Signed-off-by: Rasesh Mody
---
drivers/net/bnx2x/LICENSE.bnx2x_pmd | 29 ++---
drivers/net/bnx2x/Makefile |5 +
2 files changed, 7 insertions(+), 27 deletions(-)
diff --git a/drivers/net/bnx2x/LICENSE.bnx2x_pmd
b/drivers/net/bnx2x/LICENSE.bnx2x_pmd
ind
Signed-off-by: Rasesh Mody
---
drivers/net/qede/LICENSE.qede_pmd | 29 ++---
drivers/net/qede/base/ecore_mng_tlv.c |8
2 files changed, 10 insertions(+), 27 deletions(-)
diff --git a/drivers/net/qede/LICENSE.qede_pmd
b/drivers/net/qede/LICENSE.qede_pmd
Hi DPDK expert,
I am Nokia engineer. We are upgrading 6wind from 6wind 4.13->4.17, with DPDK
upgrading from 16.04->17.05. We use AVP PMD driver.
>From the performance test result, the CPU load of RX core increase from 72% to
>94% under same pps. The bitrate decreased from 9800M to 9000M, limitati
-Original Message-
> Date: Wed, 23 May 2018 02:36:42 +0530
> From: Nikhil Rao
> To: jerin.ja...@caviumnetworks.com
> CC: dev@dpdk.org, Nikhil Rao , sta...@dpdk.org
> Subject: [PATCH] eventdev: fix eth port in eth Rx adapter internal function
> X-Mailer: git-send-email 1.8.3.1
>
> The dev_
Hi Yongseok
From: Yongseok Koh
> Creating a flow having pattern from the middle of a packet is allowed. For
> example,
>
> testpmd> flow create 0 ingress pattern vxlan vni is 20 / end actions ...
>
> Device can parse GRE header but without proper support from library and
> firmware (HAVE_IBV_
-Original Message-
> Date: Wed, 23 May 2018 05:21:43 +
> From: Shahaf Shuler
> To: Thomas Monjalon , Andriy Berestovskyy
>
> CC: "dev@dpdk.org" , Bruce Richardson
> , "ferruh.yi...@intel.com"
> , "arybche...@solarflare.com"
> , "hemant.agra...@nxp.com"
> , "jerin.ja...@cavium.com
Sure, shared a suggestion. If not required can drop the same.
> -Original Message-
> From: Wiles, Keith
> Sent: Wednesday, May 23, 2018 10:24 AM
> To: Varghese, Vipin
> Cc: Ophir Munk ; dev@dpdk.org; Pascal Mazon
> ; Thomas Monjalon ;
> Olga Shern ; Shahaf Shuler ;
> sta...@dpdk.org
> Sub
Hi Andriy,
I think this patch addressing just small issue in a bigger problem.
The way I see it all application needs to specify is the max packet size it
expects to receive, nothing else(!).
Currently we are forcing it to toggle multiple redundant fields.
Wednesday, May 23, 2018 1:31 AM, Thom
> On May 22, 2018, at 11:50 PM, Varghese, Vipin
> wrote:
>
> Hi Ophir,
>
> One suggestion shared inline to email
>
>
>
>>
>> diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
>> index
>> c006d07..52ef799 100644
>> --- a/drivers/net/tap/rte_eth_tap.c
>> +++ b/driv
Hi Ophir,
One suggestion shared inline to email
>
> diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
> index
> c006d07..52ef799 100644
> --- a/drivers/net/tap/rte_eth_tap.c
> +++ b/drivers/net/tap/rte_eth_tap.c
> @@ -929,6 +929,15 @@ tap_dev_close(struct rte_eth_dev
> On May 22, 2018, at 11:44 PM, Varghese, Vipin
> wrote:
>
> The TX function is shared between TAP and TUN PMD. Checking TUN-TAP
> type field will ensure the TAP PMD will always have protocol field
> as 0.
>
> Signed-off-by: Vipin Varghese
> Suggested-by: Ferruh Yigit
> ---
> Changes in V4:
The TX function is shared between TAP and TUN PMD. Checking TUN-TAP
type field will ensure the TAP PMD will always have protocol field
as 0.
Signed-off-by: Vipin Varghese
Suggested-by: Ferruh Yigit
---
Changes in V4:
- convert comparision with MACRO - Keith Wiles
- add LOG err for tun using set
Hi Ophir,
Thanks for inputs, please find my answers inline to the mail
> -Original Message-
> From: Ophir Munk [mailto:ophi...@mellanox.com]
> Sent: Tuesday, May 22, 2018 8:35 PM
> To: Varghese, Vipin ; dev@dpdk.org; Yigit, Ferruh
> ; Wiles, Keith
> Cc: Thomas Monjalon ; Olga Shern
>
>
HI Keith,
Thanks for pointing out, please find my answer and update below
> > + /*
> > +* TUN and TAP are created with IFF_NO_PI disabled.
> > +* For TUN PMD this mandatory as fields are used by
> > +* Kernel tun.c t
The dev_id parameter to fill_event_buffer() should be 16 bit,
also rename to to eth_dev_id to avoid confusion with event device
id elsewhere in the file.
Fixes: c2189c907dd1 ("eventdev: make ethdev port identifiers 16-bit")
Cc: sta...@dpdk.org
Signed-off-by: Nikhil Rao
---
lib/librte_eventdev/rt
Cleanup document to convert old rxmode and txq_flags to new offload
bit mask.
Signed-off-by: Qi Zhang
---
doc/guides/nics/fm10k.rst | 27 ---
1 file changed, 8 insertions(+), 19 deletions(-)
diff --git a/doc/guides/nics/fm10k.rst b/doc/guides/nics/fm10k.rst
index c44e226
Cleanup document to convert old rxmode flags to new offload
bit mask.
Signed-off-by: Qi Zhang
---
doc/guides/nics/ixgbe.rst | 14 +++---
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
index c637bb351..070cac974 100644
-
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Wednesday, May 23, 2018 3:49 AM
> To: Yigit, Ferruh
> Cc: Yang, Zhiyong ; dev@dpdk.org; Matan Azrad
> ; Iremonger, Bernard
> ; Yao, Lei A ;
> maxime.coque...@redhat.com; Bie, Tiwei ;
> sta...@dpd
Creating a flow having pattern from the middle of a packet is allowed. For
example,
testpmd> flow create 0 ingress pattern vxlan vni is 20 / end actions ...
Device can parse GRE header but without proper support from library and
firmware (HAVE_IBV_DEVICE_MPLS_SUPPORT), a field in GRE header can
> On May 22, 2018, at 8:37 AM, Adrien Mazarguil
> wrote:
>
> This artificial limitation was inherited from the mlx4 code base and has no
> purpose other than adding unnecessary noise.
>
> This patch is a port of commit f2318196c71a ("net/mlx4: remove limitation
> on number of instances").
>
>
Thanks a lot Thomas.
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Tuesday, May 22, 2018 23:16
> To: Xu, Rosen
> Cc: dev@dpdk.org; Zhang, Roy Fan ; Doherty,
> Declan ; Richardson, Bruce
> ; shreyansh.j...@nxp.com; Yigit, Ferruh
> ; Ananyev, Konstantin
>
hi, Ferruh & Shijith
Sorry, I can't reply the email in time, because it was late at night.
I read your email, Will use commit log suggested by Shijith and the patch
Applied to dpdk-next-net/master.
That means my contribution to this bug has been done, right?
Thanks again for your help. Thanks!
A new DPDK release candidate is ready for testing:
https://dpdk.org/browse/dpdk/tag/?id=v18.05-rc5
The release notes are online:
http://dpdk.org/doc/guides/rel_notes/release_18_05.html
There are 140 new commits, but no new feature since 18.05-rc3.
The next release candidate is exp
Add LINUX VFIO support to feature list.
Add GRE tunneling offload to supported feature list.
Update firmware references to use newer FW imgae 8.33.12.0. Update
management FW version as well to 8.34.x.x.
Signed-off-by: Rasesh Mody
---
doc/guides/nics/features/qede.ini|1 +
doc/guides/ni
Do not error out on invalid devarg, log the message and continue.
Decide updating the tx-switching config in check args. Add a check for
VF when disabling tx-switching
Fixes: 612ce81b2007 ("net/qede: add devargs to disable NPAR Tx switching")
Fixes: f64b91b0eb5d ("net/qede: replace config option w
This patch fixes VF MTU update to work without having to restart the
vport and there by not requiring port re-configuration. It adds a
VF MTU Update TLV to achieve the same. Firmware can handle VF MTU update
by just pausing the vport.
Fixes: dd28bc8c6ef4 ("net/qede: fix VF port creation sequence")
25/01/2018 03:46, Wenzhuo Lu:
> Setting the default MAC address may fail on many NICs.
> But the ops return void. So, even it failed, RTE changes
> the MAC address and APP doesn't know the failure.
>
> It's not real patch, just show the idea to add a return
> value for the ops.
>
> BTW,
> Seems w
This proposal had no conclusion.
The examples have been fixed:
http://dpdk.org/commit/5e470a6654
But there is still an inconsistency in the API:
"
- for normal frames: zero max_rx_pkt_len uses a default
- for jumbo frames: zero max_rx_pkt_len gives an error
"
01/08/2017 00:33, Thomas M
On 5/22/2018 2:40 PM, Wiles, Keith wrote:
>
>
>> On May 22, 2018, at 6:01 AM, Varghese, Vipin
>> wrote:
>>
>> Fixes: ee27edbe0c10 ("drivers/net: share vdev data to secondary process")
>>
>> Enables TUN PMD sharing by attaching the port from the shared data.
>>
>> Cc: zhihong.w...@intel.com
>> C
On 5/22/2018 11:19 PM, Ferruh Yigit wrote:
> On 5/22/2018 11:09 PM, Ferruh Yigit wrote:
>> From: Vipin Varghese
>>
>
> Proto filed is fixed for tap, so title should be:
> net/tap: fix proto field for tap
>
> Will fix while merging.
>
>> The TX function is shared between TAP and TUN PMD. Checkin
On 5/22/2018 11:09 PM, Ferruh Yigit wrote:
> From: Vipin Varghese
>
Proto filed is fixed for tap, so title should be:
net/tap: fix proto field for tap
Will fix while merging.
> The TX function is shared between TAP and TUN PMD. Checking TUN-TAP
> type field will ensure the TAP PMD will always
12/12/2017 11:05, Nikhil Agarwal:
> Currently, if the rte_eth_rx_burst() function returns a value less than
> *nb_pkts*, the application will assume that no more packets are present.
>
> Some of the hw queue based hardware can only support smaller burst for RX
> and TX and thus break the expectat
From: Vipin Varghese
The TX function is shared between TAP and TUN PMD. Checking TUN-TAP
type field will ensure the TAP PMD will always have protocol field
as 0.
Fixes: 204d026a3922 ("net/tap: support tun")
Cc: vipin.vargh...@intel.com
Signed-off-by: Vipin Varghese
Signed-off-by: Ferruh Yigit
On 5/22/2018 11:04 PM, Ferruh Yigit wrote:
> From: Vipin Varghese
>
> The TX function is shared between TAP and TUN PMD. Checking TUN-TAP
> type field will ensure the TAP PMD will always have protocol field
> as 0.
>
> Signed-off-by: Vipin Varghese
> Signed-off-by: Ferruh Yigit
> ---
> Cc: Oph
From: Vipin Varghese
The TX function is shared between TAP and TUN PMD. Checking TUN-TAP
type field will ensure the TAP PMD will always have protocol field
as 0.
Signed-off-by: Vipin Varghese
Signed-off-by: Ferruh Yigit
---
Cc: Ophir Munk
---
drivers/net/tap/rte_eth_tap.c | 66 ++
19/12/2016 18:14, Bruce Richardson:
> On Mon, Dec 19, 2016 at 04:50:57PM +, Mcnamara, John wrote:
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson
> > > On Mon, Dec 19, 2016 at 03:05:20PM +0100, Thomas Monjalon wrote:
> > > > 2016-12-13 12:02, Ferruh Yigit:
> > > > > On
21/03/2016 18:56, Stephen Hemminger:
> The mk environment in DPDK puts files in build/ directory
> so it makes sense to have a .gitignore file to skip that
> directory.
>
> Signed-off-by: Stephen Hemminger
> ---
> .gitignore | 5 +
> 1 file changed, 5 insertions(+)
>
> diff --git a/.gitigno
19/04/2018 15:21, Ferruh Yigit:
> On 4/19/2018 1:00 PM, Juhamatti Kuusisaari wrote:
> > Handle properly a case where DPDK_PATCH_PATH is set
> > to point to a directory.
> >
> > Signed-off-by: Juhamatti Kuusisaari
>
> For series,
> Reviewed-by: Ferruh Yigit
Applied, thanks
On 5/17/2018 8:48 AM, Shahaf Shuler wrote:
> Signed-off-by: Shahaf Shuler
Applied to dpdk-next-net/master, thanks.
> > Update information for blacklist and whitelist options for secondary
> > process to share same from primary process.
> >
> > Signed-off-by: Vipin Varghese
>
> Acked-by: Harry van Haaren
Applied, thanks
On 5/22/2018 10:07 PM, Ferruh Yigit wrote:
> On 5/22/2018 3:33 PM, chuhong yao wrote:
>> When I was using VPP +dpdk-18.02+liqudio CN23xx,
>> I encountered such a bug.
>> When VPP called dpdk_device_start to initialize DPDK liqudio drive,
>> I found that initialization failed.
>> The reason for the
After having to change the spp (software patch panel) to get it to compile. I
had one problem with the new memory code, but was easy to fix and I had to add
the define to enable the experimental code to the Makefile.
The only other change was having to change all of the rte_eth_dev_count() to
r
On 5/22/2018 3:33 PM, chuhong yao wrote:
> When I was using VPP +dpdk-18.02+liqudio CN23xx,
> I encountered such a bug.
> When VPP called dpdk_device_start to initialize DPDK liqudio drive,
> I found that initialization failed.
> The reason for the failure is that VF MTU > PF MTU,
> but PF MTU has
27/04/2018 15:42, Ferruh Yigit:
> checks added for vDPA, MSS, UDP, EEPROM
>
> Signed-off-by: Ferruh Yigit
Applied, thanks
22/05/2018 22:56, Alex Ciobotaru:
> Guys, thank you for the info so far (sorry about the HTML thing).
> I will put some further insight/closure into this thread.
> So, my query started from the fact that when developing a new EAL
> in DPDK using an external toolchain and/or for a new OS,
> the "com
Guys, thank you for the info so far (sorry about the HTML thing).
I will put some further insight/closure into this thread.
So, my query started from the fact that when developing a new EAL in DPDK using an
external toolchain and/or for a new OS, the "common" (generic) part of the EAL
is actuall
> > Signed-off-by: Bernard Iremonger
> Acked-by: Wenzhuo Lu
Acked-by: Thomas Monjalon
Thank you Bernard for taking care of testpmd.
On 5/22/2018 9:49 PM, Ferruh Yigit wrote:
> On 5/22/2018 8:47 PM, Thomas Monjalon wrote:
>> 22/05/2018 20:35, Ferruh Yigit:
>>> vdevs detach on testpmd exit implemented as workaround to fix
>>> a virtio-user issue. The issue was virtio-user cleanup is not
>>> called and existing socket file not cle
On 5/22/2018 8:47 PM, Thomas Monjalon wrote:
> 22/05/2018 20:35, Ferruh Yigit:
>> vdevs detach on testpmd exit implemented as workaround to fix
>> a virtio-user issue. The issue was virtio-user cleanup is not
>> called and existing socket file not cleaned up which will fail
>> next run.
>>
>> The v
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Tuesday, May 22, 2018 1:33 PM
> To: Liu, Changpeng
> Cc: dev@dpdk.org; Maxime Coquelin
> Subject: Re: [dpdk-dev] [PATCH 1/2] examples/vhost_scsi: add virtio-1.0
> feature
> bit support
>
> 22/05/2018 19:
22/05/2018 16:28, Ferruh Yigit:
> Signed-off-by: Ferruh Yigit
Applied, thanks
On 5/22/2018 7:13 PM, Ajit Khaparde wrote:
> Patchset contains fixes mostly; against dpdk-next-net.
> Please apply.
>
> v1->v2: updated commit log, messages as requested.
>
> Ajit Khaparde (7):
> net/bnxt: add fallthrough comment
> net/bnxt: fix Tx and Rx burst for secondary processes
> net
On 4/19/2018 4:39 AM, Varghese, Vipin wrote:
> Hi Ferruh,
>
>
>
>> Hi Vipin,
>>
>> Thanks for providing unit test for the feature you have added. *I believe we
>> need more unit test in DPDK.*
>>
>> Only a few questions:
>> 1- Should this be part of auto test?
>
> It would be really nice to do
22/05/2018 18:35, Anatoly Burakov:
> When using --no-shconf option, the expectation is that no multiprocess
> will be supported as no shared files are created. However, fbarray
> still creates some shared files that prevent multiple processes with
> the same prefix from starting.
>
> Fix this by a
22/05/2018 19:51, Thomas Monjalon:
> 18/05/2018 14:35, Maxime Coquelin:
> >
> > On 05/18/2018 01:32 AM, Changpeng Liu wrote:
> > > Signed-off-by: Changpeng Liu
> > > ---
> > > examples/vhost_scsi/vhost_scsi.c | 7 ---
> > > 1 file changed, 4 insertions(+), 3 deletions(-)
> >
> > Reviewed-
22/05/2018 21:59, Wiles, Keith:
> You may want to do an RFC email subject to discuss your ideas on changing EAL
> code first to eliminate extra work.
Yes, definitely, RFC with first ideas can help to discuss.
One more pointer, Windows support in progress:
http://dpdk.org/browse/draft/dpd
22/05/2018 20:50, Ferruh Yigit:
> On 5/22/2018 7:10 PM, Dan Gora wrote:
> > Fix compilation errors on Centos 7.4 when CONFIG_RTE_KNI_KMOD_ETHTOOL
> > is set to 'y'.
> >
> > Centos 7.4 needs HAVE_NDO_BRIDGE_GETLINK_FILTER_MASK_VLAN_FILL:
> >
> > igb_main.c: In function ‘igb_ndo_bridge_getlink’:
>
Must use text only :-( darn mail program
> On May 22, 2018, at 2:23 PM, Alexandru Ciobotaru
> wrote:
>
> Greetings,
I can not answer all of your questions, but maybe a few.
>
> I'm currently checking on how to add new EAL "app" to the DPDK so I started
> by adding a new "xyzapp" next to "li
On May 22, 2018, at 2:23 PM, Alexandru Ciobotaru
mailto:alex.ciobot...@gmail.com>> wrote:
Greetings,
I can not answer all of your questions, but maybe a few.
I'm currently checking on how to add new EAL "app" to the DPDK so I started
by adding a new "xyzapp" next to "linuxapp" and "bsdapp".
22/05/2018 20:38, Ferruh Yigit:
> On 5/22/2018 2:12 PM, Thomas Monjalon wrote:
> > Any update to improve this workaround?
> >
> > 21/05/2018 18:38, Thomas Monjalon:
> >> 21/05/2018 18:32, Ferruh Yigit:
> >>> On 5/21/2018 11:54 AM, Thomas Monjalon wrote:
> 19/05/2018 16:19, Thomas Monjalon:
>
22/05/2018 20:35, Ferruh Yigit:
> vdevs detach on testpmd exit implemented as workaround to fix
> a virtio-user issue. The issue was virtio-user cleanup is not
> called and existing socket file not cleaned up which will fail
> next run.
>
> The vdev cleanup causing problems in failsafe PMD.
>
> R
22/05/2018 19:58, Liu, Changpeng:
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > 18/05/2018 01:32, Changpeng Liu:
> > > - strlcpy((char *)vpage->params, bdev->name,
> > > - sizeof(vpage->params));
> > > + vhost_strcpy_pad((ch
Greetings,
I'm currently checking on how to add new EAL "app" to the DPDK so I started
by adding a new "xyzapp" next to "linuxapp" and "bsdapp".
Now, I would probably expect to make this new EAL mainline compliant on
day, and to avoid future headaches, the plan is to avoid modifying things
outside
On 5/22/2018 6:20 PM, Iremonger, Bernard wrote:
>> -Original Message-
>> From: Yigit, Ferruh
>> Sent: Tuesday, May 22, 2018 5:37 PM
>> To: Lu, Wenzhuo ; Wu, Jingjing
>>
>> Cc: dev@dpdk.org; Yigit, Ferruh ; Zhang, Qi Z
>> ; Iremonger, Bernard
>>
>> Subject: [PATCH] app/testpmd: fix descrip
On 5/22/2018 7:10 PM, Dan Gora wrote:
> Fix compilation errors on Centos 7.4 when CONFIG_RTE_KNI_KMOD_ETHTOOL
> is set to 'y'.
>
> Centos 7.4 needs HAVE_NDO_BRIDGE_GETLINK_FILTER_MASK_VLAN_FILL:
>
> igb_main.c: In function ‘igb_ndo_bridge_getlink’:
> igb_main.c:2289:2: error: too few arguments to
On 5/22/2018 2:12 PM, Thomas Monjalon wrote:
> Any update to improve this workaround?
>
> 21/05/2018 18:38, Thomas Monjalon:
>> 21/05/2018 18:32, Ferruh Yigit:
>>> On 5/21/2018 11:54 AM, Thomas Monjalon wrote:
19/05/2018 16:19, Thomas Monjalon:
> 18/05/2018 18:29, Ferruh Yigit:
>> On
vdevs detach on testpmd exit implemented as workaround to fix
a virtio-user issue. The issue was virtio-user cleanup is not
called and existing socket file not cleaned up which will fail
next run.
The vdev cleanup causing problems in failsafe PMD.
Reduce the cleanup to only virtio-user and add a
The FALLTHROUGH comment for cascading switch cases was missing in
a few places. This patch adds that.
Signed-off-by: Ajit Khaparde
--
v1->v2: fix long headline
---
drivers/net/bnxt/bnxt_cpr.c| 1 +
drivers/net/bnxt/bnxt_ethdev.c | 3 +++
drivers/net/bnxt/bnxt_hwrm.c | 4
drivers/net/
For frames where the hardware is not able to calculate checksum
we are indicating such frames to be bad. And that is incorrect.
Indicate PKT_RX_IP_CKSUM_UNKNOWN or PKT_RX_L4_CKSUM_UNKNOWN
for such frames.
Fixes: 7ec39d8c524b ("net/bnxt: update status of Rx IP/L4 CKSUM")
Cc: sta...@dpdk.org
Signed
Patchset contains fixes mostly; against dpdk-next-net.
Please apply.
v1->v2: updated commit log, messages as requested.
Ajit Khaparde (7):
net/bnxt: add fallthrough comment
net/bnxt: fix Tx and Rx burst for secondary processes
net/bnxt: fix RSS hash configuration
net/bnxt: fix to use 1st
Query of port stats is permitted for VF interfaces as well.
Fix the code to allow VFs to query port stats.
Fixes: bfb9c2260be2 ("net/bnxt: support xstats get/reset")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
--
v1->v2: add sta...@dpdk.org for backport
---
drivers/net/bnxt/bnxt_ethdev.c |
In order to save completion resource, use the first completion ring from
PF or VF as the default completion ring for async event & HWRM forward
response handling. Add bnxt_hwrm_set_async_event_cr() to set
async_event_cr for either PF or VF.
Fixes: 7bc8e9a227cc ("net/bnxt: support async link notifi
While configuring RSS, the FW needs to know the rss_hash_mode that needs
to be initialized.
Set hash mode to HWRM_VNIC_RSS_CFG_INPUT_HASH_MODE_FLAGS_DEFAULT
to allow the FW to use the global mode already configured in the device.
Fixes: bcd4bcc4426f ("net/bnxt: configure RSS")
Cc: sta...@dpdk.org
If the resource requirement of a VF is more than what is allotted
to it by the FW, a VF can request to reallocate some of the resources.
This is possible only when the NIC is running the Resource Manager aware
CHiMP FW.
If necessary, calculate Tx and Rx ring count using the new RM API.
Otherwise
We were initializing Tx and Rx burst functions only for primary
processes. Fixing it in this patch.
Fixes: 88920136688c ("net/bnxt: support xstats get by id")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
--
v1->v2: shorten and update commit log and message.
---
drivers/net/bnxt/bnxt_ethdev
Fix compilation errors on Centos 7.4 when CONFIG_RTE_KNI_KMOD_ETHTOOL
is set to 'y'.
Centos 7.4 needs HAVE_NDO_BRIDGE_GETLINK_FILTER_MASK_VLAN_FILL:
igb_main.c: In function ‘igb_ndo_bridge_getlink’:
igb_main.c:2289:2: error: too few arguments to function
‘ndo_dflt_bridge_getlin
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Tuesday, May 22, 2018 10:48 AM
> To: Liu, Changpeng
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 2/2] examples/vhost_scsi: fix potential buffer
> overrun with safe copy API
>
> 18/05/2018 01:32, Cha
18/05/2018 14:35, Maxime Coquelin:
>
> On 05/18/2018 01:32 AM, Changpeng Liu wrote:
> > Signed-off-by: Changpeng Liu
> > ---
> > examples/vhost_scsi/vhost_scsi.c | 7 ---
> > 1 file changed, 4 insertions(+), 3 deletions(-)
>
> Reviewed-by: Maxime Coquelin
Patch 1 applied alone, thanks
18/05/2018 01:32, Changpeng Liu:
> Signed-off-by: Changpeng Liu
Missing explanations.
> - strlcpy((char *)vpage->params, bdev->name,
> - sizeof(vpage->params));
> + vhost_strcpy_pad((char *)vpage->params, bdev->name,
> +
21/05/2018 12:29, Vipin Varghese:
> rte_event_eth_rx_adapter_create allocates eth_devices for
> currently available eth devices. For newly created eth
> devices a new instance for rx adapter has to be created.
>
> Signed-off-by: Vipin Varghese
> Acked-by: Nikhil Rao
Applied, thanks
> > Fix the call to rte_timer_reset_sync() in sw_event_timer_cb(). The second
> > parameter is the number of ticks, the third is the timer type.
> >
> > Fixes: 6750b21bd6af ("eventdev: add default software timer adapter")
> > Cc: erik.g.carri...@intel.com
> >
> > Signed-off-by: Dan Gora
> > ---
22/05/2018 16:38, Pablo de Lara:
> http://dpdk.org/git/next/dpdk-next-crypto
Pulled, thanks
21/05/2018 15:08, Pablo de Lara:
> /**
> + * deprecated
@ is missing here.
Will fix when pulling the tree.
> * Get the size of the header session, for all registered drivers.
> *
> * @return
> * Size of the header session.
> */
> +__rte_deprecated
> unsigned int
> rte_cryptodev_get
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, May 22, 2018 5:37 PM
> To: Lu, Wenzhuo ; Wu, Jingjing
>
> Cc: dev@dpdk.org; Yigit, Ferruh ; Zhang, Qi Z
> ; Iremonger, Bernard
>
> Subject: [PATCH] app/testpmd: fix descriptor number for Rx queue setup
>
> Wrong index used to se
On 5/22/2018 5:31 PM, Ferruh Yigit wrote:
> On 5/22/2018 4:10 PM, Bernard Iremonger wrote:
>> Call the rte_eth_rxq_info_get() and rte_eth_txq_info_get() functions
>> to update the number of rx and tx descriptors.
>>
>> Fixes: d44f8a485f5d ("app/testpmd: enable per queue configure")
>> Signed-off-by
Wrong index used to select descriptor number, causing setting up queue
with wrong number of descriptors.
Fixes: d44f8a485f5d ("app/testpmd: enable per queue configure")
Signed-off-by: Ferruh Yigit
---
Cc: Qi Zhang
Cc: Bernard Iremonger
---
app/test-pmd/testpmd.c | 4 ++--
1 file changed, 2 in
When using --no-shconf option, the expectation is that no multiprocess
will be supported as no shared files are created. However, fbarray
still creates some shared files that prevent multiple processes with
the same prefix from starting.
Fix this by avoiding creating shared files whenever noshconf
On 5/22/2018 4:10 PM, Bernard Iremonger wrote:
> Call the rte_eth_rxq_info_get() and rte_eth_txq_info_get() functions
> to update the number of rx and tx descriptors.
>
> Fixes: d44f8a485f5d ("app/testpmd: enable per queue configure")
> Signed-off-by: Bernard Iremonger
Acked-by: Ferruh Yigit
https://dpdk.org/tracker/show_bug.cgi?id=50
Bug ID: 50
Summary: Secondary process launch is unreliable
Product: DPDK
Version: 18.05
Hardware: All
OS: All
Status: CONFIRMED
Severity: normal
Priori
Temporary IB device context and list are not freed in case of a successful
initialization of the device.
This issue is caused by the two following commits, the first of which
causes initialization to return early, while the second one goes a bit
overboard while switching to negative errno values;
This artificial limitation was inherited from the mlx4 code base and has no
purpose other than adding unnecessary noise.
This patch is a port of commit f2318196c71a ("net/mlx4: remove limitation
on number of instances").
Signed-off-by: Adrien Mazarguil
Cc: Nelio Laranjeiro
Cc: Yongseok Koh
---
On 5/17/2018 8:49 PM, Neil Horman wrote:
> On Thu, May 17, 2018 at 07:39:12AM -0700, Stephen Hemminger wrote:
>> On Thu, 17 May 2018 14:23:46 +0100
>> Ferruh Yigit wrote:
>>
>>> On 5/16/2018 12:47 PM, Neil Horman wrote:
On Tue, May 15, 2018 at 05:56:12PM +0100, Ferruh Yigit wrote:
> Whe
> Rosen Xu (3):
> bus/ifpga: fix error control flow issue
> bus/ifpga: fix resource leaks issue
> bus/ifpga: fix null pointer dereferences issue
Applied, thanks
Call the rte_eth_rxq_info_get() and rte_eth_txq_info_get() functions
to update the number of rx and tx descriptors.
Fixes: d44f8a485f5d ("app/testpmd: enable per queue configure")
Signed-off-by: Bernard Iremonger
---
app/test-pmd/config.c | 21 +++--
1 file changed, 19 insertions
Hi,
Overall it looks good.
Please note a few more comments below.
> -Original Message-
> From: Vipin Varghese [mailto:vipin.vargh...@intel.com]
> Sent: Tuesday, May 22, 2018 1:47 PM
> To: dev@dpdk.org; ferruh.yi...@intel.com; keith.wi...@intel.com; Ophir
> Munk
> Cc: Thomas Monjalon ; Olg
The following changes since commit 3291abb5a2a5f24c109ab74e6aad0545927333a7:
ethdev: fix type and scope of variables in Rx burst (2018-05-22 16:32:36
+0200)
are available in the Git repository at:
http://dpdk.org/git/next/dpdk-next-crypto
for you to fetch changes up to bbabaddd854f858477d
22/05/2018 15:34, Burakov, Anatoly:
> On 22-May-18 12:37 PM, Thomas Monjalon wrote:
> > A device like failsafe can manage sub-devices.
> > When removing such device, it removes its sub-devices
> > and try to take the same vdev_device_list_lock.
> > It was causing a deadlock because the lock was not
hi, shijith
I have reissued v2 patch and corrected the commit log. Please check it. Thank
you.
-- Original --
From: "Shijith Thotton";
Date: Tue, May 22, 2018 10:19 PM
To: "yaochuhong";
Cc: "shijith.thotton"; "dev";
Subject: Re: [PATCH] net/liquidio:Fix U
> -Original Message-
> From: Jain, Deepak K
> Sent: Tuesday, May 22, 2018 3:30 PM
> To: De Lara Guarch, Pablo ; Doherty, Declan
> ; akhil.go...@nxp.com; shally.ve...@cavium.com
> Cc: dev@dpdk.org; De Lara Guarch, Pablo
> Subject: RE: [dpdk-dev] [PATCH v5 0/6] Cryptodev API/ABI deprecatio
When I was using VPP +dpdk-18.02+liqudio CN23xx,
I encountered such a bug.
When VPP called dpdk_device_start to initialize DPDK liqudio drive,
I found that initialization failed.
The reason for the failure is that VF MTU > PF MTU,
but PF MTU has been modified to 9600 (> VF MTU).
Finally, I am locat
1 - 100 of 208 matches
Mail list logo
