> -Original Message-
> From: Zhang, Qi Z
> Sent: Tuesday, October 19, 2021 7:15 PM
> To: Yigit, Ferruh ; Honnappa Nagarahalli
> ; Ruifeng Wang
> ; dev@dpdk.org; Min Hu (Connor)
> ; Yisen Zhuang ; Lijun
> Ou
> Cc: Xing, Beilei ; Richardson, Bruce
> ; jer...@marvell.com;
> hemant.agra...@nx
> -Original Message-
> From: Xueming Li
> Sent: Thursday, November 4, 2021 8:33 PM
> To: dev@dpdk.org
> Cc: Viacheslav Ovsiienko ; xuemi...@nvidia.com;
> Lior Margalit ; Matan Azrad ;
> David Christensen ; Ruifeng Wang
> ; Bruce Richardson
> ; Konstantin Ananyev
>
> Subject: [PATCH v4 14/
On Fri, Nov 5, 2021 at 12:21 PM Liu, Changpeng wrote:
>
> DPDK already provides pre_msg_handle and post_msg_handle to let vhost-backend
> to process
> the differences for different virtio devices. And it's not good idea to
> start all the virtio queues in SeaBIOS,
> we tried that long time ago.
DPDK already provides pre_msg_handle and post_msg_handle to let vhost-backend
to process
the differences for different virtio devices. And it's not good idea to start
all the virtio queues in SeaBIOS,
we tried that long time ago. I suggest you to submit a SPDK issue so that we
can take a look
> -Original Message-
> From: Wang, Jie1X
> Sent: Friday, November 5, 2021 11:37 AM
> To: dev@dpdk.org
> Cc: Zhang, Yuying ; Li, Xiaoyun
> ; Yang, SteveX ; Xing, Beilei
> ; Zhang, Qi Z ; Wang, Jie1X
> ; sta...@dpdk.org
> Subject: [PATCH v2] net/i40e: fix forward outer IPv6 VXLAN packets
Testpmd forwards packets in checksum mode that it need to calculate
the checksum of each layer's protocol. Then it will fill flags and
header length into mbuf.
In process_outer_cksums, HW calculates the outer checksum if
tx_offloads contains outer UDP checksum otherwise SW calculates
the outer che
> -Original Message-
> From: Wang, Jie1X
> Sent: Tuesday, November 2, 2021 3:08 PM
> To: dev@dpdk.org
> Cc: Zhang, Yuying ; Li, Xiaoyun
> ; Yang, SteveX ; Xing, Beilei
> ; Zhang, Qi Z ; Wang, Jie1X
> ; sta...@dpdk.org
> Subject: [PATCH] net/i40e: fix forward outer IPv6 VXLAN packets
>
Add Liu Changpeng.
On Thu, Oct 14, 2021 at 8:49 PM Li Feng wrote:
>
> Thanks,
> Feng Li
>
> On Thu, Oct 14, 2021 at 8:28 PM Maxime Coquelin
> wrote:
> >
> >
> >
> > On 10/14/21 14:12, Li Feng wrote:
> > > On Thu, Oct 14, 2021 at 8:01 PM Maxime Coquelin
> > > wrote:
> > >>
> > >> Hi Li,
> > >>
> -Original Message-
> From: stable On Behalf Of Ferruh Yigit
> Sent: Thursday, November 4, 2021 7:04 PM
> To: Thomas Monjalon ; Andrew Rybchenko
> ; Stephen Hemminger
> ; Matan Azrad
> Cc: Yigit, Ferruh ; dev@dpdk.org; sta...@dpdk.org;
> Matan Azrad
> Subject: [dpdk-stable] [PATCH] ethd
> -Original Message-
> From: stable On Behalf Of Anatoly Burakov
> Sent: Thursday, October 28, 2021 10:15 PM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org
> Subject: [dpdk-stable] [PATCH v3 3/4] vfio: fix documentation to match
> intended behavior
>
> On FreeBSD, `rte_vfio_is_enabled()` and `r
> -Original Message-
> From: dev On Behalf Of Anatoly Burakov
> Sent: Thursday, October 28, 2021 10:15 PM
> To: dev@dpdk.org; Richardson, Bruce
> Cc: sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH v3 2/4] vfio: fix wrong return value for FreeBSD
>
> On FreeBSD, `rte_vfio_clear_group()` was
Hi,
在 2021/11/4 22:55, Ferruh Yigit 写道:
On 11/2/2021 3:17 AM, Min Hu (Connor) wrote:
From: Chengwen Feng
This patch remove PF/VF duplicate code of:
1. get firmware version.
2. get device info.
3. rx interrupt related functions.
Signed-off-by: Chengwen Feng
Signed-off-by: Min Hu (Connor)
This patch adds a hns3_flow.h to make the code easier to maintain.
Signed-off-by: Huisong Li
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_ethdev.c| 1 +
drivers/net/hns3/hns3_ethdev.h| 3 +--
drivers/net/hns3/hns3_ethdev_vf.c | 1 +
drivers/net/hns3/hns3_fdir.h | 31
From: Huisong Li
This patch extracts a common file to store the common code for PF and VF
driver.
Signed-off-by: Huisong Li
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_cmd.c | 2 +-
drivers/net/hns3/hns3_common.c| 427 +
drivers/net/hns3/hn
From: Huisong Li
Fixing the return value of the function to clear static warning.
Signed-off-by: Huisong Li
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_common.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/hns3/hns3_common.c b/drivers/ne
From: Huisong Li
Removing magic numbers with macros.
Signed-off-by: Huisong Li
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_common.c | 4 ++--
drivers/net/hns3/hns3_common.h | 3 +++
2 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/net/hns3/hns3_common.c b/dr
From: Huisong Li
This patch modifies some code alignment issues to make the code style more
consistent.
Signed-off-by: Huisong Li
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_rxtx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/hns3/hns3_rxtx.c b/
From: Huisong Li
The patch obtains the upper 32 bits of the Rx/Tx queue DMA address in one
step instead of two steps.
Fixes: bba636698316 ("net/hns3: support Rx/Tx and related operations")
Signed-off-by: Huisong Li
---
drivers/net/hns3/hns3_rxtx.c | 4 ++--
1 file changed, 2 insertions(+), 2
From: Huisong Li
Bitwise operations should be used only with unsigned integer. This patch
modifies some code that does not meet this rule.
Signed-off-by: Huisong Li
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_ethdev.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
dif
From: Huisong Li
This patch removes a redundant function declaration for
hns3_rx_check_vec_support().
Signed-off-by: Huisong Li
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_rxtx.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/hns3/hns3_rxtx.h b/drivers/net/hns3/hn
This patch set contains refactor patches and code check patches.
Chengwen Feng (1):
net/hns3: remove PF/VF duplicate code
Huisong Li (7):
net/hns3: fix the shift of DMA address in Rx/Tx queue
net/hns3: remove a redundant function declaration
net/hns3: modifying code alignment
net/hns3:
> -Original Message-
> From: Burakov, Anatoly
> Sent: Monday, November 1, 2021 9:57 PM
> To: Xia, Chenbo ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3 1/4] vfio: drop fallback Linux
> implementation
>
> On 01-Nov-21 6:27 AM, Xia, Chenbo wrote:
> > Hi Anatoly,
> >
> >> -Original M
Set the 'present' parameter to 0 by default. It is configured by hardware,
users can set it to 1 for manual configuration.
Fixes: f611dada1af8 ("net/txgbe: update link setup process of backplane NICs")
Cc: sta...@dpdk.org
Signed-off-by: Jiawen Wu
---
doc/guides/nics/txgbe.rst | 2 +-
d
On Wed, Nov 3, 2021 at 9:10 AM Somnath Kotur wrote:
>
> The patch introduced by
> commit 657c2a7f1dd4 ("net/bnxt: create aggregation rings when needed")
> ended up shortening the return code path from the function thereby
> resulting in not executing the line of code at the end of the function
> t
Hi David:
Not sure if below patch also help to solve the issue you met on power
arch,
Looks like the error is same: "writing 1 byte into a region of size 0"
would you help to check?
commit 1b0f3a18145468c309bb5a8cb98a8aa29af059e7
Author: Ferruh Yigit
Date: Fri Oct 29 1
This patch fixes incorrect data lengths computation in cryptodev
unit test. Previously some data lengths were incorrectly set, which
was insensitive for crypto op unit tets but is critical for raw data
path API unit tests. The patch addressed the issue by setting the
correct data lengths for some t
This patch add-in sgl oop support in qat driver
Signed-off-by: Kai Ji
---
drivers/crypto/qat/dev/qat_crypto_pmd_gen3.c | 28 --
drivers/crypto/qat/dev/qat_crypto_pmd_gen4.c | 14 -
drivers/crypto/qat/dev/qat_sym_pmd_gen1.c| 55 +---
3 files changed, 83 insertions(
This patch unitfy all raw dp api into the qat pmd driver,
some qat generation specific are implemented respectively.
The qat_sym_hw_dp.c is removed as no longer required.
Signed-off-by: Kai Ji
---
drivers/common/qat/meson.build | 2 +-
drivers/crypto/qat/dev/qat_crypto_pmd_gen2.c
This patch update the newly comp dequeue process
response function pointer introduced in dequeue burst
Signed-off-by: Kai Ji
---
drivers/compress/qat/qat_comp_pmd.c | 12 +---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/drivers/compress/qat/qat_comp_pmd.c
b/drivers/com
This patch enable op_build_request func in qat enqueue op burst.
and qat_dequeue_process_response in qat dequeue op burst.
The op_build_request invoked in crypto build request op is based
on crypto operations setuped during session init.
Signed-off-by: Kai Ji
---
drivers/common/qat/qat_qp.c
This patch integrate all the functions from qat_asym_pmd.c
into qat_asym.c, The integration unify the asym crypto pmd apis
and should make it easier for furture maintains
Signed-off-by: Kai Ji
---
drivers/common/qat/meson.build| 2 +-
drivers/crypto/qat/qat_asym.c | 180 +++
This patch integrate all the functions from qat_sym_pmd.c into qat_sym.c,
The integration unify the sym crypto pmd apis and should make it easier
for furture maintains
Signed-off-by: Kai Ji
---
drivers/common/qat/meson.build | 2 +-
drivers/common/qat/qat_device.c | 2 +-
drivers/
This patch add-in specific asymmetric crypto session and build
op request implementation for QAT generations
Signed-off-by: Kai Ji
---
drivers/common/qat/qat_qp.c | 5 +-
drivers/crypto/qat/dev/qat_asym_pmd_gen1.c | 7 +
drivers/crypto/qat/dev/qat_crypto_pmd_gens.h | 3 +
The patch introduce set_session methods to qat gen dev ops
Replace min_qat_dev_gen_id with dev_id, the session will become
invalid if the device generation id is not matching during session
init and crypto ops
Signed-off-by: Kai Ji
---
drivers/crypto/qat/dev/qat_crypto_pmd_gen2.c | 87 ++-
This patch add-in specific symmetric crypto build op request
function pointer implementation for QAT generation 1
Signed-off-by: Kai Ji
---
drivers/crypto/qat/dev/qat_crypto_pmd_gens.h | 830 +++
drivers/crypto/qat/dev/qat_sym_pmd_gen1.c| 186 +
2 files changed, 1016 inse
This patch introduce build request op and dequeue op function
pointers to qat queue pair implementation. Those two functions
are used to be assigned during qat session generation based on
crypto operation
Signed-off-by: Kai Ji
---
drivers/common/qat/qat_qp.c | 8 +++--
drivers/common/q
This patch reworks QAT symmetric crypto datapatch implementation where each
generation request building separated and the crypto operation under the
raw datapath api implementation are unified.
In addtion this patchset also enables QAT OOP support in raw datapath api
implementation.
This patch de
Some other projects using meson may not be able to use DPDK
using the standard distribution pkg-config mechanism.
Meson supports a way to handle this via the subproject
https://mesonbuild.com/Subprojects.html
This patch adds the necessary dependency to follow the
"Naming convention for dependenc
Minutes of Technical Board Meeting, 2021-Nov-03
Members Attending
-
-Aaron
-Ferruh
-Hemant
-Honnappa
-Jerin
-Kevin
-Konstantin
-Maxime (Chair)
-Olivier
-Stephen
-Thomas
NOTE: The technical board meetings every second Wednesday at
https://meet.jit.si/DPDK at 3 pm UTC.
Meetings
The following changes since commit 54abd300d582f67367ae385d37d6e60d2a6d8b96:
pipeline: remove unreachable branch (2021-11-04 18:11:08 +0100)
are available in the Git repository at:
http://dpdk.org/git/next/dpdk-next-crypto
for you to fetch changes up to 44a9e58c37fe5630babee648bd2df894c359
> Added table to the crypto device drivers documentation
> stating the support of each PMD on Linux, FreeBSD and Windows.
>
> Signed-off-by: Tal Shnaiderman
>
> ---
> v2: add chacha20_poly1305 to the table [AkhilG]
Acked-by: Akhil Goyal
Applied to dpdk-next-crypto
Title updated.
> Konstantin Ananyev (2):
> bpf: fix doxygen comments
> bpf: fix convert API can be undefined
Applied, thanks.
> > > Subject: [PATCH v3] test/crypto: fix: test vectors for zuc 256 bit key
> > >
> > > Fix the test vectors added for zuc 256-bit key Add known vectors form
> > > ZUC 256 RFC.
> > >
> > > Fixes: fa5bf9345d4e (test/crypto: add ZUC cases with 256-bit keys)
> > >
> > > Signed-off-by: Vidya Sagar Vel
On 11/3/2021 7:20 PM, Apeksha Gupta wrote:
This patch series introduce the enetfec driver, ENETFEC
(Fast Ethernet Controller) is a network poll mode driver for
the inbuilt NIC found in the NXP i.MX 8M Mini SoC.
An overview of the enetfec driver with probe and remove are in patch 1.
Patch 2 desig
01/11/2021 13:49, Konstantin Ananyev:
> +/*
> + * RTE IP Fragmentation and Reassembly
RTE is not an entity, just a prefix.
Please use "DPDK" instead, or just drop "RTE".
> + * Implementation of IP packet fragmentation and reassembly.
> + */
> +
> +#include
> +
> +enum {
> + IP_LAST_FRAG_IDX,
On 11/3/2021 7:20 PM, Apeksha Gupta wrote:
This patch adds burst enqueue and dequeue operations to the enetfec
PMD. Loopback mode is also added, compile time flag 'ENETFEC_LOOPBACK' is
used to enable this feature. By default loopback mode is disabled.
Basic features added like promiscuous enable,
On 11/3/2021 7:20 PM, Apeksha Gupta wrote:
This patch adds Rx/Tx queue configuration setup operations.
On packet reception the respective BD Ring status bit is set
which is then used for packet processing.
Signed-off-by: Sachin Saxena
Signed-off-by: Apeksha Gupta
---
drivers/net/enetfec/enet
On 11/3/2021 7:20 PM, Apeksha Gupta wrote:
Implemented the fec-uio driver in kernel. enetfec PMD uses
UIO interface to interact with "fec-uio" driver implemented in
kernel for PHY initialisation and for mapping the allocated memory
of register & BD from kernel to DPDK which gives access to
non-ca
On 11/3/2021 7:20 PM, Apeksha Gupta wrote:
ENETFEC (Fast Ethernet Controller) is a network poll mode driver
for NXP SoC i.MX 8M Mini.
This patch adds skeleton for enetfec driver with probe function.
Signed-off-by: Sachin Saxena
Signed-off-by: Apeksha Gupta
---
v7:
- Fix compilation
- code
28/10/2021 13:51, Konstantin Ananyev:
> Promote rte_frag_table_del_expired_entries() function to stable.
> It was around for few years by now without any changes.
>
> Signed-off-by: Konstantin Ananyev
> ---
> lib/ip_frag/rte_ip_frag.h | 1 -
In general, the namespace in this file is wrong.
A lot
On 11/4/21 5:33 AM, Xueming Li wrote:
From: Viacheslav Ovsiienko
When receive packet, mlx5 PMD saves mbuf port number from
RxQ data.
To support shared RxQ, save port number into RQ context as user index.
Received packet resolve port number from CQE user index which derived
from RQ context.
On 11/4/21 5:33 AM, Xueming Li wrote:
This patch fixes stale field reference.
Fixes: a18ac6113331 ("net/mlx5: add metadata support to Rx datapath")
Cc: viachesl...@nvidia.com
Cc: sta...@dpdk.org
Signed-off-by: Xueming Li
Acked-by: Slava Ovsiienko
---
drivers/net/mlx5/mlx5_rxtx_vec_altive
On 10/26/21 12:08 AM, liaobiting wrote:
Hi: Please help to see this DPDK problem. And I want to know whether
i40e vf support promisc or not. Thanks a lot. From: liaobiting
Subject: Please help to see this DPDK
problem//Reply: DPDK 20.11 - i40evf: No ZjQcmQRYFpfptBannerStart
This Message Is
29/10/2021 20:53, David Marchand:
> On Fri, Oct 29, 2021 at 7:17 PM Jim Harris wrote:
> >
> > clang-13 rightfully complains that the tot_ppi
> > variable in update_stats is set but not used, since
> > the final accumulated tot_ppi results isn't used
> > anywhere. So just remove the tot_ppi variabl
> > A previous change blamed it on compiler/ASan, while this is a real
> > (yet minor) issue.
> >
> > This return -EINVAL is never reached since we test all combinations of
> > fidx and fcin booleans.
> > All branches end up with a return 0, factorize them.
> >
> > Fixes: 84f5ac9418ea ("pipeline:
On 11/3/2021 1:13 PM, Andrew Rybchenko wrote:
From: Viacheslav Galaktionov
MAE counters can be polled from a control thread if no service core is
allocated for this.
Signed-off-by: Viacheslav Galaktionov
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: David Marchand
28/10/2021 00:15, Yogesh Jangra:
> Fix minor dead code issue reported by Coverity.
>
> Coverity issue: 373653
> Fixes: e9d870 ("pipeline: add SWX pipeline tables")
>
> Signed-off-by: Yogesh Jangra
> Acked-by: Cristian Dumitrescu
Applied, thanks
04/11/2021 17:39, Medvedkin, Vladimir:
> >> 01/11/2021 11:55, Syam Prasad N Pearson:
> >>> /** Number of items per bucket. */
> >>> *#define RTE_HASH_BUCKET_ENTRIES 8*
> >>>
> >>> defined inside:
> >>> dpdk-20.11.3/dpdk-stable-20.11.3/lib/librte_hash /rte_cuckoo_hash.h
> >>>
> >>> Why does the libr
On 11/2/2021 1:13 PM, Andrew Rybchenko wrote:
Datapath queue is either Rx or Tx, so just one counter is sufficient
for doorbells. It can count Tx doorbells in the case of Tx queue and
Rx doorbells in the case of Rx queue.
Signed-off-by: Andrew Rybchenko
Applied to dpdk-next-net/main, thanks.
Hello,
On 04/11/2021 15:46, Kinsella, Ray wrote:
I would guess it - I would say it is related to cache alignment.
Assuming each entry is 8 bytes 😊
Ray K
-Original Message-
From: Thomas Monjalon
Sent: Thursday 4 November 2021 14:12
To: Syam Prasad N Pearson
Cc: us...@dpdk.org; dev@dp
On 11/4/2021 4:00 PM, Gregory Etelson wrote:
Flex item or flex parser is port infrastructure that allows
application to add support for a custom network header and
offload flows to match the header elements.
Flex item API adds FLEX flow item to RTE flows.
Signed-off-by: Gregory Etelson
F
On 11/2/2021 8:10 AM, Jiawen Wu wrote:
Fix specific length packet statistics caused by wrong register addresses.
Fixes: 24a4c76aff4d ("net/txgbe: add error types and registers")
Cc:sta...@dpdk.org
Signed-off-by: Jiawen Wu
Applied to dpdk-next-net/main, thanks.
Hi Usama,
On 04/11/2021 12:11, Walsh, Conor wrote:
From: dev On Behalf Of Usama Nadeem
Sent: Thursday 14 October 2021 19:43
To: tho...@monjalon.net
Cc: dev@dpdk.org; Usama Nadeem
Subject: [dpdk-dev] [PATCH v4] examples/l3fwd: ipv4 and udp/tcp cksum
verification through software
checks if ipv4
On 11/2/2021 8:10 AM, Jiawen Wu wrote:
Set the 'present' parameter to 0 by default. It is configured by hardware,
users can set it to 1 for manual configuration.
Fixes: f611dada1af8 ("net/txgbe: update link setup process of backplane NICs")
Cc: sta...@dpdk.org
Signed-off-by: Jiawen Wu
---
dr
Le 21-10-21 à 12:41, Xueming Li a écrit :
In current DPDK framework, all Rx queues is pre-loaded with mbufs for
incoming packets. When number of representors scale out in a switch
domain, the memory consumption became significant. Further more,
polling all ports leads to high cache miss, high lat
On Tue, 12 Oct 2021 13:49:59 +
"St Leger, Jim" wrote:
> DPDK Community:
>
> The Tech Board has provided great input on their preferences for a Userspace
> event. Some weeks back (I'm late getting the minutes out; my apologies) a
> small team (Bruce, Honnappa, Thomas, Jim, Ashley, Jill, Rac
04/11/2021 15:55, Thomas Monjalon:
> last changes to make this series "more acceptable":
> - RTE_SCHED_CMAN in rte_config.h, replacing RTE_SCHED_RED
> - test file listed in MAINTAINERS
> - few whitespaces fixed
Applied this last version.
The maintainers of this library didn't help really.
Review
From: Wojciech Liguzinski
Adding the PIE support for IP Pipeline
Signed-off-by: Wojciech Liguzinski
Acked-by: Cristian Dumitrescu
Acked-by: Jasvinder Singh
---
examples/ip_pipeline/tmgr.c | 138 +++-
1 file changed, 72 insertions(+), 66 deletions(-)
diff --gi
From: Wojciech Liguzinski
patch add support enable PIE or RED by
parsing config file.
Signed-off-by: Wojciech Liguzinski
Acked-by: Cristian Dumitrescu
Acked-by: Jasvinder Singh
---
examples/qos_sched/cfg_file.c | 121 +++-
examples/qos_sched/cfg_file.h | 5 +
examples/qos
From: Wojciech Liguzinski
Implement PIE based congestion management based on rfc8033.
The Proportional Integral Controller Enhanced (PIE) algorithm works
by proactively dropping packets randomly.
PIE is implemented as more advanced queue management is required to
address the bufferbloat problem
On 11/2/2021 3:17 AM, Min Hu (Connor) wrote:
From: Chengwen Feng
This patch remove PF/VF duplicate code of:
1. get firmware version.
2. get device info.
3. rx interrupt related functions.
Signed-off-by: Chengwen Feng
Signed-off-by: Min Hu (Connor)
<...>
+int
+hns3_dev_infos_get(struct rt
last changes to make this series "more acceptable":
- RTE_SCHED_CMAN in rte_config.h, replacing RTE_SCHED_RED
- test file listed in MAINTAINERS
- few whitespaces fixed
From: Wojciech Liguzinski
DPDK sched library is equipped with mechanism that secures it from the
bufferbloat problem
which is
On Thu, 4 Nov 2021 11:03:21 +
"Ananyev, Konstantin" wrote:
> Hi Ben,
>
> I also don’t think 64 is a common case here.
> For such cases we probably should think up some different approach for the
> reassembly table.
Larger values make it easier to DoS the IP fragment table.
See the Linux fr
I would guess it - I would say it is related to cache alignment.
Assuming each entry is 8 bytes 😊
Ray K
> -Original Message-
> From: Thomas Monjalon
> Sent: Thursday 4 November 2021 14:12
> To: Syam Prasad N Pearson
> Cc: us...@dpdk.org; dev@dpdk.org; Wang, Yipeng1
> ; Gobriel, Sameh ;
https://bugs.dpdk.org/show_bug.cgi?id=792
David Marchand (david.march...@redhat.com) changed:
What|Removed |Added
Resolution|--- |FIXED
Sta
> -Original Message-
> From: Thomas Monjalon
> Sent: Thursday, November 4, 2021 1:58 PM
> To: Singh, Jasvinder ; Dumitrescu, Cristian
> ; Liguzinski, WojciechX
>
> Cc: dev@dpdk.org; Ajmera, Megha ; Liguzinski,
> WojciechX
> Subject: Re: [dpdk-dev] [PATCH v23 1/3] sched: add PIE based
On 11/2/2021 1:38 AM, Min Hu (Connor) wrote:
This patch set contains bugfix and code optimization for multi
process of hns3 PMD.
Huisong Li (4):
net/hns3: decrease the count when secondary process exits
net/hns3: fix MP action register and unregister
net/hns3: fix lack of unregistering
On Thu, Nov 4, 2021 at 3:11 PM Maxime Coquelin
wrote:
> On 11/2/21 08:52, David Marchand wrote:
> > The device event interrupt handler was always freed.
> >
> > Bugzilla ID: 845
> > Fixes: c2bd9367e18f ("lib: remove direct access to interrupt handle")
> >
> > Signed-off-by: David Marchand
Tested-
On 11/2/2021 1:38 AM, Min Hu (Connor) wrote:
From: Huisong Li
The multi-process has the following problems:
1) After a port in primary process is closed, the mp action of the process
is unregistered. which will cause that other device in the primary
process cannot respond to requests fr
On Thu, Nov 4, 2021 at 3:16 PM Maxime Coquelin
wrote:
> On 11/3/21 12:16, David Marchand wrote:
> > rte_pci_unmap_device() needs intr_handle objects to unregister
> > callbacks.
> >
> > Bugzilla ID: 845
> > Fixes: d61138d4f0e2 ("drivers: remove direct access to interrupt handle")
> >
> > Signed-of
On Thu, Nov 4, 2021 at 3:00 PM Maxime Coquelin
wrote:
> On 11/2/21 19:40, David Marchand wrote:
> > Caught with ASan:
> > ==9727==ERROR: AddressSanitizer: stack-buffer-overflow on address
> >0x7f0daa2fc0d0 at pc 0x7f0daeefacb2 bp 0x7f0daa2fadd0 sp 0x7f0daa2fa578
> > READ of size 1 at 0x7f0daa2
On Tue, Nov 2, 2021 at 10:35 AM Jiang, YuX wrote:
> > -Original Message-
> > From: David Marchand
> > Sent: Tuesday, November 2, 2021 3:53 PM
> > To: dev@dpdk.org
> > Cc: Jiang, YuX ; Harman Kalra
> > Subject: [PATCH] eal: fix device hotplug
> >
> > The device event interrupt handler was
On 11/3/21 12:16, David Marchand wrote:
rte_pci_unmap_device() needs intr_handle objects to unregister
callbacks.
Bugzilla ID: 845
Fixes: d61138d4f0e2 ("drivers: remove direct access to interrupt handle")
Signed-off-by: David Marchand
---
drivers/bus/pci/pci_common.c | 17 +---
+Cc hash lib maintainers
01/11/2021 11:55, Syam Prasad N Pearson:
> Dear Sir/Madam,
> I am a developer trying to get familiar with the DPDK hash library. I tried
> to make and use a hash table successfully.
> During the development I came across a variable
>
> /** Number of items per bucket. */
>
On 11/2/21 08:52, David Marchand wrote:
The device event interrupt handler was always freed.
Bugzilla ID: 845
Fixes: c2bd9367e18f ("lib: remove direct access to interrupt handle")
Signed-off-by: David Marchand
---
lib/eal/linux/eal_dev.c | 12 +---
1 file changed, 9 insertions(+)
On Thu, Nov 4, 2021 at 12:27 PM Bing Zhao wrote:
>
> For an Ethernet RQ, packets received when receive WQEs are exhausted
> are dropped. This behavior prevents slow or malicious software
> entities at the host from affecting the network. While for hairpin
> cases, even if there is no software invo
The following changes since commit b5832a0d1524b31782eb04a6e8f95f952a7eed66:
regex/mlx5: prevent double setup of queue pair (2021-11-03 23:15:10 +0100)
are available in the Git repository at:
http://dpdk.org/git/next/dpdk-next-eventdev
for you to fetch changes up to 784cc4352850895706619044
On 11/2/21 19:40, David Marchand wrote:
Caught with ASan:
==9727==ERROR: AddressSanitizer: stack-buffer-overflow on address
0x7f0daa2fc0d0 at pc 0x7f0daeefacb2 bp 0x7f0daa2fadd0 sp 0x7f0daa2fa578
READ of size 1 at 0x7f0daa2fc0d0 thread T1
#0 0x7f0daeefacb1 (/lib64/libasan.so.5+0xbacb1
04/11/2021 12:03, Liguzinski, WojciechX:
> From: Wojciech Liguzinski
>
> Implement PIE based congestion management based on rfc8033.
>
> The Proportional Integral Controller Enhanced (PIE) algorithm works
> by proactively dropping packets randomly.
> PIE is implemented as more advanced queue man
On Tue, Nov 2, 2021 at 9:59 PM Jerin Jacob wrote:
>
> On Tue, Nov 2, 2021 at 9:31 PM Thomas Monjalon wrote:
> >
> > 02/11/2021 16:49, jer...@marvell.com:
> > > From: Jerin Jacob
> > >
> > > All deprecation notice targeted for v21.11 of eventdev has been
> > > committed in the following commits,
> checks if ipv4 and udptcp cksum offload capability available
> If not available, cksum is verified through software
> If cksum is corrupt, packet is dropped, rest of the packets
> are forwarded back.
>From what I see right now l3fwd:
a) enables HW RX cksum offload
b) simply ignores HW pro
On 11/3/21 14:57, Vijay Srivastava wrote:
This patch series introduces vDPA driver for Xilinx devices.
The Xilinx vDPA (vhost data path acceleration) provides
support for the Xilinx SN1022 SmartNICs.
Vijay Kumar Srivastava (10):
vdpa/sfc: introduce Xilinx vDPA driver
vdpa/sfc: add suppo
04/11/2021 12:03, Ferruh Yigit:
> On 11/3/2021 10:48 PM, Ferruh Yigit wrote:
> > Old macros kept for backward compatibility, but this cause old macro
> > usage to sneak in silently.
> >
> > Marking old macros as deprecated. Downside is this will cause some noise
> > for applications that are using
On 11/4/2021 11:27 AM, Gregory Etelson wrote:
RTE flow API defines two flow elements types - common and PMD private.
Common RTE flow types are defined in rte_flow.h while PMD private
types exists inside specific PMD only. Application can create a flow
rule with PMD private items or actions. RTE f
On Sun, Oct 31, 2021 at 6:47 PM Jerin Jacob wrote:
>
> On Sat, Oct 30, 2021 at 10:49 PM Mattias Rönnblom
> wrote:
> >
> > On 2021-10-29 17:17, Jerin Jacob wrote:
> > > On Fri, Oct 29, 2021 at 8:33 PM Mattias Rönnblom
> > > wrote:
> > >> On 2021-10-29 16:38, Jerin Jacob wrote:
> > >>> On Tue, Oct
On 11/4/2021 12:23 PM, Gregory Etelson wrote:
Use `__rte_unused` macro to mask a debug variable instead of `#ifdef`.
This way, if the variable is used in a macro, it does not depend on
how the macro is expanded.
Fixes: 91f0e029ce5f ("net/mlx5: translate flex item pattern into matcher")
Signed-of
On Fri, Oct 29, 2021 at 8:48 PM David Marchand
wrote:
>
> On Fri, Oct 29, 2021 at 7:17 PM Jim Harris wrote:
> >
> > clang-13 rightfully complains that the total_mem
> > variable in eal_parse_socket_arg is set but not
> > used, since the final accumulated total_mem
> > result isn't used anywhere.
> -Original Message-
> From: Akhil Goyal
> Sent: Thursday, November 4, 2021 10:53 AM
> To: Vidya Sagar Velumuri ; Ankur Dwivedi
> ; Anoob Joseph ; Tejasree
> Kondoj ; Nithin Kumar Dabilpuram
> ; Zhang, Roy Fan ; De
> Lara Guarch, Pablo
> Cc: dev@dpdk.org
> Subject: RE: [PATCH v3] test/
On 11/3/2021 9:31 AM, Tudor Cornea wrote:
The poll call can return POLLERR which is ignored, or it can return
POLLOUT, even if there are no free frames in the mmap-ed area.
We can account for both of these cases by re-checking if the next
frame is empty before writing into it.
We have attempted
On 10/29/2021 4:33 PM, Andrew Rybchenko wrote:
From: Igor Romanov
Add the device and vendor numbers to the PCI ID map so
that a VF can be probed.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
Updated patch title as:
net/sfc: support Xilinx Riverhead VF
Applied to dpdk-next-n
1 - 100 of 173 matches
Mail list logo
