> -Original Message-
> From: Andre Muezerie
> Sent: Thursday, January 30, 2025 5:38 AM
> To: Ali Alnubani
> Cc: dev@dpdk.org; step...@networkplumber.org; bruce.richard...@intel.com
> Subject: Re: [PATCH v16 3/3] drivers/net: add diagnostics macros to make code
> portable
>
> On Wed, Jan
Thanks, the latest patch looks complete according to our conversation. I
can merge in the morning.
Reviewed-by: Patrick Robb
Tested-by: Patrick Robb
On Mon, Dec 9, 2024 at 2:58 PM Dean Marx wrote:
>
> -sut_node.tear_down_test_run()
> +sut_node.tear_down_test_run(test_run_config.dpdk_config)
>
My first question was why is there a need to pass all of dpdk_config
through from here all the way to cleanup_sut()? Is
On Wed, 29 Jan 2025 00:10:12 +
Long Li wrote:
> Another approach is to modify EAL to never delete driver arguments when a
> device is removed. i.e., It doesn't call rte_devargs_remove() on device
> removal, instead keep those devargs for the lifetime of the process. Do you
> think this is
On Wed, Jan 29, 2025 at 09:10:40PM +, Ali Alnubani wrote:
> > -Original Message-
> > From: Ali Alnubani
> > Sent: Wednesday, January 29, 2025 11:08 PM
> > To: Andre Muezerie
> > Cc: dev@dpdk.org; step...@networkplumber.org; bruce.richard...@intel.com
> > Subject: RE: [PATCH v16 3/3] dr
Fixes: 41d133d6c62f ("dts: automatically bring up link on interfaces")
Cc: pr...@iol.unh.edu
Signed-off-by: Patrick Robb
---
dts/framework/testbed_model/linux_session.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/dts/framework/testbed_model/linux_session.py
b/dts/framew
> -Original Message-
> From: Ali Alnubani
> Sent: Wednesday, January 29, 2025 11:08 PM
> To: Andre Muezerie
> Cc: dev@dpdk.org; step...@networkplumber.org; bruce.richard...@intel.com
> Subject: RE: [PATCH v16 3/3] drivers/net: add diagnostics macros to make code
> portable
>
> > -Orig
> -Original Message-
> From: Andre Muezerie
> Sent: Wednesday, January 22, 2025 12:36 AM
> To: andre...@linux.microsoft.com
> Cc: dev@dpdk.org; step...@networkplumber.org; bruce.richard...@intel.com
> Subject: [PATCH v16 3/3] drivers/net: add diagnostics macros to make code
> portable
>
>
On Wed, Jan 29, 2025 at 09:17:38AM -0800, Stephen Hemminger wrote:
> On Wed, 29 Jan 2025 10:54:16 +0200
> Shani Peretz wrote:
>
> > DPDK provides two formats for specifying PCI device numbers:
> > a full version (":08:00.0") and a short version ("08:00.0").
> > Issues can occur when an applic
On 28/01/2025 23:11, Ariel Otilibili wrote:
Both legs of the loop share the same logic: either to go out of the
function, or to fall through to the next instructions.
For that, maybe_cpy_pkt() is introduced.
Bugzilla ID: 1440
Signed-off-by: Ariel Otilibili
---
drivers/net/af_xdp/rte_eth_af
On Wed, Jan 29, 2025 at 03:16:51PM +0100, David Marchand wrote:
> On Wed, Jan 29, 2025 at 2:26 PM David Marchand
> wrote:
> >
> > On Tue, Jan 21, 2025 at 11:36 PM Andre Muezerie
> > wrote:
> > >
> > > v16:
> > > * Updated comment for RTE_CAST_PTR.
> > >
> > > v15:
> > > * Fixed a comment in rte
During a recent cleanup a few lines were missed which are causing
errors on ppc64le, like the ones below:
drivers/net/mlx5/mlx5_rxtx_vec_altivec.h:77:17: error: cast discards
‘volatile’ qualifier from pointer target type [-Werror=cast-qual]
lib/eal/include/rte_common.h:557:34: warning: dereferenc
On Wed, 29 Jan 2025 10:54:16 +0200
Shani Peretz wrote:
> DPDK provides two formats for specifying PCI device numbers:
> a full version (":08:00.0") and a short version ("08:00.0").
> Issues can occur when an application uses one format (e.g., short)
> while running testpmd, then attempts to u
On Wed, Jan 29, 2025 at 05:48:56PM +0530, Shaiq Wani wrote:
> updated the documentation to reflect that both AVX512 and AVX2
> support are available.
>
> Signed-off-by: Shaiq Wani
> ---
> doc/guides/nics/idpf.rst | 7 +++
> 1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/do
On Wed, Jan 29, 2025 at 05:48:55PM +0530, Shaiq Wani wrote:
> In case some CPUs don't support AVX512. Enable AVX2 for them to
> get better per-core performance.
>
> The single queue model processes all packets in order while
> the split queue model separates packet data and metadata into
> differe
On Wed, Jan 29, 2025 at 05:48:54PM +0530, Shaiq Wani wrote:
> In case some CPUs don't support AVX512. Enable AVX2 for them to
> get better per-core performance.
>
> The single queue model processes all packets in order while
> the split queue model separates packet data and metadata into
> differe
On Wed, 29 Jan 2025 10:54:16 +0200
Shani Peretz wrote:
> +create_pci_dev(const char *name)
> +{
> + int port_id;
> + uint8_t slave_mac1[] = {0x00, 0xFF, 0x00, 0xFF, 0x00, 0x00 };
> + struct rte_ether_addr *mac_addr = (struct rte_ether_addr *)slave_mac1;
Use different initializer and
On 1/7/25 7:02 PM, Gowrishankar Muthukrishnan wrote:
Add symmetric support.
Signed-off-by: Gowrishankar Muthukrishnan
---
examples/vhost_crypto/main.c | 54 ++--
1 file changed, 40 insertions(+), 14 deletions(-)
diff --git a/examples/vhost_crypto/main.
On 1/7/25 7:02 PM, Gowrishankar Muthukrishnan wrote:
Support asymmetric RSA crypto operations in vhost-user.
Signed-off-by: Gowrishankar Muthukrishnan
---
Depends-on: series-34291 ("crypto/virtio: add RSA support")
lib/vhost/vhost_crypto.c | 504 ---
l
On Thu, Jan 23, 2025 at 5:38 PM Andre Muezerie
wrote:
> > > I see there is some back and forth on the topic of passing -Wvla.
> > > It would be less fragile to put a -Wla in a upper level meson.build
> > > (like config/meson.build for example), then disable explicitly in the
> > > parts that are n
From: Pavan Nikhilesh
Implement DMA enqueue/dequeue operations when
application enables it via configuration.
Signed-off-by: Pavan Nikhilesh
Change-Id: I57883ce5d358bf23a9d940ed513d0dc762227dcc
---
drivers/dma/cnxk/cnxk_dmadev.c| 25 +-
drivers/dma/cnxk/cnxk_dmadev.h| 7 ++
driv
From: Pavan Nikhilesh
Update the documentation to replace all instances of
rte_event_dma_adapter_op with rte_dma_op
Signed-off-by: Pavan Nikhilesh
Change-Id: I0fe65d18f4601709826c11c6738cacec8991515d
---
doc/guides/prog_guide/eventdev/event_dma_adapter.rst | 6 +++---
1 file changed, 3 inserti
From: Pavan Nikhilesh
Migrate all invocations of rte_event_dma_adapter_op
API to rte_dma_op.
Signed-off-by: Pavan Nikhilesh
Change-Id: I56b6e61af72d119287b0d2ba6a9bbacc3ae808d6
---
app/test-eventdev/test_perf_common.c | 6 +--
app/test-eventdev/test_perf_common.h | 4 +-
app/test/test_event_
From: Pavan Nikhilesh
Add enqueue/dequeue operations that use struct rte_dma_op
to communicate with the dma device.
These operations need to be enabled at dma device configuration
time by setting the flag rte_dma_conf::enable_enq_deq if the
device supports RTE_DMA_CAPA_OPS_ENQ_DEQ capability.
The
On Wed, Jan 29, 2025 at 2:26 PM David Marchand
wrote:
>
> On Tue, Jan 21, 2025 at 11:36 PM Andre Muezerie
> wrote:
> >
> > v16:
> > * Updated comment for RTE_CAST_PTR.
> >
> > v15:
> > * Fixed a comment in rte_common.h to make Doxygen happy.
> > * Fixed a typo (extra comma).
> > * Added missi
On Fri, Jan 24, 2025 at 5:46 PM Andre Muezerie
wrote:
>
> MSVC does not support inline assembly so use movdiri intrinsic and
> provide abstracted rte_ffs{32,64} inline functions instead of directly
> using GCC built-ins.
>
> v3:
> * Added __rte_experimental to the new functions.
> * Added commen
On 2025/1/29 4:01, Stephen Hemminger wrote:
> On Tue, 28 Jan 2025 22:47:22 +0800
> "Renyong Wan" wrote:
>
>> This xsc PMD (**librte_net_xsc**) provides poll mode driver for
>> Yunsilicon metaScale serials NICs.
>>
>> Features:
>> -
>> - MTU update
>> - TSO
>> - RSS hash
>> - RSS key update
On Tue, Jan 21, 2025 at 11:36 PM Andre Muezerie
wrote:
>
> v16:
> * Updated comment for RTE_CAST_PTR.
>
> v15:
> * Fixed a comment in rte_common.h to make Doxygen happy.
> * Fixed a typo (extra comma).
> * Added missing RTE_PTR_UNQUAL needed for ARM64.
>
> v14:
> * Renamed RTE_PTR_DROP_QUALIF
The next DPDK Summit will happen on May 8-9 in Prague, Czech Republic.
The website is open for registrations and all venue details.
Follow this link to submit a talk proposal:
https://events.linuxfoundation.org/dpdk-summit/program/cfp/
There is one month remaining in the Call For Papers (CFP) pe
v2:
- Incorporated feedback from the review of v1.
- Updated documentation for idpf pmd.
- Removed support of buffer reassembly for multi-segment packets
- Reworked the `meson.build` script, referencing the ice driver.
- Resolved word wrapping issues.
Shaiq Wani (3):
common/idpf: enable AVX2 for
updated the documentation to reflect that both AVX512 and AVX2
support are available.
Signed-off-by: Shaiq Wani
---
doc/guides/nics/idpf.rst | 7 +++
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/doc/guides/nics/idpf.rst b/doc/guides/nics/idpf.rst
index 0370989a07..3738d0d91a
In case some CPUs don't support AVX512. Enable AVX2 for them to
get better per-core performance.
The single queue model processes all packets in order while
the split queue model separates packet data and metadata into
different queues for parallel processing and improved performance
Signed-off-b
In case some CPUs don't support AVX512. Enable AVX2 for them to
get better per-core performance.
The single queue model processes all packets in order while
the split queue model separates packet data and metadata into
different queues for parallel processing and improved performance.
Signed-off-
On Wed, Jan 29, 2025 at 10:54:16AM +0200, Shani Peretz wrote:
> DPDK provides two formats for specifying PCI device numbers:
> a full version (":08:00.0") and a short version ("08:00.0").
> Issues can occur when an application uses one format (e.g., short)
> while running testpmd, then attempts
> -Original Message-
> From: Dooley, Brian
> Sent: Monday 13 January 2025 17:10
> Cc: dev@dpdk.org; gak...@marvell.com; Ji, Kai ; De Lara
> Guarch, Pablo ; Dooley, Brian
>
> Subject: [PATCH v3 2/2] app/test: add SM4 GCM tests
>
> Added SM4-GCM tests for the AESNI MB PMD.
>
> Signed-of
DPDK provides two formats for specifying PCI device numbers:
a full version (":08:00.0") and a short version ("08:00.0").
Issues can occur when an application uses one format (e.g., short)
while running testpmd, then attempts to use the other format
(e.g., full) in a later command, resulting in
37 matches
Mail list logo
