Hi, Weifeng Li
On 2020/7/18 12:35, Weifeng Li wrote:
A dpdk bonding 802.3ad network as follows:
+--++---+
|dpdk lacp |bond1.1 <--> bond2.1|switch lacp|
| |bond1.2 <--> bond2.2| |
+--++---+
> -Original Message-
> From: Aaron Conole
> Sent: Saturday, July 18, 2020 6:39 AM
> To: Lukasz Wojciechowski
> Cc: David Marchand ; Van Haaren Harry
> ; Igor Romanov
> ; Honnappa Nagarahalli
> ; Phil Yang ; dev
> ; Ferruh Yigit
> Subject: Re: [dpdk-dev] Random failure in service_autotest
> -Original Message-
> From: Medvedkin, Vladimir
> Sent: Saturday, July 18, 2020 1:12 AM
> To: Ruifeng Wang ; Bruce Richardson
>
> Cc: dev@dpdk.org; nd ; Honnappa Nagarahalli
> ; Phil Yang
> Subject: Re: [PATCH v2] lpm: fix unchecked return value
>
> Hi Ruifeng,
>
Hi Vladimir,
> On 1
From: Farah Smith
Initialize table scope resource manager parameter.
Clear out rm_is_allocated parms before calling as base_index was added and
used incorrectly in this instance.
Signed-off-by: Farah Smith
Signed-off-by: Somnath Kotur
Reviewed-by: Kishore Padmanabha
Reviewed-by: Ajit Khaparde
From: Peter Spreadborough
Add support for new resource manager to manage CFA resources.
TCAM is split into high and low regions now and CFA resource types
are being updated accordingly.
Signed-off-by: Peter Spreadborough
Signed-off-by: Somnath Kotur
Reviewed-by: Farah Smith
Reviewed-by: Ajit
Some changes, cleanups/fixes in the TF-ULP layer
v1->v2: Got rid of patch 14 from v1 that was adding debug logs for now
v2->v3: Update commit logs based on review comments
Farah Smith (2):
net/bnxt: initialize table scope parameter
net/bnxt: fix exact match message size
Jay Ding (1):
net/b
From: Kishore Padmanabha
The protocol header are implicitly matched based on the proto
field data. For instance, if ether type is set as 0x800 in the
ether header then ipv4 protocol header is assumed to be present
for template matching even if ipv4 header is not present in the
given flow pattern.
From: Kishore Padmanabha
Removed the check to enable default flows only when VF representor
are enabled. It should be enabled all the time in truflow mode.
Signed-off-by: Kishore Padmanabha
Signed-off-by: Somnath Kotur
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/bnxt_ethdev.c | 5 ++---
From: Jay Ding
Use NAT IPv4 instead of NAT IPv4 SRC and DST.
Signed-off-by: Jay Ding
Signed-off-by: Somnath Kotur
Reviewed-by: Kishore Padmanabha
---
drivers/net/bnxt/tf_core/tf_core.h | 4 +---
drivers/net/bnxt/tf_core/tf_device_p4.h | 1 -
drivers/net/bnxt/tf_core/tf_util.c | 6 +
From: Somnath Kotur
OVS-DPDK is accumulating the flow counters that are returned as part
of the flow_query API and it is being issued at least 3 times every second.
So there is no need to accumulate the counts internally in the driver.
Fixes: 306c2d28e247 ("net/bnxt: add support for flow query w
From: Farah Smith
Fix incorrect EM message size when calling insert_em_internal.
Fixes: 98487d729b4a ("net/bnxt: cleanup and refactor session management")
Signed-off-by: Farah Smith
Signed-off-by: Somnath Kotur
Reviewed-by: Randy Schacher
Reviewed-by: Ajit Khaparde
---
drivers/net/bnxt/tf_
From: Kishore Padmanabha
The default egress rule should include buffer descriptor action
record only if the VF representor is enabled.
Signed-off-by: Kishore Padmanabha
Signed-off-by: Somnath Kotur
Reviewed-by: Michael Baucom
Reviewed-by: Ajit Khaparde
---
drivers/net/bnxt/tf_ulp/bnxt_ulp.c
From: Randy Schacher
Update cfa_resource_types.h to use SPDX license header.
Reported-by: Stephen Hemminger
Signed-off-by: Randy Schacher
Signed-off-by: Somnath Kotur
Reviewed-by: Ajit Khaparde
---
drivers/net/bnxt/tf_core/cfa_resource_types.h | 13 +++--
1 file changed, 3 insertion
From: Kishore Padmanabha
Avoid dereferencing a null pointer.
Fixes: 313ac35ac701 ("net/bnxt: support ULP session manager init")
Signed-off-by: Kishore Padmanabha
Signed-off-by: Somnath Kotur
Reviewed-by: Michael Baucom
---
drivers/net/bnxt/tf_ulp/ulp_mark_mgr.c | 8 +---
1 file changed,
From: Randy Schacher
Remove unused define TF_MSG_TCAM_SET_DEV_DATA_SIZE.
Signed-off-by: Somnath Kotur
Reviewed-by: Randy Schacher
Reviewed-by: Shahaji Bhosle
Signed-off-by: Randy Schacher
---
drivers/net/bnxt/tf_core/tf_msg.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/b
From: Somnath Kotur
remove a debug log for now
Fixes: 75f9197c0ded ("net/bnxt: add support for identifier search and ref
count")
Signed-off-by: Somnath Kotur
---
drivers/net/bnxt/tf_ulp/ulp_mapper.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/net/bnxt/tf_ulp/ulp_mapper.c
b
From: Kishore Padmanabha
The truflow session open allocation parameters are updated to
support NAT records, L2 context regions, engress encap features.
Signed-off-by: Kishore Padmanabha
Signed-off-by: Somnath Kotur
---
drivers/net/bnxt/tf_ulp/bnxt_ulp.c | 20
1 file chang
Him
> -Original Message-
> From: Thomas Monjalon
> Sent: Monday, July 13, 2020 6:37 PM
> To: dev@dpdk.org
> Cc: Raslan Darawsheh ; Ophir Munk
> ; Matan Azrad ; Shahaf
> Shuler ; Slava Ovsiienko
>
> Subject: [PATCH] common/mlx5: fix link with ibverbs glue dlopen option
>
> In case the ib
Hi,
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Friday, July 17, 2020 5:28 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Thomas Monjalon
> Subject: [PATCH 1/3] net/mlx5: fix compilation issue with missing DevX event
>
> If there is no support for DevX even
> -Original Message-
> From: dev On Behalf Of Manish Chopra
> Sent: Friday, July 17, 2020 2:19 AM
> To: Gaƫtan Rivet ; Thomas Monjalon
>
> Cc: Jerin Jacob ; Ferruh Yigit
> ; Igor Russkikh ; dpdk-dev
>
> Subject: Re: [dpdk-dev] [EXT] Re: [PATCH v2 1/7] lib/librte_pci: add
> rte_pci_regs.h
Hi Pablo,
> >
> > The RTE_CRYPTODEV_FF_SECURITY feature was disabled through the
> ff_disable
> > device configuration option for all cryptodev tests, including security
> > related
> > tests. This patch updates the cryptodev unit tests to not disable
> > RTE_CRYPTODEV_FF_SECURITY for DOCSIS and P
> > The RTE_CRYPTODEV_FF_SECURITY feature was disabled through the
> ff_disable
> > device configuration option for all crypto performance tests, including
> > security
> > related tests. This patch updates the crypto performance tool to not disable
> > RTE_CRYPTODEV_FF_SECURITY for DOCSIS and PDC
> > The AESNI-MB CPU test cases, which are executed via the
> > cryptodev_cpu_aesni_mb_autotest command, aborted when it tried to run the
> > DOCSIS security tests as these are not CPU type tests. The abort happened at
> the
> > following line in process_crypto_request():
> >
> > RTE_VERIFY(gbl_act
>
>
> > The RTE_CRYPTODEV_FF_SECURITY feature was disabled through the
> > ff_disable device configuration option for all cryptodev tests,
> > including security related tests. This patch updates the cryptodev unit
> > tests to not disable RTE_CRYPTODEV_FF_SECURITY for DOCSIS and PDCP
> > securit
> > This patch improves the DOCSIS session creation as follows:
> > - it validates the security action type as well as the protocol before
> > creating a session and now does this validation before allocating the
> > session from the mempool
> >
> > Fixes: fda5216fba55 ("crypto/aesni_mb: suppor
> > Multi-segment mbufs are not supported for DOCSIS security protocol.
> > This patch adds an explicit check for this and returns an op error if
> > this case is found. This limitation is also added to the QAT cryptodev
> > documentation.
> >
> > Fixes: 6f0ef237404b ("crypto/qat: support DOCSIS pr
> > The variable names crc_length and crc_offset have been changed to
> > crc_data_len and crc_data_ofs respectively, to make it clearer as to
> > their use i.e. the length and offset of the data over which the CRC is
> > calculated.
> >
> > Fixes: 6f0ef237404b ("crypto/qat: support DOCSIS protocol
> > This patch makes some minor improvements to the security instance setup
> > for the QAT SYM PMD. All of this setup code is now in one '#ifdef
> > RTE_LIBRTE_SECURITY' block. Enabling the RTE_CRYPTODEV_FF_SECURITY
> > feature for the device is also moved to this block.
> >
> > Fixes: 6f0ef237404
>
> > > This patch makes some minor improvements to the security instance setup
> > > for the QAT SYM PMD. All of this setup code is now in one '#ifdef
> > > RTE_LIBRTE_SECURITY' block. Enabling the RTE_CRYPTODEV_FF_SECURITY
> > > feature for the device is also moved to this block.
> > >
> > > Fix
> >
> > This patch updates the minimum driver version that supports
> > Intel QuickAssist device D15xx.
> >
> > Signed-off-by: Adam Dybkowski
> Acked-by: Fiona Trahe
Applied to dpdk-next-crypto
Thanks.
MPRQ (Multi-Packet Rx Queue) processes one packet at the time
using simple scalar instructions. MPRQ works by posting a single
large buffer (consisted of multiple fixed-size strides) in order to
receive multiple packets at once on this buffer. A Rx packet is then
copied to a user-provided mbuf or P
31 matches
Mail list logo