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
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
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
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.
v2:
- explicitly check against NULL
E830 adapters currently support Tx Time based queues.
Signed-off-by: Soumyadeep Hore
---
doc/guides/nics/ice.rst | 27 +++
1 file changed, 27 insertions(+)
diff --git a/doc/guides/nics/ice.rst b/doc/guides/nics/ice.rst
index 77985ae5a2..fe3e87c704 100644
--- a/doc/guides
From: Paul Greenwalt
Updated the Tx Time Queue Context Structure to align with HAS.
Signed-off-by: Soumyadeep Hore
Signed-off-by: Paul Greenwalt
---
drivers/net/intel/ice/base/ice_common.c | 22 +++---
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/net
Add support for Tx Time based queues. This is used to schedule
packets based on Tx timestamp.
Signed-off-by: Soumyadeep Hore
---
drivers/net/intel/common/tx.h | 1 +
drivers/net/intel/ice/base/ice_lan_tx_rx.h | 4 +
drivers/net/intel/ice/ice_ethdev.c | 3 +-
drivers/ne
Added TxPP support for E830 adapters.
---
v2:
- Fixed Compilation warnings
---
v3:
- Fixed further Compilation warnings (uinitialised one)
---
v4:
- Addressed Bruce's comments
---
v5:
- Addressed Bruce's and Ciara's comments
---
v6:
- Addressed Bruce's comments
- Fixed compilation warnings
---
v7:
Add support for sessionless asymmetric operations for cn20k.
Signed-off-by: Nithinsen Kaithakadan
---
doc/guides/cryptodevs/features/cn20k.ini | 1 +
drivers/crypto/cnxk/cn20k_cryptodev_ops.c | 566 +-
2 files changed, 564 insertions(+), 3 deletions(-)
diff --git a/doc/gu
https://bugs.dpdk.org/show_bug.cgi?id=1728
Bug ID: 1728
Summary: Segmentation fault in dpdk-test-compress-perf with
compress_zlib vdev on Ubuntu 24.04 with GCC 14.2 and
kernel 6.8.0
Product: DPDK
Version: 24.11
Hi Maintainer,
yesterday,I saw that you marked the v2 series patch status as' Changes
Requested ',
so I would like to submit a new version as per your request.
> * dpdk: [v2,1/5] net/zxdh: fix meson.build issus in compilation
> -
> http://patches.dpdk.org/project/dpdk/patch/20250617
On Tue, Jun 17, 2025 at 11:18 AM Luca Vizzarro
wrote:
> Looks good to me. just a small nit:
>
> On 16/06/2025 19:38, Dean Marx wrote:
> > +test_run.ctx.topology.setup()
> > +self.test_run.ctx.topology.configure_ports("sut", "dpdk")
>
> no need to do `self.` here. Outside of this:
On Tue, 17 Jun 2025 18:42:52 +0300
Maayan Kashani wrote:
> when using --no-numa option,
> gro should be initiated with SOCKET_ID_ANY
> to allow using cross NUMA.
>
> API changes notice:
> Changed socket_id field in struct rte_gro_param from uint16 to
> int32 to support negative value -1 (== SOCK
https://bugs.dpdk.org/show_bug.cgi?id=1727
Bug ID: 1727
Summary: arparse LTO warnings
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
Priority: Norma
https://bugs.dpdk.org/show_bug.cgi?id=1726
Bug ID: 1726
Summary: possible overrun bugs in soring found with LTO
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
> compress/zlib: support PDCP checksum
>
> compress/zlib: support zlib dictionary
>
> compressdev: add PDCP checksum
>
> compressdev: support zlib dictionary
>
> Adds support to provide predefined dictionaries to zlib. Handles setting
> and getting of dictionaries using zlib apis. Also includes
Recheck-request: iol-compile-amd64-testing
Recheck-request: iol-compile-amd64-testing
Recheck-request: iol-compile-amd64-testing
> Remove all unsupported test cases in json files
>
> Signed-off-by: Kai Ji
Applied to dpdk-next-crypto
> Due to changes in the specification related to IV size and initialization
> sequence remove ZUC 256 support from Gen 3 and 5 hardware
>
> Signed-off-by: Radu Nicolau
> Acked-by: Kai Ji
> ---
Applied to dpdk-next-crypto
Thanks.
> Acked-by: Kai Ji
>
> From: Radu Nicolau
> Sent: 12 June 2025 11:14
> To: Ji, Kai ; Kusztal, ArkadiuszX
>
> Cc: dev@dpdk.org ; Nicolau, Radu ;
> sta...@dpdk.org
> Subject: [PATCH] crypto/qat: fix out-of-place chain/cipher/auth headers
>
> Extend the original fix to gen3 and gen4 code.
>
>
> -Original Message-
> From: Tejasree Kondoj
> Sent: Monday, June 9, 2025 4:11 PM
> To: Akhil Goyal
> Cc: Anoob Joseph ; Nithinsen Kaithakadan
> ; Rupesh Chiluka ; Vidya
> Sagar Velumuri ; dev@dpdk.org
> Subject: [PATCH v2 0/7] fixes and new features to cnxk crypto PMD
>
> This series
> -Original Message-
> From: Gowrishankar Muthukrishnan
> Sent: Wednesday, May 28, 2025 8:30 PM
> To: dev@dpdk.org; Akhil Goyal ; Fan Zhang
>
> Cc: Anoob Joseph ; Gowrishankar Muthukrishnan
>
> Subject: [PATCH] test/crypto: test vectors for additional ECDH groups
>
> Add test vectors
> zsda compress code cleanup.
>
> Signed-off-by: Hanxiao Li
Patch applied to dpdk-next-crypto
Thanks.
> Realize async mode to replace sync mode for better performance
>
> v2:
> Add version check, requires uadk >= 2.9
This version DO NOT exist as of now.
> Add version table describing DPDK and external UADK library
> version compatibility
> Mention version dependence in release notes
>
>
Add virtual functions to DTS framework, along with
a field for specifying VF test runs in the config file.
Signed-off-by: Patrick Robb
Signed-off-by: Dean Marx
---
dts/framework/config/test_run.py | 2 +
dts/framework/test_run.py| 7 +++
dts/framework/testbed_m
From: Tirthendu Sarkar
dlb2_eventdev_info_get() that implements rte_event_dev_info_get() should
return the maximum available credits as supported by HW.
Set maximum credits before device probing by checking HW version.
Fixes: b66a418d2ad3 ("event/dlb2: add v2.5 probe")
Cc: sta...@dpdk.org
Sign
While unlinking ports, all associated credits should be released.
This commit avoids race condition when main thread is unlinking
while workers are running.
Fixes: a29248b57b31 ("event/dlb2: add port unlink and unlinks in progress")
Cc: sta...@dpdk.org
Signed-off-by: Pravin Pathak
---
drivers/e
update QID depth xstats counter in vector dequeue path
Fixes: 000a7b8e7582 ("event/dlb2: optimize dequeue operation")
Cc: sta...@dpdk.org
Signed-off-by: Pravin Pathak
---
drivers/event/dlb2/dlb2.c | 8
1 file changed, 8 insertions(+)
diff --git a/drivers/event/dlb2/dlb2.c b/drivers/ev
Add support for setting application specified port history
Set HL equal to CQ depth when inflight control is enabled
Added command line parameters 'use_default_hl' (default: 1)
and 'alloc_hl_entries'
- When 'use_default_hl = 1'
* Per port HL is set to DLB2_FIXED_CQ_HL_SIZE (32)
* Recommen
DLB 2.0 device has 64 single linked or directed ports.
DLB 2.5 device has 96 single linked ports.
This commit fixes issue of rte_event_dev_info_get returning 64
instead of 96 single link ports for DLB2.5
Fixes: 4ce7bf9ec1c7 ("event/dlb2: add v2.5 get resources")
Cc: sta...@dpdk.org
Signed-off-by:
While providing port_cos as vdev/pf CLI argument, the port numbers should
take into account all ports (LDB and DIR) that are created by the
application and the same order should be provided for port_cos parameter.
This fix add checks to ensure that above is validated correctly.
Fixes: bec8901bfe9f
When application configures a DIR port with CQ depth less than 8, DLB PMD
sets port's cq_depth as 8 and token reservation is used to make the
effective cq_depth smaller. However, while setting port's cq_depth_mask
application configured CQ depth was used resulting in reading incorrect
cachelines wh
This patchset introduces various fixes related to dlb2 hw resource
management. The dlb2 hw has limited resources, which are configurable
using command line options. This patch allows managing History list,
scheduling bandwidth and credits using command line options. It also
fixes some issues with r
> -Original Message-
> From: Jerin Jacob
> Sent: Tuesday 17 June 2025 16:50
>
> > > > -struct __rte_cache_aligned rte_graph_cluster_node_stats {
> > > > +struct rte_graph_cluster_node_stats {
> > >
> > > This is a fastpath structure. No need to change the alignment here.
> >
> > rte_graph
Cross NUMA support means that
if the current NUMA is out of memory,
use another available NUMA memory.
Replace socket id specific initializations
with SOCKET_ID_ANY needed for testpmd
init when --no-numa flag is set.
Signed-off-by: Maayan Kashani
---
app/test-pmd/testpmd.c | 8
l
On Tue, Jun 17, 2025 at 9:11 PM Marat Khalili wrote:
>
> > -Original Message-
> > From: Jerin Jacob
> > Sent: Tuesday 17 June 2025 16:28
> >
> > > -struct __rte_cache_aligned rte_graph_cluster_node_stats {
> > > +struct rte_graph_cluster_node_stats {
> >
> > This is a fastpath structure.
If gro context allocation with specified socket failed,
Testpmd init function would return an error.
With current change,
if --no-numa option is used,
testpmd init will use SOCKET_ID_ANY for gro init.
Signed-off-by: Maayan Kashani
---
app/test-pmd/testpmd.c | 11 ++-
1 file changed, 6 i
when using --no-numa option,
gro should be initiated with SOCKET_ID_ANY
to allow using cross NUMA.
API changes notice:
Changed socket_id field in struct rte_gro_param from uint16 to
int32 to support negative value -1 (== SOCKET_ID_ANY).
Changed gro_tbl_create typedef to receive negative socket inp
when using --no-numa option,
gro should be initiated with SOCKET_ID_ANY
to allow using cross NUMA.
Changed socket_id field in struct rte_gro_param from uint16 to
int32 to support negative value -1 (== SOCKET_ID_ANY).
Signed-off-by: Maayan Kashani
---
lib/gro/gro_tcp4.c | 2 +-
lib/gro/gro
> -Original Message-
> From: Jerin Jacob
> Sent: Tuesday 17 June 2025 16:28
>
> > -struct __rte_cache_aligned rte_graph_cluster_node_stats {
> > +struct rte_graph_cluster_node_stats {
>
> This is a fastpath structure. No need to change the alignment here.
rte_graph_cluster_stats include
On Tue, Jun 17, 2025 at 8:44 PM Marat Khalili wrote:
>
> This was flagged by undefined behaviour sanitizer: struct
> rte_graph_cluster_stats is declared as `__rte_cache_aligned` but was
> allocated using stdlib realloc which caused misaligned allocation. More
> than one test needs to be executed i
On Tue, 17 Jun 2025 10:04:59 +0800
Junlong Wang wrote:
> fix meson.build issus in compilation, which
> caused the inability to compile in the arm64 environment.
>
> Fixes: 29e89288ff14 ("net/zxdh: add driver skeleton")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Junlong Wang
> ---
This series lo
Looks good to me. just a small nit:
On 16/06/2025 19:38, Dean Marx wrote:
+test_run.ctx.topology.setup()
+self.test_run.ctx.topology.configure_ports("sut", "dpdk")
no need to do `self.` here. Outside of this:
Reviewed-by: Luca Vizzarro
This was flagged by undefined behaviour sanitizer: struct
rte_graph_cluster_stats is declared as `__rte_cache_aligned` but was
allocated using stdlib realloc which caused misaligned allocation. More
than one test needs to be executed in series in order to reproduce the
problem using graph_autotest,
This was flagged by undefined behaviour sanitizer: memset should not be
called with NULL first argument. (memset requires first argument to be
pointer to a memory object, so passing NULL may result in an undefined
behaviour including among other things optimizer potentially removing
code paths depe
The receive callback was not safe with multiple queues.
If one receive queue callback decides to take a sample it
needs to add that sample and do atomic update to the previous
TSC sample value. Add a new lock for that.
Optimize the check for when to take sample so that
it only needs to lock when l
If transmit callback is called, and there are no packets
in the burst with timestamp set, then the expensive operations
of locking and accessing TSC can be skipped.
Signed-off-by: Stephen Hemminger
---
lib/latencystats/rte_latencystats.c | 9 -
1 file changed, 8 insertions(+), 1 deletion
After investigating latencystat test failures, discovered it poorly
designed to handle bursts and multiple queues.
v3 - reduce patch changes, break a line that was too long
Stephen Hemminger (2):
latencystats: fix receive sample MP issues
latencystats: optimize locking on transmit
lib/laten
On Tue, Jun 17, 2025 at 7:07 PM Stephen Hemminger
wrote:
>
> On Tue, 17 Jun 2025 11:52:08 +0100
> Marat Khalili wrote:
>
> > This was flagged by undefined behaviour sanitizer: struct
> > rte_graph_cluster_stats is declared as `__rte_cache_aligned` but was
> > allocated using stdlib realloc which
On Tue, 17 Jun 2025 17:32:25 +0800
Bingbin Chen wrote:
> + uint32_t msg_result = 0;
> + uint32_t acl_index = 0;
> + ZXDH_AGENT_CHANNEL_ACL_MSG_T msgcfg = {
> + .dev_id = 0,
> + .type = ZXDH_ACL_MSG,
> + .oper = ZXDH_ACL_INDEX_REQUEST,
> +
On Tue, 17 Jun 2025 17:32:25 +0800
Bingbin Chen wrote:
> +static uint32_t
> +zxdh_np_agent_channel_acl_index_request(uint32_t dev_id,
> +
> uint32_t sdt_no,
> +
Release status meeting minutes 2025-06-17
=
Agenda:
* Release Dates
* Subtrees
* Roadmaps
* LTS
* Defects
* Opens
Participants:
* ARM
* Debian
* Intel
* Marvell
* Nvidia
* Red Hat
Release Dates
-
The following are the proposed working dates f
On Wed, 21 May 2025 12:37:27 -0700
Stephen Hemminger wrote:
> This was found as error when compiling with LTO.
> The function allocates new data with rte_zmalloc and then
> stores pointer in the pointer-to-pointer passed as argument.
> In the unwind case, it would call rte_free() with wrong one.
On Mon, 16 Jun 2025 20:23:37 -0700
"dimon.zhao" wrote:
> Features:
> -
> - MTU update
> - promisc mode set
> - xstats
> - Basic stats
>
> Support NICs:
> -
> - S1205CQ-A00CHT
> - S1105AS-A00CHT
> - S1055AS-A00CHT
> - S1052AS-A00CHT
> - S1051AS-A00CHT
> - S1045XS-A00CHT
> - S
MLX5 HWS flow engine does not support the SAMPLE flow action.
The patch adds the SAMPLE action support to the non-template API.
Signed-off-by: Gregory Etelson
---
drivers/net/mlx5/mlx5.c| 1 +
drivers/net/mlx5/mlx5_flow.h | 26 +-
drivers/net/mlx5/mlx5_flow_hw.c| 40 ++
The patch initiates non-template sample action environment and
adds function to create hws mirror object.
Signed-off-by: Gregory Etelson
---
drivers/net/mlx5/meson.build | 1 +
drivers/net/mlx5/mlx5.h| 7 +
drivers/net/mlx5/mlx5_flow.h | 7 +
drivers/net/mlx5/mlx5_f
Add private PMD flow action MLX5_RTE_FLOW_ACTION_TYPE_MIRROR.
The new action type provides direct access to the HWS mirror action.
Signed-off-by: Gregory Etelson
---
drivers/net/mlx5/mlx5_flow.h | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow.h b/drivers/net/
The new mlx5_hw_create_mirror() function separates existing HWS mirror
functionality into mirror action creation and indirect list
handle creation.
The new mirror creation function will be used in non-template SAMPLE
action implementation.
Signed-off-by: Gregory Etelson
---
drivers/net/mlx5/mlx
From: Bing Zhao
The HWS mirror action is created with STCs based on the flags. In the
past, there was a single type of FDB domain. After introducing the
unified FDB feature, there are 4 types of tables in FDB domain,
including FDB, FDB_RX, FDB_TX and FDB_UNIFIED. More STCs will be
allocated when
On Tue, 17 Jun 2025 14:36:04 +0800
Bingbin Chen wrote:
> Provide support for ETH, VLAN, IPv4/IPv6, TCP/UDP, VXLAN, and mask matching,
> supporting multiple actions include drop/count/mark/queue/rss,and vxlan
> decap/encap.
>
> Signed-off-by: Bingbin Chen
> ---
> drivers/net/zxdh/meson.build
Add crypto adapter support for CN20K crypto PMD.
Signed-off-by: Nithinsen Kaithakadan
---
.../crypto/cnxk/cn20k_cryptodev_event_dp.h| 14 +
drivers/crypto/cnxk/cn20k_cryptodev_ops.c | 588 +-
drivers/crypto/cnxk/cn20k_cryptodev_ops.h | 4 +
drivers/event/cnxk/cn20k
On Tue, 17 Jun 2025 11:52:08 +0100
Marat Khalili wrote:
> This was flagged by undefined behaviour sanitizer: struct
> rte_graph_cluster_stats is declared as `__rte_cache_aligned` but was
> allocated using stdlib realloc which caused misaligned allocation. More
> than one test needs to be executed
E830 adapters currently support Tx Time based queues.
Signed-off-by: Soumyadeep Hore
---
doc/guides/nics/ice.rst | 27 +++
1 file changed, 27 insertions(+)
diff --git a/doc/guides/nics/ice.rst b/doc/guides/nics/ice.rst
index 77985ae5a2..8ab693ff0b 100644
--- a/doc/guides
Add support for Tx Time based queues. This is used to schedule
packets based on Tx timestamp.
Signed-off-by: Soumyadeep Hore
---
drivers/net/intel/common/tx.h | 1 +
drivers/net/intel/ice/base/ice_lan_tx_rx.h | 4 +
drivers/net/intel/ice/ice_ethdev.c | 3 +-
drivers/ne
Adding eth_ice_read_clock() feature to get current time
for scheduling Packets based on Tx time.
Signed-off-by: Soumyadeep Hore
---
drivers/net/intel/ice/ice_ethdev.c | 17 +
1 file changed, 17 insertions(+)
diff --git a/drivers/net/intel/ice/ice_ethdev.c
b/drivers/net/intel/ic
Added TxPP support for E830 adapters.
---
v2:
- Fixed Compilation warnings
---
v3:
- Fixed further Compilation warnings (uinitialised one)
---
v4:
- Addressed Bruce's comments
---
v5:
- Addressed Bruce's and Ciara's comments
---
v6:
- Addressed Bruce's comments
- Fixed compilation warnings
---
Paul
From: Paul Greenwalt
Updated the Tx Time Queue Context Structure to align with HAS.
Signed-off-by: Soumyadeep Hore
Signed-off-by: Paul Greenwalt
---
drivers/net/intel/ice/base/ice_common.c | 22 +++---
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/net
On Tue, Jun 17, 2025 at 4:32 PM Marat Khalili wrote:
>
> This was flagged by undefined behaviour sanitizer: struct
> rte_graph_cluster_stats is declared as `__rte_cache_aligned` but was
> allocated using stdlib realloc which caused misaligned allocation. More
> than one test needs to be executed i
On Tue, Jun 17, 2025 at 4:22 PM Marat Khalili wrote:
>
> This was flagged by undefined behaviour sanitizer: memset should not be
> called with NULL first argument. (memset requires first argument to be
> pointer to a memory object, so passing NULL may result in an undefined
> behaviour including a
Created a ticket: https://bugs.dpdk.org/show_bug.cgi?id=1725
Sharing the patch for the same for quick look.( I know it can be better
modularised.)
diff --git a/drivers/net/iavf/iavf_ethdev.c b/drivers/net/iavf/iavf_ethdev.c
index 656a4c6176..25d7924c31 100644
--- a/drivers/net/iavf/iavf_ethdev.c
+
Hi @Stephen Hemminger ,
We debugged further on this issue ..
We see that position and entry_size(position * key_entry_size) crosses
above int32_t it overflows and it will corrupt random index of hash table.
in Nut shell hash table is only supporting upto 2topower32 size entries on
the table.
B
Created a ticket: https://bugs.dpdk.org/show_bug.cgi?id=1725
Sharing the patch for the same for quick look.( I know it can be better
modularised.)
diff --git a/drivers/net/iavf/iavf_ethdev.c b/drivers/net/iavf/iavf_ethdev.c
index 656a4c6176..25d7924c31 100644
--- a/drivers/net/iavf/iavf_ethdev.c
+
On Wed, Jun 11, 2025 at 09:50:57AM +, Mingjin Ye wrote:
> Get rss hash configuration, rss_hf is always the default value.
> The driver does nothing if the rss key is invalid during the rss
> hash update.
>
> This patch is get the current configuration of rss_hf. Extract
> the update rss key co
Add crypto adapter support for CN20K crypto PMD.
Signed-off-by: Nithinsen Kaithakadan
---
.../crypto/cnxk/cn20k_cryptodev_event_dp.h| 14 +
drivers/crypto/cnxk/cn20k_cryptodev_ops.c | 585 +-
drivers/crypto/cnxk/cn20k_cryptodev_ops.h | 4 +
drivers/event/cnxk/cn20k
This was flagged by undefined behaviour sanitizer: struct
rte_graph_cluster_stats is declared as `__rte_cache_aligned` but was
allocated using stdlib realloc which caused misaligned allocation. More
than one test needs to be executed in series in order to reproduce the
problem using graph_autotest,
This was flagged by undefined behaviour sanitizer: memset should not be
called with NULL first argument. (memset requires first argument to be
pointer to a memory object, so passing NULL may result in an undefined
behaviour including among other things optimizer potentially removing
code paths depe
On Tue, Jun 17, 2025 at 12:14:29AM +, Soumyadeep Hore wrote:
> E830 adapters currently support Tx Time based queues.
>
> Signed-off-by: Soumyadeep Hore
Hi,
as a general comment on adding documentation, only split lines at
punctuation marks. If line length exceeds 100 character for docs, tha
On Tue, Jun 17, 2025 at 12:14:28AM +, Soumyadeep Hore wrote:
> Add support for Tx Time based queues. This is used to schedule
> packets based on Tx timestamp.
>
> Signed-off-by: Soumyadeep Hore
> ---
Hi Soumyadeep,
couple more comments inline below.
/Bruce
> drivers/net/intel/common/tx.h
Acked-by: Kai Ji
From: Radu Nicolau
Sent: 12 June 2025 11:14
To: Ji, Kai ; Kusztal, ArkadiuszX
Cc: dev@dpdk.org ; Nicolau, Radu ;
sta...@dpdk.org
Subject: [PATCH] crypto/qat: fix out-of-place chain/cipher/auth headers
Extend the original fix to gen3 and gen4
On Tue, Jun 17, 2025 at 12:14:27AM +, Soumyadeep Hore wrote:
> Adding eth_ice_read_clock() feature to get current time
> for scheduling Packets based on Tx time.
>
> Signed-off-by: Soumyadeep Hore
> ---
> drivers/net/intel/ice/ice_ethdev.c | 13 +
> 1 file changed, 13 insertions(
V1:
- add support flow director ops.
Bingbin Chen (2):
net/zxdh: npsdk add flow director table ops
net/zxdh: add support flow director ops
doc/guides/nics/features/zxdh.ini | 16 +
doc/guides/nics/zxdh.rst |1 +
drivers/net/zxdh/meson.build |1 +
drivers/net/zxdh
Add support for Tx Time based queues. This is used to schedule
packets based on Tx timestamp.
Signed-off-by: Soumyadeep Hore
---
drivers/net/intel/common/tx.h | 1 +
drivers/net/intel/ice/base/ice_lan_tx_rx.h | 4 +
drivers/net/intel/ice/ice_ethdev.c | 3 +-
drivers/ne
E830 adapters currently support Tx Time based queues.
Signed-off-by: Soumyadeep Hore
---
doc/guides/nics/ice.rst | 25 +
1 file changed, 25 insertions(+)
diff --git a/doc/guides/nics/ice.rst b/doc/guides/nics/ice.rst
index 77985ae5a2..e7d1fb2e1b 100644
--- a/doc/guides/n
From: Paul Greenwalt
Updated the Tx Time Queue Context Structure to align with HAS.
Signed-off-by: Soumyadeep Hore
Signed-off-by: Paul Greenwalt
---
drivers/net/intel/ice/base/ice_common.c | 22 +++---
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/net
Adding eth_ice_read_clock() feature to get current time
for scheduling Packets based on Tx time.
Signed-off-by: Soumyadeep Hore
---
drivers/net/intel/ice/ice_ethdev.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/drivers/net/intel/ice/ice_ethdev.c
b/drivers/net/intel/ice/ic
Added TxPP support for E830 adapters.
---
v2:
- Fixed Compilation warnings
---
v3:
- Fixed further Compilation warnings (uinitialised one)
---
v4:
- Addressed Bruce's comments
---
v5:
- Addressed Bruce's and Ciara's comments
---
Paul Greenwalt (1):
net/ice: update E830 Tx Time Queue Context Struc
88 matches
Mail list logo
