Acked-by: Hemant Agrawal
IPsec xform struct would be updated to include IPsec SA lifetime
configuration. The existing member 'esn_soft_limit' would only track
ESN. And as sequence number control is getting introduced,
'esn_soft_limit' may not indicate the number of packets processed.
Replace that with a new structure to co
Acked-by: Hemant Agrawal
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Saturday, July 31, 2021 5:45 AM
> To: dev@dpdk.org; Honnappa Nagarahalli
> ; olivier.m...@6wind.com;
> lucp.at.w...@gmail.com; david.march...@redhat.com;
> tho...@monjalon.net
> Cc: Ruifeng Wang ; nd
> Subject: [PATCH] doc: abstrac
On Mon, Aug 2, 2021 at 11:13 AM Gregory Etelson wrote:
>
> UDP protocol reserves 0 checksum value for special purposes.
> Other protocols, like IPv4, TCP and SCTP must calculate checksum value
> in software or offload checksum calculation to hardware.
>
> If IPv4 TX checksum offload was off and he
On Mon, Aug 2, 2021 at 9:45 PM Mattias Rönnblom
wrote:
>
> Extend Eventdev API to allow for event devices which require various
> forms of internal processing to happen, even when events are not
> enqueued to or dequeued from a port.
>
> RFC v2:
> - Change rte_event_maintain() return type to be
On Tue, Aug 3, 2021 at 2:46 AM wrote:
>
> From: Pavan Nikhilesh
>
> Make driver layer as internal, remove unnecessary rte_ prefix for
> structures and functions that are not a part of public API.
> Promote experimental trace and vector APIs to stable.
> Add reserved field to `rte_event_timer` str
On Tue, Aug 3, 2021 at 8:07 AM Xia, Chenbo wrote:
>
> > -Original Message-
> > From: dev On Behalf Of Harman Kalra
> > Sent: Tuesday, August 3, 2021 12:04 AM
> > To: jer...@marvell.com; david.march...@redhat.com; tho...@monjalon.net; Ray
> > Kinsella
> > Cc: dev@dpdk.org; Harman Kalra
>
> -Original Message-
> From: dev On Behalf Of Harman Kalra
> Sent: Tuesday, August 3, 2021 12:04 AM
> To: jer...@marvell.com; david.march...@redhat.com; tho...@monjalon.net; Ray
> Kinsella
> Cc: dev@dpdk.org; Harman Kalra
> Subject: [dpdk-dev] [PATCH] doc: announce: make rte intr handle
Ethernet devices in DPDK can be released by rte_eth_dev_close() and
rte_dev_remove(). These APIs both call xxx_dev_close() in PMD layer
to uninstall hardware. However, the two APIs do not have explicit
invocation restrictions. In other words, at the ethdev layer, it is
possible to call rte_eth_dev_
On Sat, Jul 31, 2021 at 12:16:12AM +0200, Thomas Monjalon wrote:
> 27/07/2021 19:36, Nithin Dabilpuram:
> > Announce changes to make rte_security_set_pkt_metadata() and
> > rte_security_get_userdata() inline instead of C functions and
> > also addition of another field in structure rte_security_ctx
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon
> Sent: Sunday, August 1, 2021 4:44 AM
> To: Xia, Chenbo
> Cc: dev@dpdk.org; Yigit, Ferruh ; dev@dpdk.org;
> m...@ashroe.eu; david.march...@redhat.com; Richardson, Bruce
> ; andrew.rybche...@oktetlabs.ru; Ananyev,
> Konstantin
> Su
On Sat, Jul 31, 2021 at 5:15 AM Andrew Rybchenko
wrote:
>
> On 7/30/21 6:57 PM, Olivier Matz wrote:
> > The mbuf offload flags do not match the DPDK namespace (they are
> > not prefixed by RTE_). Announce their rename in 21.11, and the
> > removal of the old names in 22.11.
> >
> > A draft coccine
On Mon, Aug 2, 2021 at 12:57 PM Andrew Rybchenko
wrote:
>
> By its very name, action PORT_ID means that packets hit an ethdev with the
> given DPDK port ID. At least the current comments don't state the opposite.
>
> However some drivers implement it in a different way and direct traffic to
> the
On Mon, Aug 2, 2021 at 12:57 PM Andrew Rybchenko
wrote:
>
> Transfer flow rules may be applied to traffic entering switch from
> many sources. There are flow API pattern items which allow to specify
> ingress port match criteria explicitly, but it is not documented
> if ethdev port used to create
On 8/2/21 5:44 AM, Juraj Linkeš wrote:
+if os.name == 'posix':
+if os.path.isdir('/sys/devices/system/node'):
+numa_nodes = glob.glob('/sys/devices/system/node/node*')
+numa_nodes.sort()
+print(int(os.path.basename(numa_nodes[-1])[4:]) + 1)
+else:
+subpr
On 7/30/21 1:49 AM, jer...@marvell.com wrote:
From: Jerin Jacob
Dump the arm64 arch state register in oops
handling routine.
Signed-off-by: Jerin Jacob
---
lib/eal/unix/eal_oops.c | 19 +++
1 file changed, 19 insertions(+)
diff --git a/lib/eal/unix/eal_oops.c b/lib/eal/
18/05/2021 09:34, Thomas Monjalon:
> There is a layer violation in the vDPA API which encourages to destroy
> a full device with rte_dev_remove() instead of just closing the port.
> The plan is to introduce a new function in 21.08, promote in 21.11,
> and deprecate rte_vdpa_get_rte_device() in 21.1
On 7/30/21 1:49 AM, jer...@marvell.com wrote:
From: Jerin Jacob
Implement the base oops handling APIs.
Signed-off-by: Jerin Jacob
Building on POWER generates the following error:
ninja: Entering directory `build'
[1/244] Compiling C object 'lib/76b5a35@@rte_eal@sta/eal_unix_eal_oops.c.o
All builds were of type debugoptimized.
It is kept only for builds having an ABI check.
Others will have the default build type (release),
except if specified differently as in the x86 generic build
which will be a test of the non-optimized debug build type.
Some static builds will test the minsize
UDP protocol reserves 0 checksum value for special purposes.
Other protocols, like IPv4, TCP and SCTP must calculate checksum value
in software or offload checksum calculation to hardware.
If IPv4 TX checksum offload was off and header checksum was set to 0,
testpmd csum engine did not calculate c
On Mon, Aug 2, 2021 at 11:00 AM Gregory Etelson wrote:
>
> UDP protocol reserves 0 checksum value for special purposes.
> Other protocols, like IPv4, TCP and SCTP must calculate checksum value
> in software or offload checksum calculation to hardware.
>
> If IPv4 TX checksum offload was off and he
UDP protocol reserves 0 checksum value for special purposes.
Other protocols, like IPv4, TCP and SCTP must calculate checksum value
in software or offload checksum calculation to hardware.
If IPv4 TX checksum offload was off and header checksum was set to 0,
testpmd csum engine did not calculate c
+ c...@dpdk.org
2021-08-02 14:08 (UTC-0700), Narcisa Ana Maria Vasile:
> On Mon, Aug 02, 2021 at 10:32:17AM -0700, Narcisa Ana Maria Vasile wrote:
> > From: Narcisa Vasile
> >
> > Use a portable, type-safe representation for the thread identifier.
> > Add functions for comparing thread ids and o
> One reserved byte in rte_crypto_op struct would be used to indicate
> warnings and other information from the crypto/security operation. This
> field will be used to communicate events such as soft expiry with IPsec
> in lookaside mode.
>
> Signed-off-by: Anoob Joseph
> ---
> doc/guides/rel_
From: Pavan Nikhilesh
Make driver layer as internal, remove unnecessary rte_ prefix for
structures and functions that are not a part of public API.
Promote experimental trace and vector APIs to stable.
Add reserved field to `rte_event_timer` structure.
Signed-off-by: Pavan Nikhilesh
---
v2 Cha
On Mon, Aug 02, 2021 at 10:32:17AM -0700, Narcisa Ana Maria Vasile wrote:
> From: Narcisa Vasile
>
> Use a portable, type-safe representation for the thread identifier.
> Add functions for comparing thread ids and obtaining the thread id
> for the current thread.
>
> Signed-off-by: Narcisa Vasil
Introduce support for event devices requiring calls to
rte_event_maintain() in the Ethernet RX, Timer and Crypto Eventdev
adapters.
RFC v2:
- For simplicity, the timer adapter now unconditionally calls
rte_event_maintain().
- The RX adapter now only calls rte_event_maintain() when it has n
Extend Eventdev API to allow for event devices which require various
forms of internal processing to happen, even when events are not
enqueued to or dequeued from a port.
RFC v2:
- Change rte_event_maintain() return type to be consistent
with the documentation.
- Remove unused typedef from
Set the RTE_EVENT_DEV_CAP_REQUIRES_MAINT flag, and perform DSW
background tasks on rte_event_maintain() calls.
RFC v2: Have dsw_event_maintain() occasionally flush the port output
buffers.
Signed-off-by: Mattias Rönnblom
Tested-by: Richard Eklycke
Tested-by: Liron Himi
---
drivers/eve
Transfer flow rules may be applied to traffic entering switch from
many sources. There are flow API pattern items which allow to specify
ingress port match criteria explicitly, but it is not documented
if ethdev port used to create flow rule adds any implicit match
criteria and how it coexists with
By its very name, action PORT_ID means that packets hit an ethdev with the
given DPDK port ID. At least the current comments don't state the opposite.
However some drivers implement it in a different way and direct traffic to
the opposite end of the "wire" plugged to the given ethdev. For example
Transfer flow rules may be applied to traffic entering switch from
many sources. There are flow API pattern items which allow to specify
ingress port match criteria explicitly, but it is not documented
if ethdev port used to create flow rule adds any implicit match
criteria and how it coexists with
By its very name, action PORT_ID means that packets hit an ethdev with the
given DPDK port ID. At least the current comments don't state the opposite.
However some drivers implement it in a different way and direct traffic to
the opposite end of the "wire" plugged to the given ethdev. For example
On 8/2/21 7:03 PM, Harman Kalra wrote:
Moving struct rte_intr_handle as an internal structure to
avoid any ABI breakages in future. Since this structure defines
some static arrays and changing respective macros breaks the ABI.
Eg:
Currently RTE_MAX_RXTX_INTR_VEC_ID imposes a limit of maximum 512
On 8/2/21 6:49 PM, Ilya Maximets wrote:
On 8/1/21 12:22 PM, Andrew Rybchenko wrote:
By its very name, action PORT_ID means that packets hit an ethdev with the
given DPDK port ID. At least the current comments don't state the opposite.
That said, since port representors had been adopted, applicat
> Subject: Re: [dpdk-dev] [EXT] Re: [PATCH v4] doc: announce API changes for
> Windows compatibility
>
> External email: Use caution opening links or attachments
>
>
> > 2021-08-02 12:45 (UTC+), Akhil Goyal:
> > > > 21/07/2021 21:55, Dmitry Kozlyuk:
> > > > > Windows headers define `s_addr`,
All active ports that belong to the same E-switch share domain_id
value.
Port initialization procedure searches through a database for existing
port with matching properties. New domain_id allocated if match was
not located. Otherwise, new port inherits existing domain_id.
Port initialization did
Currently, there are two types of drop action implementation
in the PMD. One is the DR(Direct Rules) dummy placeholder drop
action and another is the dedicated dummy queue drop action.
When creates flow on the root table with DR drop action, the
action will be converted to MLX5_IB_ATTR_CREATE_FLOW_
From: Ori Kam
Currently there is a dedicated modify function for each
field that the application wants to change.
For example:
rte_flow_action_type_set_tp_port to modify destination port of UDP/TCP.
rte_flow_action_type_set_ipv4_dst to modify destination of IPv4.
A new function rte_flow_action_m
From: Ori Kam
In the current implementation,
the action rte_flow_action_modify_field is not well defined
for fields larger than 64 bits (for example IPv6 source)
In addtion, the byte order is also not well defined.
Both of those issue should be fixed.
Signed-off-by: Ori Kam
Acked-by: Matan Azr
02/08/2021 15:48, Akhil Goyal:
> > 2021-08-02 12:45 (UTC+), Akhil Goyal:
> > > > 21/07/2021 21:55, Dmitry Kozlyuk:
> > > > > Windows headers define `s_addr`, `min`, and `max` as macros.
> > > > > If DPDK headers are included after Windows ones, DPDK structure
> > > > > definitions containing fi
From: Pavan Nikhilesh
Make driver layer as internal, remove unnecessary rte_ prefix for
structures and functions that are not a part of public API.
Promote experimental trace and vector APIs to stable.
Add reserved field to `rte_event_timer` structure.
Signed-off-by: Pavan Nikhilesh
---
doc/gu
From: Narcisa Vasile
As a new API for threading is introduced,
a set of unit tests have been added to test the new interface.
Signed-off-by: Narcisa Vasile
---
app/test/meson.build| 2 +
app/test/test_threads.c | 419
2 files changed, 421 insertio
From: Narcisa Vasile
Add functions for mutex init, destroy, lock, unlock.
Add RTE_STATIC_MUTEX macro to replace static initialization
of mutexes.
Windows does not have a static initializer.
Initialization is only done through InitializeCriticalSection().
The RTE_STATIC_MUTEX calls into the rte_
From: Narcisa Vasile
Allow the user to choose the thread priority through an EAL
command line argument.
The user can choose thread priority through an EAL parameter,
when starting an application. If EAL parameter is not used,
the per-platform default value for thread priority is used.
Otherwise
From: Narcisa Vasile
Add functions for thread creation, joining, detaching.
The *rte_thread_create()* function can optionally receive
an rte_thread_attr_t object that will cause the thread to be
created with the affinity and priority described by the
attributes object. If no rte_thread_attr_t is
From: Narcisa Vasile
Add functions for barrier init, destroy, wait.
A portable type is used to represent a barrier identifier.
The rte_thread_barrier_wait() function returns the same value
on all platforms.
Signed-off-by: Narcisa Vasile
---
lib/eal/common/rte_thread.c | 61 ++
From: Narcisa Vasile
Add function for setting the priority for a thread.
Priorities on multiple platforms are similarly determined by
a priority value and a priority class/policy.
On Linux, the following mapping is created:
RTE_THREAD_PRIORITY_NORMAL corresponds to
* policy SCHED_OTHER
* priorit
From: Narcisa Vasile
Implement functions for getting/setting thread affinity.
Threads can be pinned to specific cores by setting their
affinity attribute.
Signed-off-by: Narcisa Vasile
Signed-off-by: Dmitry Malloy
---
lib/eal/common/rte_thread.c | 16
lib/eal/include/rte_thread.h |
From: Narcisa Vasile
Add function to translate Windows error codes to
errno-style error codes. The possible return values are chosen
so that we have as much semantical compatibility between platforms as
possible.
Signed-off-by: Narcisa Vasile
---
lib/eal/common/rte_thread.c | 6 +--
lib/eal/
From: Narcisa Vasile
Implement thread attributes for:
* thread affinity
* thread priority
Implement functions for managing thread attributes.
Priority is represented through an enum that allows for two levels:
- RTE_THREAD_PRIORITY_NORMAL
- RTE_THREAD_PRIORITY_REALTIME_CRITICAL
From: Narcisa Vasile
Use a portable, type-safe representation for the thread identifier.
Add functions for comparing thread ids and obtaining the thread id
for the current thread.
Signed-off-by: Narcisa Vasile
---
lib/eal/common/meson.build| 1 +
lib/eal/{unix => common}/rte_threa
From: Narcisa Vasile
EAL thread API
**Problem Statement**
DPDK currently uses the pthread interface to create and manage threads.
Windows does not support the POSIX thread programming model,
so it currently
relies on a header file that hides the Windows calls under
pthread matched interfaces. Gi
02/08/2021 19:22, Honnappa Nagarahalli:
> From: Thomas Monjalon
> > 23/07/2021 11:49, Joyce Kong:
> > Considering all the questions regarding usage of atomics, I still think we
> > need a
> > documentation about their correct use.
>
> I think few things to document are:
> 1) Use of __atomic_add_
> -Original Message-
> From: Thomas Monjalon
> Sent: Saturday, July 31, 2021 3:27 PM
> To: Honnappa Nagarahalli ; Ruifeng Wang
> ; Joyce Kong
> Cc: step...@networkplumber.org; m...@ashroe.eu; dev@dpdk.org; nd
> ; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2] doc: update atomic o
To support shared Rx queue, this patch announces new offload flag
RTE_ETH_RX_OFFLOAD_SHARED_RXQ and new shared_group field to struct
rte_eth_rxconf in DPDK v21.11.
[1] mail list discussion:
https://mails.dpdk.org/archives/dev/2021-July/215575.html
Signed-off-by: Xueming Li
---
doc/guides/rel_no
This patch announces the parameter change of eth_queue_release_t
callback API to eth_dev_ops in DPDK v21.11.
[1] mail list discussion:
https://mails.dpdk.org/archives/dev/2021-July/215654.html
Signed-off-by: Xueming Li
---
doc/guides/rel_notes/deprecation.rst | 3 +++
1 file changed, 3 insertio
To support shared Rx queue[1], plan to update testpmd with following
changes:
- Add ``--rxq-share`` to enable shared Rx queue if device supports.
- In verbose mode, dump mbuf->port for each received packet.
- Check forwarding configuration to make sure queue streams of same
share group scheduled
In the recent update, the misc5 matcher was introduced to
match VxLAN header extra fields. However, ConnectX-5
doesn't support misc5 for the UDP ports different from
VXLAN's standard one (4789).
Need to fall back to the previous approach and use legacy
misc matcher if non-standard UDP port is reco
> -Original Message-
> From: dev On Behalf Of Gregory Etelson
> Sent: Monday, August 2, 2021 13:39
> To: dev@dpdk.org
> Cc: Gregory Etelson ; Matan Azrad
> ; Raslan Darawsheh ; Ori Kam
> ; Ray Kinsella
> Subject: [dpdk-dev] [PATCH] net: announce changes in IPv4 header
>
> Announce change
> -Original Message-
> From: dev On Behalf Of Gregory Etelson
> Sent: Monday, August 2, 2021 13:42
> To: dev@dpdk.org
> Cc: Gregory Etelson ; Matan Azrad
> ; Raslan Darawsheh ; Ori Kam
> ; Ray Kinsella
> Subject: [dpdk-dev] [PATCH] net: announce changes in TCP header
>
> Announce change
Moving struct rte_intr_handle as an internal structure to
avoid any ABI breakages in future. Since this structure defines
some static arrays and changing respective macros breaks the ABI.
Eg:
Currently RTE_MAX_RXTX_INTR_VEC_ID imposes a limit of maximum 512
MSI-X interrupts that can be defined for
On 8/1/21 12:22 PM, Andrew Rybchenko wrote:
> By its very name, action PORT_ID means that packets hit an ethdev with the
> given DPDK port ID. At least the current comments don't state the opposite.
> That said, since port representors had been adopted, applications like OvS
> have been misusing th
From: Thomas Monjalon
> The struct member dataunit_len is introduced in DPDK 21.05.
> It is limited to 16 bits to fit a padding hole in 32-bit build.
> This means the maximum data-unit length is 64 KB.
> Some use cases may benefit of a bigger size as the proposed 32 bits.
>
> Signed-off-by: Tho
Hi,
Kathleen has submitted an RFC patch [1] in this regard. We’d appreciate your
comments.
[1]
https://patches.dpdk.org/project/dpdk/patch/20210430213747.41530-2-kathleen.cape...@arm.com/
Thank you!
> On Apr 30, 2021, at 4:28 AM, Ananyev, Konstantin
> wrote:
>
>>
>>
>> On Thu, Apr 29, 2021
Announce change to add a union that will provide byte and bitfield
access to TCP flags.
Signed-off-by: Gregory Etelson
---
doc/guides/rel_notes/deprecation.rst | 3 +++
1 file changed, 3 insertions(+)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/rel_notes/deprecation.rst
inde
Announce changes to add 2 unions. The first union will provide
integral and bits access to version and IHL. The second union will
provide integral and bits access to fragment flags and offset.
Signed-off-by: Gregory Etelson
---
doc/guides/rel_notes/deprecation.rst | 5 +
1 file changed, 5 in
Hi Andrew,
Acked-by: Ori Kam
Best,
Ori
> -Original Message-
> From: Andrew Rybchenko
> Sent: Sunday, August 1, 2021 1:22 PM
In the recent update, the misc5 matcher was introduced to
match VxLAN header extra fields. However, ConnectX-5
doesn't support misc5 for the UDP ports different from
VXLAN's standard one (4789).
Need to fall back to the previous approach and use legacy
misc matcher if non-standard UDP port is reco
igbvf_vlan_offload_config and igbvf_vlan_offload_set primal
implementation, setting vlan filter mask at igbvf_dev_start time.
Without the above a vlan filter for igbvf is not functional.
Signed-off-by: Renata Saiakhova
---
drivers/net/e1000/igb_ethdev.c | 28
1 file
igbvf_vlan_offload_config and igbvf_vlan_offload_set primal
implementation, setting vlan filter mask at igbvf_dev_start time.
Without setting ETH_VLAN_FILTER_OFFLOAD for offload mask by using the functions
above it is not possible to configure and use a vlan filter for igbvf.
Consider rte_eth_dev_v
https://bugs.dpdk.org/show_bug.cgi?id=767
Ajit Khaparde (ajit.khapa...@broadcom.com) changed:
What|Removed |Added
CC||ajit.khapa...@broadcom
https://bugs.dpdk.org/show_bug.cgi?id=766
Ajit Khaparde (ajit.khapa...@broadcom.com) changed:
What|Removed |Added
CC||ajit.khapa...@broadcom
> 2021-08-02 12:45 (UTC+), Akhil Goyal:
> > > 21/07/2021 21:55, Dmitry Kozlyuk:
> > > > Windows headers define `s_addr`, `min`, and `max` as macros.
> > > > If DPDK headers are included after Windows ones, DPDK structure
> > > > definitions containing fields with these names get broken (example
This patch fixes the memcpy function call which was incorrect and led
to memory corruption for tables with more that just a few actions.
Fixes: 742b0a57f50e4 ("pipeline: add table statistics to SWX")
Cc: sta...@dpdk.org
Signed-off-by: Churchill Khangar
Acked-by: Cristian Dumitrescu
---
lib/pip
On Sat, Jul 31, 2021 at 5:45 PM Andrew Rybchenko
wrote:
>
> On 7/30/21 6:57 PM, Olivier Matz wrote:
> > The mbuf offload flags do not match the DPDK namespace (they are
> > not prefixed by RTE_). Announce their rename in 21.11, and the
> > removal of the old names in 22.11.
> >
> > A draft coccine
2021-08-02 12:45 (UTC+), Akhil Goyal:
> > 21/07/2021 21:55, Dmitry Kozlyuk:
> > > Windows headers define `s_addr`, `min`, and `max` as macros.
> > > If DPDK headers are included after Windows ones, DPDK structure
> > > definitions containing fields with these names get broken (example 1),
> >
Acked-by: Ori Kam
Thanks,
Ori
Ethernet devices in DPDK can be released by rte_eth_dev_close() and
rte_dev_remove(). However, these two APIs do not have explicit invocation
restrictions. In other words, at the ethdev layer, calling
rte_eth_dev_close() and then rte_dev_remove() or rte_eal_hotplug_remove()
is allowed. In such a ba
> 21/07/2021 21:55, Dmitry Kozlyuk:
> > Windows headers define `s_addr`, `min`, and `max` as macros.
> > If DPDK headers are included after Windows ones, DPDK structure
> > definitions containing fields with these names get broken (example 1),
> > as well as any usage of such fields (example 2). If
> +if os.name == 'posix':
> +if os.path.isdir('/sys/devices/system/node'):
> +numa_nodes = glob.glob('/sys/devices/system/node/node*')
> +numa_nodes.sort()
> +print(int(os.path.basename(numa_nodes[-1])[4:]) + 1)
> +else:
> +subprocess.run(['sysctl', '-n', 'vm
> Hi Akhil,
>
> There are 2 more items that I would like to add.
> - IV gen (in ``rte_security_ipsec_sa_options``)
> - SA lifetime configuration (in ``rte_security_ipsec_xform``)
>
> http://patches.dpdk.org/project/dpdk/patch/1626759974-334-2-git-send-
> email-ano...@marvell.com/
> http://patches
> > -Original Message-
> > From: dev On Behalf Of Gregory Etelson
> > Sent: Monday, August 2, 2021 13:39
> > To: dev@dpdk.org
> > Cc: Gregory Etelson ; Matan Azrad
> > ; Raslan Darawsheh ; Ori Kam
> > ; Ray Kinsella
> > Subject: [dpdk-dev] [PATCH] net: announce changes in IPv4 header
> >
> One reserved byte in rte_crypto_op struct would be used to indicate
> warnings and other information from the crypto/security operation. This
> field will be used to communicate events such as soft expiry with IPsec
> in lookaside mode.
>
> Signed-off-by: Anoob Joseph
> ---
Acked-by: Akhil Goya
The next release 21.11 will allow API/ABI breaking changes.
The process is to announce such changes in the previous release notes.
We are closing the release 21.08 this week so it becomes very urgent
to review all these notices and vote (ack) or reject them now.
For convenience, I am adding those
21/07/2021 21:55, Dmitry Kozlyuk:
> Windows headers define `s_addr`, `min`, and `max` as macros.
> If DPDK headers are included after Windows ones, DPDK structure
> definitions containing fields with these names get broken (example 1),
> as well as any usage of such fields (example 2). If DPDK head
This patch fixes syntax of memcpy function to copy arrays which was
wrong typically leading to memory corruption for more than a few
actions involved.
Fixes: 742b0a57f50e4 ("pipeline: add table statistics to SWX")
Signed-off-by: Churchill Khangar
Acked-by: Cristian Dumitrescu
---
lib/pipeline/
14/04/2021 22:15, Thomas Monjalon:
> The struct member dataunit_len is introduced in DPDK 21.05.
> It is limited to 16 bits to fit a padding hole in 32-bit build.
> This means the maximum data-unit length is 64 KB.
> Some use cases may benefit of a bigger size as the proposed 32 bits.
>
> Signed-o
> -Original Message-
> From: Andrew Rybchenko
>
> On 8/1/21 7:13 PM, Ori Kam wrote:
> > Hi Andrew,
> >
> >> -Original Message-
> >> From: Andrew Rybchenko
> >> Sent: Sunday, August 1, 2021 4:24 PM
> >> Subject: Re: [PATCH 1/2] ethdev: announce flow API action PORT_ID
> >> chan
01/08/2021 19:53, John Levon:
> When closing file descriptors post-fork, ignore "." and ".." directory
> entries, so the test log doesn't have distracting errors like:
>
> Error converting name fd 0 .:
> Error converting name fd 0 ..:
>
> Signed-off-by: John Levon
Applied, thanks.
For info, wh
> -Original Message-
> From: dev On Behalf Of Thomas Monjalon
> Sent: Friday, July 30, 2021 8:04 PM
> To: Gregory Etelson
> Cc: dev@dpdk.org; Ajit Khaparde ; Andrew
> Rybchenko ; Yigit, Ferruh
> ; sta...@dpdk.org; Li, Xiaoyun
> ; Tomasz Kulasek ;
> Ananyev, Konstantin ; Olivier Matz
>
>
One reserved byte in rte_crypto_op struct would be used to indicate
warnings and other information from the crypto/security operation. This
field will be used to communicate events such as soft expiry with IPsec
in lookaside mode.
Signed-off-by: Anoob Joseph
---
doc/guides/rel_notes/deprecation.
02/08/2021 12:26, Rongwei Liu:
> In the recent update, the misc5 matcher was introduced to
> match VxLAN header extra fields. However, ConnectX-5
> doesn't support misc5 for the UDP ports different from
> VXLAN's standard one (4789).
>
> Need to fall back to the previous approach and use legacy
>
https://bugs.dpdk.org/show_bug.cgi?id=768
Bug ID: 768
Summary: [dpdk-21.08] received pkts with bad ip-checksum when
send ip-checksum=0 pkts
Product: DPDK
Version: 21.08
Hardware: x86
OS: Linux
St
On 8/2/21 1:38 PM, Gregory Etelson wrote:
Announce changes to add 2 unions. The first union will provide
integral and bits access to version and IHL. The second union will
provide integral and bits access to fragment flags and offset.
Signed-off-by: Gregory Etelson
Acked-by: Andrew Rybchenko
Remove the unnecessary rte_atomic.h included in app module.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
app/proc-info/main.c | 1 -
app/test-pipeline/config.c | 1 -
app/test-pipeline/init.c | 1 -
app/test-pipeline/main.c | 1 -
app/test-pipeline/runtime.c | 1 -
Convert rte_atomic usages to compiler atomic built-ins
for thread params sync in bbdev cases.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
app/test-bbdev/test_bbdev_perf.c | 135 ++-
1 file changed, 59 insertions(+), 76 deletions(-)
diff --git a/app/test-
Replace rte_atomic16_cmpset operation with compiler atomic
CAS operation for port status sync in testpmd case.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
app/test-pmd/testpmd.c | 75 +++---
1 file changed, 48 insertions(+), 27 deletions(-)
diff
Convert rte_atomic_test_and_set usage to compiler atomic
CAS operation for display sync.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
app/test-compress-perf/comp_perf_test_common.h | 2 +-
app/test-compress-perf/comp_perf_test_cyclecount.c | 10 +++---
app/test-compress-perf
1 - 100 of 119 matches
Mail list logo
