Hi,
From: Jiawei(Jonny) Wang
Sent: Friday, July 5, 2024 4:05 PM
To: Bing Zhao; Slava Ovsiienko; Dariusz Sosnowski; Ori Kam; Suanming Mou; Matan
Azrad; Alexander Kozyrev
Cc: dev@dpdk.org; Raslan Darawsheh; sta...@dpdk.org
Subject: [PATCH] net/mlx5: fix data access race condition for shared Rx que
Hi,
From: Gregory Etelson
Sent: Sunday, July 7, 2024 12:48 PM
To: dev@dpdk.org
Cc: Gregory Etelson; Maayan Kashani; Raslan Darawsheh; Dariusz Sosnowski; Slava
Ovsiienko; Bing Zhao; Ori Kam; Suanming Mou; Matan Azrad
Subject: [PATCH] net/mlx5: fix indexed pool resize
On success, indexed pool res
Hi,
From: Gregory Etelson
Sent: Sunday, July 7, 2024 1:13 PM
To: dev@dpdk.org
Cc: Gregory Etelson; Maayan Kashani; Raslan Darawsheh; Dariusz Sosnowski; Slava
Ovsiienko; Bing Zhao; Ori Kam; Suanming Mou; Matan Azrad
Subject: [PATCH] net/mlx5: fix IPv6-in-IPv6 tunnel recognition
The PMD did not r
Hi,
From: Gregory Etelson
Sent: Sunday, July 7, 2024 12:57 PM
To: dev@dpdk.org
Cc: Gregory Etelson; Maayan Kashani; Raslan Darawsheh; sta...@dpdk.org; Dariusz
Sosnowski; Slava Ovsiienko; Bing Zhao; Ori Kam; Suanming Mou; Matan Azrad
Subject: [PATCH] net/mlx5: fix compilation warning in GCC-9.1
Hi,
From: Dariusz Sosnowski
Sent: Monday, July 8, 2024 1:59 PM
To: Slava Ovsiienko; Bing Zhao; Ori Kam; Suanming Mou; Matan Azrad
Cc: dev@dpdk.org; sta...@dpdk.org
Subject: [PATCH] net/mlx5: fix MTU configuration
Apply provided MTU, derived from rte_eth_conf.rxmode.mtu,
on port configuration.
B
Hi Itamar,
From: Itamar Gozlan
Sent: Tuesday, July 9, 2024 3:30 PM
To: Itamar Gozlan; Erez Shitrit; Hamdan Agbariya; Yevgeny Kliteynik; Alex
Vesker; Slava Ovsiienko; NBU-Contact-Thomas Monjalon (EXTERNAL); Suanming Mou
Cc: dev@dpdk.org; Ori Kam
Subject: [PATCH 0/8] HW steering team updates
Thi
Adding sta...@dpdk.org and LTS maintainers as Cc.
It must be merged directly in LTS branches.
16/07/2024 10:44, Jiri Slaby:
> 6.10 removed the "support" (it was never supported [1]) of separate
> source and build dirs for out of tree modules.
>
> KNI uses "src=" hack for that purpose.
>
> Inste
Release status meeting minutes 2024-07-18
=
Agenda:
* Release Dates
* Subtrees
* Roadmaps
* LTS
* Defects
* Opens
Participants:
* AMD
* ARM
* Debian/Microsoft
* Intel
* Marvell
* Nvidia
Release Dates
-
The following are the current/updated wo
Hi Jiri,
Please follow the process described in the "stable release" paragraph at:
https://core.dpdk.org/contribute/
ie, one patch per affected LTS branch must be prepared, tested and
sent individually, and then we'll apply it. Thanks.
On Thu, 18 Jul 2024 at 10:16, Thomas Monjalon wrote:
>
> A
Patch 1 - Fixes a bug with fdb_def_rule_en device argument,
used to control default E-Switch flow rules created by mlx5 PMD.
Patches 2-3 - Fixes for flow rule validation in async flow API,
which were found during testing.
Dariusz Sosnowski (3):
net/mlx5: fix disabling E-Switch default flow rule
`fdb_def_rule_en` devarg controls whether mlx5 PMD creates default
E-Switch flow rules for:
- Transferring traffic from wire, VFs and SFs to group 1 (default jump).
- Providing default behavior for application traffic (default SQ miss
flow rules).
With these flow rules, applications effectively
mlx5 PMD supports configuration where
Rx queues managed by DPDK are not set up.
Externally allocated RQs can be used by mapping them to some
DPDK Rx queue indexes using rte_pmd_mlx5_external_rx_queue_id_map()
API. In this case, mlx5 PMD will allow creating flow rules which
reference such external R
Checking if action configuration is required should be checked based on
action type recorded in the actions template, not on user action.
Also, adds a missing internal RSS action type to configuration check
skip list.
Fixes: 57c7b94301ee ("net/mlx5: add async flow operation validation")
Signed-o
> > > Application is accepting routes for port ID up to UINT8_MAX for LPM
> > > amd EM routes on parsing the given rule file, but only up to 32 ports
> > > can be enabled as per the variable enabled_port_mask which is defined
> > > as uint32_t.
> > >
> > > This patch restricts the rules parsing
From: Dengdui Huang
The data execeed the pkt_len in mbuf is inavailable for user.
When KEEP CRC offload is enabled, CRC field length should be
included pkt_len in mbuf. However, almost of drivers supported
KEEP CRC feature didn't add the CRC data length to pkt_len.
So it is very necessary to add
From: Dengdui Huang
For hns3 NIC, when KEEP_CRC offload is enabled, the CRC data is still be
stripped in rare scenarios.
Some users of hns3 are already using this feature. So driver has to recaculate
packet CRC.
In addition, in the mbuf, the data that exceeds the length specified by pkt_len
i
From: Dengdui Huang
In the HNS3 driver, pkt_len in mbuf do not contain the CRC length.
This patch fix it.
Fixes: 8973d7c4ca12 ("net/hns3: support keeping CRC")
Cc: sta...@dpdk.org
Signed-off-by: Dengdui Huang
---
drivers/net/hns3/hns3_rxtx.c | 53 +++
drivers/
From: Dengdui Huang
When KEEP_CRC offload is enabled, the CRC data is still stripped
in following cases:
1. For HIP08 network engine, the packet type is TCP and the length
is less than or equal to 60B.
2. For HIP09 network engine, the packet type is IP and the length
is less than or equal t
> From: Jie Hai [mailto:haij...@huawei.com]
> Sent: Thursday, 18 July 2024 13.48
>
> From: Dengdui Huang
>
> The data execeed the pkt_len in mbuf is inavailable for user.
> When KEEP CRC offload is enabled, CRC field length should be
> included pkt_len in mbuf. However, almost of drivers support
> -Original Message-
> From: Alexander Kozyrev
> Sent: Wednesday, July 17, 2024 16:20
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Raslan Darawsheh ; Slava Ovsiienko
> ; Matan Azrad ; Dariusz
> Sosnowski ; Bing Zhao ; Ori Kam
> ; Suanming Mou
> Subject: [PATCH] app/testpmd: add postpone opti
For series.
Acked-by: Huisong Li
在 2024/7/18 19:48, Jie Hai 写道:
From: Dengdui Huang
For hns3 NIC, when KEEP_CRC offload is enabled, the CRC data is still be
stripped in rare scenarios.
Some users of hns3 are already using this feature. So driver has to recaculate
packet CRC.
In addition,
Thomas,
Ping can this deprecation notice be merged
> Acked-by: Zhirun Yan
>
> > -Original Message-
> > From: Nithin Dabilpuram
> > Sent: Tuesday, March 19, 2024 1:21 PM
> > To: pbhagavat...@marvell.com
> > Cc: jer...@marvell.com; ndabilpu...@marvell.com;
> kirankum...@marvell.com;
>
Fix up crypto spelling mistakes.
v2: Added more typo fixes to patchset
Joel Kavanagh (4):
crypto/aesni_mb: fix typo in error message
app/test: fix typo in error message allocation
crypto/qat: fix typo in log message
doc: fix typo in l2fwd-crypto guide
.mailmap
This patch fixes a typo in the log message for error allocation.
The typo incorrectly spelled 'allocating' as 'allocationg' in the
log message for error allocation.
Fixes: f9dfb59edbcc ("crypto/ipsec_mb: support remaining SGL")
Cc: sta...@dpdk.org
Signed-off-by: Joel Kavanagh
Acked-by: Brian Doo
This patch fixes a typo in the `test_cryptodev.c` file where "out-op" was
incorrectly used instead of "out-of-place" on three separate occassions.
Fixes: f3dbf94be60c ("app/test: check SGL on QAT")
Fixes: 43220096d66a ("test/crypto: add PDCP cases for scatter gather")
Cc: sta...@dpdk.org
Signed-o
This patch fixes a typo in the log message for rte_security support.
The typo incorrectly spelled 'enabled' as 'ensabled' in the
log message indicating that rte_security support is enabled.
Fixes: fb3b9f492205 ("crypto/qat: rework burst data path")
Cc: sta...@dpdk.org
Signed-off-by: Joel Kavanagh
This patch fixes a typo in the l2fwd-crypto documentation where
the l2fwd-crypt was changed to l2fwd-crypto.
Fixes: 7cacb0565539 ("doc: add generic build instructions for sample apps")
Cc: sta...@dpdk.org
Signed-off-by: Joel Kavanagh
---
doc/guides/sample_app_ug/l2_forward_crypto.rst | 2 +-
1
Hi Team,
Is there any way to distribute packets evenly (Like RSS) to specific multiple
RX queues in RTE_FLOW_ACTION_TYPE_QUEUE DPDK Flow director?
Desired action:
uint16_t queue_indices[] = {10, 11, 12, 13, 14, 15};
struct rte_flow_action_queue queue = {.index = queue_indices};
struct rte_flow_
Hi folks,
while working on IPv6 support for grout [1], I noticed that all DPDK
IPv6 APIs used fixed sized arrays in the route lookup functions [2].
int rte_fib6_lookup_bulk(struct rte_fib6 *fib,
uint8_t ips[][RTE_FIB6_IPV6_ADDR_SIZE],
uint64_t
> Acked-by: Arkadiusz Kusztal
> > All generations of QAT use the same Gen1 raw datapath. Gen4 needs a
> > different
> > WRITE function than other generations. Added separation for configuration of
> > the raw ctx for Gen4 from the Gen1 codepath.
> >
> > Fixes: 85fec6fd9674 ("crypto/qat: unify raw
> Subject: [EXTERNAL] [PATCH v2 1/4] crypto/aesni_mb: fix typo in error message
>
> This patch fixes a typo in the log message for error allocation.
> The typo incorrectly spelled 'allocating' as 'allocationg' in the
> log message for error allocation.
>
> Fixes: f9dfb59edbcc ("crypto/ipsec_mb: s
> Subject: [PATCH v1] test/crypto: remove unused stats in test setup
>
> Remove unused stats in test setup.
>
> Coverity issue: 373869
> Fixes: 2c6dab9cd93 ("test/crypto: add RSA and Mod tests")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Gowrishankar Muthukrishnan
Applied to dpdk-next-crypto
Than
> Subject: [PATCH v1] test/crypto: fix asymmetric capability test
>
> Fix asymmetric capability test for below:
> * Skip test if asymmetric crypto feature is not supported by device.
> * Assert return value of RTE function to get asymmetric capability.
>
> Coverity issue: 373365
> Fixes: 2c6dab
On Thu, 18 Jul 2024 16:39:35 +
Raghavan V wrote:
> Hi Stephen,
> Thanks for your response.
>
> As our application has limitations while using RSS,
> I would prefer a similar approach to RTE_ACTION_TYPE_QUEUE.
There is no action like this since hardware does not support it.
Multi queue suppo
The conversion from seconds to nanoseconds in the pcapng test
would overflow on 32 bit platforms leading to this test failing.
Reported-by: Luca Boccassi
Signed-off-by: Stephen Hemminger
---
app/test/test_pcapng.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/test/test
Acked-by: Joshua Washington
Thanks!
On Linux (and probably BSD), CPU 0 can not be fully isolated
because it receives timer interrupts and is used for other
kernel related functions. The DPDK documentation should
be updated to tell users to avoid polling on that CPU.
Signed-off-by: Stephen Hemminger
---
doc/guides/linux_gsg/enable_
Many places in the documentation are using -n 4 to set
the number of memory channels. This should not be recommended
since it is not always right and the default should be used
instead.
Signed-off-by: Stephen Hemminger
---
doc/guides/contributing/documentation.rst | 2 +-
doc/guides/cryptod
>
> My initial reaction is negative on this. The DPDK does not need more nerd
> knobs for performance. If it is a performance win, it should be automatic and
> handled by the driver.
>
> If you absolutely have to have another flag, then it should be in existing
> config
> (yes, extend the ABI) r
On Thu, 18 Jul 2024 at 18:43, Stephen Hemminger
wrote:
>
> The conversion from seconds to nanoseconds in the pcapng test
> would overflow on 32 bit platforms leading to this test failing.
>
> Reported-by: Luca Boccassi
> Signed-off-by: Stephen Hemminger
> ---
> app/test/test_pcapng.c | 2 +-
>
v3:
* Minor adjustments to doc strings
* Return labels added for testpmd methods
Nicholas Pratte (3):
dts: add boolean to adjust addresses
dts: add methods for setting mac and multicast addresses
dts: mac filter test suite refactored for new dts
dts/framework/config/conf_yaml_schema.js
This test should be using the TEST_ASSERT macros, and can be
run as part of the fast test suite now.
Signed-off-by: Stephen Hemminger
---
app/test/test_alarm.c | 53 ---
1 file changed, 20 insertions(+), 33 deletions(-)
diff --git a/app/test/test_alarm.c
Several of the unit tests were not listed in any test suite
and therefore were rarely run. When running build this was reported as
errors:
WARNING: Test "alarm_autotest" is not defined in any test suite
WARNING: Test "cksum_perf_autotest" is not defined in any test suite
Put the alarm, cksum, an
The cksum tests would not get run since not part of one
of the test suites. Meson complains with:
WARNING: Test "cksum_perf_autotest" is not defined in any test suite
Signed-off-by: Stephen Hemminger
---
app/test/test_cksum_perf.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff -
The red tests were not run because not part of any suite.
Meson warning is:
WARNING: Test "red_autotest" is not defined in any test suite
Signed-off-by: Stephen Hemminger
---
app/test/test_red.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/test/test_red.c b/app/test/t
The tests were not part of any suite so not run normally.
Meson warning is:
WARNING: Test "timer_secondary_autotest" is not defined in any test suite
Signed-off-by: Stephen Hemminger
---
app/test/test_timer_secondary.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/test/
Various test cases in the mac filter test suite called for granular
manipulation of destination mac addresses to properly test mac address
filtering functionality. To compensate, there is now an
adjust_addresses boolean which the user can toggle if they wish to send
their own addressing; the boolea
Several new methods have been added to TestPMDShell in order to produce
the mac filter's individual test cases:
- set_mac_addr
- set_multicast_mac_addr
- rx_vlan_add
- rx_vlan_rm
- vlan_filter_set_on
- vlan_filter_set_off
- set_promisc
set_mac_addr and set_multicast_addr were created for th
From: Stephen Hemminger
The current code uses unnecessary locking to set VF MTU, resulting in
deadlock on hot add/remove path. Fix this by using rte_eth_dev_set_mtu()
to set VF MTU.
Signed-off-by: Stephen Hemminger
Fixes: 45c83603087e ("net/netvsc: support MTU set")
Cc: sta...@dpdk.org
Signed-
From: Malcolm Bumgardner
In the device event unregister code, it unconditionally remove all
callbacks which are registered with device_name set to NULL. This results
in many callbacks uncorrectly removed.
Fix this by only removing callbacks with matching cb_fn and cb_arg.
Signed-off-by: Malcolm
The mac address filter test suite, whose test cases are based on old
DTS's test cases, has been refactored to interface with the new DTS
framework.
In porting over this test suite into the new framework, some
adjustments were made, namely in the EAL and TestPMD parameter provided
before executing
> Hi Brian,
>
> Since Ciara is no longer available and you are the new maintainer, can you
> investigate this patch?
> There were some concerns which Ciara highlighted. Can you check?
>
Any update on this patch?
> > > Subject: [PATCH v2] app/test-crypto-perf: add throughput OOP decryption
> >
> From: Robin Jarry [mailto:rja...@redhat.com]
>
> Hi folks,
>
> while working on IPv6 support for grout [1], I noticed that all DPDK
> IPv6 APIs used fixed sized arrays in the route lookup functions [2].
>
> int rte_fib6_lookup_bulk(struct rte_fib6 *fib,
> uint8_t ips
On Thu, 18 Jul 2024 22:27:03 +0200
Morten Brørup wrote:
> > From: Robin Jarry [mailto:rja...@redhat.com]
> >
> > Hi folks,
> >
> > while working on IPv6 support for grout [1], I noticed that all DPDK
> > IPv6 APIs used fixed sized arrays in the route lookup functions [2].
> >
> > int rte_fib6
Hi Robin,
Thanks, that is a good idea.
чт, 18 июл. 2024 г. в 21:27, Morten Brørup :
> > From: Robin Jarry [mailto:rja...@redhat.com]
> >
> > Hi folks,
> >
> > while working on IPv6 support for grout [1], I noticed that all DPDK
> > IPv6 APIs used fixed sized arrays in the route lookup functio
Vladimir Medvedkin, Jul 18, 2024 at 23:25:
I think alignment should be 1 since in FIB6 users usually don't copy IPv6
address and just provide a pointer to the memory inside the packet. Current
vector implementation loads IPv6 addresses using unaligned access (
_mm512_loadu_si512) so it doesn't re
Stephen Hemminger, Jul 18, 2024 at 23:15:
If you look at the standard netinet/in.h the storage of IPv6 addresses
is in in6_addr. DPDK has always wanted to do its own thing...
The in6_addr is a union with no explicit alignment.
struct in6_addr
{
union
{
uint8_t __u6_addr8[16]
On 7/17/2024 2:33 PM, Serhii Iliushyk wrote:
> @@ -373,6 +645,15 @@ nthw_pci_dev_init(struct rte_pci_device *pci_dev)
> return -1;
> }
>
> + /* connect structs */
> + internals->p_drv = p_drv;
> + eth_dev->data->dev_private =
On 7/17/2024 2:32 PM, Serhii Iliushyk wrote:
> Add initial ntnic ethdev skeleton and register PCI probe functions
> Update documentation: Device description and feature list
>
> Signed-off-by: Serhii Iliushyk
>
For series,
Reviewed-by: Ferruh Yigit
Series applied to dpdk-next-net/main, thanks.
On 7/17/2024 9:38 PM, Ed Czeck wrote:
> Behavior for signed integer overflow is not defined
> which can causes undesired behavior at values near
> max and min bounds.
> The used of unsigned is defined as to use modulo arithmetic
> which is the desired behavior.
> This patch replaces int32_t with ui
My ack might have been a bit premature. This patch seems to have a
number of style errors, and does not seem to apply to HEAD of
dpdk-next-net. See http://dpdk.org/patch/142498 for more detail.
The code supplied in the patch does not seem to have any indentation.
Please note that DPDK uses tabs (a
Thanks Joshua, I will fix all the nits in my next email.
On Fri, Jul 19, 2024 at 8:53 AM Joshua Washington
wrote:
> My ack might have been a bit premature. This patch seems to have a
> number of style errors, and does not seem to apply to HEAD of
> dpdk-next-net. See http://dpdk.org/patch/142498
The RSS support for GVE allows multiple CPU cores to
handle the rx/tx queues as pollers. This requires initializing
the eth_dev_ops and updating the RX/TX functions for these pollers.
Signed-off-by: Tathagat Priyadarshi
Acked-by: Rushil Gupta
Acked-by: Joshua Washington
---
drivers/net/gve/gve
> Subject: [PATCH] net/netvsc: use rte_eth_dev_set_mtu to set VF MTU
>
> From: Stephen Hemminger
>
> The current code uses unnecessary locking to set VF MTU, resulting in
> deadlock on hot add/remove path. Fix this by using rte_eth_dev_set_mtu() to
> set VF MTU.
>
> Signed-off-by: Stephen Hemmi
The RSS support for GVE allows multiple CPU cores to
handle the rx/tx queues as pollers. This requires initializing
the eth_dev_ops and updating the RX/TX functions for these pollers.
Signed-off-by: Tathagat Priyadarshi
Acked-by: Rushil Gupta
Acked-by: Joshua Washington
---
drivers/net/gve/gve
65 matches
Mail list logo
