It was a common pattern to have "GCC diagnostic ignored" pragmas
sprinkled over the code and only activate these pragmas for certain
compilers (gcc and clang). Clang supports GCC's pragma for
compatibility with existing source code, so #pragma GCC diagnostic
and #pragma clang diagnostic are synonym
It was a common pattern to have "GCC diagnostic ignored" pragmas
sprinkled over the code and only activate these pragmas for certain
compilers (gcc and clang). Clang supports GCC's pragma for
compatibility with existing source code, so #pragma GCC diagnostic
and #pragma clang diagnostic are synonym
It was a common pattern to have "GCC diagnostic ignored" pragmas
sprinkled over the code and only activate these pragmas for certain
compilers (gcc and clang). Clang supports GCC's pragma for
compatibility with existing source code, so #pragma GCC diagnostic
and #pragma clang diagnostic are synonym
v14:
* Renamed RTE_PTR_DROP_QUALIFIERS into RTE_PTR_UNQUAL to more resemble
C23 typeof_unqual.
* Added macro RTE_CAST_PTR to make the cast more readable when removing
a type qualifier from a pointer.
v13:
* Renamed RTE_IGNORE_CAST_QUAL into RTE_PTR_DROP_QUALIFIERS.
* Added (void *) cast
On Thu, Jan 16, 2025 at 07:56:52PM -0800, Andre Muezerie wrote:
> On Thu, Jan 16, 2025 at 10:08:07AM +0100, Morten Brørup wrote:
> > > From: Andre Muezerie [mailto:andre...@linux.microsoft.com]
> > > Sent: Thursday, 16 January 2025 02.55
> > >
> > > It was a common pattern to have "GCC diagnostic
On Thu, Jan 16, 2025 at 08:57:27AM +, Bruce Richardson wrote:
> On Wed, Jan 15, 2025 at 05:55:11PM -0800, Andre Muezerie wrote:
> > It was a common pattern to have "GCC diagnostic ignored" pragmas
> > sprinkled over the code and only activate these pragmas for certain
> > compilers (gcc and cla
When experimenting with the -std=c2x compiler option the error below
popped up:
../drivers/net/bnxt/tf_core/tf_sram_mgr.c:952:39: error: incompatible
types when assigning to type ‘_Bool *’ from type ‘_Bool’
The code indicates that the intention was to assign false to the bool
being pointed to,
在 2025/1/16 23:18, Thomas Monjalon 写道:
16/01/2025 12:40, Huisong Li:
During probing, before the port becomes generally available, the
rte_eth_dev_socket_id() and rte_eth_dev_owner_*() are available to
application.
Fixes: 7dcd73e37965 ("drivers/bus: set device NUMA node to unknown by default")
在 2025/1/17 2:31, Stephen Hemminger 写道:
On Thu, 16 Jan 2025 19:40:33 +0800
Huisong Li wrote:
If application verify the validity of the port id or configure this port in
the new event callback, application may happen to the port id is invalid.
In case of similar confusion, this patch have to
On Thu, Jan 16, 2025 at 09:36:30PM +0100, Morten Brørup wrote:
> > From: Bruce Richardson [mailto:bruce.richard...@intel.com]
> > Sent: Thursday, 16 January 2025 18.46
> >
> > On Thu, Jan 16, 2025 at 11:10:47PM +0530, Jerin Jacob wrote:
> > > On Thu, Jan 16, 2025 at 10:50 PM Bruce Richardson
> > >
On 1/9/25 3:31 PM, Maxime Coquelin wrote:
rte_vhost_driver_set_max_queue_num API returns early when
called for a Vhost-user device, as this API is intended to
limit the maximum number of queue pairs supported by VDUSE
devices. However, a log mentioning the maximim number of
queue pairs is bein
If application verify the validity of the port id or configure this port in
the new event callback, application may happen to the port id is invalid.
In case of similar confusion, this patch have to clarify something about
RTE_ETH_EVENT_NEW in code.
Signed-off-by: Huisong Li
Acked-by: Thomas Mon
I've had some issues when I add the verification of the port id in the
event callback, which are discussed in another patch series[1]. So this
series clarify something about RTE_ETH_EVENT_NEW based on the previous
discussion.
[1]
https://patches.dpdk.org/project/dpdk/cover/20250113025521.32703-1-
On 12/20/24 4:45 AM, Yunjian Wang wrote:
The value of tso_segsz cannot be 0, instead check that value of
gso_size was set.
Fixes: d0cf91303d73 ("vhost: add Tx offload capabilities")
Cc: sta...@dpdk.org
Signed-off-by: Yunjian Wang
---
lib/vhost/virtio_net.c | 3 +++
1 file changed, 3 inse
On 1/16/25 10:54 AM, Maxime Coquelin wrote:
This series starts with a fix for a regression in the Vhost
dequeue error path.
The other patches improve the error handling to reduce the
chance of such regressions in the future.
Changes in v3:
==
- Squashed patches 2 & 3 (David)
- Si
Some RXTX operations like queue setup and release, packet type get, and
Tx done cleanup have been supported on PF device. There are ops
functions directly added.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 3 +++
drivers/net/ngbe/ngbe_ethdev_vf.c| 5 +
2 files ch
This series adds self monitoring support i.e allows to configure and
read performance measurement unit (PMU) counters in runtime without
using perf utility. This has certain advantages when application runs on
isolated cores running dedicated tasks.
Events can be read directly using rte_pmu_read()
Add support for programming PMU counters and reading their values
in runtime bypassing kernel completely.
This is especially useful in cases where CPU cores are isolated
i.e run dedicated tasks. In such cases one cannot use standard
perf utility without sacrificing latency and performance.
Signed
Add support for reading ARM PMU events in runtime.
Signed-off-by: Tomasz Duszynski
---
app/test/test_pmu.c | 4 ++
lib/pmu/meson.build | 8
lib/pmu/pmu_arm64.c | 94 +
lib/pmu/rte_pmu.h | 4 ++
lib/pmu/rte_pmu_pmc_arm6
Add support for reading Intel x86_64 PMU events in runtime.
Signed-off-by: Tomasz Duszynski
---
app/test/test_pmu.c | 2 ++
lib/pmu/meson.build | 1 +
lib/pmu/rte_pmu.h| 2 ++
lib/pmu/rte_pmu_pmc_x86_64.h | 24
4 files changed, 29 inserti
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
---
app/test/test_trace_perf.c
The test case "test_multi_alloc_statistics" was brittle in that it did
some allocations and frees and then checked statistics without
considering the initial state of the malloc heaps. This meant that,
depending on what allocations/frees were done beforehand, the test can
sometimes fail.
We can im
On Fri, Jan 17, 2025 at 05:20:41PM +0300, Dmitry Kozlyuk wrote:
> 2025-01-17 13:52 (UTC+), Bruce Richardson:
> > The test case "test_multi_alloc_statistics" was brittle in that it did
> > some allocations and frees and then checked statistics without
> > considering the initial state of the mal
The test case "test_multi_alloc_statistics" was brittle in that it did
some allocations and frees and then checked statistics without
considering the initial state of the malloc heaps. This meant that,
depending on what allocations/frees were done beforehand, the test can
sometimes fail.
We can im
2025-01-17 13:52 (UTC+), Bruce Richardson:
> The test case "test_multi_alloc_statistics" was brittle in that it did
> some allocations and frees and then checked statistics without
> considering the initial state of the malloc heaps. This meant that,
> depending on what allocations/frees were d
Some testpmd runtime functions require that forwarding be stopped before
attempting to execute them, depending on the NIC and vendor. Adding a
decorator to these testpmdshell methods to stop, execute, and then start
forwarding again abstracts this concern away for test suite developers,
and makes f
A functional test suite that assesses MTU updating and forwarding within
a DPDK application.
This suite consolidates the previous 'mtu_update' and 'jumbo_frames' test
suites from the old dts framework into a single, comprehensive test suite,
and it covers all of mtu the adjustment options within
v(1):
* refactored suite consolidating these two test suites:
inbox.dpdk.org/dev/20241023153906.1522920-2-luca.vizza...@arm.com/
inbox.dpdk.org/dev/20240726141307.14410-3-npra...@iol.unh.edu/
* Suite is 'redesigned' to assess both runtime and pre-runtime mtu
configuration in t
The test case "test_multi_alloc_statistics" was brittle in that it did
some allocations and frees and then checked statistics without
considering the initial state of the malloc heaps. This meant that,
depending on what allocations/frees were done beforehand, the test can
sometimes fail.
We can im
On Thu, Jan 16, 2025 at 6:22 PM Bruce Richardson
wrote:
> diff --git a/drivers/meson.build b/drivers/meson.build
> index 495e21b54a..89545e618e 100644
> --- a/drivers/meson.build
> +++ b/drivers/meson.build
> @@ -47,7 +47,7 @@ enable_drivers = run_command(list_dir_globs,
> enable_drivers, check:
On Thu, Jan 16, 2025 at 6:34 PM Bruce Richardson
wrote:
>
> On Thu, Jan 16, 2025 at 05:22:21PM +, Bruce Richardson wrote:
> > Consolidate all Intel HW NIC drivers into a driver/net/intel This
> > matches the layout used for drivers in the kernel, and potentially
> > enabling easier sharing am
On Fri, 17 Jan 2025 07:20:05 +
Stefan Lässer wrote:
> > -Original Message-
> > From: Stephen Hemminger
> > Sent: Thursday, January 16, 2025 5:25 PM
> > To: Stefan Lässer
> > Cc: John W. Linville ; dev@dpdk.org
> > Subject: Re: [PATCH] net/af_packet: provide packet drop stats
> >
>
On Fri, 17 Jan 2025 15:28:47 +0800
Yang Ming wrote:
> DPDK detect vfio container according the existence of vfio
> module. But for container with non-privileged mode, there is
> possibility that no VFIO_DIR(/dev/vfio) mapping from host to
> container when host have both Intel NIC and Mellanox NIC
On Fri, 17 Jan 2025 18:41:00 +0800
Zaiyu Wang wrote:
> Introduce virtual function driver in ngbe PMD, add simple init and
> uninit function to probe and remove the device.
>
> Signed-off-by: Zaiyu Wang
> ---
> doc/guides/nics/features/ngbe_vf.ini | 11 ++
> drivers/net/ngbe/base/meson.build
If the buffer splitting feature is configured and the payload mbuf
allocation fails, the previously allocated header mbuf may be returned not
fully initialized or a memory leak may occur.
This patch handles this case correctly by freeing the corresponding header
buffer.
Fixes: 629dad3ef325 ("net/i
On Tue, 07 Jan 2025 10:49:40 +0800
"WanRenyong" wrote:
> diff --git a/doc/guides/rel_notes/release_25_03.rst
> b/doc/guides/rel_notes/release_25_03.rst
> index 426dfcd982..6f766add72 100644
> --- a/doc/guides/rel_notes/release_25_03.rst
> +++ b/doc/guides/rel_notes/release_25_03.rst
> @@ -55,6 +
On 11/27/24 3:03 AM, Jianping Zhao wrote:
Clear ring addresses during vring base retrieval to handle guest reboot
scenarios correctly. This is particularly important for vdpa-blk devices
where the following issue occurs:
When a guest OS with vdpa-blk device reboots, during UEFI stage, only
on
During probing, before the port becomes generally available, the
rte_eth_dev_socket_id() and rte_eth_dev_owner_*() are available to
the application.
Fixes: 7dcd73e37965 ("drivers/bus: set device NUMA node to unknown by default")
Fixes: 53ef1b34776b ("ethdev: add sanity checks in control APIs")
Cc:
* The meeting occurs on every Thursday at 14:30 DST over Jitsi on
https://meet.jit.si/DPDK
Correction:
The meeting occurs on every Tuesday at 14:30 DST
Add basic hardware configure flow and device information statement.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 7 +
drivers/net/ngbe/base/ngbe_mbx.h | 2 +
drivers/net/ngbe/base/ngbe_type.h| 5 +
drivers/net/ngbe/base/ngbe_vf.c | 235 +
Add basic code of PF-VF mailbox implementation to serve the communication
between VF and PF devices.
Signed-off-by: Zaiyu Wang
---
drivers/net/ngbe/base/ngbe_mbx.c | 338 ++
drivers/net/ngbe/base/ngbe_mbx.h | 29 +++
drivers/net/ngbe/base/ngbe_type.h | 7 +
drive
Introduce virtual function driver in ngbe PMD, add simple init and
uninit function to probe and remove the device.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 11 ++
drivers/net/ngbe/base/meson.build| 1 +
drivers/net/ngbe/base/ngbe.h | 1 +
drivers/net/
Add VF device interrupt handler, support to enable and disable RX queue
interrupt, and configure misx interrupt.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/ngbe_ethdev_vf.c| 227 +++
2 files changed, 228 insertions(+)
Generate a random MAC address if none was assigned by PF during
the initialization of VF device. And support to add and remove
MAC address.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_type.h| 1 +
drivers/net/ngbe/base/ngbe_vf.c
Add support for VLAN filter, offload and strip set feature.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_vf.c | 33 +++-
drivers/net/ngbe/base/ngbe_vf.h | 2 +
drivers/net/ngbe/ngbe_ethdev_vf.c| 112 ++
Add support to check link feature for VF device, including link speed,
duplex mode and link state.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_vf.c | 96
drivers/net/ngbe/base/ngbe_vf.h | 2 +
drive
This patch adds support to VF device for ngbe PMD.
---
v2:
- update description of patch content
- fix build issue
- formatting and cleanup
---
Zaiyu Wang (15):
net/ngbe: add ethdev probe and remove for VF device
net/ngbe: add support for PF-VF mailbox interface
net/ngbe: add hardware confi
Add support for datapath init, including RX and TX unit init.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 5 +
doc/guides/nics/ngbe.rst | 11 ++
drivers/net/ngbe/ngbe_ethdev.h | 6 +
drivers/net/ngbe/ngbe_ethdev_vf.c| 63
drivers/net/
Support to enable and disable promiscuous and allmulticast mode on VF
device.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 2 +
drivers/net/ngbe/base/ngbe_type.h| 1 +
drivers/net/ngbe/base/ngbe_vf.c | 39 +++
drivers/net/ngbe/base/ngbe_vf.h | 1 +
Support to update MTU for VF device.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_type.h| 1 +
drivers/net/ngbe/base/ngbe_vf.c | 24 +++
drivers/net/ngbe/base/ngbe_vf.h | 1 +
drivers/net/ngbe/ngbe_ethdev_vf
Add the complete configuration process for start/stop/reset/close ops,
so that applications can enable the device correctly.
Signed-off-by: Zaiyu Wang
---
drivers/net/ngbe/ngbe_ethdev_vf.c | 170 +-
1 file changed, 169 insertions(+), 1 deletion(-)
diff --git a/driver
Add support to update multicast MAC filter.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_vf.c | 81
drivers/net/ngbe/base/ngbe_vf.h | 3 ++
3 files changed, 85 insertions(+)
diff --git a/doc/guides/
Add support to dump registers for VF device. Currently we only support a
small number of registers. More registers will be added as needed.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/ngbe_ethdev_vf.c| 73
2 files c
Some RXTX operations like queue setup and release, packet type get, and
Tx done cleanup have been supported on PF device. There are ops
functions directly added.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 3 +++
drivers/net/ngbe/ngbe_ethdev_vf.c| 5 +
2 files ch
Add support to get stats and extended stats by reading hardware
registers.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 2 +
drivers/net/ngbe/base/ngbe_vf.h | 32 +++
drivers/net/ngbe/ngbe_ethdev_vf.c| 138 +++
3 files changed, 172
Updating Base Code for TXPP Feature Implementation.
Paul Greenwalt (2):
net/ice: add tstamp descriptor
net/ice: add Tx Time queue context configuration support
drivers/net/ice/base/ice_adminq_cmd.h | 55 +++
drivers/net/ice/base/ice_common.c | 96 +++
From: Paul Greenwalt
Tx Packet Pacing (TXPP) functionality is in addition to the Tx LAN queue
flow, so it has a separate Tx Time queue context.
Add Tx Time queue context data structures, and two new related AQCs.
- ice_aq_set_txtimeq (opcode 0x0C35) to set Tx Time queue(s) context
- ice_aq_opera
From: Paul Greenwalt
The Tx packet pacing (TXPP) tstamp queue descriptor is a 32bit format.
- Tx queue descriptor ring index, bits 12:0
- Time Stamp, bits 31:13
Add struct ice_ts_desc to hold the 32bit descriptor.
Signed-off-by: Paul Greenwalt
Signed-off-by: Soumyadeep Hore
---
drivers/net/i
https://bugs.dpdk.org/show_bug.cgi?id=1616
Bug ID: 1616
Summary: libtmp_rte_event_dlb2 sse fails to compile
Product: DPDK
Version: 24.11
Hardware: x86
OS: All
Status: UNCONFIRMED
Severity: major
Introduce virtual function driver in ngbe PMD, add simple init and
uninit function to probe and remove the device.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 11 ++
drivers/net/ngbe/base/meson.build| 1 +
drivers/net/ngbe/base/ngbe.h | 1 +
drivers/net/
This patch adds support to VF device for ngbe PMD.
---
v2:
- update description of patch content
- fix build issue
- formatting and cleanup
---
v3:
- fix Intel-compilation error
---
Zaiyu Wang (15):
net/ngbe: add ethdev probe and remove for VF device
net/ngbe: add support for PF-VF mailbox in
Add basic hardware configure flow and device information statement.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 7 +
drivers/net/ngbe/base/ngbe_mbx.h | 2 +
drivers/net/ngbe/base/ngbe_type.h| 5 +
drivers/net/ngbe/base/ngbe_vf.c | 235 +
Add basic code of PF-VF mailbox implementation to serve the communication
between VF and PF devices.
Signed-off-by: Zaiyu Wang
---
drivers/net/ngbe/base/ngbe_mbx.c | 338 ++
drivers/net/ngbe/base/ngbe_mbx.h | 29 +++
drivers/net/ngbe/base/ngbe_type.h | 7 +
drive
Support to enable and disable promiscuous and allmulticast mode on VF
device.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 2 +
drivers/net/ngbe/base/ngbe_type.h| 1 +
drivers/net/ngbe/base/ngbe_vf.c | 39 +++
drivers/net/ngbe/base/ngbe_vf.h | 1 +
Support to update MTU for VF device.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_type.h| 1 +
drivers/net/ngbe/base/ngbe_vf.c | 24 +++
drivers/net/ngbe/base/ngbe_vf.h | 1 +
drivers/net/ngbe/ngbe_ethdev_vf
Generate a random MAC address if none was assigned by PF during
the initialization of VF device. And support to add and remove
MAC address.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_type.h| 1 +
drivers/net/ngbe/base/ngbe_vf.c
Add support to check link feature for VF device, including link speed,
duplex mode and link state.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_vf.c | 96
drivers/net/ngbe/base/ngbe_vf.h | 2 +
drive
Add support for datapath init, including RX and TX unit init.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 5 +
doc/guides/nics/ngbe.rst | 11 ++
drivers/net/ngbe/ngbe_ethdev.h | 6 +
drivers/net/ngbe/ngbe_ethdev_vf.c| 63
drivers/net/
Add support for VLAN filter, offload and strip set feature.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_vf.c | 33 +++-
drivers/net/ngbe/base/ngbe_vf.h | 2 +
drivers/net/ngbe/ngbe_ethdev_vf.c| 112 ++
Add VF device interrupt handler, support to enable and disable RX queue
interrupt, and configure misx interrupt.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/ngbe_ethdev_vf.c| 230 +++
2 files changed, 231 insertions(+)
Add support to update multicast MAC filter.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/base/ngbe_vf.c | 81
drivers/net/ngbe/base/ngbe_vf.h | 3 ++
3 files changed, 85 insertions(+)
diff --git a/doc/guides/
Add the complete configuration process for start/stop/reset/close ops,
so that applications can enable the device correctly.
Signed-off-by: Zaiyu Wang
---
drivers/net/ngbe/ngbe_ethdev_vf.c | 170 +-
1 file changed, 169 insertions(+), 1 deletion(-)
diff --git a/driver
Add support to get stats and extended stats by reading hardware
registers.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 2 +
drivers/net/ngbe/base/ngbe_vf.h | 32 +++
drivers/net/ngbe/ngbe_ethdev_vf.c| 138 +++
3 files changed, 172
Add support to dump registers for VF device. Currently we only support a
small number of registers. More registers will be added as needed.
Signed-off-by: Zaiyu Wang
---
doc/guides/nics/features/ngbe_vf.ini | 1 +
drivers/net/ngbe/ngbe_ethdev_vf.c| 73
2 files c
74 matches
Mail list logo