Hi Thomas,
On 2024/2/9 0:25, Thomas Monjalon wrote:
19/12/2023 12:00, Amit Prakash Shukla:
+struct rte_dma_dev *
+rte_dma_pmd_get_dev_by_id(const int dev_id)
const does not make sense here for an int parameter.
I think it could be OK with const even if the parameter is not pointer.
Howeve
> From: Mattias Rönnblom [mailto:mattias.ronnb...@ericsson.com]
> Sent: Thursday, 8 February 2024 19.17
>
> Introduce DPDK per-lcore id variables, or lcore variables for short.
>
> An lcore variable has one value for every current and future lcore
> id-equipped thread.
>
> The primary use case
On Thu, Feb 8, 2024 at 3:20 PM Mattias Rönnblom wrote:
>
> On 2024-02-07 11:14, Jerin Jacob wrote:
> > On Fri, Feb 2, 2024 at 7:29 PM Bruce Richardson
> > wrote:
> >>
> >> Make some textual improvements to the introduction to eventdev and event
> >> devices in the eventdev header file. This text
For tx path, use LONG_PACKET_FORMAT if vlan tag is present. For rx,
extract vlan id from oob, put into mbuf and set the vlan flags in
mbuf.
Also add myself to the maintainers list for vmbus, mana and netvsc.
Signed-off-by: Wei Hu
---
MAINTAINERS | 3 +++
drivers/net/mana/mana.h |
On Fri, Feb 2, 2024 at 6:11 PM Bruce Richardson
wrote:
>
> Clarify the meaning of the NEW, FORWARD and RELEASE event types.
> For the fields in "rte_event" struct, enhance the comments on each to
> clarify the field's use, and whether it is preserved between enqueue and
> dequeue, and it's role, i
On Thu, Feb 8, 2024 at 2:32 PM Nithin Dabilpuram
wrote:
>
> Use SQ enable and disable API in TM setup to affect
> the state change.
>
> Signed-off-by: Nithin Dabilpuram
Please fix
Wrong headline prefix:
common/cnxk: remove cn9k Inline IPsec FP opcode defines
common/cnxk: skip se
On 2/8/24 17:56, Vargas, Hernan wrote:
Hi Maxime,
I just submitted v7 of this series rebased on top of next-baseband.
Thanks, that's all good.
The next-baseband PR for -rc1 will be ready once github actions run has
completed:
https://github.com/DPDK/dpdk/actions/runs/7842210322
Maxime
Tha
09/02/2024 00:54, Ferruh Yigit:
> On 1/30/2024 11:25 AM, Gavin Li wrote:
> > Currently, DPDK supports VXLAN and VXLAN-GPE with similar header
> > structures and we are working on adding support for VXLAN-GBP which is
> > another extension to VXLAN. More extension of VXLAN may be added in the
> > fu
On 2/8/24 17:50, Hernan Vargas wrote:
v7: Rebase series on top of next-baseband.
v6: Rework total_num_queues in separate commit. Fix typo in comment.
v5: Created separate commit for doc fix. Cosmetic uppercase changes.
v4: Targeting 24.03. Updated FPGA PMD based on review comments.
v3: Made ch
Hi Gregory,
> -Original Message-
> From: Gregory Etelson
> Sent: Thursday, October 26, 2023 09:31
> To: dev@dpdk.org
> Cc: Gregory Etelson ; Maayan Kashani
> ; Ori Kam ; Aman Singh
> ; Yuying Zhang
> Subject: [PATCH] app/testpmd: add size parameter to raw_encap action
>
> Testpmd always
Hi Thomas and Chengwen,
Thank you for the review and feedback. Please find my comment in-line.
Thanks,
Amit Shukla
> --
> Hi Thomas,
>
>
> On 2024/2/9 0:25, Thomas Monjalon wrote:
> > 19/12/2023 12:00, Amit Prakash Shukla:
> >
09/02/2024 12:05, Amit Prakash Shukla:
> > On 2024/2/9 0:25, Thomas Monjalon wrote:
> > > 19/12/2023 12:00, Amit Prakash Shukla:
> > >> +struct rte_dma_dev *
> > >> +rte_dma_pmd_get_dev_by_id(const int dev_id)
> > > const does not make sense here for an int parameter.
> >
> >
> > I think it could
> > >
> > > invoke (*dev->dev_ops->dma_adapter_vchan_add)(dev, dma_dev_id,
> > > vchan, event),
> > >
> > > at cnxk driver, this ops will check whether the DMA is
> > > cnxk_dmadev_pci_driver.
> > >
> > > I think this is because the cnxk's event-and-dma implement has deep
> > > coupling
> > >
>
On 2024-02-09 09:25, Morten Brørup wrote:
From: Mattias Rönnblom [mailto:mattias.ronnb...@ericsson.com]
Sent: Thursday, 8 February 2024 19.17
Introduce DPDK per-lcore id variables, or lcore variables for short.
An lcore variable has one value for every current and future lcore
id-equipped threa
On 2/9/2024 10:12 AM, Thomas Monjalon wrote:
> 09/02/2024 00:54, Ferruh Yigit:
>> On 1/30/2024 11:25 AM, Gavin Li wrote:
>>> Currently, DPDK supports VXLAN and VXLAN-GPE with similar header
>>> structures and we are working on adding support for VXLAN-GBP which is
>>> another extension to VXLAN. Mo
>
> On 1/11/2024 2:21 PM, Ferruh Yigit wrote:
> > On 1/11/2024 12:21 PM, Maryam Tahhan wrote:
> >> On 11/01/2024 11:35, Ferruh Yigit wrote:
> >>> Devarg is user interface, changing it impacts the user.
> >>>
> >>> Assume that user of '22.11.3' using 'use_cni' dev_arg, it will be broken
> >>> when
> From: Mattias Rönnblom [mailto:hof...@lysator.liu.se]
> Sent: Friday, 9 February 2024 12.46
>
> On 2024-02-09 09:25, Morten Brørup wrote:
> >> From: Mattias Rönnblom [mailto:mattias.ronnb...@ericsson.com]
> >> Sent: Thursday, 8 February 2024 19.17
> >>
> >> Introduce DPDK per-lcore id variables,
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, February 7, 2024 4:06 PM
> To: Rahul Bhansali ; dev@dpdk.org; Radu Nicolau
> ; Akhil Goyal ; Konstantin
> Ananyev ; Anoob Joseph
>
> Subject: Re: [EXT] Re: [PATCH] examples/ipsec-secgw: fix IPsec performance
> drop
>
> On 2/
> -Original Message-
> From: Dariusz Sosnowski
> Sent: Friday, February 9, 2024 12:04
> To: Gregory Etelson ; dev@dpdk.org
> Cc: Gregory Etelson ; Maayan Kashani
> ; Ori Kam ; Aman Singh
> ; Yuying Zhang
> Subject: RE: [PATCH] app/testpmd: add size parameter to raw_encap action
>
> Hi Gre
09/02/2024 13:11, Ferruh Yigit:
> On 2/9/2024 10:12 AM, Thomas Monjalon wrote:
> > 09/02/2024 00:54, Ferruh Yigit:
> >> On 1/30/2024 11:25 AM, Gavin Li wrote:
> >>> Currently, DPDK supports VXLAN and VXLAN-GPE with similar header
> >>> structures and we are working on adding support for VXLAN-GBP w
On 2/9/2024 1:10 PM, Rahul Bhansali wrote:
>
>
>> -Original Message-
>> From: Ferruh Yigit
>> Sent: Wednesday, February 7, 2024 4:06 PM
>> To: Rahul Bhansali ; dev@dpdk.org; Radu Nicolau
>> ; Akhil Goyal ; Konstantin
>> Ananyev ; Anoob Joseph
>>
>> Subject: Re: [EXT] Re: [PATCH] example
On 2/9/2024 1:43 PM, Dariusz Sosnowski wrote:
>> -Original Message-
>> From: Dariusz Sosnowski
>> Sent: Friday, February 9, 2024 12:04
>> To: Gregory Etelson ; dev@dpdk.org
>> Cc: Gregory Etelson ; Maayan Kashani
>> ; Ori Kam ; Aman Singh
>> ; Yuying Zhang
>> Subject: RE: [PATCH] app/testp
Hello Ferruh,
The patch did not fix an existing issue.
It was proposed the code improvement.
Let's drop it for now.
I'll post a general solution in the next iteration.
Regards,
Gregory
From: Ferruh Yigit
Sent: Friday, February 9, 2024 15:55
To: Dariusz Sosnowski
On 1/24/2024 3:05 AM, Mingjin Ye wrote:
The "vsi" may be null, so it needs to be used after checking.
Fixes: ab28aad9c24f ("net/iavf: fix Rx Tx burst in multi-process")
Cc: sta...@dpdk.org
Signed-off-by: Mingjin Ye
---
Acked-by: Anatoly Burakov
--
Thanks,
Anatoly
On 1/10/2024 3:25 AM, Mingjin Ye wrote:
Implemented a Tx wrapper to perform a thorough check on mbufs,
categorizing and counting invalid cases by types for diagnostic
purposes. The count of invalid cases is accessible through xstats_get.
Also, the devarg option "mbuf_check" was introduced to con
On 2/9/2024 1:44 PM, Thomas Monjalon wrote:
> 09/02/2024 13:11, Ferruh Yigit:
>> On 2/9/2024 10:12 AM, Thomas Monjalon wrote:
>>> 09/02/2024 00:54, Ferruh Yigit:
On 1/30/2024 11:25 AM, Gavin Li wrote:
> Currently, DPDK supports VXLAN and VXLAN-GPE with similar header
> structures and w
On 2/9/2024 2:01 PM, Gregory Etelson wrote:
> Hello Ferruh,
>
> The patch did not fix an existing issue.
>
I remember it is for protection against similar buffer overwrite issue,
not exactly for that specific issue.
> It was proposed the code improvement.
> Let's drop it for now.
>
Agree, I wi
On 2/8/2024 2:45 PM, Ferruh Yigit wrote:
> On 11/11/2023 7:13 AM, Gregory Etelson wrote:
>> parse_prefix(), parse_int(), parse_mac_addr(),
>> parse_ipv4_addr() and parse_ipv6_addr() unconditionally overwrite
>> the `size` parameter with token size.
>> The `size` parameter references a buffer where
On 1/10/2024 3:25 AM, Mingjin Ye wrote:
Implemented a Tx wrapper to perform a thorough check on mbufs,
categorizing and counting invalid cases by types for diagnostic
purposes. The count of invalid cases is accessible through xstats_get.
Also, the devarg option "mbuf_check" was introduced to con
09/02/2024 15:58, Ferruh Yigit:
> On 2/9/2024 1:44 PM, Thomas Monjalon wrote:
> > 09/02/2024 13:11, Ferruh Yigit:
> >> On 2/9/2024 10:12 AM, Thomas Monjalon wrote:
> >>> 09/02/2024 00:54, Ferruh Yigit:
> On 1/30/2024 11:25 AM, Gavin Li wrote:
> > Currently, DPDK supports VXLAN and VXLAN-GP
-Original Message-
From: Long Li
Sent: Friday, February 9, 2024 1:14 AM
To: stephen ; Alan Elder
Cc: dev@dpdk.org
Subject: RE: [PATCH v2] net/netvsc: fix parsing of VLAN metadata
>
> Most of this driver came from FreeBSD. Did you look there to make sure
> naming is the same. I.e wou
The previous code incorrectly parsed the VLAN ID and priority.
If the 16-bits of VLAN ID and priority/CFI on the wire was
0123456789ABCDEF the code parsed it as 456789ABCDEF3012. There
were macros defined to handle this conversion but they were not
used.
Fixes: 4e9c73e96e83 ("net/netvsc: add Hype
On 2/9/2024 3:32 PM, Thomas Monjalon wrote:
> 09/02/2024 15:58, Ferruh Yigit:
>> On 2/9/2024 1:44 PM, Thomas Monjalon wrote:
>>> 09/02/2024 13:11, Ferruh Yigit:
On 2/9/2024 10:12 AM, Thomas Monjalon wrote:
> 09/02/2024 00:54, Ferruh Yigit:
>> On 1/30/2024 11:25 AM, Gavin Li wrote:
> -Original Message-
> From: Gregory Etelson
> Sent: Thursday, October 26, 2023 09:31
> To: dev@dpdk.org
> Cc: Gregory Etelson ; Maayan Kashani
> ; Ori Kam ; Aman Singh
> ; Yuying Zhang
> Subject: [PATCH] app/testpmd: add size parameter to raw_encap action
>
> Testpmd always provides RAW
On 2/9/2024 8:52 AM, Wei Hu wrote:
> For tx path, use LONG_PACKET_FORMAT if vlan tag is present. For rx,
> extract vlan id from oob, put into mbuf and set the vlan flags in
> mbuf.
>
> Also add myself to the maintainers list for vmbus, mana and netvsc.
>
> Signed-off-by: Wei Hu
> ---
> MAINTAIN
> -Original Message-
> From: David Marchand
> Sent: Thursday, February 1, 2024 09:43
> To: dev@dpdk.org
> Cc: ktray...@redhat.com; NBU-Contact-Thomas Monjalon (EXTERNAL)
> ; Ferruh Yigit ; Andrew
> Rybchenko
> Subject: [PATCH] ethdev: recommend against using locks in event callbacks
>
>
Hi Wenjing,
Please find comments inlined
On 05/01/2024 08:16, wenjing.q...@intel.com wrote:
From: Wenjing Qiao
To supporting P4-programmed network controller, reuse devargs
"flow_parser" to specify the path of a p4 context JSON configure
file. The cpfl PMD use the JSON configuration file to t
On 2/9/2024 4:00 PM, Dariusz Sosnowski wrote:
>> -Original Message-
>> From: Gregory Etelson
>> Sent: Thursday, October 26, 2023 09:31
>> To: dev@dpdk.org
>> Cc: Gregory Etelson ; Maayan Kashani
>> ; Ori Kam ; Aman Singh
>> ; Yuying Zhang
>> Subject: [PATCH] app/testpmd: add size paramete
On 09/02/2024 12:40, Loftus, Ciara wrote:
Hi Maryam,
How do you want to continue with the patch, I think options we considered:
1. Fix 'use_cni' documentation (which we can backport to LTS) and
overload the argument for new purpose. This will enable new feature by
keeping backward compatibility
On 07/02/2024 23:24, Ferruh Yigit wrote:
Hi Maryam,
How do you want to continue with the patch, I think options we considered:
1. Fix 'use_cni' documentation (which we can backport to LTS) and
overload the argument for new purpose. This will enable new feature by
keeping backward compatibility.
09/02/2024 12:30, Amit Prakash Shukla:
>
>
> > > >
> > > > invoke (*dev->dev_ops->dma_adapter_vchan_add)(dev, dma_dev_id,
> > > > vchan, event),
> > > >
> > > > at cnxk driver, this ops will check whether the DMA is
> > > > cnxk_dmadev_pci_driver.
> > > >
> > > > I think this is because the cnxk'
On 2/9/2024 12:02 AM, lon...@linuxonhyperv.com wrote:
> From: Long Li
>
> Instead of allocating mbufs one by one during RX, use
> rte_pktmbuf_alloc_bulk() to allocate them in a batch.
>
> With this patch, there are no measurable performance improvements in
> benchmarks. However, this patch shoul
On 2/9/2024 4:52 PM, Maryam Tahhan wrote:
> On 09/02/2024 12:40, Loftus, Ciara wrote:
>>> Hi Maryam,
>>>
>>> How do you want to continue with the patch, I think options we considered:
>>>
>>> 1. Fix 'use_cni' documentation (which we can backport to LTS) and
>>> overload the argument for new purpose
On supporting hardware, the 20-bit Flow Label field in the
IPv6 header can be used to perform RSS in the ingress path.
Flow label values can be chosen such that they can be
used as part of the input to a hash function used in a load
distribution scheme.
Example to configure IPv6 flow label based
> + if (oob->rx_vlan_tag_present) {
> + mbuf->ol_flags |=
> + RTE_MBUF_F_RX_VLAN |
> RTE_MBUF_F_RX_VLAN_STRIPPED;
> + mbuf->vlan_tci = oob->rx_vlan_id;
> + }
> +
Netvsc has the following code for dealing wi
On 2/8/2024 12:09 PM, Jerin Jacob wrote:
> On Thu, Feb 8, 2024 at 6:15 AM Ferruh Yigit wrote:
>>
>> On 1/11/2024 5:25 AM, Kaiwen Deng wrote:
>>> Txonly forwarding engine does not call the Tx preparation API
>>> before transmitting packets. This may cause some problems.
>>>
>>> TSO breaks when MSS
Adds support to configure writing result to offset of the DMA
response event.
Signed-off-by: Amit Prakash Shukla
---
v2:
- Added dual workslot enqueue support.
- Fixed compilation error.
drivers/common/cnxk/roc_dpi.c | 6 +-
drivers/common/cnxk/roc_dpi.h | 2 +-
drivers/common
Added cnxk driver support for dma event enqueue and dequeue.
Also added changes for work queue entry completion status and
dual workslot DMA event enqueue.
Signed-off-by: Pavan Nikhilesh
Signed-off-by: Amit Prakash Shukla
---
v2:
- Added dual workslot enqueue support.
- Fixed compilation error.
Added support of dma driver callback assignment to eventdev
enqueue and dequeue. The change also defines dma adapter
capabilities function.
Depends-on: series-30612 ("lib/dmadev: get DMA device using device ID")
Signed-off-by: Amit Prakash Shukla
---
v2:
- Added dual workslot enqueue support.
-
Versions of Mellanox NICs starting from CX5 have device counters
related to PCI. These counters are helpful in debugging IO
bottlenecks. For instance, the outbound_pci_stalled_rd and
outbound_pci_stalled_wr counters can help with identifying NIC
stalls due to insufficient PCI credits, which otherwi
28/11/2023 03:16, Chengwen Feng:
> The m2d auto free capability was introduced in [1], but it lack the
> support in telemetry.
>
> [1] 877cb3e3742 dmadev: add buffer auto free offload
>
> Signed-off-by: Chengwen Feng
Applied, thanks.
On 2/9/2024 4:07 PM, Dariusz Sosnowski wrote:
>> -Original Message-
>> From: David Marchand
>> Sent: Thursday, February 1, 2024 09:43
>> To: dev@dpdk.org
>> Cc: ktray...@redhat.com; NBU-Contact-Thomas Monjalon (EXTERNAL)
>> ; Ferruh Yigit ; Andrew
>> Rybchenko
>> Subject: [PATCH] ethdev:
> On Feb 9, 2024, at 2:41 PM, Wathsala Vithanage
> wrote:
>
> Versions of Mellanox NICs starting from CX5 have device counters
> related to PCI. These counters are helpful in debugging IO
> bottlenecks. For instance, the outbound_pci_stalled_rd and
> outbound_pci_stalled_wr counters can help w
12/01/2024 11:26, Chengwen Feng:
> Add tracepoints at data path APIs for tracing support.
>
> Signed-off-by: Chengwen Feng
> Acked-by: Morten Brørup
Applied, thanks.
On 2/9/2024 6:16 PM, Ajit Khaparde wrote:
> On supporting hardware, the 20-bit Flow Label field in the
> IPv6 header can be used to perform RSS in the ingress path.
>
> Flow label values can be chosen such that they can be
> used as part of the input to a hash function used in a load
> distributio
On 2/9/2024 12:05 AM, lon...@linuxonhyperv.com wrote:
> From: Long Li
>
> Use a MR on the stack instead of allocating it. This fixes the memory
> leak in the code where a MR is allocated but never freed.
>
> Fixes: 0f5db3c68ba7 ("net/mana: implement memory registration")
> Cc: sta...@dpdk.org
>
On 2/8/2024 7:05 PM, Stephen Hemminger wrote:
> Rewrite the BPF program used to do queue based RSS.
> Important changes:
> - uses newer BPF map format BTF
> - accepts key as parameter rather than constant default
> - can do L3 or L4 hashing
> - supports IPv4 options
>
On Fri, 9 Feb 2024 20:41:42 +
Wathsala Vithanage wrote:
> Versions of Mellanox NICs starting from CX5 have device counters
> related to PCI. These counters are helpful in debugging IO
> bottlenecks. For instance, the outbound_pci_stalled_rd and
> outbound_pci_stalled_wr counters can help wit
On Sat, 10 Feb 2024 00:54:15 +
Ferruh Yigit wrote:
> On 2/8/2024 7:05 PM, Stephen Hemminger wrote:
> > Rewrite the BPF program used to do queue based RSS.
> > Important changes:
> > - uses newer BPF map format BTF
> > - accepts key as parameter rather than constant default
> > - c
> Hi Pavan,
>
> Alloc fp_objects from rte_memory is a good idea, but this may cause
> the rte_memory memory leak, especially in multi-process scenario.
>
> Currently, there is no mechanism for releasing such a rte_memory which
> don't belong to any driver.
>
Yeah, secondary process will leak rte
From: Pavan Nikhilesh
Align fp_objects based on cacheline size defined
by build configuration.
Signed-off-by: Pavan Nikhilesh
---
v2 Changes:
- Drop malloc changes.
lib/dmadev/rte_dmadev_core.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/dmadev/rte_dmadev_core.h b/
> > On Feb 1, 2024, at 3:57 PM, pbhagavat...@marvell.com wrote:
> >
> > From: Pavan Nikhilesh
> >
> > Allow RTE_ARM_USE_WFE to be enabled at meson configuration
> > time by passing it via c_args instead of modifying
> > `config/arm/meson.build`.
> >
> > Example usage:
> > meson build -Dc_args='-DR
> > > wrote:
> > > >
> > > > Hi Pavan,
> > > >
> > > >> The compiler options march and mtune are a subset of mcpu and will
> > > >> lead
> > > to
> > > >> conflicts if improper march is chosen for a given mcpu.
> > > >> To avoid conflicts, force part number march when mcpu is available
> > > >> a
On 2024-02-09 09:43, Jerin Jacob wrote:
On Thu, Feb 8, 2024 at 3:20 PM Mattias Rönnblom wrote:
On 2024-02-07 11:14, Jerin Jacob wrote:
On Fri, Feb 2, 2024 at 7:29 PM Bruce Richardson
wrote:
Make some textual improvements to the introduction to eventdev and event
devices in the eventdev hea
64 matches
Mail list logo
