On Tue, Apr 5, 2022 at 8:48 AM Thomas Monjalon wrote:
>
> 04/04/2022 23:13, Nicolas Chautru:
> > This serie introduces the PMD for the new bbdev device ACC101
> > (aka Mount Cirrus). This is a derivative from previous Mount Bryce
> > which includes silicon improvement, bug fixes, capacity improvem
04/04/2022 23:13, Nicolas Chautru:
> This serie introduces the PMD for the new bbdev device ACC101
> (aka Mount Cirrus). This is a derivative from previous Mount Bryce
> which includes silicon improvement, bug fixes, capacity improvement
> for 5GNR and feature improvement.
Nack for adding this dri
From: Pavan Nikhilesh
Since mbox is now accessed from multiple threads, use lock to
synchronize access.
Signed-off-by: Pavan Nikhilesh
Signed-off-by: Shijith Thotton
---
drivers/common/cnxk/roc_sso.c | 174 +
drivers/common/cnxk/roc_sso_priv.h | 1 +
drivers
Added API to set queue attributes at runtime and API to get weight and
affinity.
Signed-off-by: Shijith Thotton
---
doc/guides/eventdevs/features/cnxk.ini | 1 +
drivers/event/cnxk/cn10k_eventdev.c| 4 ++
drivers/event/cnxk/cn9k_eventdev.c | 4 ++
drivers/event/cnxk/cnxk_eventdev.c
Added test cases to test changing of queue QoS attributes priority,
weight and affinity at runtime.
Signed-off-by: Shijith Thotton
---
app/test/test_eventdev.c | 149 +++
1 file changed, 149 insertions(+)
diff --git a/app/test/test_eventdev.c b/app/test/test_
Structure rte_event_queue_conf will be extended to include fields to
support weight and affinity attribute. Once it gets added in DPDK 22.11,
eventdev internal op, queue_attr_get can be removed.
Signed-off-by: Shijith Thotton
---
doc/guides/rel_notes/deprecation.rst | 3 +++
1 file changed, 3 in
Added a new eventdev API rte_event_queue_attr_set(), to set event queue
attributes at runtime from the values set during initialization using
rte_event_queue_setup(). PMD's supporting this feature should expose the
capability RTE_EVENT_DEV_CAP_RUNTIME_QUEUE_ATTR.
Signed-off-by: Shijith Thotton
--
Extended eventdev queue QoS attributes to support weight and affinity.
If queues are of same priority, events from the queue with highest
weight will be scheduled first. Affinity indicates the number of times,
the subsequent schedule calls from an event port will use the same event
queue. Schedule
This series adds support for setting event queue attributes at runtime
and adds two new event queue attributes weight and affinity. Eventdev
capability RTE_EVENT_DEV_CAP_RUNTIME_QUEUE_ATTR is added to expose the
capability to set attributes at runtime and rte_event_queue_attr_set()
API is used to s
>
>
> +__rte_experimental
> +static inline void
> +rte_seqlock_write_lock(rte_seqlock_t *seqlock) {
> + uint32_t sn;
> +
> + /* to synchronize with other writers */
> + rte_spinlock_lock(&seqlock->lock);
> +
> + sn = seqlock->sn + 1;
> >>> The load
Add configure function to configure the device from the PF
within bbdev-test without dependency on pf_bb_config.
Signed-off-by: Nicolas Chautru
---
app/test-bbdev/test_bbdev_perf.c | 69 +++
doc/guides/rel_notes/release_22_07.rst | 4 +
drivers/baseband/acc101/meson.build |
Add capabilities and functions to support the LTE
encoder and decode processing operations.
Signed-off-by: Nicolas Chautru
---
doc/guides/bbdevs/acc101.rst | 21 +
doc/guides/bbdevs/features/acc101.ini|4 +-
drivers/baseband/acc101/rte_acc101_pmd.c | 1012 +
Adding capabiliti and functions to support MSI
interrupts, handler and info ring.
Signed-off-by: Nicolas Chautru
---
drivers/baseband/acc101/rte_acc101_pmd.c | 309 ++-
drivers/baseband/acc101/rte_acc101_pmd.h | 15 ++
2 files changed, 321 insertions(+), 3 deletions(
Add capabilities and function to do actual
LDPC encode and decode processing operations.
Signed-off-by: Nicolas Chautru
---
doc/guides/bbdevs/acc101.rst | 22 +
doc/guides/bbdevs/features/acc101.ini|8 +-
drivers/baseband/acc101/rte_acc101_pmd.c | 1737 +
Add function to do HARQ loopback on top of
default 5G UL processing.
Signed-off-by: Nicolas Chautru
---
doc/guides/bbdevs/acc101.rst | 1 +
drivers/baseband/acc101/rte_acc101_pmd.c | 157 +++
2 files changed, 158 insertions(+)
diff --git a/doc/guides/bb
Adding functions to create and configure queues.
Signed-off-by: Nicolas Chautru
---
drivers/baseband/acc101/rte_acc101_pmd.c | 543 ++-
drivers/baseband/acc101/rte_acc101_pmd.h | 46 +++
2 files changed, 588 insertions(+), 1 deletion(-)
diff --git a/drivers/baseband
Add the info get function to allow to query
device null capabilities.
Linking to bbdev-test.
Signed-off-by: Nicolas Chautru
---
app/test-bbdev/meson.build | 3 +
drivers/baseband/acc101/rte_acc101_cfg.h | 96 +
drivers/baseband/acc101/rte_acc101_pmd.c | 226 +
Add list of registers for the device and related HW
specifications definitions.
Signed-off-by: Nicolas Chautru
---
drivers/baseband/acc101/acc101_pf_enum.h | 1128 ++
drivers/baseband/acc101/acc101_vf_enum.h | 79 +++
drivers/baseband/acc101/rte_acc101_pmd.h | 453
Skeleton code and documentation for the ACC101
bbdev PMD.
Signed-off-by: Nicolas Chautru
---
MAINTAINERS | 3 +
doc/guides/bbdevs/acc101.rst | 193 +++
doc/guides/bbdevs/features/acc101.ini| 13 +++
doc/guides/bbdevs/ind
This serie introduces the PMD for the new bbdev device ACC101
(aka Mount Cirrus). This is a derivative from previous Mount Bryce
which includes silicon improvement, bug fixes, capacity improvement
for 5GNR and feature improvement.
Nicolas Chautru (9):
baseband/acc101: introduce PMD for ACC101
04/04/2022 16:43, eagost...@nvidia.com:
> From: Elena Agostini
>
> A30X GPU code for DPU.
>
> Signed-off-by: Elena Agostini
Applied, thanks.
David Marchand writes:
> Build DPDK with Fedora 35 containers.
>
> GHA container support does not allow caching images and docker hub
> seems to limit image pulls.
> On the other hand, the Fedora project hub does not seem to limit them,
> so prefer this hub.
> Nevertheless, let's try to be good c
Hello,
Wanted to follow up with some additional testing results. I believe this
is a bug at the NVM firmware level but still want someone else to confirm.
We can easily retest or change parameters of testpmd to provide additional
information if desired. In parallel to this we will be trying to r
Hi Ke,
> -Original Message-
> From: Zhang, Ke1X
> Sent: Friday, March 25, 2022 4:36 PM
> To: Li, Xiaoyun ; Singh, Aman Deep
> ; Zhang, Yuying ;
> dev@dpdk.org
> Cc: Zhang, Ke1X
> Subject: [PATCH v3] app/testpmd: fix issue with memory leaks when quit
> testpmd
>
> A multicast address poo
From: Elena Agostini
A30X GPU code for DPU.
Signed-off-by: Elena Agostini
---
drivers/gpu/cuda/cuda.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/gpu/cuda/cuda.c b/drivers/gpu/cuda/cuda.c
index 8505d39d64..92097e067e 100644
--- a/drivers/gpu/cuda/cuda.c
+++ b/drivers/gpu/c
The function ice_xmit_pkts_vec_avx2_offload was left out in the list
of tx functions for ice_tx_burst_mode_get.
Fixes: 52ccdcf2fd41 ("net/ice: add AVX2 offload Tx")
Cc: wenzhuo...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Michael Pfeiffer
Suggested-by: Michael Rossberg
---
drivers/net/ice/i
Build DPDK with Fedora 35 containers.
GHA container support does not allow caching images and docker hub
seems to limit image pulls.
On the other hand, the Fedora project hub does not seem to limit them,
so prefer this hub.
Nevertheless, let's try to be good citizens and cache (once a day) a
prepa
This commit unifies macros for asymmetric parameters,
therefore making code easier to maintain.
It additionally changes some of PMD output logs that
right now can only be seen in debug mode.
Signed-off-by: Arek Kusztal
---
drivers/crypto/qat/qat_asym.c | 230 ++---
This commit adds secp384r1 (P-384) elliptic
curve to Intel QuickAssist Technology crypto PMD.
Signed-off-by: Arek Kusztal
---
drivers/common/qat/qat_adf/qat_pke.h | 12 ++
drivers/crypto/qat/qat_ec.h | 76
2 files changed, 88 insertions(+)
diff
In packets with ESP header, The Inner IP will be encrypted, and
its fields cannot be used for RSS hashing. So, ESP packets
can be hashed only by the outer IP layer.
So, when using RSS on ESP packets, hashing may not be efficient,
because the fields used by the hash functions are only the Outer IPs,
when secondary process is initialized(rte_eal_init),
external memroy segments should not be attached.
These segments will be attached by explicitly invoking
rte_malloc_heap_memory_attach API
Fixes: ff3619d6244b ("malloc: allow attaching to external memory chunks")
Cc: sta...@dpdk.org
Signed-off-b
Hi all,
Here is a new stable release:
https://fast.dpdk.org/rel/dpdk-20.11.5.tar.xz
The git tree is at:
https://dpdk.org/browse/dpdk-stable/?h=20.11
Luca Boccassi
---
MAINTAINERS| 2 +
VERSION
>> Added a new eventdev API rte_event_queue_attr_set(), to set event queue
>> attributes at runtime from the values set during initialization using
>> rte_event_queue_setup(). PMD's supporting this feature should expose the
>> capability RTE_EVENT_DEV_CAP_RUNTIME_QUEUE_ATTR.
>>
>> Signed-off-by: Sh
+ @Jayatheerthan, Jay & @Vangati, Narender
> -Original Message-
> From: Akhil Goyal
> Sent: Monday, April 4, 2022 3:19 PM
> To: Gujjar, Abhinandan S ; Volodymyr Fialko
> ; dev@dpdk.org
> Cc: Jerin Jacob Kollanukkaran ; Anoob Joseph
>
> Subject: RE: [PATCH 1/2] security: introduce per ses
On 04/04/2022 07:15, Morten Brørup wrote:
From: Ben Magistro [mailto:konce...@gmail.com]
Sent: Monday, 4 April 2022 02.57
Enable printing of the outer vlan if flags indicate it is present.
Signed-off-by: Ben Magistro
---
While troubleshooting some QinQ offloads with various Intel i40e
firmwa
https://bugs.dpdk.org/show_bug.cgi?id=984
Luca Boccassi (luca.bocca...@gmail.com) changed:
What|Removed |Added
Status|IN_PROGRESS |RESOLVED
Resolut
https://bugs.dpdk.org/show_bug.cgi?id=986
Luca Boccassi (luca.bocca...@gmail.com) changed:
What|Removed |Added
Resolution|--- |FIXED
Status
https://bugs.dpdk.org/show_bug.cgi?id=982
Luca Boccassi (luca.bocca...@gmail.com) changed:
What|Removed |Added
Resolution|--- |FIXED
Status
Currently, building DPDK with clang + LTO is unsupported, which is a
showstopper for cross-language interprocedural optimizations. The root
cause is that pmdinfogen expects to scan through the section headers of
generated ELF object files, but clang's "-flto" flag generates LLVM
bitcode instead. Th
Currently, building DPDK with clang + LTO is unsupported, which is a
showstopper for cross-language interprocedural optimizations. The root
cause is that pmdinfogen expects to scan through the section headers of
generated ELF object files, but clang's "-flto" flag generates LLVM
bitcode instead. Th
From: mingxial
Add macro MIN_TOTAL_NUM_MBUFS (1024) to indicate
what the value of total-num-mbufs should bigger than.
Fixes: c87988187fdb ("app/testpmd: add --total-num-mbufs option")
Cc: sta...@dpdk.org
Signed-off-by: mingxial
---
app/test-pmd/parameters.c | 5 +++--
app/test-pmd/testpmd.h
On Sat, Apr 02, 2022 at 01:59:01AM +0300, Dmitry Kozlyuk wrote:
> Vipin from AMD expressed demand for telemetry support on Windows
> in order to collect port statistics.
> Implementing a PoC, he stumbled several issues.
> Together we have designed a solution that eliminates these issues.
> It affec
> -Original Message-
> From: Kevin Laatz
> Sent: Friday, April 1, 2022 4:05 PM
> To: dev@dpdk.org
> Cc: Richardson, Bruce ; Laatz, Kevin
>
> Subject: [PATCH v3] dma/idxd: add generic option for queue config
>
> The device config script currently uses some defaults to configure devices
Hi Abhinandan,
> --
> Acked-by: Abhinandan Gujjar
>
This change would be an ABI breakage. So to avoid that, we are planning to
Propose a better solution compared to this patch.
We plan to add a new cryptodev op to set the event m
> -Original Message-
> From: Shijith Thotton
> Sent: Monday, April 4, 2022 10:36 AM
> To: Van Haaren, Harry ; dev@dpdk.org; Jerin Jacob
> Kollanukkaran
> Cc: Pavan Nikhilesh Bhagavatula ; Ray Kinsella
>
> Subject: RE: [PATCH 1/6] eventdev: support to set queue attributes at runtime
>
>
>
>
>> +/**
>> + * Set an event queue attribute at runtime.
>> + *
>> + * @param dev
>> + * Event device pointer
>> + * @param queue_id
>> + * Event queue index
>> + * @param attr_id
>> + * Event queue attribute id
>> + * @param attr_value
>> + * Event queue attribute value
>> + *
>> + * @r
>> Extended eventdev queue QoS attributes to support weight and affinity.
>> If queues are of same priority, events from the queue with highest
>> weight will be scheduled first. Affinity indicates the number of times,
>> the subsequent schedule calls from an event port will use the same event
>> q
Acked-by: Abhinandan Gujjar
> -Original Message-
> From: Volodymyr Fialko
> Sent: Friday, March 25, 2022 4:46 PM
> To: dev@dpdk.org; Gujjar, Abhinandan S ; Akhil
> Goyal
> Cc: jer...@marvell.com; Volodymyr Fialko ; Anoob
> Joseph
> Subject: [PATCH 1/2] security: introduce per session e
>
>
>> +int
>> +cnxk_sso_queue_attribute_get(struct rte_eventdev *event_dev, uint8_t
>> queue_id,
>> + uint32_t attr_id, uint32_t *attr_value)
>> +{
>> +struct cnxk_sso_evdev *dev = cnxk_sso_pmd_priv(event_dev);
>> +
>> +*attr_value = attr_id == RTE_EVENT_QUEUE_ATTR_
>> >
>> > This series adds support for setting event queue attributes at runtime
>> > and adds two new event queue attributes weight and affinity. Eventdev
>> > capability RTE_EVENT_DEV_CAP_RUNTIME_QUEUE_ATTR is added to expose
>> the
>> > capability to set attributes at runtime and rte_event_queue
On Mon, Apr 4, 2022 at 8:52 AM Ali Alnubani wrote:
> > -Original Message-
> > From: christian.ehrha...@canonical.com
> >
> > Sent: Monday, March 21, 2022 1:55 PM
> > To: sta...@dpdk.org
> > Cc: dev@dpdk.org; Abhishek Marathe ;
> > Ali Alnubani ; benjamin.wal...@intel.com; David
> > Chris
Hi Christian,
[..]
> Of the parties usually verifying the 19.11.x release I'm still missing to
> hear anything from Redhat and Nvidia.
> I'd be happy if you could let me know if your results will be:
> a) in time for Wednesday
> b) delayed a bit
> c) or if I should not wait for them
[..]
J
52 matches
Mail list logo
