Hi David,
> -Original Message-
> From: David Marchand
> Sent: Thursday, June 16, 2022 10:40 PM
> To: Ding, Xuan
> Cc: Maxime Coquelin ; Xia, Chenbo
> ; dev ; Hu, Jiayu
> ; Jiang, Cheng1 ; Pai G, Sunil
> ; lian...@liangbit.com; Wang, YuanX
> ; Mcnamara, John
> Subject: Re: [PATCH v8 4/5]
The following warning is observed with GCC 12 compilation:
In file included from ../drivers/crypto/cnxk/cn10k_cryptodev_ops.c:17:
In function ‘fill_sg_comp_from_iov’,
inlined from ‘cpt_pdcp_chain_alg_prep’ at
../drivers/crypto/cnxk/cnxk_se.h:1194:8,
inlined from ‘cpt_fc_enc_hmac_pr
The following warning is observed with GCC 12 compilation:
In function ‘fill_sg_comp_from_iov’,
inlined from ‘cpt_zuc_snow3g_enc_prep’ at
../drivers/common/cpt/cpt_ucode.h:1672:9,
inlined from ‘cpt_fc_enc_hmac_prep’ at
../drivers/common/cpt/cpt_ucode.h:2472:3,
inlined f
This patch series resolves compilation warning observed with GCC 12,
in common/cpt and crypto/cnxk.
Ankur Dwivedi (2):
common/cpt: fix compilation with GCC 12
crypto/cnxk: fix compilation with GCC 12
drivers/common/cpt/cpt_mcode_defines.h | 2 +-
drivers/common/cpt/cpt_ucode.h | 21
Hello,
On Fri, Jun 17, 2022 at 6:08 AM Juan Pablo L.
wrote:
>
> Hello, I am new to dpdk ... i would like to trace memory usage and detect
> memory leaks, valgrind as well as address sanitizer (gcc) report some memory
> loss at application end. For the life of me, i cannot figure it out ... i
>
Since the commit 02798b073520 ("vhost: improve virtio-net layer logs"),
vhost logs contain the socket path as a prefix.
Async dequeue path was copied from the sync dequeue path but a log
was incorrect.
Fixes: 84d5204310d7 ("vhost: support async dequeue for split ring")
Signed-off-by: David Marcha
On Thu, Jun 16, 2022 at 11:47 AM wrote:
>
> From: Xuan Ding
>
> This patch adds missing per-virtqueue statistics in async dequeue path.
This would not happen if the async code was better integrated with the
sync code.
>
> Fixes: 84d5204310d7("vhost: support async dequeue for split ring")
>
> Si
MLX5 PMD RSS expansion implementation added L4 UDP or TCP
headers after ICMP.
For example:
ETH / IPv4 / ICMP expanded into ETH / IPv4 / ICMP / {UDP | TCP}
ETH / IPv6 / ICMPv6 expanded into ETH / IPv6 / ICMPv6 / {UDP | TCP}
The patch updates PMD expansion scheme to handle ICMP and ICMPv6 types
as
> -Original Message-
> From: xuan.d...@intel.com
> Sent: Thursday, June 16, 2022 5:45 PM
> To: maxime.coque...@redhat.com; Xia, Chenbo
> Cc: dev@dpdk.org; Hu, Jiayu ; Ma, WenwuX
> ; Ding, Xuan
> Subject: [PATCH v2] vhost: fix missing statistics update
>
> From: Xuan Ding
>
> This patc
Introduce a new command and remove the last part of specific port init
from testpmd.
Signed-off-by: David Marchand
---
app/test-pmd/meson.build | 1 -
app/test-pmd/testpmd.c| 4 --
doc/guides/nics/ixgbe.rst | 7 +++
drivers/net/ixgbe/ixgbe_testpmd.c | 82 +
Move related specific testpmd commands into this driver directory.
The bypass init is left in testpmd at this point and can be moved later.
While at it, fix checkpatch warnings.
Signed-off-by: David Marchand
---
Changes since v1:
- rebased on next-net,
- updated link in documentation to directly
Since the switch to meson, ixgbe bypass commands were ineffective as the
RTE_LIBRTE_IXGBE_BYPASS build flag was not set, even though the
net/ixgbe driver had this feature compiled in.
Fixes: 16ade738fd0d ("app/testpmd: build with meson")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
app
Move related specific testpmd commands into this driver directory.
While at it, fix checkpatch warnings.
Signed-off-by: David Marchand
---
Changes since v1:
- rebased on next-net,
- updated link in documentation to directly point at commands,
Changes since RFC v2:
- renamed file in net/bonding,
On Fri, Jun 17, 2022 at 3:29 AM Wu, WenxuanX wrote:
>
> Thanks, do I need to send a new version to resolve formatting issues?
You are not a new contributor, please pay attention to such details.
To answer your question, I don't think there is a need for a new
version unless someone has a better
Acked-by: Hemant Agrawal
> -Original Message-
> From: Sean Morrissey
> Sent: Thursday, June 16, 2022 8:47 PM
> To: Sachin Saxena (OSS) ; Hemant Agrawal
>
> Cc: dev@dpdk.org; Sean Morrissey
> Subject: [PATCH v2 13/19] rawdev: remove unneeded header includes
> Importance: High
>
> Thes
Hi,Stephen
There are some things I don't quite understand.Hope you can answer that.
This will help me avoid similar errors in subsequent patch submissions.Thanks!
There are places where rte_memcpy functions are used:
In test_ipfrag.c:
from func test_
On Fri, 17 Jun 2022 10:42:29 +0800
Yuan Wang wrote:
> The virtio-user initialization requires unix socket to receive backend
> messages in block mode. However, vhost_user_update_link_state() sets
> the same socket to nonblocking via fcntl, which affects all threads.
> Enabling the rxq interrupt c
The virtio-user initialization requires unix socket to receive backend
messages in block mode. However, vhost_user_update_link_state() sets
the same socket to nonblocking via fcntl, which affects all threads.
Enabling the rxq interrupt can causes both of these behaviors to occur
concurrently, with
Hi Maxime,
Are there any comments about the patch?
Please let me know and thanks help review it.
Regards,
Li Zhang
> -Original Message-
> From: Maxime Coquelin
> Sent: Thursday, June 16, 2022 5:02 PM
> To: Li Zhang ; Ori Kam ; Slava
> Ovsiienko ; Matan Azrad ;
> Shahaf Shuler
> Cc: dev
Thanks, do I need to send a new version to resolve formatting issues?
> -Original Message-
> From: David Marchand
> Sent: 2022年6月16日 22:29
> To: Wu, WenxuanX
> Cc: Yang, Qiming ; Zhang, Qi Z
> ; dev ; Thomas Monjalon
> ; Stephen Hemminger
> ; dpdk stable
> Subject: Re: [PATCH] ice/base:
DLB supports 4 class of service domains, to aid in managing the
device bandwidth across ldb ports. This commit allows specifying
which ldb ports will participate in the COS scheme, which class
they are a part of, and the specific bandwidth percentage
associated with each class. The cumulative bandw
Enabling the weight limit on a CQ allows the enqueued QEs' 2-bit weight
value (representing weights of 1, 2, 4, and 8) to factor into whether a
CQ is full. If the sum of the weights of the QEs in the CQ meet or exceed
its weight limit, DLB will stop scheduling QEs to it (until software pops
enough
This patch rebases the following previously submitted
patches against the latest dpdk-next-eventdev (for-main) branch,
and organizes them in a patch series instead of individually.
Changes since V3:
Fix a CentOS79-64 build error
Changes since V2:
Fix a misleading if statement (guard error)
C
DLB supports 4 class of service domains, to aid in managing the
device bandwidth across ldb ports. This commit allows specifying
which ldb ports will participate in the COS scheme, which class
they are a part of, and the specific bandwidth percentage
associated with each class. The cumulative bandw
Enabling the weight limit on a CQ allows the enqueued QEs' 2-bit weight
value (representing weights of 1, 2, 4, and 8) to factor into whether a
CQ is full. If the sum of the weights of the QEs in the CQ meet or exceed
its weight limit, DLB will stop scheduling QEs to it (until software pops
enough
This patch rebases the following previously submitted
patches against the latest dpdk-next-eventdev (for-main) branch.
Rebase DLB2 port_cos and cq_weight patches
Changes since V2:
Fix a misleading if statement (guard error)
Changes since V1:
Fixed a bug in the port-specific cos patch where we we
DLB supports 4 class of service domains, to aid in managing the
device bandwidth across ldb ports. This commit allows specifying
which ldb ports will participate in the COS scheme, which class
they are a part of, and the specific bandwidth percentage
associated with each class. The cumulative bandw
Enabling the weight limit on a CQ allows the enqueued QEs' 2-bit weight
value (representing weights of 1, 2, 4, and 8) to factor into whether a
CQ is full. If the sum of the weights of the QEs in the CQ meet or exceed
its weight limit, DLB will stop scheduling QEs to it (until software pops
enough
This patch simply rebases the following previously submitted
patches against the latest dpdk-next-eventdev (for-main) branch.
Rebase DLB2 port_cos and cq_weight patches
This patch simply rebases the following previously submitted
patches against the latest dpdk-next-eventdev (for-main) branch.
C
This patch adds the basic NEON Rx path to the iavf driver. It does not
include scatter or flex varieties.
Tested on N1SDP platform with Intel XL710 NIC and 40G connection.
Tested with a single core and testpmd rxonly mode. Saw no significant
performance difference between scalar and Arm vPMD paths
This patch adds the basic NEON Rx path to iavf driver, including
the main Rx function (_recv_raw_pkts_vec) and the functions it depends on.
Also, NEON vector path has been added to iavf_set_rx_function. Functional
testing with testpmd (rxonly and mac forwarding) and l3fwd have been done
on N1SDP pl
> -Original Message-
> From: Zhang, Qi Z
> Sent: Tuesday, June 7, 2022 3:56 AM
> To: Zhang, Qi Z ; Kathleen Capella
> ; Wu, Jingjing ; Xing,
> Beilei ; Ruifeng Wang
> Cc: dev@dpdk.org; nd ; Honnappa Nagarahalli
> ; Dharmik Thakkar
>
> Subject: RE: [PATCH v2 1/1] net/iavf: add vector P
This meeting had a lot of book-keeping. In previous meetings we've had to
skip reviewing some action items due to time constraints. This meeting we
had time to review most of them, so we have a larger-than-normal "Review
Action Items" section.
Attendees
-
Owen Hilyard
-
Juraj Linke
Use generic GTP PSC header definition in raw handler.
Fixes: 9213c50e36fa ("app/testpmd: support GTP PSC option in raw sets")
cc: sta...@dpdk.org
Signed-off-by: Gregory Etelson
Reviewed-by: Viacheslav Ovsiienko
---
v2: fix raw GTP PSC object creation.
---
app/test-pmd/cmdline_flow.c | 20 +
Fix bitmap fields order in little endian section of GTP PSC headers.
Fixes: e8ca1479cdc4 ("net: add extension header for GTP PSC")
cc: sta...@dpdk.org
Signed-off-by: Gregory Etelson
Reviewed-by: Viacheslav Ovsiienko
---
v2:
---
lib/net/rte_gtp.h | 17 +
1 file changed, 9 insert
Add mlx5 internal option in testpmd run-time function "port attach" to
add another parameter named "mlx5_socket" for attaching port and add 2
devargs before.
The arguments are "cmd_fd" and "pd_handle" using to import device
created out of PMD. Testpmd application import it using IPC, and updates
t
Add mlx5 internal test for map and unmap external RxQs.
This patch adds to Testpmd app a runtime function to test the mapping
API.
For insert mapping use this command:
testpmd> port (port_id) ext_rxq map (rte_queue_id) (hw_queue_id)
For insert mapping use this command:
testpmd> port (port_i
Recently [1] mlx5 PMD added support for external queues, in the
following patches add internal tests for in Testpmd application.
[1]
https://patchwork.dpdk.org/project/dpdk/cover/20220224232511.3238707-1-michae...@nvidia.com/
Depends-on: series=112853 ("introduce per-queue available descriptor th
On 6/15/2022 3:57 PM, Kalesh A P wrote:
From: Somnath Kotur
The current combination of checks to determine whether autoneg is
enabled in the card is a bit convoluted and may become incorrect
as well in the future as one of the fields being used - auto_link_speed
might become deprecated.
Switch
On 6/15/2022 3:56 PM, Kalesh A P wrote:
From: Damodharam Ammepalli
Currently, we fail the init/probe of pmd if eth_dev->data->nb_tx_queues
or eth_dev->data->nb_rx_queues is 0. We are removing this check.
Is there a valid usecase for Rx only or Tx only config?
I assume testpmd doesn't suppo
On 6/15/2022 3:56 PM, Kalesh A P wrote:
CAUTION: This message has originated from an External Source. Please use proper
judgment and caution when opening attachments, clicking links, or responding to
this email.
From: Somnath Kotur
Currently the PMD tries to detect a potential 0 byte DMA by
Reproduced with "gcc (GCC) 13.0.0 20220616 (experimental)"
Build error:
In file included from ../drivers/net/qede/qede_debug.c:9:
../drivers/net/qede/qede_debug.c: In function ‘qed_grc_dump_addr_range’:
../drivers/net/qede/base/ecore.h:95:17:
warning: overflow in conversion fro
Hi Junfeng,
Thanks for the patch.
On 6/6/2022 3:09 PM, Junfeng Guo wrote:
1. add throughput statistics (in pps) for forward streams.
2. display the forward statistics for every forward stream.
v2:
add parameter descriptions and fix commit title.
Signed-off-by: Xiao Wang
Signed-off-by: Junfe
On Thu, 16 Jun 2022 17:10:46 +0200
David Marchand wrote:
> On Fri, Apr 15, 2022 at 5:27 AM Huichao Cai wrote:
> >
> > According to RFC791,the options may appear or not in datagrams.
> > They must be implemented by all IP modules (host and gateways).
> > What is optional is their transmission in
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/vhost/vhost.h | 2 --
lib/vhost/vhost_user.h | 1 -
2 files changed, 3 deletions(-)
diff --git a/lib/vhost/vhost.h b/lib/vhost/vhost.h
index 14235aaf81..4ebcb7448a 100644
--- a/lib/v
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/timer/rte_timer.c | 2 --
lib/timer/rte_timer.h | 2 --
2 files changed, 4 deletions(-)
diff --git a/lib/timer/rte_timer.c b/lib/timer/rte_timer.c
index c51a393e5c..d914fcbf60 100644
---
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/table/rte_swx_table_learner.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/table/rte_swx_table_learner.c
b/lib/table/rte_swx_table_learner.c
index f7f8e8aea9..3502cbd2a4 100644
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/stack/rte_stack.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/stack/rte_stack.h b/lib/stack/rte_stack.h
index 91fc570767..af8c3804f3 100644
--- a/lib/stack/rte_stack.h
+++ b/lib
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/sched/rte_pie.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/sched/rte_pie.c b/lib/sched/rte_pie.c
index d37b79e6dd..c84f75a18c 100644
--- a/lib/sched/rte_pie.c
+++ b/lib/sched/r
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/regexdev/rte_regexdev.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/regexdev/rte_regexdev.h b/lib/regexdev/rte_regexdev.h
index 3bce8090f6..ce3dba5c10 100644
--- a/lib/regexdev/
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/rawdev/rte_rawdev.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/rawdev/rte_rawdev.h b/lib/rawdev/rte_rawdev.h
index 14e8eb972f..66080eae9e 100644
--- a/lib/rawdev/rte_rawdev.h
+
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/power/power_pstate_cpufreq.c | 1 -
lib/power/rte_power_empty_poll.h | 3 ---
lib/power/rte_power_pmd_mgmt.c | 2 --
lib/power/rte_power_pmd_mgmt.h | 5 -
4 files changed, 11 delet
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/net/rte_net.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/net/rte_net.h b/lib/net/rte_net.h
index 53a7f4d360..56611fc8f9 100644
--- a/lib/net/rte_net.h
+++ b/lib/net/rte_net.h
@
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/meter/rte_meter.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/lib/meter/rte_meter.c b/lib/meter/rte_meter.c
index da01429a8b..4549b97d36 100644
--- a/lib/meter/rte_meter.c
+++ b/
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/mempool/rte_mempool.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/mempool/rte_mempool.h b/lib/mempool/rte_mempool.h
index 3ada37cb86..8d6554fbae 100644
--- a/lib/mempool/rte_mem
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/jobstats/rte_jobstats.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/jobstats/rte_jobstats.h b/lib/jobstats/rte_jobstats.h
index 023d9dd15c..45b460e603 100644
--- a/lib/jobstats/
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/ip_frag/ip_frag_internal.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/ip_frag/ip_frag_internal.c b/lib/ip_frag/ip_frag_internal.c
index b436a4c931..043b0ffba3 100644
--- a/lib/
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/hash/rte_cuckoo_hash.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/lib/hash/rte_cuckoo_hash.c b/lib/hash/rte_cuckoo_hash.c
index 490f94af4b..de7d941638 100644
--- a/lib/hash/rte_
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/gso/gso_common.c | 1 -
lib/gso/gso_common.h | 1 -
lib/gso/gso_tcp4.h| 1 -
lib/gso/gso_tunnel_tcp4.h | 1 -
lib/gso/gso_tunnel_udp4.h | 1 -
lib/gso/gso_udp4.h|
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/gpudev/gpudev.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/gpudev/gpudev.c b/lib/gpudev/gpudev.c
index 56033f4a5f..ee3ae80f82 100644
--- a/lib/gpudev/gpudev.c
+++ b/lib/gpudev/
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/ethdev/rte_class_eth.c | 2 --
lib/ethdev/rte_ethdev.c| 9 -
lib/ethdev/rte_ethdev.h| 1 -
lib/ethdev/rte_flow.c | 2 --
lib/ethdev/rte_flow.h | 3 ---
lib/ethdev
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/eal/common/eal_common_config.c | 1 -
lib/eal/common/eal_common_launch.c | 1 -
lib/eal/common/eal_common_log.c| 1 -
lib/eal/linux/eal.c| 1 -
lib/eal/linux/eal_thread
These header includes have been flagged by the iwyu_tool
and removed.
Signed-off-by: Sean Morrissey
---
lib/cmdline/cmdline_cirbuf.h| 1 -
lib/cmdline/cmdline_parse_num.c | 3 ---
lib/cmdline/cmdline_socket.c| 4
lib/cmdline/cmdline_socket.h| 1 -
4 files changed, 9 deletions(-)
This patchset removes unused header includes flagged
by the IWYU tool for the 22.07 release.
V2:
* Fix various build issues.
Sean Morrissey (19):
cmdline: remove unneeded header includes
eal: remove unneeded header includes
ethdev: remove unneeded header includes
gpudev: remove unneeded h
On Fri, Apr 15, 2022 at 5:27 AM Huichao Cai wrote:
>
> According to RFC791,the options may appear or not in datagrams.
> They must be implemented by all IP modules (host and gateways).
> What is optional is their transmission in any particular datagram,
> not their implementation.So we have to dea
On 6/16/2022 3:39 AM, Jin Liu wrote:
NFD is part of NFP firmware, and there only exist a NFD3 version
before this patch series.
This patch series mainly add the support of the new NFP3800 chip
use firmware with NFD3/NFDk.
* Changes since v1
- Added updated documentation for NFP to cover NFD.
- D
On 6/16/2022 3:39 AM, Jin Liu wrote:
Add support for a new type of NIC NFP3800 card, and update some
network card data acquisition interface functions.
Signed-off-by: Jin Liu
Signed-off-by: Diana Wang
Signed-off-by: Peng Zhang
Signed-off-by: Chaoyong He
Signed-off-by: Niklas Söderlund
---
On 6/16/2022 3:39 AM, Jin Liu wrote:
This set patches add support for a new type of NFP nic NFP3800 and
the firmware with NFDk.
Signed-off-by: Jin Liu
Signed-off-by: Chaoyong He
Signed-off-by: Niklas Söderlund
---
doc/guides/nics/nfp.rst | 10 ++
1 file changed, 6 insertions(+), 4
On 6/16/2022 3:39 AM, Jin Liu wrote:
Add support for a new type NFP NIC NFP3800 and firmware with NFDk.
Signed-off-by: Jin Liu
Signed-off-by: Chaoyong He
Signed-off-by: Niklas Söderlund
---
doc/guides/rel_notes/release_22_07.rst | 3 +++
1 file changed, 3 insertions(+)
diff --git a/doc/gu
On Thu, Jun 16, 2022 at 11:32 AM David Marchand
wrote:
>
> GCC 12 raises the following warning:
>
> In file included from ../lib/mempool/rte_mempool.h:46,
> from ../lib/mbuf/rte_mbuf.h:38,
> from ../lib/vhost/vhost_crypto.c:7:
> ../lib/vhost/vhost_crypto.c: In fun
GCC 12 raises the following warning:
In file included from ../lib/mempool/rte_mempool.h:46,
from ../lib/mbuf/rte_mbuf.h:38,
from ../lib/vhost/vhost_crypto.c:7:
../lib/vhost/vhost_crypto.c: In function ‘rte_vhost_crypto_fetch_requests’:
../lib/eal/x86/include/rte_m
https://bugs.dpdk.org/show_bug.cgi?id=1038
Bug ID: 1038
Summary: Illegal instruction found when running dpdk-test
(built with GCC 12.1) on CPU has no AVX instruction
set
Product: DPDK
Version: 21.11
Hard
On Thu, Jun 16, 2022 at 4:38 PM David Marchand
wrote:
>
> On Mon, May 16, 2022 at 1:16 PM wrote:
> > +static __rte_always_inline uint16_t
> > +virtio_dev_tx_async_split(struct virtio_net *dev, struct vhost_virtqueue
> > *vq,
> > + struct rte_mempool *mbuf_pool, struct rte_mbuf **pk
On Mon, May 16, 2022 at 1:16 PM wrote:
> +static __rte_always_inline uint16_t
> +virtio_dev_tx_async_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
> + struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts,
> uint16_t count,
> + int16_t dma_id, uint16_t vcha
> From: Mattias Rönnblom [mailto:hof...@lysator.liu.se]
> Sent: Thursday, 16 June 2022 15.58
>
> On 2022-06-16 08:44, Morten Brørup wrote:
> > +CC Olivier Matz , Network Headers maintainer
> >
> >> -Original Message-
> >> From: Morten Brørup
> >> Sent: den 15 juni 2022 16:41
> >> To: Emil
Title should start with net/ice/base:.
On Thu, Jun 16, 2022 at 12:35 PM wrote:
>
> From: Wenxuan Wu
>
> Gcc with -O2 flag, would retrieve the value in one time.
> This patch changed the type of fv_idx in struct ice_recp_grp_entry to
> align with its callers which is also u8 type.
>
> When u8 idx
[AMD Official Use Only - General]
We were having issues with iommu. Now we will try to push the patch without
iommu enabled. Will split patch into smaller ones and submit soon.
Thanks,
Selwin
-Original Message-
From: Thomas Monjalon
Sent: Wednesday, June 15, 2022 8:06 PM
To: Sebastian
DLB supports 4 class of service domains, to aid in managing the
device bandwidth across ldb ports. This commit allows specifying
which ldb ports will participate in the COS scheme, which class
they are a part of, and the specific bandwidth percentage
associated with each class. The cumulative bandw
Enabling the weight limit on a CQ allows the enqueued QEs' 2-bit weight
value (representing weights of 1, 2, 4, and 8) to factor into whether a
CQ is full. If the sum of the weights of the QEs in the CQ meet or exceed
its weight limit, DLB will stop scheduling QEs to it (until software pops
enough
This patch simply rebases the following previously submitted
patches against the latest dpdk-next-eventdev (for-main) branch.
Timothy McDaniel (2):
event/dlb2: add CQ weight support
event/dlb2: add ldb port specific COS support
drivers/event/dlb2/dlb2.c | 323 ++
The P4 language requires marking a header as valid before any of the
header fields are written as opposed to after the writes are done.
Hence, the optimization of replacing the sequence of instructions to
generate a header by reading it from the table action data with a
single DMA internal instruct
> From: Mattias Rönnblom [mailto:hof...@lysator.liu.se]
> Sent: Thursday, 16 June 2022 15.46
>
> On 2022-06-16 09:07, Morten Brørup wrote:
> > Hi Jasvinder,
> >
> > As the Packet CRC maintainer, have you considered adding vector
> > optimized variants of the rte_raw_cksum() function?
> >
>
> The
On 2022-06-16 08:32, Emil Berg wrote:
I've been sketching on an efficient solution to this. What about something
along the way below? I've run it with the combinations of:
even buf, even len
even buf, odd len
odd buf, even len
odd buf, odd len
and it seems to give the same results as the older
On 2022-06-16 08:44, Morten Brørup wrote:
+CC Olivier Matz , Network Headers maintainer
-Original Message-
From: Morten Brørup
Sent: den 15 juni 2022 16:41
To: Emil Berg ; bugzi...@dpdk.org
Cc: dev@dpdk.org
Subject: RE: [Bug 1035] __rte_raw_cksum() crash with misaligned pointer
From:
On 2022-06-16 09:07, Morten Brørup wrote:
Hi Jasvinder,
As the Packet CRC maintainer, have you considered adding vector
optimized variants of the rte_raw_cksum() function?
The current implementation is vectorized by the compiler.
In my experience, hand-crafting it using SIMD intrinsics doe
On Thu, Jun 16, 2022 at 12:40 PM wrote:
>
> From: Wenxuan Wu
>
> when n == 1000, and it would overflow the array size of 4 bytes with
> nul terminator. Change the logic to avoid this warning.
>
> Fixes: 15c431864000 ("app/flow-perf: add packet forwarding support")
> Cc: sta...@dpdk.org
> Signed-o
Hi David,
>-Original Message-
>From: David Marchand
>Sent: Thursday, June 16, 2022 3:00 PM
>To: Ankur Dwivedi ; Jerin Jacob Kollanukkaran
>
>Cc: Anoob Joseph ; Thomas Monjalon
>; Ferruh Yigit ; dpdk stable
>; dev ; Akhil Goyal
>Subject: Re: [EXT] Re: [PATCH 01/12] common/cpt: fix build w
On Mon, Jun 13, 2022 at 3:20 PM Rakesh Kudurumalla
wrote:
>
> inline device NIX RX and RQ stats are updated
> on PKTIO extra stats
>
> Signed-off-by: Rakesh Kudurumalla
Updated the git commit as follows and applied to
dpdk-next-net-mrvl/for-next-net. Thanks
common/cnxk: update extra stats f
From: Sunil Kumar Kori
Implement API to update VLAN table for pre-coloring for
incoming packet per nixlf for CN10K platform.
Depends-on: patch-23516 ("app/testpmd: support different input color method")
Signed-off-by: Sunil Kumar Kori
---
v2..v3:
- Fix dscp table runtime update error.
v1..v2
From: Sunil Kumar Kori
As per new spec in DPDK, VLAN priority is supported for
precoloring of input packet.
Depends-on: patch-23516 ("app/testpmd: support different input color method")
Signed-off-by: Sunil Kumar Kori
---
v2..v3:
- No changes.
v1..v2:
- Aligned with latest input color spec.
I've been sketching on an efficient solution to this. What about something
along the way below? I've run it with the combinations of:
even buf, even len
even buf, odd len
odd buf, even len
odd buf, odd len
and it seems to give the same results as the older version of __rte_raw_cksum,
before 21.0
Hi!
We want the B option, i.e. the 6 bytes option. Perhaps adding alignment
detection to __rte_raw_cksum() is a good idea.
A minor comment but I think buf & 1 won't work since buf isn't an integral
type, but something along that way.
I'm starting to think about an efficient way to do this.
Th
From: Wenxuan Wu
when n == 1000, and it would overflow the array size of 4 bytes with
nul terminator. Change the logic to avoid this warning.
Fixes: 15c431864000 ("app/flow-perf: add packet forwarding support")
Cc: sta...@dpdk.org
Signed-off-by: Wenxuan Wu
---
app/test-flow-perf/main.c | 2 +-
From: Wenxuan Wu
Gcc with -O2 flag, would retrieve the value in one time.
This patch changed the type of fv_idx in struct ice_recp_grp_entry to
align with its callers which is also u8 type.
When u8 idx[5] = a value u16 index[4], gcc12 would give this warning,
because it is not big enough to stor
Release status meeting minutes 2022-06-16
=
Agenda:
* Release Dates
* Subtrees
* Roadmaps
* LTS
* Defects
* Opens
Participants:
* ARM
* Intel
* Marvell
* Nvidia
* Red Hat
* Xilinx/AMD
Release Dates
-
The following are the proposed current dat
Please ignore this particular patch 12/12. It is already part of other
patch.
https://patchwork.dpdk.org/project/dpdk/patch/20220612175612.3101-1-pbhagavat...@marvell.com/
Thanks
Nithin
On 2022-06-16 2:54 PM, Nithin Dabilpuram wrote:
Offset timestamp data only when enabled on the port instead
From: Wenxuan Wu
when n == 1000, and it would be overflow the array size of 4 bytes with
nul terminator. Change the logic to avoid this warning.
Fixes: 15c431864000 ("app/flow-perf: add packet forwarding support")
Cc: sta...@dpdk.org
Signed-off-by: Wenxuan Wu
---
app/test-flow-perf/main.c | 2
From: Wenxuan Wu
when n == 1000, and it would be overflow the array size of 4 bytes with
nul terminator. Change the logic to avoid this warning.
Fixes: 15c431864000 ("app/flow-perf: add packet forwarding support")
Cc: sta...@dpdk.org
Signed-off-by: Wenxuan Wu
---
app/test-flow-perf/main.c | 2
From: Sunil Kumar Kori
Implement API to update VLAN table for pre-coloring for
incoming packet per nixlf for CN10K platform.
Depends-on: patch-23516 ("app/testpmd: support different input color method")
Signed-off-by: Sunil Kumar Kori
---
v1..v2:
- Aligned with latest input color spec.
driv
From: Sunil Kumar Kori
As per new spec in DPDK, VLAN priority is supported for
precoloring of input packet.
Depends-on: patch-23516 ("app/testpmd: support different input color method")
Signed-off-by: Sunil Kumar Kori
---
v1..v2:
- Aligned with latest input color spec.
drivers/common/cnxk/r
1 - 100 of 156 matches
Mail list logo