Added fast mbuf release, re-using the existing mbuf pool pointer
in the queue structure.
Signed-off-by: Morten Brørup
---
drivers/net/null/rte_eth_null.c | 30 +++---
1 file changed, 27 insertions(+), 3 deletions(-)
diff --git a/drivers/net/null/rte_eth_null.c b/drivers/
In the list of EAL arguments, only the "-s" flag for service cores was
documented. Add an entry for the "-S" one too, which takes a core list
instead of a core mask.
Signed-off-by: Bruce Richardson
---
doc/guides/linux_gsg/eal_args.include.rst | 5 +
1 file changed, 5 insertions(+)
diff --g
For real-world use with dozens if not hundreds of cores, use of core
masks becomes unwieldy. Core lists are preferred so update the examples
and DPDK docs to refer to core lists over core masks i.e.
* use "-l" EAL option rather than "-c"
* use "-S" service core list option rather than "-s"
Bruce
This series does some cleanup and refactoring around the rc1 code like:
trimming unused headers,
switching to callbacks for per-arch handling, and adding trace support. It also
re-enables existing
base test to help catch reported issues on some architectures.
v4:
- change fast test so that it wo
On Mon, Jun 23, 2025 at 06:44:55PM +0200, David Marchand wrote:
> On Mon, Jun 23, 2025 at 6:13 PM Bruce Richardson
> wrote:
> > > This patch will need some rebase.
> > >
> > > I see you fixed a few docs, but there are quite some misses in
> > > copy/pasted blocks:
> > >
> > I'll take a look and re
Release status meeting minutes 2025-06-24
=
Agenda:
* Release Dates
* Subtrees
* Roadmaps
* LTS
* Defects
* Opens
Participants:
* ARM
* Intel
* Marvell
* Nvidia
* Red Hat
Release Dates
-
The following are the proposed working dates for 25.07:
RTE_FORCE_INTRINSICS with a C++ compiler causes rte_atomic.h and
rte_byteorder.h to emit on x86 an extern "C" without a closing
brace.
Signed-off-by: Edvard Fagerholm
Acked-by: Bruce Richardson
---
lib/eal/x86/include/rte_atomic.h| 6 +++---
lib/eal/x86/include/rte_byteorder.h | 9 +
On Mon, Jun 16, 2025 at 11:49:40AM +0100, Bruce Richardson wrote:
> Coverity (correctly) identified an issue[1] where, after the recent
> rework[2], the internal flag, used by argparse to track what arguments
> were previously encountered or not, was out of range for the type and no
> longer having
In order to profile app, one needs to store significant amount of samples
somewhere for an analysis later on.
Since trace library supports storing data in a CTF format,
lets take advantage of that and add a dedicated PMU tracepoint.
Signed-off-by: Tomasz Duszynski
---
MAINTAINERS
DPDK test suite provides much broader architecture coverage than
what can be tested locally so enable the test to help identify
potential issues.
Signed-off-by: Tomasz Duszynski
---
app/test/test_pmu.c | 51 +
1 file changed, 47 insertions(+), 4 deleti
On Tue, Jun 24, 2025 at 4:53 PM Bruce Richardson
wrote:
>
> On Tue, Jun 24, 2025 at 02:12:53PM +0300, Edvard Fagerholm wrote:
> > RTE_FORCE_INTRINSICS with a C++ compiler causes rte_atomic.h and
> > rte_byteorder.h to emit on x86 an extern "C" without a closing
> > brace.
> > ---
>
> Unfortunately
In eal_mem_set_dump(), when madvise() failed, an incorrect reason was
logged.
Signed-off-by: Morten Brørup
Acked-by: Anatoly Burakov
---
lib/eal/unix/eal_unix_memory.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/eal/unix/eal_unix_memory.c b/lib/eal/unix/eal_unix_memo
Recheck-request: rebase=main, iol-unit-amd64-testing
Looks good.
Reviewed-by: Marat Khalili
Thanks.
Just wanted to know - what are the next steps of the review and approval
process?
There is a test suite "ci/intel-Testing" failing now with v2 which passed
in v1. ( We know for sure, there is absolutely no code change between v1
and v2 except the commit message). Is there a way to trigge
RTE_FORCE_INTRINSICS with a C++ compiler causes rte_atomic.h and
rte_byteorder.h to emit on x86 an extern "C" without a closing
brace.
---
lib/eal/x86/include/rte_atomic.h| 4 ++--
lib/eal/x86/include/rte_byteorder.h | 9 +
2 files changed, 7 insertions(+), 6 deletions(-)
diff --git a
Recheck-request: rebase=main, iol-compile-amd64-testing
Recheck-request: rebase=main, iol-compile-amd64-testing, iol-unit-amd64-testing
Recheck-request: rebase=main, iol-compile-amd64-testing, iol-unit-amd64-testing
Recheck-request: rebase=main, iol-compile-amd64-testing, iol-unit-amd64-testing
On Wed, Jun 11, 2025 at 11:53:10AM +0100, Bruce Richardson wrote:
> When doing a build for a target that already has the instruction sets
> for AVX2/AVX512 enabled, skip emitting the AVX compiler flags, or the
> x86-64-v4 '-march' flags, as they are unnecessary. Instead, when
> the default flags pr
As the number of cores/cpus on platforms has increased over the years,
the use of coremasks rather than core-lists for identifying DPDK cores
has become more and more unwieldy. At this point, let's deprecate the
coremask-based EAL parameters for future removal, and point users to the
core-list base
Hey Stephen, I saw the comment you made to re-run UTs but I cant distinguish if
anything actually happened, the report still says everything is passing.
From: Dylan Schneider
Sent: Monday, June 16, 2025 8:29 AM
To: dev@dpdk.org ; Thomas Monjalon ; Reshma
Pattan ;
Hi, maintainers,
Kindly ping for reviews.
The CI compilation errors have been checked and are not introduced by this
patch.
We hope to merge these patches into the 25.07 version.
Thanks.
On 2025/6/11 16:18, Dengdui Huang wrote:
> This patchset adds the VF multi-TCs feature.
>
> Chengwen Feng
Reviewed-by: Marat Khalili
Just an idea, in case you have another iteration: could we maybe add a small
check that $telemetry_script actually exists and executable to avoid similar
situations in the future? Can be as simple as:
test -f "$telemetry_script"
test -x "$telemetry_script"
Due to -e
On Tue, Jun 24, 2025 at 02:12:53PM +0300, Edvard Fagerholm wrote:
> RTE_FORCE_INTRINSICS with a C++ compiler causes rte_atomic.h and
> rte_byteorder.h to emit on x86 an extern "C" without a closing
> brace.
> ---
Unfortunately, patch is missing a signoff, so isn't eligible for merge. Can
you pleas
Applied to next-dts, thanks Dean.
From: Xin Wang
Work queue is used for cmdq and tx/rx buff description.
Nic business needs to configure cmdq context and txq/rxq
context. This patch adds data structures and function codes
for work queue and context.
Signed-off-by: Xin Wang
Reviewed-by: Feifei Wang
Reviewed-by: Yi Chen
---
dr
From: Xin Wang
Add RSS and promiscuous ops related function codes.
Signed-off-by: Xin Wang
Reviewed-by: Feifei Wang
Reviewed-by: Yi Chen
---
drivers/net/hinic3/hinic3_ethdev.c | 370 +
drivers/net/hinic3/hinic3_ethdev.h | 31 +++
2 files changed, 401 insertions(+
From: Yi Chen
Add code and data structure for hardware operation, including
configuration, query, initialization and release.
Signed-off-by: Yi Chen
Signed-off-by: Xin Wang
Reviewed-by: Feifei Wang
---
drivers/net/hinic3/base/hinic3_hw_cfg.c | 240 ++
drivers/net/hinic3/base/hinic3_
From: Yi Chen
The meson.build file is added to this patch to enable
the hinic3 compilation function.
Signed-off-by: Yi Chen
Reviewed-by: Xin Wang
Reviewed-by: Feifei Wang
---
doc/guides/nics/features/hinic3.ini | 9 ++
drivers/net/hinic3/base/meson.build | 50 +++
RTE_LIB_PMU is defined by build system automatically if DPDK is build
for Linux. Otherwise it's missing.
That said all cases where conditional compilation is required
can be handled without introducing other macros.
Signed-off-by: Tomasz Duszynski
---
lib/pmu/rte_pmu.h | 3 ---
1 file changed,
From: Xin Wang
Add HW registers definition header file for SP series NIC.
Add some headers that define commands and basic defines for
use in the code.
Signed-off-by: Xin Wang
Reviewed-by: Yi Chen
Reviewed-by: Feifei Wang
---
drivers/net/hinic3/base/hinic3_cmd.h| 231
From: Yi Chen
The hinic3 PMD (**librte_net_hinic3**) provides poll mode driver support
for 25Gbps/100Gbps/200Gbps Huawei SPx series Network Adapters.
Feifei Wang (2):
net/hinic3: add dev ops
net/hinic3: add Rx/Tx functions
Xin Wang (7):
net/hinic3: add basic header files
net/hinic3: add
From: Xin Wang
Micocode is named ucode in SP series NIC. Its main responsibility is data
transmission and reception. But it can also handle some administration
works. It uses cmdq mechanism. This patch introduces data structures,
initialization, interfaces, and commands sending functions of cmdq.
From: Yi Chen
Eqs include aeq and ceq. Aeq is a kind of queue for mgmt
asynchronous message and mgmt command response message.
This patch introduces data structures, initialization,
and related interfaces about aeq.
Signed-off-by: Yi Chen
Reviewed-by: Xin Wang
Reviewed-by: Feifei Wang
---
dr
From: Yi Chen
This patch adds some HW interfaces for bar operatioin interfaces,
including: mapped bar address geeting, HW attributes getting,
msi-x reg operation, function type getting and so on.
Signed-off-by: Yi Chen
Reviewed-by: Xin Wang
Reviewed-by: Feifei Wang
---
drivers/net/hinic3/bas
From: Xin Wang
Currently, there are two types of events: pf/vf connection status
and port information printing. This patch contains related data
structures and function codes.
Signed-off-by: Xin Wang
Reviewed-by: Yi Chen
Reviewed-by: Feifei Wang
---
drivers/net/hinic3/base/hinic3_nic_event.c
From: Yi Chen
This patch adds some basic files to describe the hinic3 driver.
Signed-off-by: Feifei Wang
Signed-off-by: Yi Chen
Reviewed-by: Xin Wang
---
.mailmap | 4 +-
MAINTAINERS| 6 +++
doc/guides/nics/hinic3.rst |
From: Yi Chen
Added support for rte_flow, including ethertype, IPv4,
IPv6, and tunnel VXLAN. In addition, user can add or delete filters.
Signed-off-by: Yi Chen
Reviewed-by: Xin Wang
Reviewed-by: Feifei Wang
---
drivers/net/hinic3/hinic3_ethdev.c | 82 ++
drivers/net/hinic3/hinic3_ethdev.h
From: Yi Chen
This patch adds support for mailbox of hinic3 PMD driver,
mailbox is used for communication between PF/VF driver and MPU.
This patch provides mailbox-related data structures and functional
code.
Signed-off-by: Yi Chen
Reviewed-by: Xin Wang
Reviewed-by: Feifei Wang
---
drivers/n
From: Xin Wang
This patch contains data structures and function codes
related to device initialization.
Signed-off-by: Xin Wang
Reviewed-by: Feifei Wang
Reviewed-by: Yi Chen
---
drivers/net/hinic3/hinic3_ethdev.c | 514 +
drivers/net/hinic3/hinic3_ethdev.h | 119 +
From: Yi Chen
Mgmt module is a kind of administration module for the chip.
It is responsible for handling administration command from host.
It mainly uses aeq to implement. This patch adds related data
structures, packaged interfaces and function codes.
Signed-off-by: Yi Chen
Reviewed-by: Xin W
From: Xin Wang
Add man-machine language support and implements the get eeprom method.
Signed-off-by: Xin Wang
Reviewed-by: Feifei Wang
Reviewed-by: Yi Chen
---
drivers/net/hinic3/hinic3_ethdev.c| 13 +
drivers/net/hinic3/mml/hinic3_dbg.c | 171 +
drivers/net/hinic3/mml/hin
From: Yi Chen
The items of configurations and queries for NIC business include
MAC, VLAN, MTU, RSS and so on. These configurations and queries
are handled by mgmt module. This patch introduces related
data structures and function codes.
Signed-off-by: Yi Chen
Reviewed-by: Xin Wang
Reviewed-by:
RTE_LIB_PMU is defined by build system automatically if DPDK is build
for Linux. Otherwise it's missing.
That said all cases where conditional compilation is required
can be handled without introducing other macros.
Signed-off-by: Tomasz Duszynski
---
lib/pmu/rte_pmu.h | 3 ---
1 file changed,
Applied to next-dts, thanks Dean.
From: Feifei Wang
This patch add package sending and receiving function codes.
Signed-off-by: Feifei Wang
Signed-off-by: Yi Chen
Reviewed-by: Xin Wang
---
drivers/net/hinic3/hinic3_ethdev.c | 13 +-
drivers/net/hinic3/hinic3_rx.c | 305 +++-
drivers/net/hinic3/hinic3_tx.c |
This series does some cleanup and refactoring around the rc1 code like:
trimming unused headers,
switching to callbacks for per-arch handling, and adding trace support. It also
re-enables existing
base test to help catch reported issues on some architectures.
v5:
- add missing patch that quiesce
In order to profile app, one needs to store significant amount of samples
somewhere for an analysis later on.
Since trace library supports storing data in a CTF format,
lets take advantage of that and add a dedicated PMU tracepoint.
Signed-off-by: Tomasz Duszynski
---
MAINTAINERS
/proc/sys/kernel/perf_user_access attribute allow user process to access
perf counters. Though in order to change it binary requires elevated
capabilities or must be run as root. If that's not the case counter
access remains disabled. Hence to avoid confusion log message that
that warns user about
Replace static per-architecture ops with a callback-based ops
structure. This makes architecture-specific PMU implementations more
modular and easier to extend.
Signed-off-by: Tomasz Duszynski
---
lib/pmu/pmu.c | 17 +
lib/pmu/pmu_arm64.c | 19 +--
lib/p
DPDK test suite provides much broader architecture coverage than
what can be tested locally so enable the test to help identify
potential issues.
Signed-off-by: Tomasz Duszynski
---
app/test/test_pmu.c | 51 +
1 file changed, 47 insertions(+), 4 deleti
Make sure that out-of-bound access does not happen by saving one byte in
buffer for NUL terminator.
Fixes: a8926a65ad1d ("pmu: support Arm")
Fixes: 960c43184c4d ("pmu: introduce library for reading PMU events")
Cc: tduszyn...@marvell.com
Signed-off-by: Tomasz Duszynski
---
lib/pmu/pmu.c |
Install only architecture specific headers to avoid header pollution.
Signed-off-by: Tomasz Duszynski
---
lib/pmu/meson.build | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/lib/pmu/meson.build b/lib/pmu/meson.build
index bcb6d10f1a..53013d0ed6 100644
--- a/lib/pmu
Add a dummy rte_pmu_read() definition for chkincs when
ALLOW_EXPERIMENTAL_API is not defined to suppress warnings from
use of experimental APIs in tracepoints.
Fixes: 960c43184c4d ("pmu: introduce library for reading PMU events")
Signed-off-by: Tomasz Duszynski
---
lib/pmu/rte_pmu.h | 4
1
Added the option to jump to a specific group.
snippets that are not supported on the root table can now call
create_jump_flow to jump to other group.
Added three new snippets that uses the jump flow:
- match Network Service Header (NSH) snippet
- match RoCE IB BTH opcode/dest_qp snippet
- Switch G
This patch series adds port affinity matching for bonded ports and
refactors queue management to support the new port affinity snippets.
This refactoring also enables other snippets that require access to
the queue number to utilize it more easily.
It also introduces support for jumping to specifi
This snippet demonstrates port affinity matching in bonded ports,
ensuring packets are sent back through their ingress port.
The NR_QUEUES constant was moved to common.h to support mapping
four TX queues (0-3) to two port affinities (0,1→1 and 2,3→2).
Signed-off-by: Shani Peretz
---
examples/fl
Coverity reports some defects, where the root cause seems to be negative
return value from sysconf(_SC_PAGESIZE) not being handled.
The PMU library cannot use the EAL function rte_mem_page_size(), because
of the dependency chain. (EAL depends on PMU, because Trace is part of
EAL, and Trace depends
Coverity reports some defects, where the root cause seems to be negative
return value from sysconf(_SC_PAGESIZE) not being handled.
This series addresses those defects in the DPDK libraries.
PS: "_SC_PAGESIZE" has the alias "_SC_PAGE_SIZE". Both are covered here.
Morten Brørup (3):
eal/unix: fi
Coverity reports some defects, where the root cause seems to be negative
return value from sysconf(_SC_PAGESIZE) not being handled.
rte_mem_page_size() was updated to handle negative return value from
sysconf(_SC_PAGESIZE).
All library functions directly calling sysconf(_SC_PAGESIZE) were updated
> Subject: Re: [PATCH v2] net/iavf: fix VLAN offload strip flag
>
> Hi Ciara
> Thanks for your effort in reproducing the issue and confirming that the patch
> works. However, I have taken care of the indentation in the commit message
> and sent out a v2 patch. Appreciate your review comments.
>
>
63 matches
Mail list logo
