Add the option to use resources (Tables, Matchers, Actions, etc.)
from one gvmi (AKA ibv_cntext) to other gvmi's.
When specific gvmi allows other to use its resources, steering objects
Will created and used on that gvmi.
It is done by aliases objects that map between local resources to
shared/rem
Added Yevgeny Kliteynik to the list
Signed-off-by: Erez Shitrit
---
.mailmap | 1 +
1 file changed, 1 insertion(+)
diff --git a/.mailmap b/.mailmap
index 75884b6fe2..c6f34d18a6 100644
--- a/.mailmap
+++ b/.mailmap
@@ -1495,6 +1495,7 @@ Yash Sharma
Yasufumi Ogawa
Yelena Krivosheev
Yerde
The new fields define the ability to access from one vhca to other one.
Signed-off-by: Erez Shitrit
Reviewed-by: Alex Vesker
---
drivers/common/mlx5/mlx5_prm.h | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_p
From: Yevgeny Kliteynik
Removing macros for wrong capability checks.
Signed-off-by: Yevgeny Kliteynik
Reviewed-by: Alex Vesker
---
drivers/common/mlx5/mlx5_prm.h | 6 --
1 file changed, 6 deletions(-)
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 19c
From: Yevgeny Kliteynik
And keep them for future processing.
Signed-off-by: Yevgeny Kliteynik
Reviewed-by: Alex Vesker
---
drivers/net/mlx5/hws/mlx5dr_cmd.c | 24
drivers/net/mlx5/hws/mlx5dr_cmd.h | 1 +
2 files changed, 25 insertions(+)
diff --git a/drivers/net/ml
From: Yevgeny Kliteynik
Each new cap was defined.
Signed-off-by: Yevgeny Kliteynik
Reviewed-by: Alex Vesker
---
drivers/common/mlx5/mlx5_prm.h | 19 ++-
1 file changed, 18 insertions(+), 1 deletion(-)
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm
From: Yevgeny Kliteynik
Added FW command to allow creation of alias objects.
Signed-off-by: Yevgeny Kliteynik
Reviewed-by: Alex Vesker
---
drivers/common/mlx5/mlx5_prm.h| 23 +++
drivers/net/mlx5/hws/mlx5dr_cmd.c | 28
drivers/net/mlx5/hws
For context, table and matcher.
Signed-off-by: Erez Shitrit
Signed-off-by: Hamdan Igbaria
Reviewed-by: Alex Vesker
---
drivers/net/mlx5/hws/mlx5dr_debug.c | 22 --
1 file changed, 16 insertions(+), 6 deletions(-)
diff --git a/drivers/net/mlx5/hws/mlx5dr_debug.c
b/driver
From: Yevgeny Kliteynik
Added support for a command that can create alias objects - objects
that are accessed across VHCA.
Signed-off-by: Yevgeny Kliteynik
Reviewed-by: Alex Vesker
---
drivers/common/mlx5/mlx5_prm.h| 23 ++--
drivers/net/mlx5/hws/mlx5dr_cmd.c | 44 +++
And read it in the query_cap function
Signed-off-by: Erez Shitrit
Reviewed-by: Alex Vesker
---
drivers/net/mlx5/hws/mlx5dr_cmd.c | 3 +++
drivers/net/mlx5/hws/mlx5dr_cmd.h | 1 +
2 files changed, 4 insertions(+)
diff --git a/drivers/net/mlx5/hws/mlx5dr_cmd.c
b/drivers/net/mlx5/hws/mlx5dr_cm
The idea is to have a shared ibv_context that all the resources
allocated on it (FT + TIR are exceptions)
When ever a resource created locally an alias object to that resource
allocated and it used in the other context.
The connections between the resources are done according to each type of
the
TIR/FT actions are different in the context of shared ibv resource, it
created on the local ibv_context and aliased to the shared ibv_context.
Other actions should be created on the shared ibv resource, new flag was
added to indicates where this object came from.
Signed-off-by: Erez Shitrit
Rev
PING mempool maintainers.
If you don't provide ACK or Review to patches, how should Thomas know that it
is ready for merging?
-Morten
> From: Morten Brørup [mailto:m...@smartsharesystems.com]
> Sent: Wednesday, 16 November 2022 18.39
>
> > From: Honnappa Nagarahalli [mailto:honnappa.nagaraha..
> From: Ferruh Yigit
> Sent: 2022年12月16日 20:11
> To: Thomas Monjalon
> Cc: dev@dpdk.org; David Marchand ;
> sta...@dpdk.org; christian.ehrha...@canonical.com; Gao, DaxueX
>
> Subject: [PATCH v19.11 LTS] kni: fix build for Suse
>
> Wrong macro is used in the patch that detects if '.ndo_tx_timeou
This patchset contains dmadev/ethdev stats reset, and also support
hide zero for ethdev xstats.
Chengwen Feng (5):
dmadev: support stats reset telemetry command
telemetry: fix repeated display when callback don't set dict
ethdev: support xstats reset telemetry command
ethdev: telemetry xst
The stats reset is useful for debugging, so add it to the dmadev
telemetry command lists.
Signed-off-by: Chengwen Feng
---
lib/dmadev/rte_dmadev.c | 40
1 file changed, 40 insertions(+)
diff --git a/lib/dmadev/rte_dmadev.c b/lib/dmadev/rte_dmadev.c
index
When telemetry callback didn't set dict and return a non-negative
number, the telemetry will repeat to display the last result.
Fixes: 6dd571fd07c3 ("telemetry: introduce new functionality")
Cc: sta...@dpdk.org
Signed-off-by: Chengwen Feng
---
lib/telemetry/telemetry.c | 4 +++-
1 file changed,
The xstats reset is useful for debugging, so add it to the ethdev
telemetry command lists.
Signed-off-by: Chengwen Feng
---
lib/ethdev/rte_ethdev.c | 23 +++
1 file changed, 23 insertions(+)
diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index 5d5e18db1e..077
The telemetry related code may invoke RTE_ETHDEV_LOG to display
information, the newline character is not added automatically to the
RTE_ETHDEV_LOG, therefore, the newline character must be explicitly
added to the log string.
Cc: sta...@dpdk.org
Signed-off-by: Chengwen Feng
---
lib/ethdev/rte_e
The number of xstats may be large, after the hide zero option is added,
only non-zero values can be displayed.
Signed-off-by: Chengwen Feng
---
lib/ethdev/rte_ethdev.c | 28 ++--
1 file changed, 22 insertions(+), 6 deletions(-)
diff --git a/lib/ethdev/rte_ethdev.c b/lib/
On Mon, Dec 19, 2022 at 03:06:46PM +0800, Huisong Li wrote:
> Sometimes displaying a unsigned integer value as hexadecimal encoded style
> is more expected for human consumption, such as, offload capability and
> device flag. This patch introduces two APIs to add unsigned integer value
> as hexadec
Hi Morten,
+1 for features.
Also this is a compilation option. Can you add compilation and related test
cases
to the DPDK CI? In this way, we can check whether the patch affects the
code(IOVA_AS_PA).
On 2022/12/7 16:06, Morten Brørup wrote:
> Should support for IOVA as VA be listed under
On Mon, Dec 19, 2022 at 09:07:20AM +, Chengwen Feng wrote:
> When telemetry callback didn't set dict and return a non-negative
> number, the telemetry will repeat to display the last result.
>
> Fixes: 6dd571fd07c3 ("telemetry: introduce new functionality")
> Cc: sta...@dpdk.org
>
> Signed-of
15/12/2022 14:58, Bruce Richardson:
> On Thu, Dec 15, 2022 at 02:36:51PM +0100, Thomas Monjalon wrote:
> > 15/12/2022 10:44, Bruce Richardson:
> > > On Wed, Dec 14, 2022 at 09:38:45AM -0800, Tyler Retzlaff wrote:
> > > > On Tue, Dec 13, 2022 at 06:27:25PM +, Bruce Richardson wrote:
> > > > > Fo
On 15/12/2022 17:51, Ali Alnubani wrote:
-Original Message-
From: Kevin Traynor
Sent: Tuesday, December 6, 2022 1:30 PM
To: sta...@dpdk.org
Cc: dev@dpdk.org; Abhishek Marathe ;
Ali Alnubani ; benjamin.wal...@intel.com; David
Christensen ; Hemant Agrawal
; Ian Stokes ; Jerin
Jacob ; John
From: Satheesh Paul
Implement rte_flow_info_get API to get the maximum
number of counters and meters.
Signed-off-by: Satheesh Paul
Reviewed-by: Kiran Kumar K
---
Depends-on: patch-26075 ("common/cnxk: fix dual VLAN parsing issue")
drivers/net/cnxk/cn10k_ethdev.c| 1 +
drivers/net/cnxk/c
On Mon, Dec 19, 2022 at 11:37:19AM +0100, Thomas Monjalon wrote:
> 15/12/2022 14:58, Bruce Richardson:
> > On Thu, Dec 15, 2022 at 02:36:51PM +0100, Thomas Monjalon wrote:
> > > 15/12/2022 10:44, Bruce Richardson:
> > > > On Wed, Dec 14, 2022 at 09:38:45AM -0800, Tyler Retzlaff wrote:
> > > > > On
On 2022-12-18 11:01, Morten Brørup wrote:
> This RFC introduces per-thread constructors/destructors:
> * Per-thread constructors are functions called as the first thing from newly
> created threads. This can be used to initialize variables in thread-local
> storage, variables depending on the (ti
On Tue, Dec 13, 2022 at 06:11:06AM +, Zhou, Xiangyun wrote:
> Dear dpdk dev,
>
> I'm using dpdk 21.11 LTS, when compile my program with CPP flag "-std=c++20",
> the compiler report below errors. After checking file rte_spinlock.h, I think
> the error report by compiler is valid, there should
> On Tue, Dec 13, 2022 at 06:11:06AM +, Zhou, Xiangyun wrote:
> > Dear dpdk dev,
> >
> > I'm using dpdk 21.11 LTS, when compile my program with CPP flag
> > "-std=c++20", the compiler report below errors. After checking file
> rte_spinlock.h, I think the error report by compiler is valid, th
Hi Harish,
Adding a couple of comments inline:
> -Original Message-
> From: Naga Harish K, S V
> Sent: Monday, December 19, 2022 12:29 AM
> To: jer...@marvell.com; Carrillo, Erik G ; Gujjar,
> Abhinandan S
> Cc: dev@dpdk.org; Jayatheerthan, Jay
> Subject: [PATCH v4 4/4] eventdev/timer:
Hi all
Josh just found out some inconsistencies in the Tx/Rx statistics sum
for all ports. Not sure if we can screenshot here but it goes like
this:
Tx-dropped for port0: 447034
Tx-dropped for port1: 0
Accumulated forward statistics for all ports: 807630
Please note that this issue is only with Tx
Introduce an event timer adapter API which allows users to determine how
many adapter ticks remain until an event timer fires.
Signed-off-by: Erik Gabriel Carrillo
---
v2:
* Rename API to rte_event_timer_get_remaining_ticks
* Assert that API out param is non-NULL instead of checking and returning
> -Original Message-
> From: Erik Gabriel Carrillo
> Sent: Tuesday, December 20, 2022 1:29 AM
> To: Jerin Jacob Kollanukkaran
> Cc: hof...@lysator.liu.se; s.v.naga.haris...@intel.com;
> jay.jayatheert...@intel.com; Pavan Nikhilesh Bhagavatula
> ; Shijith Thotton ;
> dev@dpdk.org
> Subj
Introduce an event timer adapter API which allows users to determine how
many adapter ticks remain until an event timer fires.
Signed-off-by: Erik Gabriel Carrillo
---
v3:
* Handle ENOTSUP case in unit test
v2:
* Rename API to rte_event_timer_get_remaining_ticks
* Assert that API out param is no
<... snipped ...>
> > diff --git a/app/test/test_event_timer_adapter.c
> > b/app/test/test_event_timer_adapter.c
> > index 1a440dfd10..1a1fb48b24 100644
> > --- a/app/test/test_event_timer_adapter.c
> > +++ b/app/test/test_event_timer_adapter.c
> > @@ -1920,6 +1920,72 @@ adapter_create_max(void)
>
iavf admin queue commands aren't thread-safe. Bugs surrounding this
issue can manifest in a variety of ways but frequently pend_cmd is
over written. Simultaneously executing commands can result in a
misconfigured device or DPDK sleeping in a thread for 2 second.
Despite this limitation, vf command
To improve the performance of async vhost packed ring. We remove the
unnecessary data copy in async vhost packed ring. And add the batch
data path in both enqueue data path and dequeue data path.
Cheng Jiang (3):
vhost: remove redundant copy for packed shadow used ring
vhost: add batch enqueue
In the packed ring enqueue data path of the current asynchronous
Vhost design, the shadow used ring is first copied to the sync
shadow used ring, and then it will be moved to the async shadow
used ring for some historical reasons. This is completely unnecessary.
This patch removes redundant copy fo
Add batch enqueue function in asynchronous vhost packed ring to
improve the performance. Chained mbufs are not supported, it will
be handled in single enqueue function.
Signed-off-by: Cheng Jiang
---
lib/vhost/virtio_net.c | 157 +
1 file changed, 157 inse
Add batch dequeue function in asynchronous vhost packed ring to
improve the performance. Chained mbufs are not supported, it will
be handled in single dequeue function.
Signed-off-by: Cheng Jiang
Signed-off-by: Yuan Wang
---
lib/vhost/virtio_net.c | 170 -
There are many high-performance DMA devices supported in DPDK now, and
these DMA devices can also be integrated into other modules of DPDK as
accelerators, such as Vhost. Before integrating DMA into applications,
developers need to know the performance of these DMA devices in various
scenarios and
[PATCH 1/3] code refactoring.
[PATCH 2/3] add related definitions for ptp timesync.
[PATCH 3/3] add IEEE1588 API to support timesync.
Simei Su (3):
net/igc: code refactoring
net/igc/base: support PTP timesync
net/igc: support IEEE 1588 PTP
drivers/net/igc/base/igc_defines.h | 11 ++
drive
Move related structures for Rx/Tx queue from igc_txrx.c to igc_txrx.h
to make code cleaner and variables used more conveniently.
Signed-off-by: Simei Su
---
drivers/net/igc/igc_txrx.c | 118 -
drivers/net/igc/igc_txrx.h | 115 ++
Add definitions for timesync enabling.
Signed-off-by: Simei Su
---
drivers/net/igc/base/igc_defines.h | 11 +++
1 file changed, 11 insertions(+)
diff --git a/drivers/net/igc/base/igc_defines.h
b/drivers/net/igc/base/igc_defines.h
index 61964bc..dd7330a 100644
--- a/drivers/net/igc/base
Add igc support for new ethdev APIs to enable/disable and read/write/adjust
IEEE1588 PTP timestamps.
The example command for running ptpclient is as below:
./build/examples/dpdk-ptpclient -c 1 -n 3 -- -T 0 -p 0x1
Signed-off-by: Simei Su
---
drivers/net/igc/igc_ethdev.c | 222 +++
[PATCH 1/2] add related definitions to support Tx timestamp offload.
[PATCH 2/2] enable Tx timestamp offload by "Launch Time".
Simei Su (2):
net/igc/base: support Tx timestamp offload
net/igc: enable Tx timestamp offload
drivers/net/igc/base/igc_defines.h | 9 +
drivers/net/igc/base/igc
Add definitions for Tx timestamp offload
"RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP".
Signed-off-by: Simei Su
---
drivers/net/igc/base/igc_defines.h | 9 +
drivers/net/igc/base/igc_regs.h| 8
2 files changed, 17 insertions(+)
diff --git a/drivers/net/igc/base/igc_defines.h
b/dr
This patch supports Tx timestamp offload by leveraging NIC's
"Launch Time" for "RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP".
Signed-off-by: Simei Su
---
drivers/net/igc/igc_ethdev.c | 70
drivers/net/igc/igc_ethdev.h | 6 +++-
drivers/net/igc/igc_txrx.c
When segment size is provided, the total number of segments would be
calculated. Segment size updates due to headroom/tailroom need to be
accounted for when determining total number of segments required.
Fixes: c1670ae0022b ("app/crypto-perf: honour min headroom/tailroom")
Signed-off-by: Anoob Jo
> -Original Message-
> From: Ferruh Yigit
> Sent: 2022年12月13日 21:28
> To: You, KaisenX ; dev@dpdk.org; Burakov,
> Anatoly ; David Marchand
>
> Cc: sta...@dpdk.org; Yang, Qiming ; Zhou, YidingX
> ; Wu, Jingjing ; Xing,
> Beilei ; Zhang, Qi Z ; Luca
> Boccassi ; Mcnamara, John
> ; Kevin T
Currently, rte_flow API does not support matching
ID and sequence fields of icmp6 echo packets.
This patchset is used to support match icmpv6 ID and
sequence in rte_flow. It adds needed API in rte_flow,
and gives corresponding implementation for mlx5 pmd.
Leo Xu (3):
ethdev: add ICMPv6 ID and s
This patch adds API support for ICMPv6 ID and sequence.
1: Add two new pattern item types for ICMPv6 echo request and reply:
RTE_FLOW_ITEM_TYPE_ICMP6_ECHO_REQUEST
RTE_FLOW_ITEM_TYPE_ICMP6_ECHO_REPLY
2: Add new header file rte_icmp6.h for ICMPv6 packet definitions.
3: Enhance testpmd flow patte
This patch adds ICMPv6 ID and sequence match support.
Since type and code of ICMPv6 echo is already specified by ITEM type:
RTE_FLOW_ITEM_TYPE_ICMP6_ECHO_REQUEST
RTE_FLOW_ITEM_TYPE_ICMP6_ECHO_REPLY
mlx5 pmd will set appropriate type and code automatically:
Echo request: type(128), code(0)
E
This patch adds ICMPv6 ID and sequence match support for HWS.
Since type and code of ICMPv6 echo is already specified by ITEM type:
RTE_FLOW_ITEM_TYPE_ICMP6_ECHO_REQUEST
RTE_FLOW_ITEM_TYPE_ICMP6_ECHO_REPLY
mlx5 pmd will set appropriate type and code automatically:
Echo request: type(128), cod
55 matches
Mail list logo
