Hi Yuan,
> -Original Message-
> From: Wang, YuanX
> Sent: Wednesday, September 22, 2021 4:56 PM
> To: dev@dpdk.org
> Cc: maxime.coque...@redhat.com; Xia, Chenbo ; Hu,
> Jiayu ; Ding, Xuan ; Jiang,
> Cheng1 ; Ma, WenwuX ;
> Yang, YvonneX ; Pai G, Sunil
>
> Subject: [PATCH v3 2/2] vhost: a
> -Original Message-
> From: Dmitry Kozlyuk
> Sent: Monday, September 6, 2021 3:34 PM
> To: Peng, ZhihongX
> Cc: olivier.m...@6wind.com; dev@dpdk.org; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] lib/cmdline: release cl when cmdline exit
>
> 2021-09-06 05:51 (UTC+), Peng, Zhihon
> -Original Message-
> From: Peng, ZhihongX
> Sent: Friday, September 17, 2021 10:15 AM
> To: olivier.m...@6wind.com; step...@networkplumber.org
> Cc: dev@dpdk.org; Peng, ZhihongX ;
> sta...@dpdk.org
> Subject: [PATCH v2 1/2] lib/cmdline: release cl when cmdline exit
>
> From: Zhihong Pen
https://bugs.dpdk.org/show_bug.cgi?id=817
Bug ID: 817
Summary: net/ice build failure with gcc 4.8.5
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
P
Hi. Thomas
I've summed up our previous discussion.
Can you look at the final proposal again?
Do you think we should deal with the problem better?
在 2021/9/27 9:44, Huisong Li 写道:
在 2021/9/27 3:16, Thomas Monjalon 写道:
26/09/2021 14:20, Huisong Li:
在 2021/9/18 16:46, Thomas Monjalon 写道:
18
Hello,
Please find the slides and the excel sheet containing the work
items to fix DTS. We will review the slides in this meeting. Please provide
your review comments before the meeting if possible.
The update to Techboard will happen on 6th October.
Thank you,
Honnappa
> -Original Message-
> From: Andrew Rybchenko
> Sent: Wednesday, September 29, 2021 16:40
> To: Li, Xiaoyun ; Yigit, Ferruh
> ; Xing, Beilei
> ; Xu, Rosen ; Wang, Haiyue
> ; Ray
> Kinsella ; Jiawen Wu ; Jian Wang
> ;
> Thomas Monjalon
> Cc: dev@dpdk.org
> Subject: [PATCH v2] ethdev: re
On Wed, Sep 29, 2021 at 2:27 PM Thomas Monjalon wrote:
>
> 29/09/2021 10:39, Andrew Rybchenko:
> > A more fine-grain flow API action RTE_FLOW_ACTION_TYPE_SAMPLE should
> > be used instead of it.
> >
> > Signed-off-by: Andrew Rybchenko
> > ---
> > v2:
> > - fix description
> > - mention RT
From: Zhihong Peng
After adding ASan, the gcc compilation check will be stricter.
"Control reaches end of non-void function" error occurs here.
Fixes: f38913b7fb8e (pipeline: add meter array to SWX)
Cc: sta...@dpdk.org
Signed-off-by: Xueqin Lin
Signed-off-by: Zhihong Peng
---
lib/pipeline/rt
From: Zhihong Peng
AddressSanitizer (ASan) is a google memory error detect
standard tool. It could help to detect use-after-free and
{heap,stack,global}-buffer overflow bugs in C/C++ programs,
print detailed error information when error happens, large
improve debug efficiency.
`AddressSanitizer
Some packets are discarded by the NIC because they are larger than
the MTU, these packets should be counted as "RX error" instead of
"RX packet", for example:
pkt1 = Ether()/IP()/Raw('x' * 1400)
pkt2 = Ether()/IP()/Raw('x' * 1500)
Forward statistics for port 0 -
> -Original Message-
> From: Ding, Xuan
> Sent: Wednesday, September 29, 2021 10:41 AM
> To: dev@dpdk.org; Burakov, Anatoly ;
> maxime.coque...@redhat.com; Xia, Chenbo
> Cc: Hu, Jiayu ; Jiang, Cheng1 ;
> Richardson, Bruce ; Pai G, Sunil
> ; Wang, Yinan ; Yang,
> YvonneX ; Ding, Xuan
>
> -Original Message-
> From: Burakov, Anatoly
> Sent: Monday, September 27, 2021 8:03 PM
> To: Peng, ZhihongX ; Ananyev, Konstantin
> ; step...@networkplumber.org
> Cc: dev@dpdk.org; Lin, Xueqin
> Subject: Re: [PATCH v3] Enable AddressSanitizer feature on DPDK
>
> On 18-Sep-21 8:41 AM, z
> -Original Message-
> From: Burakov, Anatoly
> Sent: Wednesday, September 29, 2021 5:39 PM
> To: Hu, Jiayu ; Ding, Xuan ;
> dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo
>
> Cc: Jiang, Cheng1 ; Richardson, Bruce
> ; Pai G, Sunil ; Wang,
> Yinan ; Yang, YvonneX
> Subject: Re: [
Hi Konstantin,
Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Wednesday, September 29, 2021 5:09 PM
> To: Anoob Joseph ; Archana Muniganti
> ; Akhil Goyal ; Nicolau, Radu
> ; Zhang, Roy Fan ;
> hemant.agra...@nxp.com
> Cc: Tejasree Kondoj ; Ank
Hi
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, September 29, 2021 17:17
> To: dev@dpdk.org; Xia, Chenbo ;
> amore...@redhat.com; david.march...@redhat.com;
> andrew.rybche...@oktetlabs.ru; Yigit, Ferruh ;
> michae...@nvidia.com; viachesl...@nvidia.com; Li, Xiaoyun
>
>
> Subject: [PATCH 1/3] bus/vmbus: fix leak on device scan
>
> Caught running ASAN.
>
> The device name is leaked on scan.
> rte_device name field being a const, use the private vmbus struct to store the
> device name and point at it.
>
> Fixes: 831dba47bd36 ("bus/vmbus: add Hyper-V virtual bus s
For native build, enabling building the highest cpu_instruction_set
supported by the build host, including the new POWER10.
For cross compile, verifying that the compiler supports the
cpu_instruction_set specified in the cross-file
Signed-off-by: Thinh Tran
Reviewed-by: David Christensen
--
On Wed, 29 Sep 2021 20:52:43 +0200
Thomas Monjalon wrote:
> 29/09/2021 19:44, Stephen Hemminger:
> > Have a problem with auto-detecting whether device driver supports rte_flow.
> >
> > Ideally in application would like to be able adapt to handle devices that
> > do rte_flow and those that do not
28/09/2021 10:50, Rongwei Liu:
> In socket direct mode, it's possible to bind any two (maybe four
> in future) PCIe devices with IDs like :xx:xx.x and
> :yy:yy.y. Bonding member interfaces are unnecessary to have
> the same PCIe domain/bus/device ID anymore,
>
> Kernel driver uses "system_
Hi Andrew,
On Wed, Sep 29, 2021 at 10:37:34AM +0300, Andrew Rybchenko wrote:
> Removed offload flag PKT_RX_EIP_CKSUM_BAD. PKT_RX_OUTER_IP_CKSUM_BAD
> should be used as a replacement.
>
> Signed-off-by: Andrew Rybchenko
FYI, I just submitted a patchset that removes all PKT_ flags and
fixes the n
The mbuf offload flags do not match the DPDK namespace (they are not
prefixed by RTE_). This coccinelle script is used in the next commit to
do the replacement in the code.
A draft script was initially submitted in commit d7595795b760 ("doc:
announce renaming of mbuf offload flags"), but dropped b
The flags PKT_TX_VLAN_PKT, PKT_TX_QINQ_PKT, PKT_RX_EIP_CKSUM_BAD are
marked as deprecated since commit 380a7aab1ae2 ("mbuf: rename deprecated
VLAN flags") (2017). Remove their definitions from rte_mbuf_core.h,
and replace their usages.
Signed-off-by: Olivier Matz
---
app/test-pmd/flowgen.c
This patchset fixes the mbuf offload flags namespace by adding an RTE_
prefix to the definitions. The old flags remain usable, but a deprecation
warning is issued at compilation.
Note for committers: I can rebase this patchset quite easily (most of
the work is scripted), so don't hesitate to sync
A '*' is missing at 2 places, add them.
Fixes: e1a00536c8ed ("kvargs: add a new library to parse key/value arguments")
Fixes: 3ab385063cb9 ("kvargs: add get by key")
Signed-off-by: Olivier Matz
Reviewed-by: Xueming Li
---
lib/kvargs/rte_kvargs.h | 4 ++--
1 file changed, 2 insertions(+), 2 del
The function was designed to be used as a handler for
rte_kvargs_process() to compare the value string in a kvlist. For
readability, its usages in DPDK have been replaced by
rte_kvargs_get_with_value() in previous commit.
Remove this function, as it is not used anymore.
Signed-off-by: Olivier Mat
A quite common scenario with kvargs is to lookup for a = in
a kvlist. For instance, check if name=foo is present in
name=toto,name=foo,name=bar. This is currently done in drivers/bus with
rte_kvargs_process() + the rte_kvargs_strcmp() handler.
This approach is not straightforward, and can be repla
The function rte_kvargs_get() is used by eal and pci bus driver since
its introduction in commit 3ab385063cb9 ("kvargs: add get by key") and
commit d2a66ad79480 ("bus: add device arguments name parsing"), in
dpdk 21.05.
Let's promote it as stable.
Signed-off-by: Olivier Matz
Reviewed-by: Xueming
This function is used by EAL to parse key/value strings separated with
specified delimiters.
It was introduced in 2018 by commit 5d6af85ab00c ("kvargs: introduce a
more flexible parsing function"), and can be promoted as stable.
Signed-off-by: Olivier Matz
Reviewed-by: Xueming Li
---
lib/kvarg
This patchset promotes 2 functions rte_kvargs_parse_delim() and
rte_kvargs_get() as stable.
It also replaces rte_kvargs_strcmp() by a new one
rte_kvargs_get_with_value(), which is easier to use.
v2
* remove rte_kvargs_strcmp from version.map
Olivier Matz (5):
kvargs: promote delimited parsing
Hi Ali,
On Wed, Sep 29, 2021 at 08:03:17AM +, Ali Alnubani wrote:
> Hi Olivier,
>
> I wanted to retest the patch on latest main, but it no longer applies, could
> you please rebase it?
I rebased the patch:
https://patchwork.dpdk.org/project/dpdk/patch/20210929213707.17727-1-olivier.m...@6w
m->nb_seg must be reset on mbuf free whatever the value of m->next,
because it can happen that m->nb_seg is != 1. For instance in this
case:
m1 = rte_pktmbuf_alloc(mp);
rte_pktmbuf_append(m1, 500);
m2 = rte_pktmbuf_alloc(mp);
rte_pktmbuf_append(m2, 500);
rte_pktmbuf_chain(m1, m2);
m0 =
27/09/2021 10:02, Bing Zhao:
> The metadata can be set in the mbuf dynamic field and then used in
> flow rules steering for egress direction. The hardware requires
> network order for both the insertion of a rule and sending a packet.
> Indeed, there is no strict restriction for the endianness. The
Hi Maxime,
On Wed, Sep 29, 2021 at 10:17:39PM +0200, Maxime Coquelin wrote:
> This patch removes the simplification in Virtio descriptors
> handling, where their buffer addresses are IOVAs for Virtio
> PCI devices, and VA-only for Virtio-user devices, which
> added a requirement on Virtio-user tha
By design, in a GROUP flow, outer match criteria go to "ENC" fields
of the action rule match specification. The current HW/FW hasn't
got support for these fields (except the VXLAN VNI) yet.
As a workaround, start parsing the pattern from the tunnel item.
Signed-off-by: Ivan Malov
Reviewed-by: An
Such a counter will only report the number of hits, which is actually
a sum of two contributions (the JUMP rule's own counter + indirect
increments issued by counters of the associated GROUP rules.
Signed-off-by: Ivan Malov
Reviewed-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_flow.c|
By design, JUMP flows should be represented solely by the outer rules. But
the HW/FW hasn't got support for setting Rx mark from RECIRC_ID on outer
rule lookup yet. Neither does it support outer rule counters. As a
workaround, an action rule of lower priority is used to do the job.
Signed-off-by:
The current HW/FW doesn't allow to match on MAC addresses in outer rules.
One day this will change for sure, but right now a workaround is needed.
Match on VLAN presence in outer rules is also unsupported. Ignore it.
Signed-off-by: Ivan Malov
Reviewed-by: Andrew Rybchenko
---
drivers/net/sfc/s
Support generic callbacks which callers will invoke to get
PMD-specific actions and items used to produce JUMP and
GROUP flows and to detect tunnel information.
Signed-off-by: Ivan Malov
Reviewed-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_dp.c | 48 +
drivers/net/sfc/sfc_dp.h
GROUP is an in-house term for so-called "tunnel_match" flows.
On parsing, they are detected by virtue of PMD-internal item
MARK. It associates a given flow with its tunnel context.
Such a flow is represented by a MAE action rule which is
chained with the corresponding JUMP rule's outer rule
by vir
Currently, there is an API for setting recirculation ID in
outer rules. Add an API to let action rules match on it.
Signed-off-by: Ivan Malov
Reviewed-by: Andrew Rybchenko
---
drivers/common/sfc_efx/base/efx.h | 13 ++
drivers/common/sfc_efx/base/efx_mae.c | 36 +
JUMP is an in-house term for so-called "tunnel_set" flows. On parsing,
they are identified by virtue of actions MARK (PMD-internal) and JUMP.
The action MARK associates a given flow with its tunnel context.
Such a flow is represented by a MAE outer rule (OR) which has its
recirculation ID set. Thi
When an outer rule is hit, it can pass recirculation ID down
to action rule lookup, and action rules can match on this ID
instead of matching on the outer rule allocation handle.
By default, recirculation ID is assumed to be zero.
Add an API to set recirculation ID in outer rules.
Signed-off-by:
Later patches add support for tunnel offload on Riverhead (EF100).
A board can host at most 254 tunnels. Partially offloaded (missed)
tunnel packets are identified by virtue of 8 high bits in Rx mark.
Add basic definitions of the upcoming tunnel offload support and
take care of the dedicated bits
The first 6 patches comprise the fundamental part of the series.
They are trying to be future-proof with respect to the planned
HW/FW changes. 4 more patches form the adaptation part of some
sort to make the offload work on the currently available HW/FW.
This patch series should be applied on top
29/09/2021 09:55, Matan Azrad:
> From: Bing Zhao
> > In the function mlx5_alloc_shared_dr(), there are various reasons to result
> > in
> > a failure and error clean up process. While in the caller of
> > mlx5_dev_spawn(),
> > once there is a error occurring after the mlx5_alloc_shared_dr(), the
From: Long Li
The driver code had wrong assumption that all the addresses to ring buffers
in the secondary process are the same as those in the primary process. This
is not always correct as the channels could be mapped to different
addresses in the secondary process.
Fix this by keeping track o
On Wed, Sep 29, 2021 at 2:44 AM Ferruh Yigit wrote:
>
> On 9/29/2021 9:20 AM, Thomas Monjalon wrote:
> > 28/09/2021 23:32, Ajit Khaparde:
> >> On Tue, Sep 28, 2021 at 5:43 AM Ferruh Yigit
> >> wrote:
> >>> Following warning is reported by Jerin & Thomas:
> >>>
> >>> $ ./devtools/check-doc-vs-cod
Hi Thomas,
PFA the test report. It covers all the features that were tested across
various platforms.
The features mentioned in the test report depend on a modified FreeBSD
OFED. There is an ongoing review of these changes by the FreeBSD community.
https://reviews.freebsd.org/p/vag.singh_oneconve
This patch removes the simplification in Virtio descriptors
handling, where their buffer addresses are IOVAs for Virtio
PCI devices, and VA-only for Virtio-user devices, which
added a requirement on Virtio-user that it only supported
IOVA as VA.
This change introduced a regression for applications
On 9/15/2021 9:26 AM, Tal Shnaiderman wrote:
Build the security library on Windows.
Remove unneeded export from version file.
Signed-off-by: Tal Shnaiderman
---
Depends-on: patch-98796 ("cryptodev: build on Windows")
---
lib/meson.build | 1 +
lib/security/version.map | 1 -
2 f
23/09/2021 08:45, Xueming Li:
> This patch support new global device syntax like:
> bus=pci,addr=BB:DD.F/class=eth/driver=mlx5,devargs,..
>
> In driver parameters check, ignores "driver" key which is part of new
> global device syntax instead of reporting error.
>
> Signed-off-by: Xueming L
29/09/2021 19:44, Stephen Hemminger:
> Have a problem with auto-detecting whether device driver supports rte_flow.
>
> Ideally in application would like to be able adapt to handle devices that
> do rte_flow and those that do not. If device does not support rte_flow,
> then configure with RSS acro
> -Original Message-
> From: David Christensen
> Sent: Tuesday, September 28, 2021 8:53 AM
> To: De Lara Guarch, Pablo ; Wang, Yipeng1
> ; Marohn, Byron
> Cc: dev@dpdk.org; Mcnamara, John
> Subject: Re: [PATCH v4] efd: change data type of parameter
>
>
>
> On 9/28/21 6:58 AM, Pablo de
Cc maillist for history record.
On Thu, 2021-09-23 at 23:34 +0800, Xueming Li wrote:
Hi Min,
On Thu, 2021-09-23 at 17:15 +0800, Min Hu (Connor) wrote:
Hi, Xueming,
Not only "rte_eth_devices[(hw)->data->port_id]" exist in HNS3 PMD, but
also "rte_eth_devices[rxq->port_id]", so marco wh
Have a problem with auto-detecting whether device driver supports rte_flow.
Ideally in application would like to be able adapt to handle devices that
do rte_flow and those that do not. If device does not support rte_flow,
then configure with RSS across multiple cores; if device does support rte_f
On 9/29/21 12:51 AM, De Lara Guarch, Pablo wrote:
Hi
-Original Message-
From: David Christensen
Sent: Tuesday, September 28, 2021 4:53 PM
To: De Lara Guarch, Pablo ; Wang, Yipeng1
; Marohn, Byron
Cc: dev@dpdk.org; Mcnamara, John
Subject: Re: [PATCH v4] efd: change data type of par
Hi, Aman
An example:
testpmd> flow create 0 ingress pattern eth / end actions rss key
0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef
queues 0 end / e
From: Piotr Bronowski
This patch enables out-of-place auth-cipher operations where
digest should be encrypted along with the rest of raw data.
It also adds support for partially encrypted digest when using
auth-cipher operations.
Signed-off-by: Damian Nowak
Signed-off-by: Kai Ji
Signed-off-by:
From: Kai Ji
Add in new chacha20_poly1305 support in ipsec_mb.
Add in new chacha20_poly1305 test vector for SGL test.
Signed-off-by: Kai Ji
Signed-off-by: Ciara Power
---
v3:
- Fixed some formatting.
- Removed unnecessary get session function.
v2:
- Added unused tag to session configur
From: Piotr Bronowski
This patch removes the crypto/zuc folder and gathers all zuc PMD
implementation specific details into a single file,
pmd_zuc.c in the crypto/ipsec_mb folder.
Signed-off-by: Piotr Bronowski
Signed-off-by: Ciara Power
---
v2: Updated maintainers file.
---
MAINTAINERS
The SW Crypto PMDs were consolidated into one IPSec_MB PMD.
This patch adds a release note to highlight this change.
Signed-off-by: Ciara Power
---
v3: Modified release note wording and added CHACHA20-POLY1305.
---
doc/guides/rel_notes/release_21_11.rst | 15 +++
1 file changed, 15
From: Piotr Bronowski
This patch removes the crypto/snow3g folder and gathers all snow3g PMD
implementation specific details into a single file,
pmd_snow3g.c in the crypto/ipsec_mb folder.
Signed-off-by: Piotr Bronowski
Signed-off-by: Ciara Power
---
v3: Removed extra empty lines.
v2: Updated
From: Piotr Bronowski
This patch removes the crypto/kasumi folder and gathers all kasumi PMD
implementation specific details into a single file,
pmd_kasumi.c in the crypto/ipsec_mb folder.
Signed-off-by: Piotr Bronowski
Signed-off-by: Ciara Power
---
v2: Updated maintainers file.
---
MAINTAI
From: Piotr Bronowski
This patch removes the crypto/aesni_gcm folder and gathers all
aesni-gcm PMD implementation specific details into a single file,
pmd_aesni_gcm.c in the crypto/ipsec_mb folder.
A redundant check for iv length is removed.
GCM ops are stored in the queue pair for multi process
The ipsec_mb SW PMD now has multiprocess support.
The queue-pair IMB_MGR is stored in a memzone instead of being allocated
externally by the Intel IPSec MB library, when v1.1 is used.
If v1.0 is used, multi process is not supported, and allocation is
done as before.
The secondary process needs to r
From: Fan Zhang
This patch introduces the new framework to share common code between
the SW crypto PMDs that depend on the intel-ipsec-mb library.
This change helps to reduce future effort on the code maintenance and
feature updates.
The PMDs that will be added to this framework in subsequent pa
This set of patches introduces a new framework, making all common code of
SW crypto PMD implementations built on top of intel-ipsec-mb library
sharable. This helps to reduce future effort on the code maintenance and
future updates. It also moves all SW PMD implementation specific details
into singl
On 9/28/2021 4:37 AM, dapengx...@intel.com wrote:
> From: Dapeng Yu
>
> When the iavf_adapter instance is not initialized completedly in the
> primary process, the secondary process accesses its "rte_eth_dev"
> member, it causes secondary process crash.
>
> This patch replaces adapter->eth_dev w
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> Add flags for outer vlan and include set port parameters in Linux
> compilation.
Isn't this a shared code drop, why it has changes specific to Linux compilation?
> Add flags, which describe port and switch state for both double vlan
> functionality and ou
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> PF has to delete all the filters during reset.
> If it is fully loaded with filters then it is possible
> that it will take more than 200 ms to finish the reset
> resulting in timeout during pf_reset and
> PF reset failed, -15 error indication.
> Increasing
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> Continuing the path to support MEM_TYPE_XSK_BUFF_POOL, the AF_XDP
> zero-copy/sk_buff rx_bi rings are now separate. Functions to properly
> allocate the different rings are added as well.
>
> Signed-off-by: Björn Töpel
> Signed-off-by: Robin Zhang
Again
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> Add definitions for Shadow RAM pointers: 6th FPA module, 5th FPA module
> in X722 and Preservation Rules Module.
>
> Signed-off-by: Stanislaw Grzeszczak
> Signed-off-by: Robin Zhang
Can you please update patch title to use all lowercase except abbreviat
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> For Active Optical Cable (AOC) the correct media type is "Fibre",
> not "Direct Attach Copper".
>
> Fixes: d749d4d89969 ("i40e/base: add AOC PHY types")
> Fixes: aa153cc89ff0 ("net/i40e/base: add new PHY types for 25G AOC and
> ACC")
> Cc: sta...@dpdk.org
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> Driver did not Set TSA table values when parsing CEE configuration
> obtained from FW.
>
> Signed-off-by: Pawel Malinowski
> Signed-off-by: Robin Zhang
Can you please long version of the 'TSA' & 'CEE' abbreviations in the commit
log?
There are more in
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> This change increments X722 API version and adds new constants related to
> the extended implementation of Security Version Opt-In.
>
There are new 'I40E_AQ_RREV_MODULE_PHY_*' macros, what is their relation with
"Security Version Opt-In"?
Also title ment
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> Unlike other supported adapters, 2.5G and 5G use different
> PHY type identifiers for reading/writing PHY settings
> and for reading link status. This commit intruduces
s/intruduces/introduces/
> separate PHY identifiers for these two operation types.
>
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> update i40e base code.
>
> source code of i40e driver:
> cid-i40e.2021.08.16.tar.gz
>
> changelog in i40e share repo:
> From 59a080f4fafe ("i40e-shared: Add opcode 0x0406 and 0x0416 to Linux
> support") To 2c7aab559654 ("i40e-shared: Add defines related t
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> ASQ send command functions are returning only i40e status codes
> yet some calling functions also need Admin Queue status
> that is stored in hw->aq.asq_last_status. Since hw object
> is stored on a heap it introduces a possibility for
> a race condition in
29/09/2021 17:56, Srikanth K:
> Hi Thomas,
>
> PFA the test report. It covers all the features that were tested across
> various platforms.
>
> The features mentioned in the test report depend on a modified FreeBSD
> OFED. There is an ongoing review of these changes by the FreeBSD community.
> ht
On 29/09/2021 16:31, Bruce Richardson wrote:
On Wed, Sep 29, 2021 at 04:24:06PM +0100, Bruce Richardson wrote:
On Wed, Sep 29, 2021 at 03:54:48PM +0100, Kevin Traynor wrote:
On 29/09/2021 14:32, Bruce Richardson wrote:
On Wed, Sep 29, 2021 at 01:28:53PM +0100, Kevin Traynor wrote:
Hi Bruce,
On 9/6/2021 3:02 AM, Robin Zhang wrote:
> Fix several kernel-doc warnings when building with W=1. These changes
> are only to comments.
>
Same here, why shared code drop has Linux kernel specific updates?
> Fixes: 8db9e2a1b232 ("i40e: base driver")
> Fixes: 842ea1996335 ("i40e/base: save link mo
> Subject: [PATCH v1 1/3] common/cnxk: set key length setting for PDCP algos
>
> Set proper bits in the context based on key length for PDCP
>
> Signed-off-by: Vidya Sagar Velumuri
>
Series
Acked-by: Akhil Goyal
Applied to dpdk-next-crypto
Thanks.
Update the calculation of the max length needed when converting mbuf to
data vec in partial digest test case. This update make sure the enough
vec buffers are allocated for the appended digest in sgl op for QAT raw
datapath api.
Fixes: 4868f6591c6f ("test/crypto: add cases for raw datapath API")
C
On Wed, Sep 29, 2021 at 04:24:06PM +0100, Bruce Richardson wrote:
> On Wed, Sep 29, 2021 at 03:54:48PM +0100, Kevin Traynor wrote:
> > On 29/09/2021 14:32, Bruce Richardson wrote:
> > > On Wed, Sep 29, 2021 at 01:28:53PM +0100, Kevin Traynor wrote:
> > > > Hi Bruce,
> > > >
> > > > On 24/09/2021 1
>
> On 9/15/2021 9:33 AM, Ruifeng Wang wrote:
> > Rx descriptor is 16B/32B in size. If the DD bit is set, it indicates
> > that the rest of the descriptor words have valid values. Hence, the
> > word containing DD bit must be read first before reading the rest of
> > the descriptor words.
> >
> >
On Wed, Sep 29, 2021 at 03:54:48PM +0100, Kevin Traynor wrote:
> On 29/09/2021 14:32, Bruce Richardson wrote:
> > On Wed, Sep 29, 2021 at 01:28:53PM +0100, Kevin Traynor wrote:
> > > Hi Bruce,
> > >
> > > On 24/09/2021 17:18, Bruce Richardson wrote:
> > > > When DPDK is run with --in-memory mode,
On 9/15/2021 9:33 AM, Ruifeng Wang wrote:
> Rx descriptor is 16B/32B in size. If the DD bit is set, it indicates
> that the rest of the descriptor words have valid values. Hence, the
> word containing DD bit must be read first before reading the rest of
> the descriptor words.
>
> Since the entire
On 29/09/2021 14:32, Bruce Richardson wrote:
On Wed, Sep 29, 2021 at 01:28:53PM +0100, Kevin Traynor wrote:
Hi Bruce,
On 24/09/2021 17:18, Bruce Richardson wrote:
When DPDK is run with --in-memory mode, multiple processes can run
simultaneously using the same runtime dir. This leads to each pr
On Wed, 2021-09-29 at 12:35 +, Ananyev, Konstantin wrote:
>
> > -Original Message-
> > From: Xueming(Steven) Li
> > Sent: Wednesday, September 29, 2021 1:09 PM
> > To: jerinjac...@gmail.com; Ananyev, Konstantin
> >
> > Cc: NBU-Contact-Thomas Monjalon ;
> > andrew.rybche...@oktetlab
> Add option to indicate whether UDP encapsulation ports verification
> need to be done as part of inbound IPsec processing.
> CNXK PMD support and unit tests are also added for the same.
>
> Depends on
> https://patches.dpdk.org/project/dpdk/list/?series=18755
>
Series
Acked-by: Akhil Goyal
Ap
From: Dmitry Kozlyuk
When the first port in a given protection domain (PD) starts,
install a mempool event callback for this PD and register all existing
memory regions (MR) for it. When the last port in a PD closes,
remove the callback and unregister all mempools for this PD.
This behavior can b
From: Dmitry Kozlyuk
Add internal API to register mempools, that is, to create memory
regions (MR) for their memory and store them in a separate database.
Implementation deals with multi-process, so that class drivers don't
need to. Each protection domain has its own database. Memory regions
can
From: Dmitry Kozlyuk
Mempool is a generic allocator that is not necessarily used for device
IO operations and its memory for DMA. Add MEMPOOL_F_NON_IO flag to mark
such mempools.
Signed-off-by: Dmitry Kozlyuk
Acked-by: Matan Azrad
---
doc/guides/rel_notes/release_21_11.rst | 3 +++
lib/mempoo
From: Dmitry Kozlyuk
Performance of MLX5 PMD of different classes can benefit if PMD knows
which memory it will need to handle in advance, before the first mbuf
is sent to the PMD. It is impractical, however, to consider
all allocated memory for this purpose. Most often mbuf memory comes
from mem
From: Dmitry Kozlyuk
MLX5 hardware has its internal IOMMU where PMD registers the memory.
On the data path, PMD translates VA into a key consumed by the device
IOMMU. It is impractical for the PMD to register all allocated memory
because of increased lookup cost both in HW and SW. Most often mb
Thanks Stephen, for the suggestion
I've sent v4 of the patch, which adds the succinct description in the
af_packet documentation..
On Fri, 24 Sept 2021 at 18:11, Stephen Hemminger
wrote:
> On Fri, 24 Sep 2021 14:44:45 +0300
> Tudor Cornea wrote:
>
> > +Features and Limitations of the af_packe
The af_packet pmd driver binds to a raw socket and allows
sending and receiving of packets through the kernel.
Since commit [1], the kernel strips the vlan tags early in
__netif_receive_skb_core(), so we receive untagged packets while
running with the af_packet pmd.
Luckily for us, the skb vlan-r
On Wed, 2021-09-22 at 12:54 +, Xueming(Steven) Li wrote:
> On Wed, 2021-09-22 at 11:57 +0100, Ferruh Yigit wrote:
> > > >
> > > > <...>
> > > >
> > > > > void
> > > > > -i40e_dev_rx_queue_release(void *rxq)
> > > > > +i40e_dev_rx_queue_release(struct rte_eth_dev *dev, uint16_t qid)
> > > > >
When DPDK is run with --in-memory mode, multiple processes can run
simultaneously using the same runtime dir. This leads to each process,
as it starts up, removing the telemetry socket of another process,
giving unexpected behaviour.
This patch changes that behaviour to first check if the existing
1 - 100 of 169 matches
Mail list logo
