Hi,
One of our drivers is using the rte_cfgfile and meson is failing on
'rte_cfgfile_section_num_entries_by_index' which is undefined.
After a few debug cycles, I found out that this function is missing from the
.map file.
So I added it and created a patch but checkpatch is failing with
E
From: Tonghao Zhang
When creating the dr rule of meter, the matcher which
struct is "struct mlx5dv_dr_matcher" should not be
shared, if shared, mlx5dv_dr_rule_create will return
NULL. We can't install more metering offload actions.
The call tree (rdma-core-47mlnx1 OFED 4.7-3.2.9):
* dr_rule_hand
On 9/26/19 4:26 PM, Jiayu Hu wrote:
> DMA engines, like I/OAT, are efficient in moving large data
> within memory. Offloading large copies in vhost side to DMA
> engines can save precious CPU cycles and improve vhost
> performance.
>
> However, using the DMA engine requires to populate guest's
[AMD Official Use Only - Internal Distribution Only]
Hi Ferruh,
Current driver was developed for EPYC 3000 processors. New processors
V1000/R1000 is also using the same PCI id for axgbe but register definitions
for determining the window settings for indirect PCS access is changed. In
o
The link status for ixgbevf is not correct when PF link up.
IXGBE_ESDP register is only used when media type is fiber.
Fixes: 1ca05831b9be ("net/ixgbe: fix link status")
Cc: sta...@dpdk.org
Signed-off-by: Lunyuan Cui
---
drivers/net/ixgbe/ixgbe_ethdev.c | 8 +---
1 file changed, 5 insertion
Now that L2 filters can be re-used for an n-tuple filter(s), delete
L2 filter as well so the reference count of an L2 filter (if reused)
can be decremented appropriately.
Fixes: 0ba82dee ("net/bnxt: fix to check for L2 filters that doesn't have any
references")
Signed-off-by: Somnath Kotur
Revi
Sync flow flush routine with flow destroy so that the operations
performed per flow during a flush are the same as that are done for an
individual flow destroy by having a common function to call for both.
One of the things that was missed in the flow flush routine was the
deletion of the L2 filter
The software L2 filter was being released back to the free pool,
after it was created in HW and the filter corresponding to an actual
'flow' would have reference to the HW L2 filter.
But if this 'flow were to be deleted, then this HW L2 filter also
would be gone.
Fix this by storing the L2 filter c
From: Santoshkumar Karanappa Rastapur
As part of ntuple filter, we were creating L2 filter with the ntuple
redirect queue resulting in any L2 matching flow getting steered to
this queue. For ntuple filters, we need to create the L2 filter with
default queue. The user specified redirect queue will
In the case when CoS classification is disabled, driver was iterating
looking for only lossy profiles as that is what is expected to be used
for regular NIC operations. But in certain custom profiles, there were
no lossy profiles configured, only lossless profiles instead.
To handle such cases, it
Please apply.
Santoshkumar Karanappa Rastapur (2):
net/bnxt: fix link failure during port toggle by increasing link wait
time
net/bnxt: fix non matching flow hitting filter rule
Somnath Kotur (4):
net/bnxt: fix to use first valid profile if lossy profile not found
net/bnxt: fix flow f
From: Santoshkumar Karanappa Rastapur
We need to wait for up to 500ms to receive async event notification after
forcing link down. Similarly we need to wait for up to 10s for link to
come up after configuring the hardware for link up.
Signed-off-by: Santoshkumar Karanappa Rastapur
Reviewed-by:
The function eth_dev_vhost_create() could return errors,
the return value need to be checked.
Fixes: ee584e9710b9 ("vhost: add driver on top of the library")
Cc: sta...@dpdk.org
Signed-off-by: Yunjian Wang
---
v2:
-change function eth_dev_vhost_create return 0 on success
---
drivers/net/vhost/
On Mon, Dec 16, 2019 at 06:38:28AM +, wangyunjian wrote:
> > -Original Message-
> > From: Tiwei Bie [mailto:tiwei@intel.com]
> > Sent: Monday, December 16, 2019 1:33 PM
> > To: wangyunjian
> > Cc: dev@dpdk.org; maxime.coque...@redhat.com; zhihong.w...@intel.com;
> > xudingke ; sta.
It is useful to know when the next timer will expire when
using rte_epoll_wait (or sleep when idle). This experimental
API provides a hook to query the number of ticks remaining.
Signed-off-by: Stephen Hemminger
---
v1 - incorporate feedback from old RFC
lib/librte_timer/rte_timer.c |
On Wed, 13 Nov 2019 06:59:48 +
Hemant Agrawal wrote:
> HI Stephen,
> Will you please enhance it to also provide number of files in each
> category?
>
> We also need to think about how to handle the scripts "*.sh", as many of
> these are without SPDX.
> - we can either leave them as
The config options are updated with sed and the short in-place option.
In order to avoid creating a backup file when using sed in-place,
the argument was tentatively set as an empty suffix.
On Linux, the suffix argument is optional, without space or equal before.
On FreeBSD, the suffix argument of
16/12/2019 17:59, Bruce Richardson:
> On Mon, Dec 16, 2019 at 05:47:03PM +0100, Thomas Monjalon wrote:
> > 16/12/2019 17:40, Bruce Richardson:
> > > On Mon, Dec 16, 2019 at 05:22:42PM +0100, Thomas Monjalon wrote:
> > > > The config options are updated with sed and the short inline option.
> > > >
On Mon, Dec 16, 2019 at 05:47:03PM +0100, Thomas Monjalon wrote:
> 16/12/2019 17:40, Bruce Richardson:
> > On Mon, Dec 16, 2019 at 05:22:42PM +0100, Thomas Monjalon wrote:
> > > The config options are updated with sed and the short inline option.
> > > In FreeBSD, the suffix argument of the inline
On Wed, Dec 11, 2019 at 7:26 PM Ali Alnubani wrote:
> The header linux/version.h isn't included when CONFIG_RTE_EAL_VFIO
> is explicitly disabled. LINUX_VERSION_CODE and KERNEL_VERSION are
> therefore undefined, causing the build failure:
>
> lib/librte_eal/linux/eal/eal.c: In function ‘rte_eal_
16/12/2019 17:40, Bruce Richardson:
> On Mon, Dec 16, 2019 at 05:22:42PM +0100, Thomas Monjalon wrote:
> > The config options are updated with sed and the short inline option.
> > In FreeBSD, the suffix argument of the inline option is mandatory.
> > In order to avoid creating a backup file when us
Minutes of Technical Board Meeting, 2019-11-20
Members Attending
-
-Bruce
-Ferruh
-Hemant
-Honnappa (Chair)
-Kevin
-Konstantin
-Maxime
-Olivier
-Stephen
-Thomas
NOTE: The technical board meetings every second Wednesday on IRC channel
#dpdk-board, at 3pm UTC. Meetings are public
On Mon, Dec 16, 2019 at 05:22:42PM +0100, Thomas Monjalon wrote:
> The config options are updated with sed and the short inline option.
> In FreeBSD, the suffix argument of the inline option is mandatory.
> In order to avoid creating a backup file when using sed inline,
> the argument is set as an
The config options are updated with sed and the short inline option.
In FreeBSD, the suffix argument of the inline option is mandatory.
In order to avoid creating a backup file when using sed inline,
the argument is set as an empty suffix.
The short option '-i' does not expect '=' before the suffi
Hi Vladimir,
Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Medvedkin, Vladimir
> Sent: Monday, December 16, 2019 9:29 PM
> To: Anoob Joseph ; Ananyev, Konstantin
> ; Akhil Goyal ; Adrien
> Mazarguil ; Doherty, Declan
> ; Yigit, Ferruh ; Jerin
> Jacob
> Kollanukkaran ; T
> /* Create dummy pci device to get devargs */
> + dummy_dev.addr.domain = matches[i].pc_sel.pc_domain;
> + dummy_dev.addr.bus = matches[i].pc_sel.pc_bus;
> + dummy_dev.addr.devid = matches[i].pc_sel.pc_dev;
> +
Including Anatoly as maintainer for lib/librte_eal/common/eal_common_mem*
> -Original Message-
> From: Trybula, ArturX
> Sent: Monday, December 16, 2019 3:44 PM
> To: dev@dpdk.org; Trahe, Fiona ; shal...@marvell.com;
> Dybkowski, AdamX
> ; Danilewicz, MarcinX
> ; Trybula, ArturX
> ; akh
Hi Anoob,
On 11/12/2019 17:33, Anoob Joseph wrote:
Hi Konstantin,
Please see inline.
Thanks,
Anoob
-Original Message-
From: dev On Behalf Of Ananyev, Konstantin
Sent: Wednesday, December 11, 2019 4:36 PM
To: Anoob Joseph ; Akhil Goyal ;
Adrien Mazarguil ; Doherty, Declan
; Yigit, Fe
Hi Konstantin,
Thanks for the review. Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Monday, December 16, 2019 7:51 PM
> To: Anoob Joseph ; Akhil Goyal ;
> Nicolau, Radu ; Thomas Monjalon
>
> Cc: Ankur Dwivedi ; Jerin Jacob Kollanukkaran
> ; N
In case of too low number of memzone segements user notification
was misleading. This patch improves the description by providing
better explanation about the cause.
Signed-off-by: Artur Trybula
---
lib/librte_eal/common/eal_common_memzone.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Hi Konstantin,
Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Monday, December 16, 2019 6:24 PM
> To: Anoob Joseph ; Akhil Goyal ;
> Adrien Mazarguil ; Doherty, Declan
> ; Yigit, Ferruh ; Jerin
> Jacob
> Kollanukkaran ; Thomas Monjalon
>
> Cc
When testing build with +debug options, the statistics are enabled.
It was wrongly matching CONFIG_RTE_IBVERBS_LINK_STATIC.
The pattern is fixed to match only statistics config options.
Fixes: 2c0dd7b69fb0 ("config: add static linkage of mlx dependency")
Cc: sta...@dpdk.org
Reported-by: Ali Alnub
After each mbox send operation, context waits for minimum 1ms to get
corresponding response although response can come earlier.
So reducing wait time to lower granularity.
Signed-off-by: Sunil Kumar Kori
---
drivers/common/octeontx2/otx2_mbox.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletio
After each mbox send operation, context waits for minimum 1ms to get
corresponding response although response can come earlier.
So reducing wait time to lower granularity.
Signed-off-by: Sunil Kumar Kori
---
drivers/common/octeontx2/otx2_mbox.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletio
> From: Ankur Dwivedi
>
> The default flow created would enable security processing on all ESP
> packets. If the default flow is created, SA based rte_flow creation
> would be skipped.
I suppose that one depends on:
http://patches.dpdk.org/patch/63621/
http://patches.dpdk.org/cover/63625/
to w
On Fri, Dec 13, 2019 at 5:42 PM Ajit Khaparde
wrote:
>
> Add support for RTE_FLOW_ACTION_TYPE_MARK
> Signed-off-by: Ajit Khaparde
> ---
> diff --git a/drivers/net/bnxt/bnxt_rxtx_vec_sse.c
> b/drivers/net/bnxt/bnxt_rxtx_vec_sse.c
> index 22d9f9e84..ce00da633 100644
> --- a/drivers/net/bnxt/bnx
> > > > > > > The rte_security API which enables inline protocol/crypto
> > > > > > > feature mandates that for every security session an rte_flow is
> > > > > > > created.
> > > > > > > This would internally translate to a rule in the hardware
> > > > > > > which would do packet classification.
On 12/12/2019 11:58, Bruce Richardson wrote:
The soname for each stable ABI version should be just the ABI version major
number without the minor number. Unfortunately both major and minor were
used causing version 20.1 to be incompatible with 20.0.
This patch fixes the issue by switching from 2
Hi Konstantin,
Please could you give a status?
What is the plan?
05/08/2019 16:30, Thomas Monjalon:
> Ping
> What is the status of this deprecation plan?
>
> 28/12/2018 17:18, Ananyev, Konstantin:
> > Hi everyone,
> > As you probably know, all un-implemented API inside DPDK
> > planned to be de
> -Original Message-
> From: dev On Behalf Of Xiaoyun Li
> Sent: Monday, December 16, 2019 9:59 AM
> To: jingjing...@intel.com
> Cc: dev@dpdk.org; omkar.masle...@intel.com; Xiaoyun Li
> ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH v2] raw/ntb: fix write memory barrier issue
>
> All b
Currently otx2_mbox_get_rsp_xxx get response once AF driver
interrupts after completion. But this funciton will get into
deadlock if called in another interrupt context.
To avoid it, implemented another version of this function which polls
on dedicated memory for a given timeout.
Also after clear
From: Harman Kalra
Added an API to check if current execution is in interrupt
context. This will be helpful to handle nested interrupt cases.
Signed-off-by: Harman Kalra
Signed-off-by: Sunil Kumar Kori
---
v3:
- API Comment is updated as per man page.
- Scope updated within the library/drive
Hi Param,
Those fields are no longer existing in the newer version of the ena_com
(and newer DPDK), so please upgrade if you are encountering any issues. But
I don't think that TSO is supported on any of the ENA devices on the AWS.
Thanks,
Michal
niedz., 8 gru 2019 o 20:03 kumaraparameshwaran ra
On 12/16/19 11:19 AM, Andrew Rybchenko wrote:
> On 12/16/19 1:04 PM, Maxime Coquelin wrote:
>>
>>
>> On 12/16/19 10:39 AM, Andrew Rybchenko wrote:
>>> Hi Maxime,
>>>
>>> On 12/16/19 11:50 AM, Maxime Coquelin wrote:
Hi Andrew,
On 12/16/19 9:46 AM, Andrew Rybchenko wrote:
> On 1
Adding FDIR support for L2TPv3 over IP header matching and adding
a new customized pctype for l2tpv3 over IP.
Signed-off-by: Rory Sexton
Signed-off-by: Dariusz Jagus
---
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 4 ++
drivers/net/i40e/i40e_ethdev.c | 11 +++-
drivers/net/i40e/
This patch adds the new flow item RTE_FLOW_ITEM_TYPE_L2TPV3OIP to
flow API to match a L2TPv3 over IP header. This patch supports only
L2TPv3 over IP header format which is different to L2TPv2/L2TPv3
over UDP. The difference in header formats between L2TPv3 over IP
and L2TP over UDP require a separa
On 12/16/19 1:04 PM, Maxime Coquelin wrote:
>
>
> On 12/16/19 10:39 AM, Andrew Rybchenko wrote:
>> Hi Maxime,
>>
>> On 12/16/19 11:50 AM, Maxime Coquelin wrote:
>>> Hi Andrew,
>>>
>>> On 12/16/19 9:46 AM, Andrew Rybchenko wrote:
On 12/16/19 11:29 AM, Matan Azrad wrote:
>
> Hi all
>>>
This patch fixes the situation where datapath does not work properly when
vhost reconnects to virtio in server mode with packed ring.
Currently, virtio and vhost share memory of vring. For split ring, vhost
can read the status of discriptors directly from the available ring and
the used ring durin
Hi Beilei,
See below,
Rory
> > > > +/* A structure used to define the input for L2TPv3 flow */ struct
> > > > +i40e_l2tpv3_flow {
> > >
> > > Seems missed struct rte_eth_ipv4_flow or struct rte_eth_ipv6_flow here?
> > >
> >
> > I'm not convinced we need struct rte_eth_ipv4_flow or struct
> >
On 12/16/19 10:39 AM, Andrew Rybchenko wrote:
> Hi Maxime,
>
> On 12/16/19 11:50 AM, Maxime Coquelin wrote:
>> Hi Andrew,
>>
>> On 12/16/19 9:46 AM, Andrew Rybchenko wrote:
>>> On 12/16/19 11:29 AM, Matan Azrad wrote:
Hi all
I understand all of you agree \ not object with th
On 12/16/19 10:38 AM, Jerin Jacob wrote:
> On Mon, Dec 9, 2019 at 2:47 PM Andrew Rybchenko
> wrote:
>>
>> On 12/5/19 11:12 AM, Jerin Jacob wrote:
>>> On Mon, Dec 2, 2019 at 5:27 PM Andrew Rybchenko
>>> wrote:
>>
> Ack.
Yes, I agree as well, but in general we already have a
On 12/16/19 7:06 AM, Tiwei Bie wrote:
> On Fri, Dec 13, 2019 at 08:39:11PM +0300, Ivan Dyukov wrote:
>> Hi Maxime,
>> Thank you for comments.
>>
>>
>> 13.12.2019 17:59, Maxime Coquelin пишет:
>>> Hi Ivan,
>>>
>>> On 12/13/19 3:44 PM, Ivan Dyukov wrote:
Some applications like pktgen use link
Hi Maxime,
On 12/16/19 11:50 AM, Maxime Coquelin wrote:
> Hi Andrew,
>
> On 12/16/19 9:46 AM, Andrew Rybchenko wrote:
>> On 12/16/19 11:29 AM, Matan Azrad wrote:
>>>
>>> Hi all
>>>
>>> I understand all of you agree \ not object with the new class for vdpa
>>> drivers.
>>
>> I have two control qu
The eth devices which share one ibv device only need one hash list of
flow table.
Currently, flow table hash list is created per each eth device
whatever whether they share one ibv device or not.
If the devices share one ibv device, the previously created hash list
will become dangle because the
On 12/16/19 11:47 AM, Somnath Kotur wrote:
> On Mon, Dec 16, 2019 at 12:01 PM Andrew Rybchenko
> wrote:
>>
>> On 12/16/19 6:16 AM, Somnath Kotur wrote:
>>> Certain hardware may be able to strip and/or save only the outermost
>>> VLAN instead of both the VLANs in the mbuf in a QinQ scenario.
>>> To
Hi Andrew,
On 12/16/19 9:46 AM, Andrew Rybchenko wrote:
> On 12/16/19 11:29 AM, Matan Azrad wrote:
>>
>> Hi all
>>
>> I understand all of you agree \ not object with the new class for vdpa
>> drivers.
>
> I have two control questions:
>
> 1. If so, is it allowed to have vDPA driver in
>driv
Hi,
On 12/16/19 9:29 AM, Matan Azrad wrote:
>
> Hi all
>
> I understand all of you agree \ not object with the new class for vdpa
> drivers.
>
> Based on that, I'm going to start it.
Please go ahead, I'll rebase my virtio vDPA series on top of it.
Thanks,
Maxime
> From: Tiwei Bie
>> On Tue,
On Mon, Dec 16, 2019 at 12:01 PM Andrew Rybchenko
wrote:
>
> On 12/16/19 6:16 AM, Somnath Kotur wrote:
> > Certain hardware may be able to strip and/or save only the outermost
> > VLAN instead of both the VLANs in the mbuf in a QinQ scenario.
> > To handle such cases, we could re-interpret setting
On 12/16/19 11:29 AM, Matan Azrad wrote:
>
> Hi all
>
> I understand all of you agree \ not object with the new class for vdpa
> drivers.
I have two control questions:
1. If so, is it allowed to have vDPA driver in
drivers/net/ if it is better from code sharing point
of view?
2. If driv
On 12/10/19 9:07 PM, Ferruh Yigit wrote:
> On 1/23/2018 2:34 PM, Shahaf Shuler wrote:
>> Tuesday, January 23, 2018 3:53 PM, Olivier Matz:
>
> <...>
>
>>>
>>> 2/ meaning of rxmode.jumbo_frame, rxmode.enable_scatter,
>>> rxmode.max_rx_pkt_len
>>>
>>> While it's not related to the new API, it is pr
Hi all
I understand all of you agree \ not object with the new class for vdpa drivers.
Based on that, I'm going to start it.
From: Tiwei Bie
> On Tue, Dec 10, 2019 at 09:00:33AM +0100, Thomas Monjalon wrote:
> > 10/12/2019 03:41, Tiwei Bie:
> > > On Mon, Dec 09, 2019 at 02:22:27PM +0300, Andrew
61 matches
Mail list logo
