On Fri, Feb 28, 2025 at 02:33:04PM +, Bruce Richardson wrote:
> On Thu, Feb 27, 2025 at 05:52:17PM -0800, Andre Muezerie wrote:
> > This patchset allows users to specify the CPU for which the generated
> > code should be optimized for by passing the CPU name.
> >
> > MSVC does not provide this
Hi,
Are there known issues with rcu lib?
I tried to remove the VLA from it by calling alloca() and gcc 14.2 on Linux
immediately complains about "array subscript outside array bounds".
$ ninja -C build
ninja: Entering directory `build'
[1/144] Compiling C object lib/librte_rcu.a.p/rcu_rte_rcu_qs
On Fri, Feb 28, 2025 at 02:30:54PM +, Bruce Richardson wrote:
> On Thu, Feb 27, 2025 at 05:52:16PM -0800, Andre Muezerie wrote:
> > Up to now MSVC has being used with the default mode, which uses SSE2
> > instructions for scalar floating-point and vector calculations.
> > https://learn.microsof
In preparation to add better MSVC support, existing common code was
moved up.
A split was added which in future will call an MSVC specific meson.build
file:
if is_ms_compiler
subdir_done()
endif
v2:
- removed call to get_option('cpu_instruction_set') from
config/x86/meson.build as that cal
In preparation to add better MSVC support, existing common code was
moved up.
A split was added which in future will call an MSVC specific meson.build
file:
if is_ms_compiler
subdir_done()
endif
Signed-off-by: Andre Muezerie
Acked-by: Bruce Richardson
---
config/x86/meson.build | 90 +
Up to now MSVC has being used with the default mode, which uses SSE2
instructions for scalar floating-point and vector calculations.
https://learn.microsoft.com/en-us/cpp/build/reference/arch-x64?view=msvc-170
This patchset allows users to specify the CPU for which the generated
code should be opt
This patchset allows users to specify the CPU for which the generated
code should be optimized for by passing the CPU name.
MSVC does not provide this functionality natively, so logic was
added. This additional logic relies on a table which stores instruction
set availability (like AXV512F) for di
File config/meson.build has logic to move cpu_instruction_set from 'auto'
to 'native' or 'generic'.
When calling get_option('cpu_instruction_set') again from
config/x86/meson.build we get 'auto' again, instead of expected 'native'.
The fix is to not call get_option('cpu_instruction_set') again, j
Updated meson.build to use common variable cc_avx512_flags for
msvc and avoiding code duplication for other compilers.
Signed-off-by: Andre Muezerie
---
lib/member/meson.build | 11 ---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/lib/member/meson.build b/lib/member/meso
Updated meson.build to use common variable cc_avx512_flags.
Signed-off-by: Andre Muezerie
---
config/x86/meson.build | 2 +-
lib/acl/meson.build| 8 ++--
2 files changed, 3 insertions(+), 7 deletions(-)
diff --git a/config/x86/meson.build b/config/x86/meson.build
index 47a5b0c04a..12bef
Hi Maxime,
I believe that for 25.03 we can just apply the first 2 commits of the serie.
For the last commit, it will take more time to try your suggestion out, we can
do this in subsequent release.
Does that sound okay with you?
Thanks
Nic
> -Original Message-
> From: Maxime Coquelin
Minor changes to clean up the documentation for bbdev programming guide
and updating vectors to avoid false alarms when using different
windowing configuration assumption by users.
Nicolas Chautru (2):
doc: update bbdev documentation
test/bbdev: update to fft test vectors
app/test-bbdev/test
Some FFT operations vectors could create false alarms depending
on implementation and dependency SW versions.
Updated one vector and removing one previous vector.
Signed-off-by: Nicolas Chautru
---
app/test-bbdev/test_vectors/fft_9.data | 870
app/test-bbdev/test_vector
Correcting the scope of supported bbdev operations.
Signed-off-by: Nicolas Chautru
---
doc/guides/prog_guide/bbdev.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/doc/guides/prog_guide/bbdev.rst b/doc/guides/prog_guide/bbdev.rst
index e3f356450b..f0fbb0c1c0 100644
--- a/d
Bulk requests to get or put objects in a mempool often vary in size.
A series of tests with pseudo random request sizes, to mitigate the
benefits of the CPU's dynamic branch predictor, was added.
Also, various other minor changes:
- Improved the output formatting for readability.
- Added test for
In preparation to add better MSVC support, existing common code was
moved up.
A split was added which in future will call an MSVC specific meson.build
file:
if is_ms_compiler
subdir_done()
endif
Signed-off-by: Andre Muezerie
Acked-by: Bruce Richardson
---
config/x86/meson.build | 91 +
Sorry for the delay in getting back to this and appreciate the assistance.
I do not have this in simple setup right now to reproduce but imagine
cloning libarchive into say /tmp and setting the appropriate prefixes would
get you to a minimum needed to reproduce. I've substituted out the
company an
Hi Gowri,
On 2/28/25 2:59 PM, Gowrishankar Muthukrishnan wrote:
Hi Maxime,
Before your series arrived, we were wondering if we should not deprecate Vhost
crypto as it was not really maintained and we had no identified user.
Since it seems you are going to use it, which is great, would you co
On Thu, Feb 27, 2025 at 05:52:17PM -0800, Andre Muezerie wrote:
> This patchset allows users to specify the CPU for which the generated
> code should be optimized for by passing the CPU name.
>
> MSVC does not provide this functionality natively, so logic was
> added. This additional logic relies
Hi David,
> >
> > It is due to local vc_req that is passed to func that requires iotlb
> > lock In vc_req->vq. Even though vc_req->vq is locked vq, GCC does not allow
> > it,
> as I understand.
>
> *cough* clang.
>
> >
> > vc_req = &data_req;
> > vc_req->desc_idx = desc_idx;
> >
On Thu, Feb 27, 2025 at 05:52:16PM -0800, Andre Muezerie wrote:
> Up to now MSVC has being used with the default mode, which uses SSE2
> instructions for scalar floating-point and vector calculations.
> https://learn.microsoft.com/en-us/cpp/build/reference/arch-x64?view=msvc-170
>
> This patch all
On Tue, Feb 25, 2025 at 06:16:36PM +, Medvedkin, Vladimir wrote:
> Acked-by: Vladimir Medvedkin
>
> On 21/02/2025 08:25, Mingjin Ye wrote:
> > The pf has enabled the ACL filter, so uninit is no longer limited
> > to the DCF.
> >
> > Fixes: a9d612291c2d ("net/ice: support IPv4 fragments in AC
Hi Maxime,
>
> Before your series arrived, we were wondering if we should not deprecate Vhost
> crypto as it was not really maintained and we had no identified user.
>
> Since it seems you are going to use it, which is great, would you commit to
> make
> the necessary changes to make it reliabl
Support asymmetric RSA crypto operations in vhost-user.
Signed-off-by: Gowrishankar Muthukrishnan
Acked-by: Akhil Goyal
---
doc/guides/rel_notes/release_25_03.rst | 3 +
lib/vhost/vhost_crypto.c | 484 +++--
lib/vhost/virtio_crypto.h | 67
Support asymmetric crypto operations.
Signed-off-by: Gowrishankar Muthukrishnan
Acked-by: Akhil Goyal
---
doc/guides/sample_app_ug/vhost_crypto.rst | 5 +++
examples/vhost_crypto/main.c | 50 +--
2 files changed, 43 insertions(+), 12 deletions(-)
diff --git a/
In order to handle new vhost user connection, use new_connection
and destroy_connection callbacks.
Fixes: f5188211c721 ("examples/vhost_crypto: add sample application")
Cc: sta...@dpdk.org
Signed-off-by: Gowrishankar Muthukrishnan
Acked-by: Akhil Goyal
---
examples/vhost_crypto/main.c | 4 ++--
Until virtio avail ring is initialized (by VHOST_USER_SET_VRING_ADDR),
worker thread should not try to fetch crypto op, which would lead to
memory fault.
Fixes: 939066d96563 ("vhost/crypto: add public function implementation")
Cc: sta...@dpdk.org
Signed-off-by: Gowrishankar Muthukrishnan
Acked-b
As per requirements on vhost_user spec, session id should be
located at the end of session parameter.
Update VhostUserCryptoSessionParam structure to support newer QEMU
versions (v9). Due to additional parameters added in QEMU,
received payload from QEMU would be larger than existing payload.
Henc
For thread safety check to succeed (as in clang), calling function
should ensure vq->iotlb_lock locked before passing vq to a function
that has thread safety attribute, in vhost crypto implementation.
When vhost_crypto_data_req is local and its vq is pointer to a
locked vq, clang does not recognis
This patch series supports asymmetric RSA in vhost crypto library.
It also includes changes to improve vhost crypto library:
* support newer QEMU versions.
* fix broken vhost_crypto example application.
* stabilize crypto fastpath operations.
v9:
- new patch 1/6
Gowrishankar Muthukrishnan (6)
On 2025/2/26 21:45, Stephen Hemminger wrote:
Caution: This is an external email. Please be very careful when clicking links
or opening attachments. See http://nok.it/nsb for additional information.
On Wed, 22 Jan 2025 16:15:03 +0800
Yang Ming wrote:
On 2025/1/18 00:47, Stephen Hemminger wr
https://bugs.dpdk.org/show_bug.cgi?id=1666
Bug ID: 1666
Summary: It is not possible to increase the MTU for AF_PACKET
PMD beyond 1500B
Product: DPDK
Version: 21.11
Hardware: All
OS: All
Status: U
Hi Nicolas,
On 2/7/25 10:52 AM, Maxime Coquelin wrote:
Hi Nicolas,
On 1/24/25 7:00 PM, Stephen Hemminger wrote:
On Fri, 24 Jan 2025 17:52:43 +
"Chautru, Nicolas" wrote:
Hi Stephen,
The commit message may be misleading, the logging interface doesn't
change here. Note also that I reuse
This change ensures that the current process is checked for
being run with 'setarch' before verifying the value of
'/proc/sys/kernel/randomize_va_space'. The '-R' or
'--addr-no-randomize' parameter of the 'setarch' command is used
to disable the randomization of the virtual address space.
Fixes: a
Hi Gowri,
On 2/28/25 9:48 AM, David Marchand wrote:
On Thu, Feb 27, 2025 at 7:07 PM Gowrishankar Muthukrishnan
wrote:
Ha, and also you should be able to remove:
__rte_no_thread_safety_analysis /* FIXME: requires iotlb_lock? */ in
vhost_crypto_process_one_req() once implemented.
Removing it
Hi.
At the point of a DPDK app crash, or some other abnormal event, you may
want to save the trace buffer, especially if a complete core file is too
large to fit on the disk.
This would be straight-forward to implement on top of DPDK trace.
However, you may also want to save data which is re
On Thu, Feb 27, 2025 at 7:07 PM Gowrishankar Muthukrishnan
wrote:
> > > Ha, and also you should be able to remove:
> > > __rte_no_thread_safety_analysis /* FIXME: requires iotlb_lock? */ in
> > > vhost_crypto_process_one_req() once implemented.
> > >
> >
> Removing it would break compilation for t
37 matches
Mail list logo
