On Wed, Feb 7, 2024 at 11:10 AM Srikanth Yalavarthi
wrote:
>
> > -Original Message-
> > From: Honnappa Nagarahalli
> > Sent: Wednesday, February 7, 2024 9:06 AM
> > To: dev@dpdk.org; Srikanth Yalavarthi
> > Cc: Jerin Jacob ; n...@arm.com; Honnappa Nagarahalli
> >
> > Subject: [EXT] [PAT
Hello Ferruh,
I work on the patch update with detailed user guide for
the table resize API.
Regards,
Gregory
So, by design, driver will keep the old table when it is resized.
- Can this have a performance impact, like when rules
updated/removed/inserted driver will need to look more tables?
-
> -Original Message-
> From: Alan Elder
> Sent: Thursday, February 8, 2024 7:09 AM
> To: Long Li
> Cc: dev@dpdk.org
> Subject: [PATCH v3] net/netvsc: fix parsing of VLAN metadata
>
> The previous code incorrectly parsed the VLAN ID and priority.
> If the 16-bits of VLAN ID and priorit
> > +struct ndis_pkt_vlan_info {
> > + union {
> > + struct {
> > + uint32_t pri:3; /* User
> > Priority */
> > + uint32_t cfi:1; /* Canonical
> > Format ID / DEI */
> >
From: Long Li
On MR cache expension failure, the request should fail as there is no path
to get a new MR into the tree. Attempting to insert a new MR to the cache
tree will result in memory violation.
Fixes: 0f5db3c68ba7 ("net/mana: implement memory registration")
Cc: sta...@dpdk.org
Signed-off-
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
Signed-off-by: Long Li
---
Change in v2:
change commit message to in
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 should improve CPU cycles and reduce
potential locking conflicts in real-
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
> future.
>
> VXLAN and VXLAN-GBP use the sam
On 10/26/2023 8:30 AM, Gregory Etelson wrote:
> Testpmd always provides RAW_ENCAP flow action configuration with
> encap buffer and the buffer size.
> That implementation does not allow to create non-masked raw_encap
> action in the template API actions template.
>
> The patch adds the `size` para
On 2/7/2024 3:51 PM, Michael Baum wrote:
> Add new "rte_flow_field_id" enumeration values to describe both IPv6
> traffic class and IPv6 flow label fields.
>
> The TC value is "RTE_FLOW_FIELD_IPV6_TRAFFIC_CLASS" in flow API and
> "ipv6_traffic_class" in testpmd command.
> The FL value is "RTE_FLOW
On 1/3/2024 11:10 AM, Mário Kuka wrote:
> The rte_flow_query_count structure returned from the bonding driver
> always indicates that hits and bytes are invalid (bytes_set and
> hits_set flags are zero) because bond_flow_query_count() from the
> net/bonding driver does not set the bytes_set and hit
On Thu, Feb 8, 2024 at 2:23 PM Ferruh Yigit wrote:
>
> On 2/8/2024 10:06 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
On 2/8/2024 10:06 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
> distributi
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.
On supporting hardware, the 20-bit Flow Lab
On Thu, Feb 8, 2024 at 9:13 AM Ajit Khaparde wrote:
>
> Patchset with bug fixes for bnxt PMD.
> Patch based against the
> next-net-brcm for-next-net branch.
>
> Please apply.
Patchset merged to the dpdk-next-brcm for-next-net branch.
Thanks
>
> Ajit Khaparde (4):
> net/bnxt: modify locking for
On Fri, Nov 3, 2023 at 9:07 PM Weiguo Li wrote:
>
> The function 'ulp_ha_mgr_timer_cb' acquires a lock on the context
> entry at the beginning with bnxt_ulp_cntxt_entry_acquire(). This lock
> is expected to be released by bnxt_ulp_cntxt_entry_release() at the
> end of the function.
>
> However, th
On 2/8/2024 6:56 PM, Ajit Khaparde wrote:
> On Thu, Feb 8, 2024 at 10:47 AM Ferruh Yigit wrote:
>>
>> On 2/8/2024 5:43 AM, Ajit Khaparde wrote:
>>> The use of 5-tuple of the source address, destination address,
>>> source port, destination port, and the transport protocol type
>>> may not be possi
On Thu, 8 Feb 2024 11:05:53 -0800
Stephen Hemminger wrote:
> There were multiple issues in the RSS queue support in the TAP
> driver. This required extensive rework of the BPF support.
>
> Change the BPF loading to use bpftool to
> create a skeleton header file, and load with libbpf.
> The BPF
Please remove Centos79 for the CI infrastructure.
It uses an older no longer unsupported kernel and headers, and its version gcc
is not guaranteed to be C11 compatiable
Begin forwarded message:
Date: 08 Feb 2024 10:51:06 -0800
From: sys_...@intel.com
To: daxuex@intel.com, step...@networkplum
https://bugs.dpdk.org/show_bug.cgi?id=1378
Bug ID: 1378
Summary: Coverity defect reported in rte_mempool.h :
Out-of-bounds access
Product: DPDK
Version: 22.11
Hardware: x86
OS: Linux
Status: UNCO
The BPF api was replaced by use of libbpf.
And the BPF instruction header was replaced by the skeleton.
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/tap_bpf_api.c | 196
drivers/net/tap/tap_bpf_insns.h | 1742 ---
2 files changed, 1938 deletions(-)
de
Add myself as maintainer for TAP device.
Signed-off-by: Stephen Hemminger
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 5fb3a73f840e..92d27e97aa9e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1015,6 +1015,7 @@ F: doc/guides/nics/pcap_ring.r
There were multiple issues in the RSS queue support in the TAP
driver. This required extensive rework of the BPF support.
Change the BPF loading to use bpftool to
create a skeleton header file, and load with libbpf.
The BPF is always compiled from source so less chance that
source and instructions
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
- supports IPv6 extension headers
- restru
The proper place for finding bpf structures and functions is
in linux/bpf.h. The original version was trying to workaround the
case where the build environment was running on old pre BPF
version of Glibc, but the target environment had BPF. This is not
a supportable build method, and not how rest o
The flow RSS support via BPF was not using the key, or
hash type parameters. Which is good because they were never
properly setup.
Fix the setup and validate the flow parameters, the BPF
side gets fixed later.
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/tap_bpf_insns.h | 16
d
The driver doesn't support these other hash types, and there
is no reason to implement these in future.
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/tap_rss.h | 6 --
1 file changed, 6 deletions(-)
diff --git a/drivers/net/tap/tap_rss.h b/drivers/net/tap/tap_rss.h
index dff46a012f94
The support of doing RSS for rte_flow_action was a cool idea
but it has been broken for several releases of DPDK as the
kernel and BPF infrastructure changed.
This series cleans up the BPF program, implements several
features that were never completed in the original code
and changes to use the cu
On Thu, Feb 8, 2024 at 10:47 AM Ferruh Yigit wrote:
>
> On 2/8/2024 5:43 AM, Ajit Khaparde wrote:
> > The use of 5-tuple of the source address, destination address,
> > source port, destination port, and the transport protocol type
> > may not be possible due to IP fragmentation, encryption, or
>
On 2/8/2024 5:43 AM, Ajit Khaparde wrote:
> The use of 5-tuple of the source address, destination address,
> source port, destination port, and the transport protocol type
> may not be possible due to IP fragmentation, encryption, or
> inability to parse past IPv6 extensions headers.
>
> Flow labe
Signed-off-by: Mattias Rönnblom
---
app/test/meson.build | 1 +
app/test/test_lcore_var.c | 384 ++
2 files changed, 385 insertions(+)
create mode 100644 app/test/test_lcore_var.c
diff --git a/app/test/meson.build b/app/test/meson.build
index 6389ae83e
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 is for statically allocating
small chunks of often-used data, which is related logically, but where
there are performan
Signed-off-by: Mattias Rönnblom
---
lib/power/rte_power_pmd_mgmt.c | 27 ++-
1 file changed, 14 insertions(+), 13 deletions(-)
diff --git a/lib/power/rte_power_pmd_mgmt.c b/lib/power/rte_power_pmd_mgmt.c
index 591fc69f36..bb20e564de 100644
--- a/lib/power/rte_power_pmd_mg
Signed-off-by: Mattias Rönnblom
---
lib/eal/common/rte_service.c | 119 ---
1 file changed, 68 insertions(+), 51 deletions(-)
diff --git a/lib/eal/common/rte_service.c b/lib/eal/common/rte_service.c
index d959c91459..c557e80409 100644
--- a/lib/eal/common/rte_serv
Move keeping PRNG state in a RTE_MAX_LCORE-sized static array of
cache-aligned and RTE_CACHE_GUARDed struct instances to keeping the
same state in to a more cache-friendly lcore variable.
Signed-off-by: Mattias Rönnblom
---
lib/eal/common/rte_random.c | 30 ++
1 file
This RFC presents a new API for static per-lcore id
data allocation.
Please refer to the API documentation for both a
rationale for this new API, and a comparison to the alternatives
available.
The adoption of this API would affect many different DPDK modules, but
the author updated only a few,
On Thu, 8 Feb 2024 09:41:29 -0800
Stephen Hemminger wrote:
> diff --git a/drivers/net/tap/bpf/tap_bpf_program.o
> b/drivers/net/tap/bpf/tap_bpf_program.o
> new file mode 100644
> index
> ..db016eaadefc63e0bbc45b3115f497a465438d33
> GIT binary patch
> lit
On Thu, 8 Feb 2024 14:42:44 +
Alan Elder wrote:
> + struct ndis_pkt_vlan_info *vlan = (struct
> ndis_pkt_vlan_info *)pi_data;
> + vlan->value = 0;
> + vlan->vlanid = (m->vlan_tci & HN_VLAN_VID_MASK);
> +
Add myself as maintainer for TAP device.
Signed-off-by: Stephen Hemminger
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 5fb3a73f840e..92d27e97aa9e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1015,6 +1015,7 @@ F: doc/guides/nics/pcap_ring.r
The BPF api was replaced by use of libbpf.
And the BPF instruction header was replaced by the skeleton.
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/tap_bpf_api.c | 196
drivers/net/tap/tap_bpf_insns.h | 1742 ---
2 files changed, 1938 deletions(-)
de
There were multiple issues in the RSS queue support in the TAP
driver. This required extensive rework of the BPF support.
Change the BPF loading to use bpftool to
create a skeleton header file, and load with libbpf.
The BPF is always compiled from source so less chance that
source and instructions
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
- supports IPv6 extension headers
- restru
The proper place for finding bpf structures and functions is
in linux/bpf.h. The original version was trying to workaround the
case where the build environment was running on old pre BPF
version of Glibc, but the target environment had BPF. This is not
a supportable build method, and not how rest o
The flow RSS support via BPF was not using the key, or
hash type parameters. Which is good because they were never
properly setup.
Fix the setup and validate the flow parameters, the BPF
side gets fixed later.
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/tap_bpf_insns.h | 16
d
The driver doesn't support these other hash types, and there
is no reason to implement these in future.
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/tap_rss.h | 6 --
1 file changed, 6 deletions(-)
diff --git a/drivers/net/tap/tap_rss.h b/drivers/net/tap/tap_rss.h
index dff46a012f94
The support of doing RSS for rte_flow_action was a cool idea
but it has been broken for several releases of DPDK as the
kernel and BPF infrastructure changed.
This series cleans up the BPF program, implements several
features that were never completed in the original code
and changes to use the cu
Update rss_algo_capa in ethdev.
This information was not being set.
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_ethdev.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index fecc8666e8..09a70b7529 100644
--- a/dri
Update the consumer index of the default CQ/NQ at regular intervals.
Since the size of the queue can vary, ring the queue at 1/8th the queue
depth.
Also skip NQ doorbell update if done already.
If the NQ is rearmed already or if there was no valid entry,
which is indicated by cnt being 0, skip ri
From: Shuanglin Wang
On multi-host system, pci-id on PFs are same on each host.
The currect code is using the pci-id as the session name to
create a session. This would cause a name confliction on firmware
then fw rejects the session creation.
The patch will change the session name with parent p
From: Damodharam Ammepalli
Cleanup vnic ref count when port is stopped.
When vlan strip is set/unset the current active
vnics are destroyed and recreated with VNIC id
provided by firmware. The default vnic at index 0
still has ref_cnt=1 while rx_queues are reset to 0,
which fails the check under
Currently the VNIC context cleanup is being called a little early
leading to the VNIC RSS context being freed prior to the filter
cleanup corresponding to the VNIC. But since these filters could
still be referenced by the default VNIC the hardware fails to find
the corresponding VNIC context in som
Currently the representor Tx function is synchronized using a per
device lock. But that is not sufficient when there is simultaneous
traffic on the parent Tx ring and the representor rings.
Moreover the representor Tx is not protected from incursions by the
parent transmits. This can cause parent T
From: Kishore Padmanabha
The tx queue mutex should be freed before the tx queue structure and
similarly the completion ring stats should be reset before ring free.
Signed-off-by: Kishore Padmanabha
Reviewed-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_txq.c | 2 +-
1 file changed, 1 insertion(
Patchset with bug fixes for bnxt PMD.
Patch based against the
next-net-brcm for-next-net branch.
Please apply.
Ajit Khaparde (4):
net/bnxt: modify locking for representor Tx
net/bnxt: refactor VNIC context cleanup
net/bnxt: update consumer index of NQ regularly
net/bnxt: update RSS algori
On 2/8/2024 9:09 AM, Ori Kam wrote:
> During encapsulation of a packet, it is possible to change some
> outer headers to improve flow destribution.
> For example, from VXLAN RFC:
> "It is recommended that the UDP source port number
> be calculated using a hash of fields from the inner packet --
> o
On (02/03/24 04:57), Rahul Gupta wrote:
> Date: Sat, 3 Feb 2024 04:57:49 -0800
> From: Rahul Gupta
> To: Thomas Monjalon
> Cc: David Marchand , dev@dpdk.org,
> bruce.richard...@intel.com, dmitry.kozl...@gmail.com,
> step...@networkplumber.org, sovar...@linux.microsoft.com,
> ok...@kernel.org,
Hi Maxime,
I just submitted v7 of this series rebased on top of next-baseband.
Thanks,
Hernan
> -Original Message-
> From: Maxime Coquelin
> Sent: Thursday, February 8, 2024 4:45 AM
> To: Vargas, Hernan ; dev@dpdk.org;
> gak...@marvell.com; Rix, Tom
> Cc: Chautru, Nicolas ; Zhang, Qi Z
Cosmetic changes for comments.
No functional impact.
Signed-off-by: Hernan Vargas
Reviewed-by: Maxime Coquelin
---
.../baseband/fpga_5gnr_fec/fpga_5gnr_fec.h| 49 ++--
.../fpga_5gnr_fec/rte_fpga_5gnr_fec.c | 258 +-
.../fpga_5gnr_fec/rte_pmd_fpga_5gnr_fec.h | 1
Add support for new FPGA variant AGX100 (on Arrow Creek N6000).
Signed-off-by: Hernan Vargas
Reviewed-by: Maxime Coquelin
---
doc/guides/bbdevs/fpga_5gnr_fec.rst | 69 +-
drivers/baseband/fpga_5gnr_fec/agx100_pmd.h | 273
.../baseband/fpga_5gnr_fec/fpga_5gnr_fec.h| 10
Add total_num_queues to the FPGA device struct as a preliminary rework
for the introduction of different FPGA variants.
Signed-off-by: Hernan Vargas
Reviewed-by: Maxime Coquelin
---
.../baseband/fpga_5gnr_fec/fpga_5gnr_fec.h| 2 +
.../fpga_5gnr_fec/rte_fpga_5gnr_fec.c | 37
Create a new file vc_5gnr_pmd.h to store structures and macros specific
to Vista Creek 5G FPGA implementation and rename functions specific to
the Vista Creek variant.
Signed-off-by: Hernan Vargas
Reviewed-by: Maxime Coquelin
---
.../baseband/fpga_5gnr_fec/fpga_5gnr_fec.h| 183 ++-
.../
Rename generic functions and constants using the FPGA 5GNR prefix naming
to prepare for code reuse for new FPGA implementation variant.
No functional impact.
Signed-off-by: Hernan Vargas
Reviewed-by: Maxime Coquelin
---
.../baseband/fpga_5gnr_fec/fpga_5gnr_fec.h| 117 +++--
.../fpga_5gnr_fe
flr_timeout was removed from the code a while ago, updating doc.
Fix minor typo in 5GNR example.
Fixes: 2d4306438c92 ("baseband/fpga_5gnr_fec: add configure function")
Cc: sta...@dpdk.org
Signed-off-by: Hernan Vargas
Reviewed-by: Maxime Coquelin
---
doc/guides/bbdevs/fpga_5gnr_fec.rst | 7 +---
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 changes requested during review.
v2: Targetin
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.
> +{
> + if (!rte_dma_is_valid(dev_id))
> + return NULL;
> +
> + return &rte_dma_devices[dev_id];
> +}
[...]
> +/*
> -Original Message-
> From: Brian Dooley
> Sent: Thursday, December 14, 2023 4:42 PM
> To: Ji, Kai ; De Lara Guarch, Pablo
>
> Cc: dev@dpdk.org; gak...@marvell.com; Dooley, Brian
>
> Subject: [PATCH v1] crypto/ipsec_mb: use new ipad/opad calculation API
>
> From: Pablo de Lara
>
>
Hi Slava
> -Original Message-
> From: Slava Ovsiienko
> Sent: Wednesday, February 7, 2024 2:29 PM
>
> The following IPsec related field definitions added:
>
> - RTE_FLOW_FIELD_ESP_SPI - SPI value in IPsec header
> - RTE_FLOW_FIELD_ESP_SEQ_NUM - sequence number in header
> - RTE_FLOW_
On 2/7/2024 3:45 PM, Ferruh Yigit wrote:
> On 2/7/2024 3:13 AM, Andrew Boyer wrote:
>> This patchset provides miscellaneous fixes and improvements for
>> the net/ionic driver used by AMD Pensando devices.
>>
>> V3:
>> - Resend to fix patchwork threading.
>>
>> V2:
>> - Update device stop and device
> >
> >> 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 spans more than 8 data fragments. Those
> >>> packets will be dropped by Tx prepara
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.
This fix takes an approach similar to the
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 the parser functions
> will store their result.
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.
This fix takes an approach similar to the
David Marchand writes:
> GitHub started deprecating GHA actions based on Node 16 [1].
> For now, only warnings are raised, but we might as well switch to v4
> versions of the common actions, now.
>
> Link:
> https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-nod
David Marchand writes:
> Fedora 37 has reached end of life in December 2023.
> Ubuntu 20.04 is getting quite old.
>
> Switch to more recent versions.
>
> With this move, some packages provided by those distributions are now
> recent enough to extend our build coverage.
> Install additional depend
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.
This fix takes an approach similar to the
On 2/2/2024 3:04 AM, Chaoyong He wrote:
> Make multiple devices can use single core to run services for
> flower firmware.
> Also add synchronize module and service module to support it.
>
> ---
> v2:
> * Merge the last commit of v1 into the second commit.
> ---
>
> Long Wu (3):
> net/nfp: add
On 1/30/2024 6:15 PM, Etelson, Gregory wrote:
> Hello Ferruh,
>
>> So, by design, driver will keep the old table when it is resized.
>> - Can this have a performance impact, like when rules
>> updated/removed/inserted driver will need to look more tables?
>> - Or can this cause additional capacity
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 spans more than 8 data fragments. Those
> > p
On 12/7/2023 6:56 PM, Stephen Hemminger wrote:
> Replace static logtype with dynamic logtype and
> remove dead code. Compile tested on Fedora.
>
> Stephen Hemminger (3):
> net/nfb: remove unused device args
> net/nfb: make device path local to init function
> net/nfb: use dynamic logtype
>
> From: Konstantin Ananyev [mailto:konstantin.anan...@huawei.com]
> Sent: Thursday, 8 February 2024 11.50
>
> > 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.
> > >
> > >
On 2/8/2024 10:51 AM, Sivaramakrishnan Venkat wrote:
> Maintainers remove the Cc author line when merging the patch.
> So, the guidelines is updated with a suggestion for the placement
> of Cc lines in a commit message for easy merging.
>
> Signed-off-by: Sivaramakrishnan Venkat
>
Acked-by: Ferr
On 2/8/2024 10:50 AM, Konstantin Ananyev 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 spans more than 8 data fragments. Those
>>>
Maintainers remove the Cc author line when merging the patch.
So, the guidelines is updated with a suggestion for the placement
of Cc lines in a commit message for easy merging.
Signed-off-by: Sivaramakrishnan Venkat
---
v4:
- Reverted removal of "Cc: sta...@dpdk.org" in the commit log
v3:
-
> 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 spans more than 8 data fragments. Those
> > packets will be dropped by Tx preparation API, but it
On 2/7/24 18:13, Hernan Vargas wrote:
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 changes requested during review.
v2: Targetin
On 2024-02-08 10:18, Jerin Jacob wrote:
On Fri, Feb 2, 2024 at 6:11 PM Bruce Richardson
wrote:
The description of ordered and atomic scheduling given in the eventdev
doxygen documentation was not always clear. Try and simplify this so
that it is clearer for the end-user of the application
Sig
On 2/7/24 18:13, Hernan Vargas wrote:
Add support for new FPGA variant AGX100 (on Arrow Creek N6000).
Signed-off-by: Hernan Vargas
---
doc/guides/bbdevs/fpga_5gnr_fec.rst | 69 +-
drivers/baseband/fpga_5gnr_fec/agx100_pmd.h | 273
.../baseband/fpga_5gnr_fec/fpga_5gnr_
> On 2/2/2024 3:04 AM, Chaoyong He wrote:
> > Make multiple devices can use single core to run services for flower
> > firmware.
> > Also add synchronize module and service module to support it.
> >
> > ---
> > v2:
> > * Merge the last commit of v1 into the second commit.
> >
>
> Ask was to move t
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 appears in the doxygen
output for the header file, and introduces the key conce
On Fri, Feb 2, 2024 at 6:11 PM Bruce Richardson
wrote:
>
> The description of ordered and atomic scheduling given in the eventdev
> doxygen documentation was not always clear. Try and simplify this so
> that it is clearer for the end-user of the application
>
> Signed-off-by: Bruce Richardson
>
>
On 2/7/24 18:13, Hernan Vargas wrote:
Add total_num_queues to the FPGA device struct as a preliminary rework
for the introduction of different FPGA variants.
Signed-off-by: Hernan Vargas
---
.../baseband/fpga_5gnr_fec/fpga_5gnr_fec.h| 2 +
.../fpga_5gnr_fec/rte_fpga_5gnr_fec.c
This commits add support for calculating the encap hash.
Command structure:
flow hash {port} encap {target field} pattern {item} [/ {item} [...] ] / end
Example:
calculate hash to be used by VXLAN encapsulation.
flow hash 0 encap hash_field_sport pattern ipv4 dst is 7.7.7.7 src is 8.8.8.8
/ ud
This commit adds support for encap hash calculation.
Signed-off-by: Ori Kam
Acked-by: Dariusz Sosnowski
---
drivers/net/mlx5/mlx5_flow.c| 29 +++
drivers/net/mlx5/mlx5_flow.h| 8
drivers/net/mlx5/mlx5_flow_hw.c | 66 +
3 files changed, 1
From: Hamdan Igbaria
Add new function for encap entropy hash calculation, the function
will check the device capability for the entropy hash type used
by the device, and will calculate the entropy hash value of the
user passed fields according this type.
Signed-off-by: Hamdan Igbaria
Acked-by:
During encapsulation of a packet, it is possible to change some
outer headers to improve flow destribution.
For example, from VXLAN RFC:
"It is recommended that the UDP source port number
be calculated using a hash of fields from the inner packet --
one example being a hash of the inner Ethernet fr
Use SQ enable and disable API in TM setup to affect
the state change.
Signed-off-by: Nithin Dabilpuram
---
drivers/common/cnxk/roc_nix_tm_ops.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/common/cnxk/roc_nix_tm_ops.c
b/drivers/common/cnxk/roc_nix_tm_ops.c
ind
IO attribute is needed to mbox structs to avoid unaligned or pair
access causing by compiler optimization. Add them to structs
where it is missing.
Fixes: 503b82de2cbf ("common/cnxk: add mbox request and response definitions")
Fixes: ddf955d3917e ("common/cnxk: support CPT second pass")
Signed-of
From: Rahul Bhansali
Fix missing check cookies with multi-seg offload case
Fixes: 3626d5195d49 ("net/cnxk: add multi-segment Tx for CN10K")
Signed-off-by: Rahul Bhansali
---
drivers/net/cnxk/cn10k_tx.h | 21 -
1 file changed, 20 insertions(+), 1 deletion(-)
diff --git a/d
Indirect mbuf can be pointing to data from different pool. Use the right
aura in NIX send header in SG2 and SG case.
Fixes: 862e28128707 ("net/cnxk: add vector Tx for CN9K")
Fixes: f71b7dbbf04b ("net/cnxk: add vector Tx for CN10K")
Fixes: 7e95c11df4f1 ("net/cnxk: add multi-segment Tx for CN9K")
Fi
From: Kommula Shiva Shankar
This patch updates queue entries copy in reta table
based on data type
Signed-off-by: Kommula Shiva Shankar
---
drivers/common/cnxk/roc_nix_rss.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/common/cnxk/roc_nix_rss.c
b/drivers/com
1 - 100 of 109 matches
Mail list logo
