Hi, dapengx,
Why not free internals->kvlist at the end of "bond_ethdev_configure" ?
Does it call some bugs?
在 2021/9/15 13:08, dapengx...@intel.com 写道:
From: Dapeng Yu
If the bond device was created by vdev mode, the kvlist was not free
after the bond device was closed.
This patch fixes it
Hi Xuan,
> -Original Message-
> From: Ding, Xuan
> Sent: Thursday, September 9, 2021 1:58 PM
> To: dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo
>
> Cc: Hu, Jiayu ; cheng.ji...@intel.com; Richardson, Bruce
> ; Pai G, Sunil ; Ding, Xuan
>
> Subject: [PATCH] vhost: add unsafe API
Add test cases for zuc 256 bit key.
Add test case for zuc 8 and 16 byte digest with 256 bit key mode
Signed-off-by: Vidya Sagar Velumuri
diff --git a/app/test/test_cryptodev.c b/app/test/test_cryptodev.c
index 16d770a17f..27dd3355b2 100644
--- a/app/test/test_cryptodev.c
+++ b/app/test/test_cryp
Add support for 256 bit key length for ZUC in crpto_cn10k PMD.
Add support for digest length of 8 and 16 bytes for ZUC with 256 bit
key length.
Signed-off-by: Vidya Sagar Velumuri
diff --git a/doc/guides/rel_notes/release_21_11.rst
b/doc/guides/rel_notes/release_21_11.rst
index 3fa8018695..7422
Set proper bits in the context based on key length for PDCP
Signed-off-by: Vidya Sagar Velumuri
diff --git a/drivers/common/cnxk/roc_se.c b/drivers/common/cnxk/roc_se.c
index 03fbc5f2f7..4edbc8e547 100644
--- a/drivers/common/cnxk/roc_se.c
+++ b/drivers/common/cnxk/roc_se.c
@@ -160,6 +160,13 @@
This patch defines new RSS offload types for IPv4 and
L4(TCP/UDP/SCTP) checksum, which are required when users want
to distribute packets based on the IPv4 or L4 checksum field.
For example "flow create 0 ingress pattern eth / ipv4 / end
actions rss types ipv4-chksum end queues end / end", this fl
The E810 supports four single-ended GPIO signals (SDP[20:23]). The 1PPS
signal outputs via SDP[20:23], which is measured by an oscilloscope.
This feature can be turned by a devargs which can select GPIO pin index
flexibly. Pin index 0 means SDP20, pin index 1 means SDP21 and so on.
The example for
From: Dapeng Yu
If the bond device was created by vdev mode, the kvlist was not free
after the bond device was closed.
This patch fixes it.
Fixes: 144dc4739975 ("net/bonding: fix leak on remove")
Cc: sta...@dpdk.org
Signed-off-by: Dapeng Yu
---
drivers/net/bonding/rte_eth_bond_pmd.c | 5 +++-
Like for python, multiline statements in meson must either use a
backslash character (explicit continuation) or be enclosed in ()
(implicit continuation).
python PEP8 recommends the latter [1], and it looks like meson had
an issue with backslash before 0.50 [2].
1: https://www.python.org/dev/peps
Currently compress, decompress and dma are allowed only when all 3
capabilities are on.
A case where the user wants decompress offload, if decompress capability
is on but one of compress, dma is off, is not allowed.
Split compress/decompress/dma support check to allow partial
transformations.
V2:
A new configuration MMO was added to QP Context.
If set, MMO WQEs are supported on this QP.
For DMA MMO, supported only when dma_mmo_qp==1.
For REGEXP MMO, supported only when regexp_mmo_qp==1.
For COMPRESS MMO, supported only when compress_mmo_qp==1.
For DECOMPRESS MMO, supported only when decompr
The mlx5 PMD for regex class uses an MMO WQE operated by the GGA engine
in BF devices.
Currently, all the MMO WQEs are managed by the SQ object.
Starting from BF3, the queue of the MMO WQEs should be connected to the
GGA engine using a new configuration, MMO, that will be supported only
in the QP o
The mlx5 PMD for compress class uses an MMO WQE operated by the GGA
engine in BF devices.
Currently, all the MMO WQEs are managed by the SQ object.
Starting from BF3, the queue of the MMO WQEs should be connected to the
GGA engine using a new configuration, MMO, that will be supported only
in the Q
New MMO HCA capabilities were added and others were renamed.
Align hca capabilities with new prm.
Add support in devx interface for changes in HCA capabilities.
Signed-off-by: Raja Zidane
Acked-by: Matan Azrad
---
drivers/common/mlx5/mlx5_devx_cmds.c | 15 ---
drivers/common/mlx5/ml
The mlx5 PMDs for compress and regex classes use an MMO WQE operated by
the GGA engine in BF devices.
Currently, all the MMO WQEs are managed by the SQ object.
Starting from BF3, the queue of the MMO WQEs should be connected to the
GGA engine using a new configuration, mmo, that will be supported o
Currently drivers using QP (vDPA, crypto and compress, regex soon)
manage their memory, creation, modification and destruction of the QP,
in almost identical code.
Move QP memory management, creation and destruction to common.
Add common function to change QP state to RTS.
Add user_index attribute
> -Original Message-
> From: Zhang, RobinX
> Sent: Wednesday, September 15, 2021 11:10 AM
> To: dev@dpdk.org
> Cc: Wang, Haiyue ; Xing, Beilei
> ; m...@ashroe.eu; Wu, Jingjing
> ; Burakov, Anatoly ;
> Zhang, Qi Z ; Guo, Junfeng ;
> Yang, SteveX ; Zhang, RobinX
>
> Subject: [PATCH v5 0/
Hi,
> -Original Message-
> From: Ma, WenwuX
> Sent: Tuesday, September 7, 2021 4:49 AM
> To: dev@dpdk.org
> Cc: maxime.coque...@redhat.com; Xia, Chenbo ; Jiang,
> Cheng1 ; Hu, Jiayu ; Pai G, Sunil
> ; Yang, YvonneX ; Ma, WenwuX
>
> Subject: [PATCH 4/4] examples/vhost: support vhost async
> -Original Message-
> From: dev On Behalf Of Qiming Chen
> Sent: Friday, September 10, 2021 4:32 PM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Wu, Jingjing
> ;
> Qiming Chen ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH v2] net/iavf: fix mbuf leak
>
> In the iavf_dev_rx_queue_start fun
As announced in the deprecation note, i40evf has been removed. So removing
deprecation notice and other i40evf related documentation.
Signed-off-by: Robin Zhang
---
doc/guides/howto/lm_bond_virtio_sriov.rst | 4 ++--
doc/guides/nics/intel_vf.rst | 8 +---
doc/guides/rel_notes/de
Due to i40evf will be removed, so there's no need to keep the devargs
option "driver=i40evf" in iavf.
Signed-off-by: Robin Zhang
---
drivers/net/iavf/iavf_ethdev.c | 52 ++
1 file changed, 2 insertions(+), 50 deletions(-)
diff --git a/drivers/net/iavf/iavf_ethdev
The default VF driver for Intel 700 Series Ethernet Controller already
switch to iavf in DPDK 21.05. And i40evf is no need to maintain now,
so remove i40evf related code.
Signed-off-by: Robin Zhang
---
drivers/net/i40e/i40e_ethdev.h|1 -
drivers/net/i40e/i40e_ethdev_vf.c | 3006 -
In DPDK 21.05, iavf already became the default VF for i40e devices.
So remove i40evf due to it's no need to maintain now.
v5:
- rebase code.
v4:
- resolve compile warning issue.
v3:
- remove VF related code in i40e_rxtx.c.
v2:
- update 21.11 release note, remove some missed documentation.
Robi
> -Original Message-
> From: dev On Behalf Of Qiming Chen
> Sent: Friday, September 10, 2021 3:49 PM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Wu, Jingjing
> ;
> Qiming Chen ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/iavf: fix vf probe resource leak
>
> During the port probe pr
> -Original Message-
> From: Ma, WenwuX
> Sent: Tuesday, September 7, 2021 4:49 AM
> To: dev@dpdk.org
> Cc: maxime.coque...@redhat.com; Xia, Chenbo ; Jiang,
> Cheng1 ; Hu, Jiayu ; Pai G, Sunil
> ; Yang, YvonneX ; Ma, WenwuX
>
> Subject: [PATCH 3/4] examples/vhost: use a new API to query r
Hi,
> -Original Message-
> From: Ma, WenwuX
> Sent: Tuesday, September 7, 2021 4:49 AM
> To: dev@dpdk.org
> Cc: maxime.coque...@redhat.com; Xia, Chenbo ; Jiang,
> Cheng1 ; Hu, Jiayu ; Pai G, Sunil
> ; Yang, YvonneX ; Ma, WenwuX
>
> Subject: [PATCH 2/4] examples/vhost: refactor vhost enqu
Hi,
> -Original Message-
> From: Ma, WenwuX
> Sent: Tuesday, September 7, 2021 4:49 AM
> To: dev@dpdk.org
> Cc: maxime.coque...@redhat.com; Xia, Chenbo ; Jiang,
> Cheng1 ; Hu, Jiayu ; Pai G, Sunil
> ; Yang, YvonneX ; Wang, YuanX
> ; Ma, WenwuX ; Wang, Yinan
>
> Subject: [PATCH 1/4] vhost
> -Original Message-
> From: dev On Behalf Of Qiming Chen
> Sent: Saturday, September 11, 2021 10:08 AM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Wu, Jingjing
> ;
> Qiming Chen ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/iavf: fix rxq buf size alignment
>
> The RTE_ALIGN macro i
> -Original Message-
> From: dev On Behalf Of Qiming Chen
> Sent: Monday, September 13, 2021 11:40 AM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Wu, Jingjing
> ;
> Qiming Chen ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/iavf: fix queue start failed
>
> In the iavf_dev_start funct
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, September 14, 2021 10:01 PM
> To: Zhang, AlvinX ; Zhang, Qi Z
> ; Guo, Junfeng
> Cc: dev@dpdk.org; Ajit Khaparde ; Singh,
> Aman Deep
> Subject: Re: [dpdk-dev] [PATCH v7] ethdev: add IPv4 and L4 checksum RSS
> offload types
>
>
> -Original Message-
> From: dev On Behalf Of
> chenqiming_hua...@163.com
> Sent: Saturday, August 21, 2021 4:14 PM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Qiming Chen
> ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/i40e: fix vf resource leakage problem
>
> From: Qiming Chen
>
> -Original Message-
> From: dev On Behalf Of Qiming Chen
> Sent: Saturday, September 11, 2021 9:47 AM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Wu, Jingjing
> ;
> Qiming Chen ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/iavf: fix mbuf leak
>
> A local test found that repeated po
Add Intel Ethernet Virtual Function device IDs to netuio inf file
to support Intel 40GbE and 100GbE deives on Windows VM.
Signed-off-by: Pallavi Kadam
Reviewed-by: Ranjit Menon
---
windows/netuio/netuio.inf | 12
1 file changed, 12 insertions(+)
diff --git a/windows/netuio/netuio.
On Tue, 14 Sep 2021 22:22:04 +
"Ananyev, Konstantin" wrote:
> >
> > From: usamanadeem321
> >
> > Checks if IPV4, UDP and TCP Checksum offloads are available.
> > If not available, prints a warning message.
> >
> > Bugzilla ID: 545
> > Signed-off-by: usamanadeem321
> > ---
> > examples/l
On 8/25/2021 1:34 AM, Robin Zhang wrote:
For VF hosted by Intel 700 series NICs, internal rx interrupt and adminq
interrupt share the same source, that cause a lot cpu cycles be wasted on
interrupt handler on rx path.
The patch disable pci interrupt and remove the interrupt handler, replace
it
>
> From: usamanadeem321
>
> Checks if IPV4, UDP and TCP Checksum offloads are available.
> If not available, prints a warning message.
>
> Bugzilla ID: 545
> Signed-off-by: usamanadeem321
> ---
> examples/l3fwd/main.c | 22 +-
> 1 file changed, 21 insertions(+), 1 dele
On Tue, Sep 14, 2021 at 9:50 AM Thomas Monjalon wrote:
>
> 14/09/2021 18:34, Ferruh Yigit:
> > On 9/14/2021 8:56 AM, Thomas Monjalon wrote:
> > > From: Asaf Penso
> > >
> > > Adding more information about the release milestones.
> > > This includes the scope of change, expectations, etc.
> > >
>
On Tue, Sep 14, 2021 at 12:53 AM Thomas Monjalon wrote:
>
> 03/09/2021 17:35, Ferruh Yigit:
> > On 9/3/2021 12:50 PM, Thomas Monjalon wrote:
> > > 02/09/2021 18:33, Ferruh Yigit:
> > >> On 8/26/2021 11:11 AM, Thomas Monjalon wrote:
> > >>> +* Any issue found in -rc1 should be fixed.
> > >>> +
> >
The arguments of actions that are learned are now specified as part of
the learn instruction as opposed to being statically specified as part
of the learner table configuration.
Signed-off-by: Cristian Dumitrescu
---
Depends-on: series-18878 ("[V3,01/24] pipeline: move data structures to
internal
Similar comments that I have to patch 2/2
>
> Rx descriptor is 16B/32B in size and consists of multiple words.
> The word that includes DD field should be read first. Read result with DD bit
> set indicates the rest part in a descriptor is valid.
Suggest rewording as follows:
Rx descriptor is 16
On Tue, 14 Sep 2021 23:08:27 +0500
Usama Nadeem wrote:
> +
> + if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_UDP_CKSUM)
> + local_port_conf.rxmode.offloads |=
> + DEV_RX_OFFLOAD_UDP_CKSUM;
> +
> + else
> + printf(
On 9/14/21 12:10 AM, David Marchand wrote:
On Fri, Sep 10, 2021 at 6:54 PM Pablo de Lara
wrote:
rte_efd_create() function was using uint8_t for a socket bitmask,
for one of its parameters.
This limits the maximum of NUMA sockets to be 8.
Changing to to uint64_t increases it to 64, which sho
From: usamanadeem321
Checks if IPV4, UDP and TCP Checksum offloads are available.
If not available, prints a warning message.
Bugzilla ID: 545
Signed-off-by: usamanadeem321
---
examples/l3fwd/main.c | 22 +-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/exam
>
> Rx descriptor is 16B/32B in size and consists of multiple words.
> The word that includes DD field should be read first. Read result with DD bit
> set indicates the rest part in a descriptor is valid.
Suggest rewording as follows:
Rx descriptor is 16B/32B in size. If the DD bit is set, it in
On 14/09/2021 09:05, David Marchand wrote:
On Mon, Sep 13, 2021 at 8:47 PM Ben Pfaff wrote:
This is probably due to conversion from ms word to rst format.
Fixes: fc1f2750a3ec ("doc: programmers guide")
Cc: sta...@dpdk.org
Signed-off-by: Ben Pfaff
Reviewed-by: David Marchand
Acke
14/09/2021 18:51, Ajit Khaparde:
> On Tue, Sep 14, 2021 at 9:50 AM Thomas Monjalon wrote:
> >
> > 14/09/2021 18:34, Ferruh Yigit:
> > > On 9/14/2021 8:56 AM, Thomas Monjalon wrote:
> > > > From: Asaf Penso
> > > >
> > > > Adding more information about the release milestones.
> > > > This includes
> -Original Message-
> From: John Levon
> Sent: 14 сентября 2021 г. 15:48
> To: Dmitry Kozlyuk
> Cc: dev@dpdk.org; Anatoly Burakov ; Slava
> Ovsiienko
> Subject: Re: [PATCH v3 1/3] eal/linux: make hugetlbfs analysis reusable
>
> External email: Use caution opening links or attachments
>
Since the addition of support for runtime queue setup,
receive queues that are started by default no longer
have the correct state. Fix this by setting the state
when a port is started.
Fixes: 0105ea1296c9 ("net/bnxt: support runtime queue setup")
Signed-off-by: Lance Richardson
Reviewed-by: Ajit
14/09/2021 18:34, Ferruh Yigit:
> On 9/14/2021 8:56 AM, Thomas Monjalon wrote:
> > From: Asaf Penso
> >
> > Adding more information about the release milestones.
> > This includes the scope of change, expectations, etc.
> >
> > Signed-off-by: Asaf Penso
> > Signed-off-by: Thomas Monjalon
> > A
14/09/2021 18:11, Ajit Khaparde:
> On Tue, Sep 14, 2021 at 12:53 AM Thomas Monjalon wrote:
> > 03/09/2021 17:35, Ferruh Yigit:
> > > On 9/3/2021 12:50 PM, Thomas Monjalon wrote:
> > > > 02/09/2021 18:33, Ferruh Yigit:
> > > >> On 8/26/2021 11:11 AM, Thomas Monjalon wrote:
> > > >>> +* Any issue fo
On 9/14/2021 5:17 PM, Andrew Rybchenko wrote:
> On 9/14/21 6:52 PM, Ferruh Yigit wrote:
>> On 8/31/2021 5:12 PM, Andrew Rybchenko wrote:
>>> From: Viacheslav Galaktionov
>>>
>>> Make it simpler to debug configurations and code related to the representor
>>> info API.
>>>
>>> Signed-off-by: Viaches
On 9/14/2021 8:56 AM, Thomas Monjalon wrote:
> From: Asaf Penso
>
> Adding more information about the release milestones.
> This includes the scope of change, expectations, etc.
>
> Signed-off-by: Asaf Penso
> Signed-off-by: Thomas Monjalon
> Acked-by: John McNamara
> Acked-by: Ajit Khaparde
On 9/14/21 6:52 PM, Ferruh Yigit wrote:
> On 8/31/2021 5:12 PM, Andrew Rybchenko wrote:
>> From: Viacheslav Galaktionov
>>
>> Make it simpler to debug configurations and code related to the representor
>> info API.
>>
>> Signed-off-by: Viacheslav Galaktionov
>> Signed-off-by: Andrew Rybchenko
>>
On 9/1/2021 12:17 PM, Kinsella, Ray wrote:
>
>
> On 01/09/2021 09:53, Ferruh Yigit wrote:
>> On 9/1/2021 8:08 AM, Andrew Rybchenko wrote:
>>> On 9/1/21 4:50 AM, Xiaoyun Li wrote:
Remove the experimental tag for rte_eth_dev_rx_intr_ctl_q_get_fd API
that was introduced in 18.11 and have b
Add support for dicts of dicts to telemetry library.
Increase the max string size to 128.
Signed-off-by: Declan Doherty
Signed-off-by: Radu Nicolau
---
app/test/test_telemetry_data.c | 29
lib/telemetry/rte_telemetry.h | 2 +-
lib/telemetry/telemetry.c | 48 +
On 8/31/2021 5:12 PM, Andrew Rybchenko wrote:
> From: Viacheslav Galaktionov
>
> Make it simpler to debug configurations and code related to the representor
> info API.
>
> Signed-off-by: Viacheslav Galaktionov
> Signed-off-by: Andrew Rybchenko
> Reviewed-by: Andy Moreton
> ---
> v2:
> -
Hi Radu,
Thanks for adding the test, one more comment inline that I have just noticed.
>-Original Message-
>From: Nicolau, Radu
>Sent: Friday 10 September 2021 12:28
>To: Power, Ciara
>Cc: dev@dpdk.org; Richardson, Bruce ; Nicolau,
>Radu ; Doherty, Declan
>
>Subject: [PATCH v2] telemet
Update mbuf.l2_len with L2 header size for outbound
inline processing.
This patch also fixes a bug in arg parsing.
Signed-off-by: Nithin Dabilpuram
Acked-by: Akhil Goyal
---
examples/ipsec-secgw/ipsec-secgw.c | 2 ++
examples/ipsec-secgw/ipsec_worker.c | 41 --
Currently rte_security_set_pkt_metadata() and rte_security_get_userdata()
methods to set pkt metadata on Inline outbound and get userdata
after Inline inbound processing is always driver specific callbacks.
For drivers that do not have much to do in the callbacks but just
to update metadata in rte
Not all net PMD's/HW can parse packet and identify L2 header and
L3 header locations on Tx. This is inline with other Tx offloads
requirements such as L3 checksum, L4 checksum offload, etc,
where mbuf.l2_len, mbuf.l3_len etc, needs to be set for HW to be
able to generate checksum. Since Inline IPSe
Improvements to Inline inbound and outbound processing fast path routines
rte_security_set_pkt_metadata() and rte_security_get_userdata() to make
them inline functions and also provide mechanism for drivers to support
fast userdata and metadata access instead of driver specific per-pkt
function cal
https://bugs.dpdk.org/show_bug.cgi?id=809
Bug ID: 809
Summary: KNI request overwritten with new asynchronous
kni_net_release mechanism
Product: DPDK
Version: 21.11
Hardware: x86
OS: Linux
Status:
Memory allocator performance is crucial to applications that deal
with large amount of memory or allocate frequently. DPDK allocator
performance is affected by EAL options, API used and, at least,
allocation size. New autotest is intended to be run with different
EAL options. It measures performanc
get_hugepage_dir() searched for a hugetlbfs mount with a given page size
using handcraft parsing of /proc/mounts and mixing traversal logic with
selecting the needed entry. Separate code to enumerate hugetlbfs mounts
to eal_hugepage_mount_walk() taking a callback that can inspect already
parsed ent
From: Viacheslav Ovsiienko
The primary DPDK process launch might take a long time if initially
allocated memory is large. From practice allocation of 1 TB of memory
over 1 GB hugepages on Linux takes tens of seconds. Fast restart
is highly desired for some applications and launch delay presents
a
Hugepage allocation from the system takes time, resulting in slow
startup or sporadic delays later. Most of the time spent in kernel
is zero-filling memory for security reasons, which may be irrelevant
in a controlled environment. The bottleneck is memory access speed,
so for speeduup the amount of
Hi Ferruh,
>
> Overall this enables us hiding the ethdev internals, which is good. But it
> duplicates most of the datapath function (rx burst for this patch) per each
> PMD ops.
Yes, same as right now rte_eth_rx/tx_burst() code can be duplicated in dozen
places
inside user-level code. And
On 8/31/2021 10:52 AM, Alvin Zhang wrote:
> This patch defines new RSS offload types for IPv4 and
> L4(TCP/UDP/SCTP) checksum, which are required when users want
> to distribute packets based on the IPv4 or L4 checksum field.
>
> For example "flow create 0 ingress pattern eth / ipv4 / end
> action
20/08/2021 18:08, William Tu:
> On Thu, Aug 19, 2021 at 4:15 PM Dmitry Kozlyuk
> wrote:
> >
> > Windows EAL depends on some system libraries. They were linked using
> > add_project_link_arguments('-l'), which prevented meson from adding
> > them to Libs.private of pkg-config file. As a result, ap
On 8/28/2021 10:47 AM, Qiming Chen wrote:
> When the pcap port is probed, the size of the pcap message buffer is not
> set, the default is 2M, and then this value has a great impact on the
> message forwarding performance. Therefore, parameters are provided for
> users to set.
>
Hi Qiming,
I ass
Hi Jerin,
> > NOTE: This is just an RFC to start further discussion and collect the
> > feedback.
> > Due to significant amount of work, changes required are applied only to two
> > PMDs so far: net/i40e and net/ice.
> > So to build it you'll need to add:
> > -Denable_drivers='common/*,mempool/*
Adds event vector support to inline protocol offload mode.
By default vector support is disabled, it can be enabled by
using the option --event-vector.
Additional options to configure vector size and vector timeout are
also implemented and can be used by specifying --vector-size and
--vector-tmo.
Thanks Stephen,
While I think this option is more clear and simple:
+const char *
+rte_eth_link_speed_to_str(uint32_t link_speed)
+{
+#define SPEED_STRING_LEN 16
+ static char name[SPEED_STRING_LEN];
+
+ if (link_speed == ETH_SPEED_NUM_NONE)
+ return "None";
+ if (l
On Tue, Sep 14, 2021 at 01:34:54PM +0300, Dmitry Kozlyuk wrote:
> get_hugepage_dir() searched for a hugetlbfs mount with a given page size
> using handcraft parsing of /proc/mounts and mixing traversal logic with
> selecting the needed entry. Separate code to enumerate hugetlbfs mounts
> to eal_hu
Below is NVIDIA Mellanox's roadmap for DPDK21.11, on which we are currently
working:
ethdev new APIs:
===
[1] Introduce an optimization in memory/performance for the case of scaled-up
interfaces.
Motivation: An application (e.g. OVS) polls all representors
que
On 9/7/21 2:51 AM, Gaoxiang Liu wrote:
> Add log print of socket path in vhost_user_add_connection.
> It's useful when adding a mass of socket connections,
> because the information of every connection is clearer.
>
> Fixes: 8f972312b8f4 ("vhost: support vhost-user")
> Cc: sta...@dpdk.org
>
>
On Tue, Sep 14, 2021 at 1:07 PM David Hunt wrote:
> >> “ERROR: logical core 212 is above the maximum lcore number permitted.
> >> Please use the --lcores option to map lcores onto physical cores, e.g.
> >> --lcores="(0-3)@(212-215).”
> > If you could directly provide the right --lcores syntax base
On 9/7/21 4:58 AM, Chenbo Xia wrote:
> As reported by symbol bot, APIs listed in this patch have been
> experimental for more than two years. This patch promotes these
> 18 APIs to stable.
>
> Signed-off-by: Chenbo Xia
> ---
> lib/vhost/rte_vhost.h| 13 -
> lib/vhost/rte_v
On 9/2/21 5:45 PM, Gaoxiang Liu wrote:
> The rte_vhost_driver_unregister() and vhost_user_read_cb()
> can be called at the same time by 2 threads.
> when memory of vsocket is freed in rte_vhost_driver_unregister(),
> the invalid memory of vsocket is accessed in vhost_user_read_cb().
> It's a bug
On 9/14/21 1:17 PM, Andrew Rybchenko wrote:
> On 9/14/21 2:07 PM, Maxime Coquelin wrote:
>>
>>
>> On 9/2/21 4:39 PM, Andrew Rybchenko wrote:
>>> From: Ivan Ilchenko
>>>
>>> Use max-pkt-len only if jumbo frames offload is requested
>>> since otherwise this field isn't valid.
>>>
>>> Fixes: 8b90e
On 9/2/21 4:39 PM, Andrew Rybchenko wrote:
> From: Ivan Ilchenko
>
> Use max-pkt-len only if jumbo frames offload is requested
> since otherwise this field isn't valid.
>
> Fixes: 8b90e4358112 ("net/virtio: set offload flag for jumbo frames")
> Fixes: 4e8169eb0d2d ("net/virtio: fix Rx scatter
On 8/31/21 5:54 PM, David Marchand wrote:
> Trying to use virtio-user as a replacement for taps in OVS, I ended up
> with some fixes on the interrupt side.
> The patches for OVS are not ready yet, but sending the DPDK fixes in
> any case.
>
> @CI guys:
> Patch 2 probably means there is a hole i
On 8/31/21 4:39 PM, Gaoxiang Liu wrote:
> When virtio_init_queue returns error, the memory of vq is freed.
> But the value of hw->vqs[queue_idx] does not restore.
> If virtio_init_queue returns error, the memory of vq is freed again
> in virtio_free_queues.
>
> Fixes: 69c80d4ef89b ("net/virtio:
On 8/20/21 2:48 PM, Andrew Rybchenko wrote:
> From: Ivan Ilchenko
>
> Report max/min/align descriptors limits in device info get callback.
> Before calling the callback, rte_eth_dev_info_get() provides
> default values of nb_min as zero and nb_max as UINT16_MAX that are
> not correct for the d
On 8/20/21 2:47 PM, Andrew Rybchenko wrote:
> From: Ivan Ilchenko
>
> Descriptors number may be set less than queue size for split queue
> vectorized Rx path. Pointers to mbufs for received packets are
> obtained from SW ring, that is initially filled with them in the end
> of queue setup in v
On 8/20/21 2:47 PM, Andrew Rybchenko wrote:
> From: Ivan Ilchenko
>
> Rx queue setup finish function may report wrong number of
> allocated mbufs in case of in-order feature. Fix the
> function to not ignore allocation error and count only
> successfully allocated number of buffers.
>
> Fixes
On 8/20/21 2:47 PM, Andrew Rybchenko wrote:
> From: Ivan Ilchenko
>
> Rx queue setup callback allows to use the whole ring when
> descriptor number argument equals zero. There's no point to
> handle zero in any way since RTE Rx queue setup function
> rte_eth_rx_queue_setup() doesn't pass zero
On 8/20/21 2:44 PM, Jiayu Hu wrote:
> Copy threshold is introduced in async vhost data path to select
> the appropriate copy engine to do copies for higher efficiency.
> However, it may cause packets out-of-order, and it also causes
> data path performance unpredictable.
>
> Therefore, this pat
On 9/14/21 2:07 PM, Maxime Coquelin wrote:
>
>
> On 9/2/21 4:39 PM, Andrew Rybchenko wrote:
>> From: Ivan Ilchenko
>>
>> Use max-pkt-len only if jumbo frames offload is requested
>> since otherwise this field isn't valid.
>>
>> Fixes: 8b90e4358112 ("net/virtio: set offload flag for jumbo frames"
On 14/9/2021 11:00 AM, David Marchand wrote:
On Tue, Sep 14, 2021 at 11:34 AM David Hunt wrote:
On 10/9/2021 9:24 AM, Thomas Monjalon wrote:
10/09/2021 10:06, David Marchand:
On Fri, Sep 10, 2021 at 9:54 AM Bruce Richardson
wrote:
On Fri, Sep 10, 2021 at 08:51:04AM +0200, David Marchand
On 9/2/21 4:39 PM, Andrew Rybchenko wrote:
> From: Ivan Ilchenko
>
> Use max-pkt-len only if jumbo frames offload is requested
> since otherwise this field isn't valid.
>
> Fixes: 8b90e4358112 ("net/virtio: set offload flag for jumbo frames")
> Fixes: 4e8169eb0d2d ("net/virtio: fix Rx scatter
On 14/09/2021 08:10, David Marchand wrote:
> On Fri, Sep 10, 2021 at 6:54 PM Pablo de Lara
> wrote:
>>
>> rte_efd_create() function was using uint8_t for a socket bitmask,
>> for one of its parameters.
>> This limits the maximum of NUMA sockets to be 8.
>> Changing to to uint64_t increases it t
Hi Jerin,
> -Original Message-
> From: Jerin Jacob
> Sent: Thursday, September 2, 2021 12:20 PM
> To: Kaladi, Ashok K
> Cc: Harman Kalra ; Nithin Dabilpuram
> ; Yigit, Ferruh ;
> Burakov, Anatoly ; Richardson, Bruce
> ; Ananyev, Konstantin
> ; Thomas Monjalon
> ; David Marchand ;
> jer.
On Tue, Sep 14, 2021 at 12:16:36PM +0200, David Marchand wrote:
> On Tue, Sep 14, 2021 at 11:18 AM Ferruh Yigit wrote:
> >
> > On 9/3/2021 12:53 AM, David Christensen wrote:
> > > Suppress the gcc warning "note: the layout of aggregates containing
> > > vectors with 4-byte alignment has changed in
On Tue, Sep 14, 2021 at 11:18 AM Ferruh Yigit wrote:
>
> On 9/3/2021 12:53 AM, David Christensen wrote:
> > Suppress the gcc warning "note: the layout of aggregates containing
> > vectors with 4-byte alignment has changed in GCC 5" on POWER systems
> > by setting "-Wno-psabi". Warning was origina
On Tue, Sep 14, 2021 at 11:34 AM David Hunt wrote:
>
>
> On 10/9/2021 9:24 AM, Thomas Monjalon wrote:
> > 10/09/2021 10:06, David Marchand:
> >> On Fri, Sep 10, 2021 at 9:54 AM Bruce Richardson
> >> wrote:
> >>> On Fri, Sep 10, 2021 at 08:51:04AM +0200, David Marchand wrote:
> On Thu, Sep 9,
This patch implements asynchronous dequeue data path for packed ring.
Signed-off-by: Cheng Jiang
---
It's based on these 2 patches:
1. vhost: remove copy threshold for async vhost
http://patches.dpdk.org/project/dpdk/patch/1629463466-450012-1-git-send-email-jiayu...@intel.com/
2. vhost: support a
On 8/20/21 2:48 PM, Andrew Rybchenko wrote:
> From: Ivan Ilchenko
>
> Report max/min/align descriptors limits in device info get callback.
> Before calling the callback, rte_eth_dev_info_get() provides
> default values of nb_min as zero and nb_max as UINT16_MAX that are
> not correct for the d
The size of the UMR WQE allocated object is decided by a sizof
operation on the struct, however since the struct contains
a union of flexible array members this sizeof results can differ
between compilers.
GCC for example treats the union as 0 sized, MSVC adds a padding
of 16Bits.
To resolve the
use the functions mlx5_os_alloc_pd, mlx5_os_dealloc_pd
mlx5_os_get_pdn instead of the glue functions to support
PD operations on all OSs.
Signed-off-by: Tal Shnaiderman
---
drivers/crypto/mlx5/mlx5_crypto.c | 15 ++-
drivers/crypto/mlx5/mlx5_crypto.h | 2 +-
2 files changed, 7 inser
1 - 100 of 129 matches
Mail list logo
