> > -Original Message-
> > From: pbhagavat...@marvell.com
> > Sent: Thursday, February 22, 2024 8:24 PM
> > To: jer...@marvell.com; ndabilpu...@marvell.com;
> kirankum...@marvell.com;
> > Yan, Zhirun
> > Cc: dev@dpdk.org; Pavan Nikhilesh
> > Subject: [24.11 PATCH v3 1/5] graph: add suppo
> > -Original Message-
> > From: pbhagavat...@marvell.com
> > Sent: Thursday, February 22, 2024 8:24 PM
> > To: jer...@marvell.com; ndabilpu...@marvell.com;
> kirankum...@marvell.com;
> > Yan, Zhirun ; Pavan Nikhilesh
> > ; Ruifeng Wang ;
> > Richardson, Bruce ; Konstantin Ananyev
> >
> >
From: Pavan Nikhilesh
Some ARM CPUs have specific march requirements and
are not compatible with the supported march list.
Add fallback march in case the mcpu and the march
advertised in the part_number_config are not supported
by the compiler.
Example
mcpu = neoverse-n2
march =
From: Pavan Nikhilesh
Allow RTE_ARM_USE_WFE to be enabled at meson configuration
time by passing it via c_args instead of modifying
`config/arm/meson.build`.
Example usage:
meson build -Dc_args='-DRTE_ARM_USE_WFE' \
--cross-file config/arm/arm64_cn10k_linux_gcc
Signed-off-by: Pavan Nik
From: Pavan Nikhilesh
The compiler options march and mtune are a subset
of mcpu and will lead to conflicts if improper march
is chosen for a given mcpu.
To avoid conflicts, discard part number march when
mcpu is available and is supported by the compiler.
Example:
march = armv9-a
I Forgot to add my tag:
Reviewed-by: Juraj Linkeš
On Mon, Feb 26, 2024 at 8:31 AM Juraj Linkeš wrote:
>
> On Mon, Feb 26, 2024 at 8:11 AM Pavan Nikhilesh Bhagavatula
> wrote:
> >
> > > On Thu, Feb 22, 2024 at 1:45 PM wrote:
> > > >
> > > > From: Pavan Nikhilesh
> > > >
> > > > Some ARM CPUs h
On Mon, Feb 26, 2024 at 8:11 AM Pavan Nikhilesh Bhagavatula
wrote:
>
> > On Thu, Feb 22, 2024 at 1:45 PM wrote:
> > >
> > > From: Pavan Nikhilesh
> > >
> > > Some ARM CPUs have specific march requirements and
> > > are not compatible with the supported march list.
> > > Add fallback march in cas
> On Thu, Feb 22, 2024 at 1:45 PM wrote:
> >
> > From: Pavan Nikhilesh
> >
> > Some ARM CPUs have specific march requirements and
> > are not compatible with the supported march list.
> > Add fallback march in case the mcpu and the march
> > advertised in the part_number_config are not supported
> Other than the one point below,
> Reviewed-by: Juraj Linkeš
>
> > diff --git a/config/arm/meson.build b/config/arm/meson.build
> > index 36f21d2259..d05d54b564 100644
> > --- a/config/arm/meson.build
> > +++ b/config/arm/meson.build
>
> > @@ -695,13 +698,37 @@ if update_flags
> >
> > mach
> The event vector struct was missing comments on two members, and also
> was inadvertently creating a local variable called "__rte_aligned" in
> the doxygen output.
>
> Correct the comment markers to fix the former issue, and fix the latter
> by putting "#ifdef __DOXYGEN" around the alignment con
> Make the comments on the unnamed unions in the rte_event structure
> regular comments rather than doxygen ones. The comments do not add
> anything meaningful to the doxygen output.
>
> Signed-off-by: Bruce Richardson
Acked-by: Pavan Nikhilesh
> ---
> lib/eventdev/rte_eventdev.h | 4 ++--
>
> Clarify the meaning of the NEW, FORWARD and RELEASE event types.
> For the fields in "rte_event" struct, enhance the comments on each to
> clarify the field's use, and whether it is preserved between enqueue and
> dequeue, and it's role, if any, in scheduling.
>
> Signed-off-by: Bruce Richardson
> The description of ordered and atomic scheduling given in the eventdev
> doxygen documentation was not always clear. Try and simplify this so
> that it is clearer for the end-user of the application
>
> Signed-off-by: Bruce Richardson
>
Acked-by: Pavan Nikhilesh
> ---
> V4: reworked follow
> -Original Message-
> From: Pavan Nikhilesh Bhagavatula
> Sent: Monday, February 26, 2024 12:13 PM
> To: Bruce Richardson ; dev@dpdk.org; Jerin
> Jacob ; mattias.ronnb...@ericsson.com
> Subject: RE: [EXT] [PATCH v4 07/12] eventdev: improve doxygen comments
> on config fns
>
> > Improve
> The doxygen comments for the port attributes, start and stop (and
> related functions) are improved.
>
> Signed-off-by: Bruce Richardson
Acked-by: Pavan Nikhilesh
>
> ---
> V3: add missing "." on end of sentences/lines.
> ---
> lib/eventdev/rte_eventdev.h | 47 +++--
> Improve the documentation text for the configuration functions and
> structures for configuring an eventdev, as well as ports and queues.
> Clarify text where possible, and ensure references come through as links
> in the html output.
>
> Signed-off-by: Bruce Richardson
Pavan Nikhilesh
>
>
> General rewording and cleanup on the rte_event_dev_config structure.
> Improved the wording of some sentences and created linked
> cross-references out of the existing references to the dev_info
> structure.
>
> As part of the rework, fix issue with how single-link port-queue pairs
> were counte
> General improvements to the doxygen docs for eventdev functions for
> querying basic information:
> * number of devices
> * id for a particular device
> * socket id of device
> * capability information for a device
>
> Signed-off-by: Bruce Richardson
>
Acked-by: Pavan Nikhilesh
> ---
> V3:
> Some small rewording changes to the doxygen comments on struct
> rte_event_dev_info.
>
> Signed-off-by: Bruce Richardson
Acked-by: Pavan Nikhilesh
>
> ---
> V3: reworked following feedback
> - added closing "." on comments
> - added more cross-reference links
> - reworded priority level com
> Update the device capability docs, to:
>
> * include more cross-references
> * split longer text into paragraphs, in most cases with each flag having
> a single-line summary at the start of the doc block
> * general comment rewording and clarification as appropriate
>
> Signed-off-by: Bruce R
> Inside the doxygen introduction text, some internal details of how
> eventdev works was mixed in with application-relevant details. Move
> these details on probing etc. to the driver-relevant section.
>
> Signed-off-by: Bruce Richardson
Acked-by: Pavan Nikhilesh
> ---
> lib/eventdev/rte_eve
> Make some textual improvements to the introduction to eventdev and event
> devices in the eventdev header file. This text appears in the doxygen
> output for the header file, and introduces the key concepts, for
> example: events, event devices, queues, ports and scheduling.
>
> This patch makes
Hi Radu,
Using same session across multiple devices would only work if the device
instances are same. For example, if you use QAT device 0 & QAT device 1, then
the sharing is okay. But if we have QAT and some SW crypto PMD, then the same
session will not work. Is it possible to throw a warning
On Thu, Feb 22, 2024 at 2:50 PM Tomasz Duszynski wrote:
>
> Use standard logging functions from DPDK instead of platform ones.
>
> Signed-off-by: Tomasz Duszynski
Applied to dpdk-next-net-mrvl/for-main. Thanks
On 2024/2/23 21:53, Ferruh Yigit wrote:
On 2/20/2024 3:58 AM, Jie Hai wrote:
Hi, Ferruh,
Thanks for your review.
On 2024/2/7 22:15, Ferruh Yigit wrote:
On 2/6/2024 1:10 AM, Jie Hai wrote:
From: Dengdui Huang
When KEEP_CRC offload is enabled, some packets will be truncated and
the CRC is st
This patch supports reporting names of the dfx registers
which filtering them by names.
Signed-off-by: Jie Hai
---
drivers/net/hns3/hns3_regs.c | 277 +--
1 file changed, 230 insertions(+), 47 deletions(-)
diff --git a/drivers/net/hns3/hns3_regs.c b/drivers/net/h
This patch supports reporting names of registers which
can be directly accessed by addresses and filtering
them by names.
Signed-off-by: Jie Hai
---
drivers/net/hns3/hns3_regs.c | 198 +--
1 file changed, 167 insertions(+), 31 deletions(-)
diff --git a/drivers/ne
This patch adds names for all registers to be dumped.
For those who can be directly accessed by their addresses,
a new structure containing both name and address is added
and the related arrays is refactored and renamed.
For the remaining modules, there may be different meanings
on different platf
Since the driver is going to support reporting names of
all registers, remove the counter and insert of separators
between different register modules.
Signed-off-by: Jie Hai
---
drivers/net/hns3/hns3_regs.c | 67 ++--
1 file changed, 18 insertions(+), 49 deletions
This patch adds "filter" and "names" fields to "rte_dev_reg_info"
structure. Names of registers in data fields can be reported and
the registers can be filtered by their names.
The new API rte_eth_dev_get_reg_info_ext() is added to support
reporting names and filtering by names. And the original A
Since the driver dumps the queue interrupt registers according
to the intr_tqps_num, the counter should be the same.
Fixes: acb3260fac5c ("net/hns3: fix dump register out of range")
Fixes: 936eda25e8da ("net/hns3: support dump register")
Signed-off-by: Jie Hai
Cc: sta...@dpdk.org
---
drivers/ne
This patch adds a telemetry command for registers dump,
and supports get registers with specified names.
The length of the string exported by telemetry is limited
by MAX_OUTPUT_LEN. Therefore, the filter should be more
precise.
An example usage is shown below:
--> /ethdev/regs,0,INTR
{
"/ethdev/
The registers can be dumped through the API rte_eth_dev_get_reg_info.
However, only register values are exported, which is inconvenient
for users to interpret. Therefore, an extension of the structure
"rte_dev_reg_info" and a new API rte_eth_dev_get_reg_info_ext
is added to support the capability o
On 2024/2/20 23:14, Stephen Hemminger wrote:
On Tue, 20 Feb 2024 18:58:17 +0800
Jie Hai wrote:
@@ -20,6 +25,12 @@ struct rte_dev_reg_info {
uint32_t length; /**< Number of registers to fetch */
uint32_t width; /**< Size of device register */
uint32_t version; /**< Devic
On 2024/2/20 23:13, Stephen Hemminger wrote:
On Tue, 20 Feb 2024 18:58:17 +0800
Jie Hai wrote:
This patch adds "filter" and "names" fields to "rte_dev_reg_info"
structure. Names of registers in data fields can be reported and
the registers can be filtered by their names.
The new API rte_eth_d
On 2024/2/20 23:14, Stephen Hemminger wrote:
On Tue, 20 Feb 2024 18:58:17 +0800
Jie Hai wrote:
int
rte_eth_dev_get_reg_info(uint16_t port_id, struct rte_dev_reg_info *info)
+{
+ struct rte_dev_reg_info reg_info = { 0 };
+ int ret;
+
+ if (info == NULL) {
+ R
On 2024/2/20 23:09, Stephen Hemminger wrote:
On Tue, 20 Feb 2024 18:58:17 +0800
Jie Hai wrote:
+* **Added support for dumping regiters with names and filter.**
Spelling
.
Hi, Stephen,
Thanks for your review.
Will fix in V4.
Best Regards,
Jie Hai
Hi Vipin,
On 2023/12/20 19:03, Vipin Varghese wrote:
> From: Vipin Varghese
>
> Replace pktmbuf pool with mempool, this allows increase in MOPS
> especially in lower buffer size. Using Mempool, allows to reduce
> the extra CPU cycles.
>
> Changes made are
> 1. pktmbuf pool create with mempool c
From: Long Wu
Add the corresponding logics to support the offload of RSS action.
Signed-off-by: Long Wu
Reviewed-by: Chaoyong He
Reviewed-by: Peng Zhang
---
doc/guides/nics/features/nfp.ini | 1 +
drivers/net/nfp/flower/nfp_flower_flow.c | 124 ++
drivers/
From: Long Wu
Add RSS configuration logics in representor initialization function.
Signed-off-by: Long Wu
Reviewed-by: Chaoyong He
Reviewed-by: Peng Zhang
---
drivers/common/nfp/nfp_common_ctrl.h| 1 +
drivers/net/nfp/flower/nfp_flower.c | 12 ++--
drivers/ne
From: Long Wu
Add the corresponding logics to support the offload of MARK action.
Signed-off-by: Long Wu
Reviewed-by: Chaoyong He
Reviewed-by: Peng Zhang
---
drivers/net/nfp/flower/nfp_flower_cmsg.h | 16 ++
drivers/net/nfp/flower/nfp_flower_flow.c | 27
From: Long Wu
Add a function to check if a device is representor port, also
modified the related codes for PMDs.
Signed-off-by: Long Wu
Reviewed-by: Chaoyong He
Reviewed-by: Peng Zhang
---
drivers/net/bnxt/bnxt.h| 3 ---
drivers/net/bnxt/bnxt_ethdev.c | 4 ++
This patch series add the support of MARK and RSS flow action for NFP
PMD, also add a new function to help check if a device is representor
port.
---
v2:
* Modify the title and description of patch series to make it more
clear.
* Add a new function to ethdev library, PMDs can use it to check if a
Please submit patches individually inline, so that people do not have to
download attachments
and patchwork can be used to track the status.
See https://doc.dpdk.org/guides/contributing/patches.html
On Tue, 13 Feb 2024 15:33:28 -0800
Tyler Retzlaff wrote:
> Here is the latest iteration of the proposed change to allow struct rte_mbuf
> to be consumed by MSVC.
>
> * Introduce an internal __rte_marker macro conditionally expanded for MSVC
> vs existing users of the struct. At some point we c
On 2024-02-25 16:03, Mattias Rönnblom wrote:
Replace static array of cache-aligned structs with an lcore variable,
to slightly benefit code simplicity and performance.
RFC v4:
* Remove strange-looking lcore value lookup potentially containing
invalid lcore id. (Morten Brørup)
* Replace m
On Fri, Feb 23, 2024 at 9:35 PM Vamsi Attunuru wrote:
>
> Adds a devarg option to enable/disable ISM memory accesses
> for reading packet count details. This option is disabled
> by default, as ISM memory accesses effect throughput of
> bigger size packets.
>
> Signed-off-by: Vamsi Attunuru
> ---
On Fri, Feb 23, 2024 at 9:10 PM wrote:
>
> From: Satha Rao
>
> Added CNXK APIs to get used txq descriptor count.
>
> Signed-off-by: Satha Rao
> ---
>
> Depends-on: series-30833 ("ethdev: support Tx queue used count")
>
> v2:
> Updated release notes and fixed API for CPT queues.
1)Please rebas
On Sat, Feb 10, 2024 at 1:14 AM Amit Prakash Shukla
wrote:
>
> Adds support to configure writing result to offset of the DMA
> response event.
>
> Signed-off-by: Amit Prakash Shukla
> ---
> v2:
> - Added dual workslot enqueue support.
> - Fixed compilation error.
Please rebase to next-eventdev.
On Fri, Feb 2, 2024 at 5:59 AM wrote:
>
> From: Pavan Nikhilesh
>
> Use WFE LDP loop while polling for GETWORK completion for better
> power savings.
> Disabled by default and can be enabled by configuring meson with
> -Dc_args='-DRTE_ARM_USE_WFE'.
Since this section is not yet merged. We can r
Replace static array of cache-aligned structs with an lcore variable,
to slightly benefit code simplicity and performance.
RFC v4:
* Remove strange-looking lcore value lookup potentially containing
invalid lcore id. (Morten Brørup)
* Replace misplaced tab with space. (Morten Brørup)
Signed-o
Replace keeping PRNG state in a RTE_MAX_LCORE-sized static array of
cache-aligned and RTE_CACHE_GUARDed struct instances with keeping the
same state in a more cache-friendly lcore variable.
RFC v3:
* Remove cache alignment on unregistered threads' rte_rand_state.
(Morten Brørup)
Signed-off-by
Keep per-lcore power intrinsics state in a lcore variable to reduce
cache working set size and avoid any CPU next-line-prefetching causing
false sharing.
Signed-off-by: Mattias Rönnblom
---
lib/eal/x86/rte_power_intrinsics.c | 17 +++--
1 file changed, 11 insertions(+), 6 deletions(-
Replace static array of cache-aligned structs with an lcore variable,
to slightly benefit code simplicity and performance.
RFC v3:
* Replace for loop with FOREACH macro.
Signed-off-by: Mattias Rönnblom
---
lib/power/rte_power_pmd_mgmt.c | 36 --
1 file changed,
Add test suite to exercise the API.
RFC v4:
* Check all lcore id's values for all variables in the many variables
test case.
* Introduce test case for max-sized lcore variables.
RFC v2:
* Improve alignment-related test coverage.
Signed-off-by: Mattias Rönnblom
---
app/test/meson.build
Introduce DPDK per-lcore id variables, or lcore variables for short.
An lcore variable has one value for every current and future lcore
id-equipped thread.
The primary use case is for statically allocating
small chunks of often-used data, which is related logically, but where
there are performan
This RFC presents a new API for static per-lcore id
data allocation.
Please refer to the API documentation for both a
rationale for this new API, and a comparison to the alternatives
available.
The adoption of this API would affect many different DPDK modules, but
the author updated only a few,
Hi,
> -Original Message-
> From: Gavin Li
> Sent: Tuesday, January 30, 2024 8:49 AM
> To: Dariusz Sosnowski ; Slava Ovsiienko
> ; Ori Kam ; Suanming Mou
> ; Matan Azrad
> Cc: dev@dpdk.org; Raslan Darawsheh ; Jiawei(Jonny)
> Wang
> Subject: [PATCH V1] net/mlx5: store IPv6 TC detection res
Hi,
> -Original Message-
> From: Tyler Retzlaff
> Sent: Monday, November 13, 2023 7:21 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Ori Kam ;
> Suanming Mou ; Slava Ovsiienko
> ; Tyler Retzlaff
> Subject: [PATCH] net/mlx5: remove non constant size from type cast
>
> Placing a non-constant
Hi Pavel,
You can use a symmetric key,
Or even better, in case of MLNX devices you can use
RTE_ETH_HASH_FUNCTION_SYMMETRIC_TOEPLITZ_SORT as the hash function,
This will sort the fields based on their value and only do the hash, resulting
in a symmetric hash.
Best,
Ori
From: Pavel Vazharov
Se
60 matches
Mail list logo
