled automatically when inl_cpt_channel
is set i.e inline dev is masking CHAN field in IPsec rules.
Also decouple the custom meta aura feature from custom sa action
so that the custom sa action can independently be
Update SA userdata as part of session_update() and
keep the original cookie that is used to identify
SA.
Fixes: 8efa348e8160 ("net/cnxk: support custom SA index")
Cc: sta...@dpdk.org
Signed-off-by: Nithin Dabilpuram
---
drivers/net/cnxk/cn10k_ethdev_sec.c | 57 -
1 f
Override UDP encap ports with session info when non-zero on cn10k.
This makes the UDP encap ports configurable by user as needed.
Default UDP source and destination ports will still be 4500.
Signed-off-by: Nithin Dabilpuram
---
drivers/common/cnxk/cnxk_security.c | 22 ++
1 f
From: Satha Rao
To get better performance on LBK or VF interfaces, set the default
root schedule weight to known tested value.
Signed-off-by: Satha Rao
---
drivers/net/cnxk/cnxk_ethdev.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/net/cnxk/cnxk_ethdev.c b/drivers/net/cnxk/c
From: Rakesh Kudurumalla
Avoid double free of extbuf when during TX path in
multisegmented packet with extbuf as one of segment.
Fixes: dd9446991212 ("net/cnxk: add transmit completion handler")
Cc: sta...@dpdk.org
Signed-off-by: Rakesh Kudurumalla
---
drivers/net/cnxk/cn9k_tx.h | 1 +
1 file
From: Satha Rao
By default set VF root scheduling weight same as other kernel
configured VFs. Also fix a compilation issue when cflags has
-Werror=shadow=compatible-local.
Signed-off-by: Satha Rao
---
v2:
- Added fixes tag to 9/10 and documentation to 10/10, 6/10
patches
drivers/common/cnx
89 matches
Mail list logo
