On Mon, May 22, 2023 at 5:26 PM wrote:
>
> From: Pavan Nikhilesh
>
> Use LMTST when all events in the burst are enqueue with
> rte_event:op as RTE_EVENT_OP_NEW i.e. events are enqueued
> with the `rte_event_enqueue_new_burst` API.
>
> Signed-off-by: Pavan Nikhilesh
> Acked-by: Shijith Thotton
From: Satheesh Paul
Added support for Tx queue flow pattern item.
Signed-off-by: Satheesh Paul
Reviewed-by: Kiran Kumar K
---
doc/guides/nics/features/cnxk.ini | 1 +
doc/guides/nics/features/cnxk_vec.ini | 1 +
doc/guides/nics/features/cnxk_vf.ini | 1 +
doc/guides/nics/features/default
From: Satheesh Paul
Added ROC API changes to support Tx queue flow
pattern item.
Signed-off-by: Satheesh Paul
Reviewed-by: Kiran Kumar K
---
v2:
* Updated documentation for Tx queue pattern item and
verified generated documents as well.
drivers/common/cnxk/roc_npc.c | 16 +---
dr
> -Original Message-
> From: Burakov, Anatoly
> Sent: Monday, May 22, 2023 6:19 PM
> To: Ruifeng Wang ; olivier.m...@6wind.com
> Cc: dev@dpdk.org; sta...@dpdk.org; tho...@monjalon.net;
> step...@networkplumber.org; Justin
> He ; Honnappa Nagarahalli ;
> nd
>
> Subject: Re: [PATCH] test/
When a DPDK application is started on only one numa node, memory is
allocated for only one socket. When interrupt threads use memory,
memory may not be found on the socket where the interrupt thread
is currently located, and memory has to be reallocated on the hugepage,
this operation will lead
In TSO, It is possible mbuf->data_len exceed mtu.
Fixed the incorrect data length check in ice_prep_pkts.
Fixes: ccf33dccf7aa ("net/ice: check illegal packet sizes")
Cc: sta...@dpdk.org
Signed-off-by: Qi Zhang
---
v2:
- fix build warning
drivers/net/ice/ice_rxtx.c | 5 +
1 file changed, 1
> -Original Message-
> From: Yang, Qiming
> Sent: Thursday, May 18, 2023 11:16 PM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Yang, Qiming
>
> Subject: [PATCH v2 00/20] net/ice/base: code update
>
> Updated share code to 2023.02 version.
>
> Qiming Yang (20):
> net/ice/base: updated cop
https://bugs.dpdk.org/show_bug.cgi?id=1220
gaodaxue (daxuex@intel.com) changed:
What|Removed |Added
Resolution|--- |FIXED
Status|CONFIR
> -Original Message-
> From: Deng, KaiwenX
> Sent: Friday, May 5, 2023 10:31 AM
> To: Ferruh Yigit ; dev@dpdk.org
> Cc: sta...@dpdk.org; Yang, Qiming ; Zhou, YidingX
> ; Chas Williams ; Min Hu (Connor)
> ; Wu, Jingjing ; Xing, Beilei
> ; Mike Pattrick ; Zhang, Qi Z
> ; Doherty, Declan ;
>
with 2/5 fixed,
Series-acked-by: Chengwen Feng
On 2023/1/31 11:33, Huisong Li wrote:
> This patchset fix some bugs and support attaching and detaching port
> in primary and secondary.
>
> ---
> -v5: move 'ALLOCATED' state to the back of 'REMOVED' to avoid abi break.
> -v4: fix a misspelling.
On Mon, 22 May 2023 15:04:52 -0400
Kamil Godzwon wrote:
> /home/vagrant/dpdk/build/include/rte_crypto_sym.h:1009:4: \
> warning: Value stored to 'left' is never read [deadcode.DeadStores]
> left = 0;
> ^ ~
> 1 warning generated.
>
> Comp
Add support for MPLS modify header using "RTE_FLOW_FIELD_MPLS" id.
Since MPLS heaser might appear more the one time in inner/outer/tunnel,
a new field was added to "rte_flow_action_modify_data" structure in
addition to "level" field.
The "tag_index" field is the index of the header inside encapsul
Add modify field support for GENEVE option fields:
- "RTE_FLOW_FIELD_GENEVE_OPT_TYPE"
- "RTE_FLOW_FIELD_GENEVE_OPT_CLASS"
- "RTE_FLOW_FIELD_GENEVE_OPT_DATA"
Each GENEVE TLV option is identified by both its "class" and "type", so
2 new fields were added to "rte_flow_action_modify_data" structure
The modify field action description inside "Generic flow API (rte_flow)"
documentation, lists all operations supported for a destination field.
In addition, it lists the values supported for a encapsulation level
field.
Before the lists, in both cases, miss a blank line causing them to look
regula
The RSS action description inside "Generic flow API (rte_flow)"
documentation, lists the values supported for a encapsulation level
field.
For "2" value, it uses 3 spaces as an indentation instead of 2 after
line breaking, causing the first line to be bold.
This patch updates the number of spaces
The asynchronous operations description inside "Generic flow API
(rte_flow)" documentation, adds some bullets to describe asynchronous
operations behavior.
Before the first bullet, miss a blank line causing it to look a regular
text line.
This patch adds the blank line.
Fixes: 197e820c6685 ("eth
This patch-set extend the modify field action API to support both
multiple MPLS and GENEVE option headers.
In current API, the header type is provided by rte_flow_field_id
enumeration and the encapsulation level (inner/outer/tunnel) is
specified by data.level field.
However, there is no way to spe
/home/vagrant/dpdk/build/include/rte_crypto_sym.h:1009:4: \
warning: Value stored to 'left' is never read [deadcode.DeadStores]
left = 0;
^ ~
1 warning generated.
Compilator sees that the variable 'left' is never read after
assignment a '0
/home/vagrant/dpdk/build/include/rte_crypto_sym.h:1009:4: warning: Value stored
to 'left' is never read [deadcode.DeadStores]
left = 0;
^ ~
1 warning generated.
Compilator sees that the variable 'left' is never read after
assignment a '0'
> Acked-by: Hemant Agrawal
Thank you.
Do I need to do anything else for this patch to be merged?
On 5/22/2023 2:17 PM, Dongdong Liu wrote:
> This patchset contains some features and bugfixes for hns3.
>
> v1->v2:
> -Fix check-git-log warnings.
>
> Chengwen Feng (1):
> net/hns3: fix receive multiple firmware reset interrupts
>
> Dengdui Huang (2):
> net/hns3: fix loop code variable type
On Mon, May 22, 2023 at 10:22:41AM +0100, Bruce Richardson wrote:
> Functions which take no parameters should explicitly have "(void)" as
> the parameter list, rather than "()".
>
> Reported upstream on FreeBSD ports collection [1].
>
> [1] https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=271524
1. This is the excerpt from the google's virtual nic spec:
"In addition to the device-owned register file, vector table, and
doorbells, the gVNIC device uses *DMA* (which in most cases amounts to
ordinary memory access by host software since we're dealing with a virtual
device, but guests must assu
On 5/22/2023 4:21 PM, Stephen Hemminger wrote:
On Mon, 22 May 2023 11:19:24 +0100
"Burakov, Anatoly" wrote:
This case validates mbuf. IMO there is no need to do validation in a secondary
process.
Unit test for rte_panic() also uses fork() and could have the same issue.
In that case, rt
On Mon, 22 May 2023 11:19:24 +0100
"Burakov, Anatoly" wrote:
> >
> > This case validates mbuf. IMO there is no need to do validation in a
> > secondary process.
> > Unit test for rte_panic() also uses fork() and could have the same issue.
> >
>
> In that case, rte_panic() test should be fix
Pre and post computations currently use the OpenSSL library by default.
This patch changes the default option to Intel IPsec MB library version
1.4 for the required computations. If this version of IPsec is not met
it will fallback to use OpenSSL.
Added version checks for libipsecmb and libcrypto
On 5/22/23 16:09, Dengdui Huang wrote:
The API rte_eth_dev_is_valid_rxq/txq checks
the port ID validity and then the Rx/Tx queue ID is valid.
What is valid Tx/Rx queue? It depends on on caller
expectations. Some functions are satisfied with just
check vs configured number of queues. Some requir
On Thu, May 18, 2023 at 3:35 PM wrote:
>
> From: Satheesh Paul
>
> Fix uninitialized pointer read reported in coverity scan.
>
> Coverity issue: 375811
> Fixes: 84d2ea9d4fb3 ("common/cnxk: support custom pre L2 header parsing as
> raw")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Satheesh Paul
> R
On 5/22/2023 1:41 PM, Fengnan Chang wrote:
Under legacy mode, if the number of continuous memsegs greater
than RTE_MAX_MEMSEG_PER_LIST, eal init will failed even though
another memseg list is empty, because only one memseg list used
to check in remap_needed_hugepages.
Fix this by add a argment in
On Fri, May 19, 2023 at 9:12 AM wrote:
>
> From: Satheesh Paul
>
> Added support for Tx queue flow pattern item.
>
> Signed-off-by: Satheesh Paul
> Reviewed-by: Kiran Kumar K
Update to doc/guides/nics/features/cnxk_*.ini is missing.
Please check generated documentation too,.
> ---
> drivers/
From: Dengdui Huang
Add Tx/Rx descriptor logs, controlled by 'RTE_ETHDEV_DEBUG_RX/TX'
compile time flag with 'pmd.net.hns3.rx/tx' log type.
Signed-off-by: Dengdui Huang
Signed-off-by: Dongdong Liu
---
drivers/net/hns3/hns3_ethdev.c | 6 ++
drivers/net/hns3/hns3_logs.h | 18
From: Huisong Li
When some hardware and firmware support speed auto-negotiation
but do not support flow control auto-negotiation, driver can
never successfully set MAC flow control by flow_ctrl_set() API.
So only tell user driver doesn't support flow control autoneg
when user enable it.
Fixes: 1
From: Chengwen Feng
In the firmware (also known as IMP) reset scenario, driver interrupt
processing and firmware watchdog initialization are asynchronous.
If the driver interrupt processing is faster than firmware watchdog
initialization (that is, the driver clears the firmware reset
interrupt s
From: Dengdui Huang
Loop conditions are compared with different variable types,
which may cause overflow risks.
Fixes: 67d010346933 ("net/hns3: adjust data type of some variables")
Fixes: 6ee07e3cb589 ("net/hns3: fix insecure way to query MAC statistics")
Cc: sta...@dpdk.org
Signed-off-by: Deng
From: Huisong Li
This patch support flow control autoneg for fiber and backplane port.
And it depends on the capability of firmware.
Signed-off-by: Huisong Li
Signed-off-by: Dongdong Liu
---
drivers/net/hns3/hns3_cmd.c| 30 +-
drivers/net/hns3/hns3_cmd.h| 20 ++
This patchset contains some features and bugfixes for hns3.
v1->v2:
-Fix check-git-log warnings.
Chengwen Feng (1):
net/hns3: fix receive multiple firmware reset interrupts
Dengdui Huang (2):
net/hns3: fix loop code variable type mismatch
net/hns3: add Tx/Rx descriptor logs
Huisong Li (2)
This patch applys PI servo algorithm to leverage frequency adjustment
API to improve PTP timesync accuracy.
The command for starting ptpclient with PI algorithm is:
./build/examples/dpdk-ptpclient -a :81:00.0 -c 1 -n 3 -- -T 0 -p 0x1
--controller=pi
Signed-off-by: Simei Su
Signed-off-by: Wen
This patch reworks code to split delay request message parsing
from follow up message parsing which doesn't break original logic.
Signed-off-by: Simei Su
Signed-off-by: Wenjun Wu
---
examples/ptpclient/ptpclient.c | 48 --
1 file changed, 32 insertions(+)
On Thu, May 18, 2023 at 9:19 PM Rahul Bhansali wrote:
>
> Add mempool cookies get mark to all frags in case of
> reassembly failure.
>
> Signed-off-by: Rahul Bhansali
Series applied to dpdk-next-net-mrvl/for-next-net. Thanks
> ---
> Changes in v2: No change
>
> drivers/net/cnxk/cn10k_rx.h |
This patch introduces a new timesync API "rte_eth_timesync_adjust_fine"
which enables finer adjustment of the PHC clock. During PTP timesync,
"rte_eth_timesync_adjust_time" focuses on phase adjustment while
"rte_eth_timesync_adjust_fine" focuses on frequency adjustment.
This new function gets the
This patchset cover below parts:
(1)Introduce a new timesync API called "rte_eth_timesync_adjust_freq" that
enables frequency adjustment during PTP timesync. This new API aligns with
the kernel PTP which already supports frequency adjustment. It brings DPDK
closer in alignment with the ker
The API rte_eth_dev_is_valid_rxq/txq checks
the port ID validity and then the Rx/Tx queue ID is valid.
Signed-off-by: Dengdui Huang
---
doc/guides/rel_notes/release_23_07.rst | 5
lib/ethdev/rte_ethdev.c| 30 +
lib/ethdev/rte_ethdev.h| 36
add API to check queue ID validity and use it to fix a bug
Dengdui Huang (2):
ethdev: add API to check queue ID validity
app/testpmd: fix segment fault with invalid queue id
app/test-pmd/cmdline.c | 23 +++-
doc/guides/rel_notes/release_23_07.rst | 5
lib/et
When input queue id is invalid, it will lead to
Segmentation fault, like:
dpdk-testpmd -a :01:00.0 -- -i
testpmd> show port 0 txq/rxq 99 desc 0 status
Segmentation fault
dpdk-testpmd -a :01:00.0 -- -i
testpmd> show port 0 rxq 99 desc used count
Segmentation fault
This patch fixes it.
Fi
On 5/22/2023 1:09 PM, Fengnan Chang wrote:
Burakov, Anatoly 于2023年5月20日周六 23:03写道：
Hi,
On 5/16/2023 1:21 PM, Fengnan Chang wrote:
Under legacy mode, if the number of continuous memsegs greater
than RTE_MAX_MEMSEG_PER_LIST, eal init will failed even though
another memseg list is empty, becaus
Under legacy mode, if the number of continuous memsegs greater
than RTE_MAX_MEMSEG_PER_LIST, eal init will failed even though
another memseg list is empty, because only one memseg list used
to check in remap_needed_hugepages.
Fix this by add a argment indicate how many pages mapped in
remap_segment
Hi Ferruh
Many thanks for your review.
On 2023/5/22 19:57, Ferruh Yigit wrote:
On 5/18/2023 12:29 PM, Dongdong Liu wrote:
This patchset contains some features and bugfixes for hns3.
Chengwen Feng (1):
net/hns3: fix receive multiple firmware reset interrupts
Dengdui Huang (2):
net/hns3: f
Burakov, Anatoly 于2023年5月20日周六 23:03写道：
>
> Hi,
>
> On 5/16/2023 1:21 PM, Fengnan Chang wrote:
> > Under legacy mode, if the number of continuous memsegs greater
> > than RTE_MAX_MEMSEG_PER_LIST, eal init will failed even though
> > another memseg list is empty, because only one memseg list used
>
Hi Ori,
> -Original Message-
> From: Ori Kam
> Sent: Sunday, 21 May 2023 22:03
>
> Hi Michael,
>
> > -Original Message-
> > From: Michael Baum
> > Sent: Thursday, May 18, 2023 8:40 PM
> >
> > Add support for MPLS modify header using "RTE_FLOW_FIELD_MPLS" id.
> >
> > Since MPLS
On 5/18/2023 12:29 PM, Dongdong Liu wrote:
> This patchset contains some features and bugfixes for hns3.
>
> Chengwen Feng (1):
> net/hns3: fix receive multiple firmware reset interrupts
>
> Dengdui Huang (2):
> net/hns3: fix loop code variable type mismatch
> net/hns3: add Tx/Rx descriptor
From: Pavan Nikhilesh
Use LMTST when all events in the burst are enqueue with
rte_event:op as RTE_EVENT_OP_NEW i.e. events are enqueued
with the `rte_event_enqueue_new_burst` API.
Signed-off-by: Pavan Nikhilesh
Acked-by: Shijith Thotton
---
v3 Changes:
- Fix checkpatch issues.
v2 Changes:
Raw crypto APIs may return -ENOTSUP when the cryptodev does not support
the requested feature. Handle it gracefully so that tests get marked as
"SKIPPED" instead of "FAILED".
Signed-off-by: Anoob Joseph
---
app/test/test_cryptodev.c | 449 +++---
app/test/test_cry
Clarify the error codes returned by rte_cryptodev_raw_dp_ctx. Cryptodev
can return -ENOTSUP to indicate any unsupported features with raw APIs.
Remove redundant references about 'rte_cryptodev_raw_attach_session()'.
The API is not part of the specification.
Signed-off-by: Anoob Joseph
Signed-off
Add support of showing firmware version.
When using the flower firmware, the firmware version
output of common port is '0.0.5.5 0.31 AOTC-2.14.A.54 flo',
while the firmware version output of representor port is
'* 0.31 AOTC-2.14.A.54 flower'.
Signed-off-by: Chaoyong He
Reviewed-by: Niklas Söderlu
Align the method of reading the version information with the linux
driver. This is done to make it easier to share code between the
DPDK PMD and the kernel driver.
Signed-off-by: Chaoyong He
Reviewed-by: Niklas Söderlund
---
drivers/net/nfp/flower/nfp_flower.c | 4 ++--
drivers/net/nfp/nfp_com
This patch series add the support of showing firmware version,
also modify the data structure and logic of reading and store
firmware version, to make it sync with the kernel driver.
Chaoyong He (2):
net/nfp: align reading of version info with kernel driver
net/nfp: add support of showing firm
Hi Akhil,
Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Akhil Goyal
> Sent: Thursday, May 18, 2023 3:13 PM
> To: Anoob Joseph ; Thomas Monjalon
> ; Jerin Jacob Kollanukkaran ;
> Konstantin Ananyev ; Bernard
> Iremonger
> Cc: Volodymyr Fialko ; Hemant Agrawal
> ; Mattias
Hi Akhil,
Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Akhil Goyal
> Sent: Thursday, May 18, 2023 2:45 PM
> To: Anoob Joseph ; Thomas Monjalon
> ; Jerin Jacob Kollanukkaran ;
> Konstantin Ananyev ; Bernard
> Iremonger
> Cc: Hemant Agrawal ; Mattias Rönnblom
> ; Kiran K
On 2023/1/31 11:33, Huisong Li wrote:
> The event callback in application may use the macro RTE_ETH_FOREACH_DEV to
> iterate over all enabled ports to do something(like, verifying the port id
> validity) when receive a probing event. If the ethdev state of a port is
> not RTE_ETH_DEV_UNUSED, this p
On 5/18/2023 10:48 PM, Alexander Kozyrev wrote:
> Introduce the new rte_flow_update() API allowing users
> to update the action list in the already existing rule.
If the API is only to update actions, does make sense to rename it to
explicitly state this, like:
`rte_flow_action_update()`
Same for
Hi Akhil,
Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Akhil Goyal
> Sent: Thursday, May 18, 2023 1:56 PM
> To: Anoob Joseph ; Thomas Monjalon
> ; Jerin Jacob Kollanukkaran ;
> Konstantin Ananyev ; Bernard
> Iremonger
> Cc: Hemant Agrawal ; Mattias Rönnblom
> ; Kiran K
On 5/19/2023 10:01 AM, Ivan Malov wrote:
> Hi Ferruh,
>
> On Fri, 19 May 2023, Ferruh Yigit wrote:
>
>> On 5/18/2023 6:21 PM, Ivan Malov wrote:
>>> Hi Ferruh,
>>>
>>> Thanks for reviewing this. PSB.
>>>
>>> On Thu, 18 May 2023, Ferruh Yigit wrote:
>>>
On 4/24/2023 3:30 PM, Ivan Malov wrote:
On 5/22/2023 7:48 AM, Andrew Rybchenko wrote:
> On 5/21/23 11:36, Ivan Malov wrote:
>> When reinserting a flow (on port restart, for instance)
>> FW resource IDs found in the action set specification
>> need to be invalidated so that the new (reallocated)
>> FW resource IDs can be accepted by libef
On 5/22/2023 10:55 AM, Ruifeng Wang wrote:
-Original Message-
From: Burakov, Anatoly
Sent: Monday, May 22, 2023 5:24 PM
To: Ruifeng Wang ; olivier.m...@6wind.com
Cc: dev@dpdk.org; sta...@dpdk.org; tho...@monjalon.net;
step...@networkplumber.org; Justin
He ; Honnappa Nagarahalli ; nd
Su
> -Original Message-
> From: Burakov, Anatoly
> Sent: Monday, May 22, 2023 5:24 PM
> To: Ruifeng Wang ; olivier.m...@6wind.com
> Cc: dev@dpdk.org; sta...@dpdk.org; tho...@monjalon.net;
> step...@networkplumber.org; Justin
> He ; Honnappa Nagarahalli ;
> nd
>
> Subject: Re: [PATCH] test/
In TSO, It is possible mbuf->data_len exceed mtu.
Fixed the incorrect data length check in ice_prep_pkts.
Fixes: ccf33dccf7aa ("net/ice: check illegal packet sizes")
Cc: sta...@dpdk.org
Signed-off-by: Qi Zhang
---
drivers/net/ice/ice_rxtx.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-
The purpose of the event dispatcher is to decouple different parts of
an application (e.g., processing pipeline stages), sharing the same
underlying event device.
The event dispatcher replaces the conditional logic (often, a switch
statement) that typically follows an event device dequeue operatio
On 5/18/2023 2:47 PM, Samina Arshad wrote:
This bug fix ensures that the runtime socket path is generated
correctly, based on the user-specified file_prefix value,
resolving the issue that occurred in the previous implementation.
Fixes: a15fc792cfb6 ("usertools/telemetry: add file prefix argumen
On 5/20/2023 7:07 PM, Philip Prindeville wrote:
From: Philip Prindeville
pread64() and pwrite64() are declared in in MUSL and
other (i.e. not glibc) C runtimes.
Signed-off-by: Philip Prindeville
---
drivers/bus/pci/linux/pci_vfio.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drive
On 5/22/2023 7:01 AM, Ruifeng Wang wrote:
Access of any memory in the hugepage shared file-backed area will trigger
an unexpected forked child process segment fault. The root cause is DPDK
doesn't support fork model [1] (calling rte_eal_init() before fork()).
Forked child process can't be treated
Provide programming guide the for the event dispatcher.
Signed-off-by: Mattias Rönnblom
---
doc/api/doxy-api-index.md | 1 +
doc/guides/prog_guide/event_dispatcher.rst | 423 +
doc/guides/prog_guide/index.rst| 1 +
3 files changed, 425 inserti
Add unit tests for the event dispatcher.
Signed-off-by: Mattias Rönnblom
---
app/test/meson.build | 1 +
app/test/test_event_dispatcher.c | 814 +++
2 files changed, 815 insertions(+)
create mode 100644 app/test/test_event_dispatcher.c
diff --git a/app
The purpose of the event dispatcher is to help reduce coupling in an
Eventdev-based DPDK application.
In addition, the event dispatcher also provides a convenient and
flexible way for the application to use service cores for
application-level processing.
Signed-off-by: Mattias Rönnblom
---
lib/
Functions which take no parameters should explicitly have "(void)" as
the parameter list, rather than "()".
Reported upstream on FreeBSD ports collection [1].
[1] https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=271524
Fixes: 764bf26873b9 ("add FreeBSD support")
Cc: sta...@dpdk.org
Reported-by
On Wed, May 17, 2023 at 6:57 PM Bruce Richardson
wrote:
>
> On Thu, May 11, 2023 at 11:14:04AM +0200, Juraj Linkeš wrote:
> > Augment the meson build system with dts api generation. The api docs are
> > generated from Python docstrings in DTS using Sphinx. The format of
> > choice is the Google fo
On 5/19/2023 9:46 PM, Rushil Gupta wrote:
> +static int
> +gve_verify_driver_compatibility(struct gve_priv *priv)
> +{
> + const struct rte_memzone *driver_info_mem;
> + struct gve_driver_info *driver_info;
> + int err;
> +
> + driver_info_mem =
> rte_memzone_reserve_aligned("verif
On Tue, May 9, 2023 at 11:34 AM Zhirun Yan wrote:
>
> Rename rte_graph_work.h to rte_graph_work_common.h for supporting
> multiple graph worker model.
I have requested to check the performance with dpdk-test and l3fwd
graph in last series.
Have you checked the performance? In my testing, there i
https://bugs.dpdk.org/show_bug.cgi?id=1236
Bug ID: 1236
Summary: [dpdk-23.07]VM crash when start dpdk-l3fwd-power in VM
with QEMU-8.0.0
Product: DPDK
Version: 23.07
Hardware: All
OS: All
Status:
Hi Burakov,
sure, will amend the changeset. currently I'm travelling, will get back by the
end of this week if that's ok.
From: Burakov, Anatoly
Sent: 19 May 2023 22:15
To: Vipin P R
Cc: dev@dpdk.org ; sta...@dpdk.org
Subject: Re: [PATCH 2/2] Memory Allocation:
On 2023/5/16 23:12, Stephen Hemminger wrote:
> On Tue, 16 May 2023 19:00:21 +0800
> Dengdui Huang wrote:
>
>> When input queue id is invalid, it will lead to
>> Segmentation fault, like:
>>
>> dpdk-testpmd -a :01:00.0 -- -i
>> testpmd> show port 0 txq/rxq 99 desc 0 status
>> Segmentation fa
> -Original Message-
> From: Yang, Qiming
> Sent: Thursday, May 18, 2023 8:16 AM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Yang, Qiming ;
> Keller, Jacob E
> Subject: [PATCH v2 10/20] net/ice/base: reduce time to read Option data
>
> Re-write ice_get_orom_civd_data to allocate memory to
Hello Bruce,
I had a question regarding the DMA ability to DMA directly to file a system.
Currently I am able to bind my FPGA to a DPDK driver and read the packets from
it and fill my mbuf buffers. However, is it possible to send these mbuf buffers
to the file system. I am having trouble zero c
This bug fix ensures that the runtime socket path is generated
correctly, based on the user-specified file_prefix value,
resolving the issue that occurred in the previous implementation.
Fixes: a15fc792cfb6 ("usertools/telemetry: add file prefix argument")
Cc: lihuis...@huawei.com
Cc: sta...@dpdk.
From: Qin Ke
Firstly, the hash type is originally used as the keyword to calculate
rss hash value, not packet type itself.
Secondly, there are some issues in the existing logic and it is conflict
with packet type offload which to do next.
Removes the logic of reporting packet type by hash type.
From: Qin Ke
There are some issues about reporting packet type by hash type of
metadata. And it may cause more performance loss and space wasting.
Parses packet type from Rx descriptor and set it to mbuf. And opens
the feature by default in nfp_net_start().
Signed-off-by: Qin Ke
Reviewed-by: N
From: Qin Ke
There are some issues about return value and code style related with
nfp_net_reconfig(), standardizes them.
The line of code nn_cfg_writel(hw, NFP_NET_CFG_CTRL, ctrl) only needs
to be executed once, deletes the redundant line in nfp_net_start() which
has called nfp_net_reconfig() in
From: Qin Ke
As rxd.vlan in Rx descriptor has been out of use and can be used
for packet type offload and other offloading information based on
comprehensive evaluation, it is renamed to rxd.offload_info.
Also adds the comment for Rx descriptor structure.
Signed-off-by: Qin Ke
Reviewed-by: Nik
From: Qin Ke
Add a new contributor.
Signed-off-by: Qin Ke
Reviewed-by: Chaoyong He
---
.mailmap | 1 +
1 file changed, 1 insertion(+)
diff --git a/.mailmap b/.mailmap
index 4f4d8eb749..cdf2cc8a65 100644
--- a/.mailmap
+++ b/.mailmap
@@ -1090,6 +1090,7 @@ Qiming Chen
Qiming Yang
Qinglai X
This patch series add the support of report packet type function for
NFP PMD:
- Add a new contributor entry
- Rename one data field of RX descriptor
- Refactor the logic of NFP reconfig
- Add the logic of report packet type
Qin Ke (5):
mailmap: update contributor entry
net/nfp: rename field an
Hi,
I am trying to enable DPDK interrupts with the function
rte_eth_dev_rx_intr_enable with a virtual function of i40e NIC then
following segmentation fault coming when the function is called. The same
code does not give a fault when used against the virtual function of the
Intel 82599 NIC. I am u
On Thu, May 18, 2023 at 9:12 PM Shijith Thotton wrote:
>
> >From: Pavan Nikhilesh
> >
> >Use LMTST when all events in the burst are enqueue with
> >rte_event:op as RTE_EVENT_OP_NEW i.e. events are enqueued
> >with the `rte_event_enqueue_new_burst` API.
> >
> >Signed-off-by: Pavan Nikhilesh
>
> A
Thanks Yan for the review comments.
> -Original Message-
> From: Yan, Zhirun
> Sent: Friday, May 12, 2023 4:38 PM
> To: Vamsi Krishna Attunuru ; dev@dpdk.org;
> tho...@monjalon.net; Jerin Jacob Kollanukkaran
> Cc: Nithin Kumar Dabilpuram ; Liang, Cunming
> ; Wang, Haiyue ; Sunil
> Kumar
Hi Akhil,
Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Akhil Goyal
> Sent: Thursday, May 18, 2023 2:16 PM
> To: Anoob Joseph ; Thomas Monjalon
> ; Jerin Jacob Kollanukkaran ;
> Konstantin Ananyev ; Bernard
> Iremonger
> Cc: Hemant Agrawal ; Mattias Rönnblom
> ; Kiran K
On 5/17/23 20:06, Ori Kam wrote:
Hi Bill,
-Original Message-
From: Bill Zhou
Sent: Thursday, May 11, 2023 10:55 AM
Subject: [PATCH v1 1/3] ethdev: add flow item for RoCE infiniband BTH
RoEC should be added devtools/words-case.txt
IB as well.
IB(InfiniBand) is one type of networkin
94 matches
Mail list logo
