On Tue, Jul 30, 2019 at 12:18:59AM +0200, Thomas Monjalon wrote:
> External Email
>
> --
> 25/07/2019 17:51, Harman Kalra:
> > Offloafing Rx timestamp is a device capability than queue capability.
>
> Why is it a device capabilit
Hi Simei,
> -Original Message-
> From: dev On Behalf Of simei
> Sent: Monday, July 29, 2019 5:44 AM
> To: qi.z.zh...@intel.com; jingjing...@intel.com; ferruh.yi...@intel.com;
> Adrien Mazarguil
> Cc: dev@dpdk.org; simei...@intel.com
> Subject: [dpdk-dev] [RFC,v3] ethdev: extend RSS off
>
> > > > All the functionality of the legacy code path in now available in the
> librte_ipsec
> > > > library. It is planned to deprecate the legacy code path in the 19.11
> > > > release
> and
> > > > remove the legacy code path in the 20.02 release.
> > > >
> > > > Signed-off-by: Bernard Ire
Hi Slava,
Monday, July 29, 2019 6:27 PM, Viacheslav Ovsiienko:
> Subject: [dpdk-dev] [PATCH v2] net/mlx5: fix ESXi VLAN in virtual machine
>
> On ESXi setups when we have SR-IOV and E-Switch enabled there is the
> problem to receive VLAN traffic on VF interfaces. The NIC driver in ESXi
> hypervis
25/07/2019 17:51, Harman Kalra:
> Offloafing Rx timestamp is a device capability than queue capability.
Why is it a device capability and not a queue capability?
> Hence the logic to enable HW timestamp via DEV_RX_OFFLOAD_TIMESTAMP
> flag should be before device configuration.
>
> Fixes: cd1dade
> > Observed an issue with the length and domain number of the delay request
> > message sent out by the client. Due to which delay response from master
> > was not received.
> >
> > Fixes: ab129e9065a5 ("examples/ptpclient: add minimal PTP client")
> > Cc: sta...@dpdk.org
> >
> > Signed-off-by:
> > Application uses different pool to allocate direct and indirect
> > mbufs which are further spliced together to consturct a fragmented
> > packet and same is transmitted over the port which is configured
> > with DEV_TX_OFFLOAD_MBUF_FAST_FREE enabled i.e. all segments
> > must belong to the sam
> > Caught while looking at the rx offloads code.
> >
> > rx_mode is a global variable for the default rx configuration.
> > Rename the local rx_mode variable in cmd_set_vf_rxmode_parsed.
> >
> > Fixes: 7741e4cf16c0 ("app/testpmd: VMDq and DCB updates")
> > Cc: sta...@dpdk.org
> >
> > Signed-off
> > In the rather unlikely case where the first segment is too small to contain
> > an
> > ethernet header, we can't go and directly dereference the mbuf data buffer.
> >
> > Using rte_pktmbuf_read is a little more expensive but this is still
> > acceptable
> > for a debugging feature.
> >
> >
From: Kalesh AP
Fixed to return the checksum status of rx packets by setting
"ol_flags" correctly in vector mode receive.
These changes have been there for non vector mode receive.
In vector mode receive also indicate inner and outer checksum
errors individually in "ol_flag" to indicate L3 and L
From: Kalesh AP
There is a bug in context memory allocation because of which
it results in reusing the context memory allocated for the first
port while allocating memory for next ports.
Fix it by passing the port id in the name field while
allocating context memory.
Fixes: f8168ca0e690 ("net/b
25/07/2019 11:03, David Hunt:
> From: Liang Ma
>
> The Distributor autotest can lock if ran enough times. Worker and
> distributir threads get into a livelock situation waiting on each
> other.
> Issue first encountered by RedHat in Travis CI
> https://bugs.dpdk.org/show_bug.cgi?id=316
>
> To re
> -Original Message-
> From: dev On Behalf Of Xiaolong Ye
> Sent: Friday, July 26, 2019 9:44 AM
> To: Yigit, Ferruh ; Xing, Beilei
> ; Zhang, Qi Z
> Cc: dev@dpdk.org; Ye, Xiaolong
> Subject: [dpdk-dev] [PATCH v2 02/11] net/i40e: replace license text with
> SPDX tag
>
> Signed-off-by: Xi
> -Original Message-
> From: dev On Behalf Of Xiaolong Ye
> Sent: Friday, July 26, 2019 2:30 AM
> To: Yigit, Ferruh ; Lu, Wenzhuo
>
> Cc: dev@dpdk.org; Ye, Xiaolong
> Subject: [dpdk-dev] [PATCH v1 03/11] net/e1000: replace license text with
> SPDX tag
>
> Signed-off-by: Xiaolong Ye
> -
> -Original Message-
> From: dev On Behalf Of Xiaolong Ye
> Sent: Friday, July 26, 2019 2:30 AM
> To: Yigit, Ferruh ; Lu, Wenzhuo
> ; Ananyev, Konstantin
>
> Cc: dev@dpdk.org; Ye, Xiaolong
> Subject: [dpdk-dev] [PATCH v1 01/11] net/ixgbe: replace license text with
> SPDX tag
>
> Signed-
> -Original Message-
> From: dev On Behalf Of Xiaolong Ye
> Sent: Friday, July 26, 2019 2:30 AM
> To: Yigit, Ferruh ; Xing, Beilei
> ; Zhang, Qi Z
> Cc: dev@dpdk.org; Ye, Xiaolong
> Subject: [dpdk-dev] [PATCH v1 02/11] net/i40e: replace license text with
> SPDX tag
>
> Signed-off-by:
29/07/2019 09:32, Xiaolong Ye:
> Signed-off-by: Xiaolong Ye
Applied, thanks
> From: Jerin Jacob
>
> Replace mvasm and mvpp2 Marvell PMD driver documentation license text with
> SPDX tag.
>
> Cc: Hemant Agrawal
> Cc: Tomasz Duszynski
> Cc: Liron Himi
>
> Signed-off-by: Jerin Jacob
> Acked-by: Liron Himi
Applied, thanks
29/07/2019 09:33, Hemant Agrawal:
> Signed-off-by: Hemant Agrawal
> ---
> lib/librte_eal/common/eal_common_bus.c | 32 ++---
> lib/librte_eal/common/include/rte_bus.h | 32 ++---
> 2 files changed, 4 insertions(+), 60 deletions(-)
Applied, thanks
> > This was missed when promoting this API to stable.
> >
> > Fixes: 7a0ac7cdb454 ("service: promote experimental functions to stable")
> >
> > Signed-off-by: David Marchand
>
> Acked-by: Gage Eads
Applied, thanks
29/07/2019 17:10, Michael Santana Francisco:
> On Sat, Jul 27, 2019 at 3:21 AM David Marchand
> wrote:
> >
> > Sort the experimental symbols per release to make it easier/quicker to
> > check for how long we have them.
> >
> > Signed-off-by: David Marchand
> > Acked-by: Ferruh Yigit
> > ---
> >
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Monday, July 29, 2019 5:34 PM
> To: Iremonger, Bernard
> Cc: dev@dpdk.org; Akhil Goyal ; Anoob Joseph
> ; Ananyev, Konstantin
> ; Jerin Jacob Kollanukkaran
> ; Narayana Prasad Raju Athreya
>
> Subject:
29/07/2019 10:40, David Marchand:
> On Sun, Jul 28, 2019 at 9:55 PM Thomas Monjalon wrote:
> > 25/07/2019 10:42, David Marchand:
> > > > > > 24/07/2019 17:20, Sean Morrissey:
> > > > On further investigation, the full fix involves
> > > > a change in the EAL command line parameter handling,
> > >
29/07/2019 14:32, Ferruh Yigit:
> build error:
> .../dpdk/build/build/kernel/linux/igb_uio/igb_uio.c:
>In function ‘igbuio_pci_enable_interrupts’:
>.../dpdk/build/build/kernel/linux/igb_uio/igb_uio.c:230:6:
>error: this statement may fall through
>[-Werror=implicit-fallthrough=]
>
26/07/2019 07:24, jer...@marvell.com:
> From: Jerin Jacob
>
> OTX2 AP core can sometimes fissure STP instructions when it is more
> optimal to send such writes into the pipeline as 2 separate
> instructions. However registers should be excluded from such
> optimization. This commit ensures that n
27/07/2019 13:56, Jerin Jacob Kollanukkaran:
> > -Original Message-
> > From: Harman Kalra
> > Sent: Thursday, July 25, 2019 3:57 PM
> > To: Jerin Jacob Kollanukkaran ; Nithin Kumar
> > Dabilpuram ; Vamsi Krishna Attunuru
> > ; Kiran Kumar Kokkilagadda
> >
> > Cc: dev@dpdk.org; Harman Kal
> > > All the functionality of the legacy code path in now available in the
> > > librte_ipsec
> > > library. It is planned to deprecate the legacy code path in the 19.11
> > > release and
> > > remove the legacy code path in the 20.02 release.
> > >
> > > Signed-off-by: Bernard Iremonger
> > >
On Fri, 26 Jul 2019 08:35:50 +0800
simei wrote:
> +#define ETH_RSS_INSET_L2_SRC 0x0400
This won't work on 32 bit systems you need to cast it or add a
unsigned long long modifier (ull or ULL)
> -Original Message-
> From: Dekel Peled
> Sent: Monday, July 29, 2019 18:15
> To: Yongseok Koh ; Slava Ovsiienko
> ; Shahaf Shuler
> Cc: Ori Kam ; dev@dpdk.org; sta...@dpdk.org
> Subject: [PATCH] net/mlx5: fix validation of VLAN pcp item
>
> Function mlx5_flow_validate_item_vlan() valid
On ESXi setups when we have SR-IOV and E-Switch enabled there is the
problem to receive VLAN traffic on VF interfaces. The NIC driver
in ESXi hypervisor does not setup E-Switch vport setting correctly
and VLAN traffic targeted to VF is dropped.
The patch provides the temporary workaround - if the
Hi, Ferruh
On 07/29, Ferruh Yigit wrote:
>On 7/24/2019 4:35 PM, Xiaolong Ye wrote:
>> This patch adds support to allow users enable/disable allmulticast mode for
>> kni interface.
>>
>> This requirement comes from bugzilla 312, more details can refer to:
>> https://bugs.dpdk.org/show_bug.cgi?id=3
Hi,
> -Original Message-
> From: dev On Behalf Of Viacheslav Ovsiienko
> Sent: Monday, July 29, 2019 3:41 PM
> To: dev@dpdk.org
> Cc: Yongseok Koh ; Shahaf Shuler
>
> Subject: [dpdk-dev] [PATCH 0/3] net/mlx5: transmit datapath cumulative fix
> pack
>
> This series contains the pack of b
This patch reduces the memory footprint of tables for the unit test.
Lower memory footprint means the test now passes when trying to allocate
the tables. This patch is mainly to make table_autotest pass in CI.
Signed-off-by: Michael Santana
Acked-by: Cristian Dumitrescu
---
app/test/test_table_
Function mlx5_flow_validate_item_vlan() validates the user setting
is supported by NIC, using a mask with TCI mask 0x0fff.
This check will reject a flow rule specifying a vlan pcp item.
This patch updates mlx5_flow_validate_item_vlan() to use mask 0x,
so flow rules with vlan pcp item are accep
From: Viacheslav Ovsiienko
> On ESXi setups when we have SR-IOV and E-Switch enabled there is the
> problem to receive VLAN traffic on VF interfaces. The NIC driver in ESXi
> hypervisor does not setup E-Switch vport setting correctly and VLAN traffic
> targeted to VF is dropped.
>
> The patch p
From: Viacheslav Ovsiienko
> This series contains the pack of bug fixes and performance
> improvements:
>
> - limit the amount of freed buffers per one tx_burst call
> - set the completion generating request in more uniform
> fashion
> - limit the number of packets in one descriptor t
On Sat, Jul 27, 2019 at 3:21 AM David Marchand
wrote:
>
> Sort the experimental symbols per release to make it easier/quicker to
> check for how long we have them.
>
> Signed-off-by: David Marchand
> Acked-by: Ferruh Yigit
> ---
> Changelog since v2:
> - fixed alphabetical order per release
>
>
On Sun, Jul 14, 2019 at 02:46:58PM +0300, Andrew Rybchenko wrote:
> On 11.07.2019 10:44, Adrien Mazarguil wrote:
> > On Wed, Jul 10, 2019 at 04:37:46PM +, Yongseok Koh wrote:
> > > > On Jul 10, 2019, at 5:26 AM, Thomas Monjalon
> > > > wrote:
> > > >
> > > > 10/07/2019 14:01, Bruce Richardso
When IOMMU is not available, /sys/kernel/iommu_groups will not be
populated. This is happening since at least 3.6 when VFIO support
was added. If the directory is empty, EAL should not pick IOVA as
VA as the default IOVA mode.
Signed-off-by: Anatoly Burakov
Tested-by: Darek Stojaczyk
Tested-by:
On 7/29/2019 2:04 PM, Jerin Jacob Kollanukkaran wrote:
>
>
>> -Original Message-
>> From: dev On Behalf Of Xiaolong Ye
>> Sent: Friday, July 26, 2019 10:14 PM
>> To: Ferruh Yigit ; Cristian Dumitrescu
>> ; Thomas Monjalon
>> ; Andrew Rybchenko
>>
>> Cc: dev@dpdk.org; Xiaolong Ye
>> Sub
On 7/29/2019 2:19 PM, Andrew Rybchenko wrote:
> Fix license from BSD-2-Clause to BSD-3-Clause since the file was
> lost on the driver license change.
>
> Bump copyright year.
>
> Signed-off-by: Andrew Rybchenko
>
> Acked-by: Hemant Agrawal
Applied to dpdk-next-net/master, thanks.
Hi,
> -Original Message-
> From: dev On Behalf Of Matan Azrad
> Sent: Monday, July 29, 2019 2:53 PM
> To: Shahaf Shuler ; Yongseok Koh
> ; Slava Ovsiienko
> Cc: dev@dpdk.org; Dekel Peled
> Subject: [dpdk-dev] [PATCH 00/11] net/mlx5: LRO fixes and enhancements
>
> 1. Fixes.
> 2. 3 modes
On 7/26/2019 5:43 PM, Xiaolong Ye wrote:
> This patchset replaces full BSD-3 license header with spdx tag for the
> remaining files that have Intel copyright.
>
>
> V2 changes:
>
> 1. remove "All rights reserved"
> 2. change "Intel shannon Ltd" to "Intel Corporation"
> 3. add ack tag from Bruce
https://bugs.dpdk.org/show_bug.cgi?id=323
Thomas Monjalon (tho...@monjalon.net) changed:
What|Removed |Added
CC||tho...@monjalon.net
On 7/24/2019 4:35 PM, Xiaolong Ye wrote:
> This patch adds support to allow users enable/disable allmulticast mode for
> kni interface.
>
> This requirement comes from bugzilla 312, more details can refer to:
> https://bugs.dpdk.org/show_bug.cgi?id=312
>
> Bugzilla ID: 312
>
> Signed-off-by: Xia
> -Original Message-
> From: Andrew Rybchenko
> Sent: Monday, July 29, 2019 6:12 PM
> To: Vamsi Krishna Attunuru ; dev@dpdk.org
> Cc: tho...@monjalon.net; Jerin Jacob Kollanukkaran ;
> olivier.m...@6wind.com; ferruh.yi...@intel.com;
> anatoly.bura...@intel.com; Kiran Kumar Kokkilagadda
>
> -Original Message-
> From: Wang, Ying A
> Sent: Monday, July 29, 2019 4:42 AM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org; Ye, Xiaolong ; Yang, Qiming
> ; Wang, Ying A ;
> sta...@dpdk.org
> Subject: [PATCH v3] net/ice: fix LLDP forward
>
> The patch fix the issue that lldp packet can't be f
Acked-by: Liron Himi
Regards,
Liron
-Original Message-
From: jer...@marvell.com
Sent: Monday, July 29, 2019 16:17
To: dev@dpdk.org; Tomasz Duszynski ; Michael Shamis
; Liron Himi ; John McNamara
; Marko Kovacevic
Cc: Jerin Jacob Kollanukkaran ; Hemant Agrawal
Subject: [dpdk-dev] [
> -Original Message-
> From: Igor Ryzhov
> Sent: Monday, July 29, 2019 5:55 PM
> To: Vamsi Krishna Attunuru
> Cc: dev@dpdk.org; Thomas Monjalon ; Jerin Jacob
> Kollanukkaran ; Olivier Matz
> ; Ferruh Yigit ;
> anatoly.bura...@intel.com; Andrew Rybchenko
> ; Kiran Kumar Kokkilagadda
>
>
Acked-by: Hemant Agrawal
Acked-by: Hemant Agrawal
Fix license from BSD-2-Clause to BSD-3-Clause since the file was
lost on the driver license change.
Bump copyright year.
Signed-off-by: Andrew Rybchenko
---
doc/guides/nics/sfc_efx.rst | 25 ++---
1 file changed, 2 insertions(+), 23 deletions(-)
diff --git a/doc/guides/nics
From: Jerin Jacob
Replace mvasm and mvpp2 Marvell PMD driver
documentation license text with SPDX tag.
Cc: Hemant Agrawal
Cc: Tomasz Duszynski
Cc: Liron Himi
Signed-off-by: Jerin Jacob
---
doc/guides/cryptodevs/mvsam.rst | 29 +
doc/guides/nics/mvpp2.rst |
On 29-Jul-19 12:18 PM, Anatoly Burakov wrote:
Currently, mem config will be mapped without using the virtual
area reservation infrastructure, which means it will be mapped
at an arbitrary location. This may cause failures to map the
shared config in secondary process due to things like PCI
whitel
On Wed, Jul 10, 2019 at 11:49 PM Thomas Monjalon wrote:
>
> 09/07/2019 13:09, Bernard Iremonger:
> > This patch fixes the out-of-bounds coverity issue by removing the
> > offending line of code at line 107 in rte_flow_classify_parse.c
> > which is never executed.
> >
> > Coverity issue: 343454
> >
> -Original Message-
> From: dev On Behalf Of Xiaolong Ye
> Sent: Friday, July 26, 2019 10:14 PM
> To: Ferruh Yigit ; Cristian Dumitrescu
> ; Thomas Monjalon
> ; Andrew Rybchenko
>
> Cc: dev@dpdk.org; Xiaolong Ye
> Subject: [dpdk-dev] [PATCH v2 07/11] ethdev: replace license text with
On Mon, Jul 29, 2019 at 2:19 PM Thomas Monjalon wrote:
>
> 29/07/2019 12:36, David Marchand:
> > On Wed, Jul 17, 2019 at 5:53 PM Thomas Monjalon wrote:
> > >
> > > In order to ease basic testing with customized options,
> > > EAL and testpmd options can be added as third and fourth arguments
> >
On Mon, Jul 29, 2019 at 2:16 PM Thomas Monjalon wrote:
>
> 29/07/2019 12:35, David Marchand:
> > On Wed, Jul 17, 2019 at 5:53 PM Thomas Monjalon wrote:
> > > --- a/devtools/test-null.sh
> > > +++ b/devtools/test-null.sh
> > > -if grep -q SHARED_LIB=y $build/.config; then
> > > - pmd='-d lib
Not all OS's follow Linux's memory layout, which may lead to
problems following the suggested common address hint absent
of a base-virtaddr flag. Make this address hint OS-specific.
Cc: sta...@dpdk.org
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/common/eal_common_memory.c | 19 +--
Currently, mem config will be mapped without using the virtual
area reservation infrastructure, which means it will be mapped
at an arbitrary location. This may cause failures to map the
shared config in secondary process due to things like PCI
whitelist arguments allocating memory in a space where
Mellanox ConnectX-4LX NIC in configurations with disabled
E-Switch can operate without minimal required inline data
into Tx descriptor. There was the hardcoded limit set to
18B in PMD, fixed to be no limit (0B).
Fixes: 38b4b397a57d ("net/mlx5: add Tx configuration and setup")
Signed-off-by: Viach
On 7/29/19 3:13 PM, vattun...@marvell.com wrote:
From: Vamsi Attunuru
Patch adds a routine to populate mempool from page aligned and
page sized chunks of memory to ensure memory objs do not fall
across the page boundaries. It's useful for applications that
require physically contiguous mbuf mem
The packets transmitting in mlx5 is performed by building
Tx descriptors (WQEs) and sending last ones to the NIC.
The descriptor can contain the special flags, telling the NIC
to generate Tx completion notification (CQEs). At the beginning
of tx_burst() routine PMD checks whether there are some Tx
This patch limits the amount of fetched and processed
completion descriptors in one tx_burst routine call.
The completion processing involves the buffer freeing
which may be time consuming and introduce the significant
latency, so limiting the amount of processed completions
mitigates the latency
This series contains the pack of bug fixes and performance
improvements:
- limit the amount of freed buffers per one tx_burst call
- set the completion generating request in more uniform
fashion
- limit the number of packets in one descriptor to improve
latency
Signed-off-by: Viache
Traffic bps statistics is very useful for performance testing.
Add bits per second statistics for Rx and Tx.
Signed-off-by: Matan Azrad
---
app/test-pmd/config.c | 24
1 file changed, 20 insertions(+), 4 deletions(-)
diff --git a/app/test-pmd/config.c b/app/test-pmd/co
When the mbuf data size cannot contain the maximum Rx packet length with
the mbuf headroom, a packet should be scattered in more than one mbuf.
The application did not configure scatter offload in the above case.
Enable the Rx scatter offload in the above case.
Fixes: 33f9630fc23d ("app/testpmd:
Acked-by: Viacheslav Ovsiienko
> -Original Message-
> From: Matan Azrad
> Sent: Monday, July 29, 2019 14:53
> To: Shahaf Shuler ; Yongseok Koh
> ; Slava Ovsiienko
> Cc: dev@dpdk.org; Dekel Peled
> Subject: [PATCH 00/11] net/mlx5: LRO fixes and enhancements
>
> 1. Fixes.
> 2. 3 modes t
build error:
.../dpdk/build/build/kernel/linux/igb_uio/igb_uio.c:
In function ‘igbuio_pci_enable_interrupts’:
.../dpdk/build/build/kernel/linux/igb_uio/igb_uio.c:230:6:
error: this statement may fall through
[-Werror=implicit-fallthrough=]
230 | if (pci_alloc_irq_vectors(udev->pdev,
Hi,
I believe iova_mode check should not be automatic and should be a part
of rte_kni_conf.
What if I want to use KNI just as a pure virtual device without any
connection to a real PCI device in an application that works in VA
mode?
Best regards,
Igor
On Mon, Jul 29, 2019 at 3:14 PM wrote:
>
>
The WQ size configuration via DevX didn't take into acount the maximum
number of segments per packet what wrongly caused to configure bigger
WQE size than the size expected by the PMD in other places.
The scatter mode stride size should be the size of segment multiplied
by the number of maximum se
29/07/2019 12:36, David Marchand:
> On Wed, Jul 17, 2019 at 5:53 PM Thomas Monjalon wrote:
> >
> > In order to ease basic testing with customized options,
> > EAL and testpmd options can be added as third and fourth arguments
> > of the "null PMD" script.
> >
> > Also, the first argument becomes m
29/07/2019 12:35, David Marchand:
> On Wed, Jul 17, 2019 at 5:53 PM Thomas Monjalon wrote:
> > --- a/devtools/test-null.sh
> > +++ b/devtools/test-null.sh
> > -if grep -q SHARED_LIB=y $build/.config; then
> > - pmd='-d librte_pmd_null.so'
> > +testpmd=$build/app/dpdk-testpmd
> > +[ -f "$test
If the mbuf size of the Rx mempool supplied by the user in the Rx setup
is unable to contain the maximum Rx packet length in addition to the
mbuf head-room, the Rx scatter offload must be configured. Otherwise,
there is not enough space in single mbuf to contain a packet with size of
the maximum Rx
LRO support was only for MPRQ, hence mprq Rx burst was selected when
LRO was configured in the port.
The current support for MPRQ is suffering from bad memory utilization
since an external mempool is allocated by the PMD for the packets data
in addition to the user mempool, besides that, the user
Enabling LRO offload per queue makes sense because the user will
probably want to allocate different mempool for LRO queues - the LRO
mempool mbuf size may be bigger than non LRO mempool.
Change the LRO offload to be per queue instead of per port.
If one of the queues is with LRO enabled, all the
Patch [1] zeroes the mbuf headroom when the port is configured with LRO
because when working with more than one stride per packet the HW cannot
guaranty an headroom in the start stride of each packet.
Change the solution to support mbuf headroom by adding an empty buffer
as the first packet segmen
The alignment requested by the FW for WQ buffer allocation is 512.
Change it from cache line alignment to 512.
Fixes: dc9ceff73c99 ("net/mlx5: create advanced RxQ via DevX")
Signed-off-by: Matan Azrad
Acked-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_prm.h | 3 +++
drivers/net/mlx5/mlx
The field max_rx_pkt_len in Rx configuration indicates the maximum size
for Rx packet to be received.
There was no any field to indicate the maximum size of LRO packet to be
received by the application.
Assuming the user configures max_rx_pkt_len as the maximum LRO packet
length when LRO is confi
When a user configures LRO in the port offloads, he probably wants each
TCP packet will have a chance to open an LRO session.
The PMD wasn't configure LRO in the flow TIR if the flow is not
explicitly configured TCP item despite the flow included TCP traffic.
For example, the next flows were not
When LRO offload is configured in Rx queue, the HW may coalesce TCP
packets from same TCP connection into single packet.
In this case the SW should fix the relevant packet headers because
the HW doesn't update them according to the new created packet
characteristics but provides the update values
1. Fixes.
2. 3 modes to support headroom with LRO.
3. Allow LRO per queue.
Matan Azrad (11):
net/mlx5: fix Rx scatter mode validation
net/mlx5: limit LRO size to the maximum Rx packet
net/mlx5: remove redundant offload flag reset
net/mlx5: support mbuf headroom for LRO packet
net/mlx5: f
When the Rx queue is not in striding RQ mode it should be configured as
cyclic RQ.
In this case the type remains 0 which means linked-list type.
Set the RQ type to be cyclic when the queue is not in striding RQ mode.
Fixes: dc9ceff73c99 ("net/mlx5: create advanced RxQ via DevX")
Signed-off-by:
When mbuf is allocated by rte_pktmbuf_alloc the offload flag is reset by
it, so data-path function should not do it again.
Remove the above offload flag reset from MPRQ data-path.
Signed-off-by: Matan Azrad
Acked-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_rxtx.c | 2 --
1 file changed,
From: Vamsi Attunuru
Patch addresses checks in KNI and eal that enforce IOVA=PA when
IOVA=VA mode is enabled, since KNI kernel module supports VA
mode for kernel versions >= 4.4.0.
Updated KNI documentation with above details.
Signed-off-by: Vamsi Attunuru
Signed-off-by: Kiran Kumar K
---
do
From: Kiran Kumar K
Patch adds support for kernel module to work in IOVA = VA mode,
the idea is to get physical address from IOVA address using
iommu_iova_to_phys API and later use phys_to_virt API to
convert the physical address to kernel virtual address.
When compared with IOVA = PA mode, ther
From: Vamsi Attunuru
Current KNI implementation only operates in IOVA=PA mode, patch adds
required functionality in KNI lib to support IOVA=VA mode.
KNI kernel module requires device info to get iommu domain related
information for IOVA addr related translations. Patch defines device
related inf
From: Vamsi Attunuru
When KNI operates in IOVA = VA mode, it requires mbuf memory
to be physically contiguous to ensure KNI kernel module could
translate IOVA addresses properly. Patch adds a KNI specific
mempool create routine to populate the KNI packet mbuf pool
with memory objects that are bei
From: Vamsi Attunuru
---
V9 Changes:
* Used rte_mempool_ops_calc_mem_size() instead of default handler in
the new mempool populate routine.
* Check min_chunk_size and return values.
* Removed ethdev_info memset to '0' and moved pci dev_info populate into
kni_dev_pci_addr_get() routine.
* Addresse
From: Vamsi Attunuru
Patch adds a routine to populate mempool from page aligned and
page sized chunks of memory to ensure memory objs do not fall
across the page boundaries. It's useful for applications that
require physically contiguous mbuf memory while running in
IOVA=VA mode.
Signed-off-by:
Hi
I had a check in code for mbuf double release
I used to check if the reference count <= 0
Since the following change i can't check anymore this way since the reference
count is 1 even after it is release to the pool
http://mails.dpdk.org/archives/dev/2017-January/056188.html
I ther
From: Kusztal, ArkadiuszX
Sent: 25 July 2019 19:57
To: Shally Verma ; Anoob Joseph ; Ayuj
Verma ; akhil.go...@nxp.com
Cc: Sunila Sahu ; Kanaka Durga Kotamarthy
; dev@dpdk.org ; Trahe, Fiona
Subject: RE: [PATCH v1 0/2] declare crypto asym xform immutable
H
Acked-by: Hemant Agrawal
Dear Maintainers,
DPDK moved to using SPDX based license tag last year. However
some of the code is still using old style detailed copyrights. Will you please
help DPDK by moving your code to use SPDX tags?
This will make running legal checks on DPDK easy for all.
Let me know i
On 29-Jul-19 10:31 AM, David Marchand wrote:
On Fri, Jul 26, 2019 at 5:37 PM Anatoly Burakov
wrote:
When IOMMU is not available, /sys/kernel/iommu_groups will not be
populated. This is happening since at least 3.6 when VFIO support
was added. If the directory is empty, EAL should not pick IOVA
On 7/26/2019 5:43 PM, Xiaolong Ye wrote:
> Signed-off-by: Xiaolong Ye
> Acked-by: Bruce Richardson
Hi Ethan,
Can you please check this patch, this is switching license representation (not
license itself) to SPDX tags, as a copyright owner, the change requires ack.
Thanks,
ferruh
On 7/26/2019 5:43 PM, Xiaolong Ye wrote:
> Signed-off-by: Xiaolong Ye
> Acked-by: Bruce Richardson
Hi Jerin, Hemant,
Can you please check this patch, it requires both your ack?
Thanks,
ferruh
On 7/26/2019 9:12 PM, John Daley wrote:
> Prior to the fix, RTE_LOGTYPE_INFO messages were displayed by default.
> After the fix, only NOTICE level and higher were displayed by default
> and INFO level were not. There are INFO level vNIC config related
> messages which customers and tech support cu
On Wed, Jul 17, 2019 at 5:53 PM Thomas Monjalon wrote:
>
> In order to ease basic testing with customized options,
> EAL and testpmd options can be added as third and fourth arguments
> of the "null PMD" script.
>
> Also, the first argument becomes more flexible by accepting
> the testpmd path as
On Wed, Jul 17, 2019 at 5:53 PM Thomas Monjalon wrote:
>
> This small testpmd test was not working for a long time
> because of several changes in EAL and mempool.
> The 3 main issues solved are:
> - Make --no-huge working by specifying an amount of memory
> to allocate in
1 - 100 of 114 matches
Mail list logo
